diff --git "a/checkpoint-2594869/trainer_state.json" "b/checkpoint-2594869/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2594869/trainer_state.json" @@ -0,0 +1,30705 @@ +{ + "best_metric": 3.89139986038208, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/transformer/0/checkpoints/checkpoint-915829", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2594869, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9248, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8446, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1909, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9688, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8177, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6907, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5974, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5201, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4566, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3848, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3377, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.2926, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2597, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1964, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1551, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.127, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0856, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0578, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0367, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0035, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 4.9911, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9647, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9332, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9263, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.8997, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8761, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8612, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8522, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8181, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8087, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7864, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7768, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7772, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7543, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7432, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7315, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7236, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7098, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.6959, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6883, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6707, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 4.6663, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 4.6414, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6486, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6443, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 4.6319, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961434468733847e-05, + "loss": 4.6124, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6117, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6073, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.5876, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 4.578, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5738, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.583, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5493, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 4.5732, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 4.5352, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5441, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5357, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5319, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 4.5215, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5167, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.4999, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5103, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4935, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4955, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4901, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4795, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4624, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4754, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4665, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4523, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4574, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4485, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4488, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4501, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4431, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4345, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.419, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4263, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4221, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4254, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4202, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4047, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.39, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3942, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3955, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.3955, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.3922, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3856, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3756, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 4.3721, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 4.3716, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.378, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.368, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3452, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3519, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3568, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3588, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3504, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3464, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3429, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3379, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3427, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.3405, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912820541378427e-05, + "loss": 4.3194, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911981946627375e-05, + "loss": 4.3303, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.911143351876323e-05, + "loss": 4.3093, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3194, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3191, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.312, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3133, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.301, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.2962, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3028, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3145, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.2876, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.9027606801265495e-05, + "loss": 4.2832, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019220853754975e-05, + "loss": 4.2858, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010834906244455e-05, + "loss": 4.2988, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.9002448958733935e-05, + "loss": 4.2871, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2886, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.284, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2864, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2774, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.277, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2714, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2806, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893539413625723e-05, + "loss": 4.2595, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2724, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2663, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2552, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890186672501889e-05, + "loss": 4.2668, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889348077750837e-05, + "loss": 4.2602, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888509482999785e-05, + "loss": 4.2646, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2618, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886833931378054e-05, + "loss": 4.243, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885995336627002e-05, + "loss": 4.2421, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.88515674187595e-05, + "loss": 4.2444, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2538, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.8834811902542186e-05, + "loss": 4.2543, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.8826425955031666e-05, + "loss": 4.2484, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.8818040007521146e-05, + "loss": 4.2356, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.8809654060010626e-05, + "loss": 4.2374, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.8801268112500106e-05, + "loss": 4.2385, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879289854379332e-05, + "loss": 4.2352, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878452897508653e-05, + "loss": 4.2312, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877614302757601e-05, + "loss": 4.2485, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876775708006549e-05, + "loss": 4.2321, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875937113255497e-05, + "loss": 4.2237, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875098518504445e-05, + "loss": 4.2225, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.238885879516602, + "eval_runtime": 600.8169, + "eval_samples_per_second": 635.12, + "eval_steps_per_second": 19.848, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.874259923753393e-05, + "loss": 4.2297, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873421329002341e-05, + "loss": 4.2254, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872582734251289e-05, + "loss": 4.2143, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.871744139500237e-05, + "loss": 4.2142, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.870905544749185e-05, + "loss": 4.207, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2042, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.1988, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1998, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2057, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2033, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.1984, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2014, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1945, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1894, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1864, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1594, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1812, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.1806, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1804, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.1917, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1742, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1773, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1781, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.854978796000689e-05, + "loss": 4.1733, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1666, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1633, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.171, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.851626054876854e-05, + "loss": 4.156, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.162, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.1472, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1507, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.84827331375302e-05, + "loss": 4.1631, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847434719001968e-05, + "loss": 4.1554, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846596124250916e-05, + "loss": 4.1553, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1517, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844920572629185e-05, + "loss": 4.1513, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.1534, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.149, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1474, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.8415678315053496e-05, + "loss": 4.1361, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.8407292367542976e-05, + "loss": 4.1442, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1276, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.1409, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838215090381515e-05, + "loss": 4.1438, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.837376495630463e-05, + "loss": 4.139, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1311, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.1341, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1383, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.834023754506628e-05, + "loss": 4.1171, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1214, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1193, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.831509608133845e-05, + "loss": 4.135, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.830671013382793e-05, + "loss": 4.1121, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1336, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1051, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1189, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1179, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1195, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.111, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.1157, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1031, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1129, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.1034, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.1089, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1051, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1022, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.0856, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.1094, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.0966, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816419816256029e-05, + "loss": 4.0914, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.0993, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.814745902514671e-05, + "loss": 4.095, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.813907307763619e-05, + "loss": 4.0974, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1036, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.0999, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811393161390836e-05, + "loss": 4.0922, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810554566639784e-05, + "loss": 4.0834, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809715971888732e-05, + "loss": 4.0888, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.0909, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.1005, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0909, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.0851, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.0712, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0757, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.079, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0815, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.0868, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0785, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.8004930675075325e-05, + "loss": 4.0721, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0769, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0702, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0781, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0757, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.057, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0601, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0652, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0779, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0624, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0714, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.0631, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0593, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0676, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0651, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0522, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0657, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.7862435082611415e-05, + "loss": 4.0461, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854049135100895e-05, + "loss": 4.0513, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0597, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.0474, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828891292569335e-05, + "loss": 4.054, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0458, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0417, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0478, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0611, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0406, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0414, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.777022241760315e-05, + "loss": 4.0391, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0492, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0463, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0441, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0454, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.047, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0418, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.035, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0389, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0474, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0311, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0338, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.046, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0239, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0382, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0327, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0449, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0373, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0243, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0216, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0261, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.0381, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0393, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0362, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0193, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0246, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.0305, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0273, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0213, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0403, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0202, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.0231, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0185, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.071280002593994, + "eval_runtime": 570.0359, + "eval_samples_per_second": 669.416, + "eval_steps_per_second": 20.92, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0287, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.0254, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.0146, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0153, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0079, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.009, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0078, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 4.0068, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0118, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.011, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0101, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0098, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0051, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0004, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 4.0033, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 3.9751, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735945839882125e-05, + "loss": 4.0009, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735107245131073e-05, + "loss": 3.9977, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734268650380021e-05, + "loss": 3.9964, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733430055628969e-05, + "loss": 4.0149, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 3.9962, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731754504007238e-05, + "loss": 4.0006, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730915909256186e-05, + "loss": 3.9992, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730077314505134e-05, + "loss": 3.9953, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729238719754082e-05, + "loss": 3.9918, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 3.9867, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 3.998, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 3.9847, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725885978630247e-05, + "loss": 3.9902, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725047383879195e-05, + "loss": 3.9749, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 3.9835, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 3.9952, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 3.984, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216946427553606e-05, + "loss": 3.9903, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.984, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 3.987, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9912, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183419016315255e-05, + "loss": 3.9862, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175033068804735e-05, + "loss": 3.9827, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9737, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 3.9822, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149891605076904e-05, + "loss": 3.9697, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141505657566384e-05, + "loss": 3.9861, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.983, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.9828, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9737, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710797824632804e-05, + "loss": 3.9735, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9828, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9619, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9673, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9629, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9826, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9619, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9813, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9541, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9656, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9695, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9701, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9648, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9769, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9487, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9631, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9601, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.968, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9577, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9603, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9439, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9645, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9539, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9522, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9589, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9563, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9547, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9686, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9617, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864900420149076e-05, + "loss": 3.9554, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.947, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9501, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.955, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9619, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9527, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9545, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9367, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679784559767238e-05, + "loss": 3.9461, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9399, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9494, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9551, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9475, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9391, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674756267021672e-05, + "loss": 3.9464, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.67391767227062e-05, + "loss": 3.9395, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9476, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9461, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9308, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9309, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9375, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9492, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668049146893629e-05, + "loss": 3.9376, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667210552142577e-05, + "loss": 3.9475, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9343, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9359, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664696405769794e-05, + "loss": 3.9429, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663857811018742e-05, + "loss": 3.94, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.9296, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662182259397011e-05, + "loss": 3.9461, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9199, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9249, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9394, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658829518273176e-05, + "loss": 3.923, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657990923522124e-05, + "loss": 3.937, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657152328771072e-05, + "loss": 3.9256, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9197, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.9268, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9445, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.9216, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9258, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.9174, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9269, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65044520864303e-05, + "loss": 3.932, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649606613891978e-05, + "loss": 3.9268, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9254, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.928, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9261, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9233, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454169158974635e-05, + "loss": 3.9243, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445783211464115e-05, + "loss": 3.9311, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437397263953595e-05, + "loss": 3.9176, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.9198, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642064174773629e-05, + "loss": 3.9322, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641225580022577e-05, + "loss": 3.9107, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640386985271525e-05, + "loss": 3.9235, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639548390520473e-05, + "loss": 3.9224, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638711433649794e-05, + "loss": 3.9322, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637872838898742e-05, + "loss": 3.9225, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.63703424414769e-05, + "loss": 3.9169, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636195649396638e-05, + "loss": 3.9096, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635357054645586e-05, + "loss": 3.9146, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9258, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633681503023855e-05, + "loss": 3.9292, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632842908272803e-05, + "loss": 3.9275, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632004313521751e-05, + "loss": 3.912, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.911, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303287619000204e-05, + "loss": 3.9268, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294901671489684e-05, + "loss": 3.9161, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286515723979164e-05, + "loss": 3.9162, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9305, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626976020776185e-05, + "loss": 3.911, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626137426025133e-05, + "loss": 3.9166, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625298831274081e-05, + "loss": 3.9131, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9977993965148926, + "eval_runtime": 567.9532, + "eval_samples_per_second": 671.87, + "eval_steps_per_second": 20.996, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624460236523029e-05, + "loss": 3.9213, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.6236216417719766e-05, + "loss": 3.921, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.6227830470209246e-05, + "loss": 3.9085, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219444522698726e-05, + "loss": 3.9086, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621105857518821e-05, + "loss": 3.9072, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.9029, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9032, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9024, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.617753116394986e-05, + "loss": 3.9083, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616914521643934e-05, + "loss": 3.9115, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9052, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9048, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614400375271151e-05, + "loss": 3.9058, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613561780520099e-05, + "loss": 3.9015, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612723185769047e-05, + "loss": 3.8991, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.8769, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.8965, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.8992, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.8969, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9121, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.8963, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9057, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.8959, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051791087703256e-05, + "loss": 3.8948, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.8927, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.8927, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.8958, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.889, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8905, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.878, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.8878, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.8957, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.891, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.8932, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959578422695e-05, + "loss": 3.8894, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.892, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8927, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8971, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8864, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8799, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.8898, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.8726, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.8964, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8892, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.5875768084000994e-05, + "loss": 3.8886, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8812, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.8816, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.893, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584224067276264e-05, + "loss": 3.8691, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583385472525212e-05, + "loss": 3.8771, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.8772, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8877, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580871326152429e-05, + "loss": 3.8688, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580032731401377e-05, + "loss": 3.8928, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8675, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8706, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577518585028595e-05, + "loss": 3.8839, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576679990277543e-05, + "loss": 3.8744, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.57584139552649e-05, + "loss": 3.8849, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.575002800775438e-05, + "loss": 3.8881, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.5741658439047596e-05, + "loss": 3.8637, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.5733272491537076e-05, + "loss": 3.8696, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572488654402655e-05, + "loss": 3.8747, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571650059651603e-05, + "loss": 3.8781, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.5708131027809245e-05, + "loss": 3.8688, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.5699745080298725e-05, + "loss": 3.8717, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.5691359132788205e-05, + "loss": 3.857, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8796, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.56746036165709e-05, + "loss": 3.8664, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666217669060374e-05, + "loss": 3.8653, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657831721549854e-05, + "loss": 3.8722, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.564946215284307e-05, + "loss": 3.8711, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.564107620533255e-05, + "loss": 3.8678, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.563269025782202e-05, + "loss": 3.878, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.56243043103115e-05, + "loss": 3.8776, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.561591836280098e-05, + "loss": 3.8714, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8646, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8667, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.8674, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.558239095156264e-05, + "loss": 3.8802, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.557400500405212e-05, + "loss": 3.8708, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8644, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.856, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.554886354032429e-05, + "loss": 3.8614, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554047759281377e-05, + "loss": 3.8582, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.8656, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8655, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551533612908594e-05, + "loss": 3.8672, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550695018157542e-05, + "loss": 3.859, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8679, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8585, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8616, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8631, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.8521, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545665087531603e-05, + "loss": 3.85, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544826492780551e-05, + "loss": 3.8627, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8602, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8659, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8619, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.8558, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8545, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.539798200034985e-05, + "loss": 3.8652, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.861, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.8508, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.5372840536622026e-05, + "loss": 3.8661, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.8401, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8494, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8615, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8454, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8581, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8462, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8396, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8496, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8668, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8486, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8453, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8421, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.849, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8541, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.524710046037542e-05, + "loss": 3.8511, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8465, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8535, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.85, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.8485, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.520517072282281e-05, + "loss": 3.8462, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.8544, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.8417, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.518002925909499e-05, + "loss": 3.8438, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.517164331158447e-05, + "loss": 3.8565, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.516325736407395e-05, + "loss": 3.8371, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8465, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514650184785664e-05, + "loss": 3.8514, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513811590034612e-05, + "loss": 3.8563, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.51297299528356e-05, + "loss": 3.847, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.8455, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.8365, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.5104588489107766e-05, + "loss": 3.8403, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.5096202541597246e-05, + "loss": 3.8499, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.8535, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8532, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507106107786942e-05, + "loss": 3.8405, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.50626751303589e-05, + "loss": 3.8354, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.505428918284838e-05, + "loss": 3.8521, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8421, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503753366663107e-05, + "loss": 3.8457, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502914771912055e-05, + "loss": 3.8584, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502076177161003e-05, + "loss": 3.8419, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.843, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500400625539272e-05, + "loss": 3.8409, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.9589924812316895, + "eval_runtime": 577.3589, + "eval_samples_per_second": 660.925, + "eval_steps_per_second": 20.654, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956203078822e-05, + "loss": 3.8517, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498723436037168e-05, + "loss": 3.8472, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497884841286116e-05, + "loss": 3.8369, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497046246535065e-05, + "loss": 3.8351, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496207651784013e-05, + "loss": 3.8381, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495369057032961e-05, + "loss": 3.8321, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945304622819087e-05, + "loss": 3.8343, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936918675308567e-05, + "loss": 3.8289, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.839, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8453, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8328, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903391264070216e-05, + "loss": 3.8305, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.8382, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8342, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8307, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8066, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486149428412508e-05, + "loss": 3.8265, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485310833661456e-05, + "loss": 3.8295, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8288, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8469, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482796687288673e-05, + "loss": 3.8247, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481958092537621e-05, + "loss": 3.8378, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8254, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8305, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479443946164838e-05, + "loss": 3.8207, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478605351413786e-05, + "loss": 3.8251, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477766756662734e-05, + "loss": 3.8271, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476928161911682e-05, + "loss": 3.8227, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760912050410034e-05, + "loss": 3.823, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752526102899514e-05, + "loss": 3.8132, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4744140155388994e-05, + "loss": 3.8159, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473575420787847e-05, + "loss": 3.8304, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472738463917168e-05, + "loss": 3.8246, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471899869166116e-05, + "loss": 3.8264, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710612744150636e-05, + "loss": 3.8229, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702226796640116e-05, + "loss": 3.8284, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469385722793333e-05, + "loss": 3.8248, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468547128042281e-05, + "loss": 3.8308, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677085332912285e-05, + "loss": 3.8222, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466869938540177e-05, + "loss": 3.8127, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466032981669499e-05, + "loss": 3.828, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465194386918447e-05, + "loss": 3.8065, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464355792167394e-05, + "loss": 3.8296, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463517197416342e-05, + "loss": 3.8225, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462680240545664e-05, + "loss": 3.8283, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461841645794611e-05, + "loss": 3.8151, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461003051043559e-05, + "loss": 3.814, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460164456292507e-05, + "loss": 3.827, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593274994218286e-05, + "loss": 3.8096, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458488904670776e-05, + "loss": 3.8111, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457650309919724e-05, + "loss": 3.815, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568133530490455e-05, + "loss": 3.8194, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455974758297994e-05, + "loss": 3.8102, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551361635469415e-05, + "loss": 3.8227, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542975687958895e-05, + "loss": 3.8041, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453460611925211e-05, + "loss": 3.8079, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526220171741584e-05, + "loss": 3.8187, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517834224231064e-05, + "loss": 3.8076, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509448276720543e-05, + "loss": 3.8261, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450107870801376e-05, + "loss": 3.8276, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449269276050323e-05, + "loss": 3.7988, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448430681299271e-05, + "loss": 3.806, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447592086548219e-05, + "loss": 3.8135, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446755129677541e-05, + "loss": 3.8202, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445916534926489e-05, + "loss": 3.8046, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445077940175437e-05, + "loss": 3.8068, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444239345424385e-05, + "loss": 3.7998, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443402388553706e-05, + "loss": 3.8136, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442563793802654e-05, + "loss": 3.8059, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441725199051602e-05, + "loss": 3.8007, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088660430055e-05, + "loss": 3.8115, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400496474298706e-05, + "loss": 3.8074, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392110526788186e-05, + "loss": 3.8056, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383724579277666e-05, + "loss": 3.8173, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375338631767146e-05, + "loss": 3.8162, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436695268425663e-05, + "loss": 3.8104, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8053, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.8094, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.8014, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433342527301828e-05, + "loss": 3.8236, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432503932550776e-05, + "loss": 3.8085, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.8058, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.7926, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429989786177993e-05, + "loss": 3.8057, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429151191426941e-05, + "loss": 3.7958, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8087, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8017, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266370450541586e-05, + "loss": 3.806, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257984503031066e-05, + "loss": 3.7994, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249614934324276e-05, + "loss": 3.812, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241228986813756e-05, + "loss": 3.7985, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232843039303235e-05, + "loss": 3.8035, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224457091792715e-05, + "loss": 3.8082, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.7897, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207685196771675e-05, + "loss": 3.7904, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.8046, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190913301750635e-05, + "loss": 3.7981, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.8135, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.8019, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.7915, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157385890512284e-05, + "loss": 3.798, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.41490163218055e-05, + "loss": 3.805, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.8026, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413226080558819e-05, + "loss": 3.7951, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412387485807767e-05, + "loss": 3.8061, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411548891056715e-05, + "loss": 3.7829, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.7914, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.8049, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.7834, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.8005, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.7958, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.7762, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056820035600974e-05, + "loss": 3.7926, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048434088090454e-05, + "loss": 3.808, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4040048140579934e-05, + "loss": 3.7901, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031662193069414e-05, + "loss": 3.7923, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023276245558894e-05, + "loss": 3.7861, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401489029804837e-05, + "loss": 3.7907, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400650435053785e-05, + "loss": 3.7992, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399813478183106e-05, + "loss": 3.7946, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398974883432054e-05, + "loss": 3.7887, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981362886810016e-05, + "loss": 3.7921, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972976939299496e-05, + "loss": 3.7961, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964590991788976e-05, + "loss": 3.7908, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956205044278456e-05, + "loss": 3.7908, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394783547557167e-05, + "loss": 3.7969, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393944952806115e-05, + "loss": 3.7828, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393106358055063e-05, + "loss": 3.7931, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392267763304011e-05, + "loss": 3.7972, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391429168552959e-05, + "loss": 3.7842, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390590573801907e-05, + "loss": 3.79, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.7974, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.7972, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388076427429124e-05, + "loss": 3.7952, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387237832678072e-05, + "loss": 3.7897, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.38639923792702e-05, + "loss": 3.7813, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385562281056341e-05, + "loss": 3.7862, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847236863052896e-05, + "loss": 3.7927, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838850915542376e-05, + "loss": 3.798, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830464968031856e-05, + "loss": 3.8001, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822095399325065e-05, + "loss": 3.7893, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813709451814545e-05, + "loss": 3.7793, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805323504304025e-05, + "loss": 3.7967, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796937556793505e-05, + "loss": 3.7846, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788567988086714e-05, + "loss": 3.7901, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780182040576194e-05, + "loss": 3.8044, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771796093065674e-05, + "loss": 3.7913, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763410145555154e-05, + "loss": 3.7848, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375504057684836e-05, + "loss": 3.788, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.934941053390503, + "eval_runtime": 572.972, + "eval_samples_per_second": 665.985, + "eval_steps_per_second": 20.813, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.374667100814158e-05, + "loss": 3.7973, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373828506063106e-05, + "loss": 3.7962, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372989911312054e-05, + "loss": 3.7814, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.372151316561002e-05, + "loss": 3.7798, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.37131272180995e-05, + "loss": 3.788, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370474127058898e-05, + "loss": 3.7789, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369635532307846e-05, + "loss": 3.7798, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.7717, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367959980686115e-05, + "loss": 3.787, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367123023815436e-05, + "loss": 3.7967, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.7761, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365445834313332e-05, + "loss": 3.7778, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.7862, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7791, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.7807, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362093093189497e-05, + "loss": 3.7549, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361254498438445e-05, + "loss": 3.7713, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360415903687393e-05, + "loss": 3.7756, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359577308936341e-05, + "loss": 3.7774, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358738714185289e-05, + "loss": 3.7964, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.7728, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.7868, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.7755, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355385973061454e-05, + "loss": 3.7782, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.7678, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.35370878355935e-05, + "loss": 3.7731, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352871826688672e-05, + "loss": 3.7782, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.35203323193762e-05, + "loss": 3.7732, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351194637186568e-05, + "loss": 3.7715, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350356042435515e-05, + "loss": 3.765, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.3495190855648366e-05, + "loss": 3.7591, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486804908137846e-05, + "loss": 3.7795, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347841896062732e-05, + "loss": 3.7772, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.34700330131168e-05, + "loss": 3.7744, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461663444410015e-05, + "loss": 3.7723, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453277496899495e-05, + "loss": 3.7764, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444891549388975e-05, + "loss": 3.7774, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.774, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.342813603317167e-05, + "loss": 3.773, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341975008566115e-05, + "loss": 3.7623, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7757, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.7586, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339460862193332e-05, + "loss": 3.778, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338622267442279e-05, + "loss": 3.77, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7786, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.766, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336108121069497e-05, + "loss": 3.7637, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335269526318445e-05, + "loss": 3.7807, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7568, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.7614, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.3327553799456624e-05, + "loss": 3.7653, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.33191678519461e-05, + "loss": 3.7668, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.7626, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330239595692506e-05, + "loss": 3.7715, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7597, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285640440707746e-05, + "loss": 3.7583, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7724, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7609, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3260498976979915e-05, + "loss": 3.7739, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.32521130294694e-05, + "loss": 3.7773, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324372708195888e-05, + "loss": 3.7535, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.7559, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322697156574157e-05, + "loss": 3.761, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321858561823105e-05, + "loss": 3.7751, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321019967072053e-05, + "loss": 3.758, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7609, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319344415450322e-05, + "loss": 3.7494, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.31850582069927e-05, + "loss": 3.7663, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317667225948218e-05, + "loss": 3.7545, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7548, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315991674326487e-05, + "loss": 3.7604, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151530795754356e-05, + "loss": 3.7611, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143144848243836e-05, + "loss": 3.7571, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7674, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126389332026525e-05, + "loss": 3.7675, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3118003384516005e-05, + "loss": 3.762, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109617437005485e-05, + "loss": 3.7551, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.7656, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3092861920788174e-05, + "loss": 3.7536, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084475973277654e-05, + "loss": 3.7722, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3076090025767134e-05, + "loss": 3.7573, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067704078256614e-05, + "loss": 3.762, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305933450954982e-05, + "loss": 3.7462, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.30509485620393e-05, + "loss": 3.7575, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304256261452879e-05, + "loss": 3.7477, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034193045822e-05, + "loss": 3.7637, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302580709831148e-05, + "loss": 3.7557, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301742115080096e-05, + "loss": 3.7576, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.7562, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300066563458365e-05, + "loss": 3.7684, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299227968707313e-05, + "loss": 3.7443, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298389373956261e-05, + "loss": 3.7561, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297550779205209e-05, + "loss": 3.7606, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296712184454157e-05, + "loss": 3.7465, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295873589703105e-05, + "loss": 3.7457, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295034994952053e-05, + "loss": 3.76, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294196400201001e-05, + "loss": 3.7489, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7698, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.292522486459643e-05, + "loss": 3.754, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291683891708591e-05, + "loss": 3.7468, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.75, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.762, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289169745335808e-05, + "loss": 3.7584, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288331150584756e-05, + "loss": 3.7481, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7593, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7388, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.745, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284976771580548e-05, + "loss": 3.7569, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.7403, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7537, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.7557, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281624030456714e-05, + "loss": 3.7296, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807854357056617e-05, + "loss": 3.7481, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.762, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791098840839306e-05, + "loss": 3.7524, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.2782712893328786e-05, + "loss": 3.7445, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774326945818266e-05, + "loss": 3.7421, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765940998307746e-05, + "loss": 3.7449, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757555050797225e-05, + "loss": 3.754, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7513, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740799534579915e-05, + "loss": 3.7434, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732413587069394e-05, + "loss": 3.7493, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2724027639558874e-05, + "loss": 3.7494, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715641692048354e-05, + "loss": 3.7492, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707255744537834e-05, + "loss": 3.7429, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698869797027314e-05, + "loss": 3.7508, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690483849516794e-05, + "loss": 3.7422, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.7492, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.752, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7379, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.7462, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264858686957165e-05, + "loss": 3.7566, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264020092206113e-05, + "loss": 3.7525, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.7507, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7477, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261505945833331e-05, + "loss": 3.7344, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7403, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7488, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.7608, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.7521, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7424, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7417, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.25563742045634e-05, + "loss": 3.7481, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2548004635856606e-05, + "loss": 3.7444, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.2539618688346086e-05, + "loss": 3.7438, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7628, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252284679332505e-05, + "loss": 3.7464, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251447722461826e-05, + "loss": 3.7412, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7444, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.919722318649292, + "eval_runtime": 569.191, + "eval_samples_per_second": 670.409, + "eval_steps_per_second": 20.951, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249772170840095e-05, + "loss": 3.754, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248933576089043e-05, + "loss": 3.7525, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248094981337991e-05, + "loss": 3.743, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247256386586939e-05, + "loss": 3.7394, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246417791835887e-05, + "loss": 3.7424, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245579197084835e-05, + "loss": 3.7355, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244740602333783e-05, + "loss": 3.7377, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243902007582731e-05, + "loss": 3.7297, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243065050712052e-05, + "loss": 3.7411, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422264559610006e-05, + "loss": 3.7577, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413894990903215e-05, + "loss": 3.734, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405509043392695e-05, + "loss": 3.7346, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7459, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7371, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7426, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371981632154344e-05, + "loss": 3.7131, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363595684643824e-05, + "loss": 3.7266, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355209737133304e-05, + "loss": 3.7346, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346823789622784e-05, + "loss": 3.7324, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338437842112264e-05, + "loss": 3.756, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7334, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7478, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7291, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230491043087392e-05, + "loss": 3.7362, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7268, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7338, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227976896714609e-05, + "loss": 3.7361, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227138301963557e-05, + "loss": 3.7275, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7349, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225461112461453e-05, + "loss": 3.7219, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224624155590774e-05, + "loss": 3.7176, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7389, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7362, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7361, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212714144669394e-05, + "loss": 3.7264, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.7385, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7311, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7371, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217918673343104e-05, + "loss": 3.7313, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.7235, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7361, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7156, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214565932219269e-05, + "loss": 3.7377, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213727337468217e-05, + "loss": 3.7318, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.736, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7284, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211213191095435e-05, + "loss": 3.7223, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210374596344383e-05, + "loss": 3.7386, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7187, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7222, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078604499715996e-05, + "loss": 3.7245, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070218552205476e-05, + "loss": 3.7265, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206183260469495e-05, + "loss": 3.7241, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205344665718443e-05, + "loss": 3.7257, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045077088477645e-05, + "loss": 3.721, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036691140967125e-05, + "loss": 3.724, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028305193456605e-05, + "loss": 3.7269, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019919245946085e-05, + "loss": 3.7234, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115496772393e-05, + "loss": 3.7346, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200316372972878e-05, + "loss": 3.7358, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994777782218254e-05, + "loss": 3.7148, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986391834707734e-05, + "loss": 3.7166, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197802226600095e-05, + "loss": 3.7176, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196963631849042e-05, + "loss": 3.7365, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612503709799e-05, + "loss": 3.7215, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195286442346938e-05, + "loss": 3.7195, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.19444948547626e-05, + "loss": 3.7113, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193610890725207e-05, + "loss": 3.7229, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192772295974156e-05, + "loss": 3.7182, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191933701223104e-05, + "loss": 3.7162, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191096744352425e-05, + "loss": 3.7228, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190258149601373e-05, + "loss": 3.721, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189419554850321e-05, + "loss": 3.7199, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188580960099269e-05, + "loss": 3.7272, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18774400322859e-05, + "loss": 3.7306, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186905408477538e-05, + "loss": 3.724, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186066813726486e-05, + "loss": 3.7181, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185228218975434e-05, + "loss": 3.7228, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843912621047546e-05, + "loss": 3.7159, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835526673537026e-05, + "loss": 3.7337, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182714072602651e-05, + "loss": 3.7194, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181875477851599e-05, + "loss": 3.7248, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.18103852098092e-05, + "loss": 3.7071, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180199926229868e-05, + "loss": 3.7227, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179361331478816e-05, + "loss": 3.705, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178524374608137e-05, + "loss": 3.7254, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177685779857085e-05, + "loss": 3.7186, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176847185106033e-05, + "loss": 3.7223, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176008590354981e-05, + "loss": 3.7156, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175171633484302e-05, + "loss": 3.7255, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17433303873325e-05, + "loss": 3.7104, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173494443982198e-05, + "loss": 3.7179, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726558492311466e-05, + "loss": 3.7224, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.7089, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7082, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7182, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7114, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684645133562595e-05, + "loss": 3.7346, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676275564855804e-05, + "loss": 3.715, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667889617345284e-05, + "loss": 3.7128, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659503669834764e-05, + "loss": 3.7115, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651117722324244e-05, + "loss": 3.7212, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.7232, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7099, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7205, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7042, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7049, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.718, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7063, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.7145, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.718, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.6926, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155890505731599e-05, + "loss": 3.7103, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15505354886092e-05, + "loss": 3.7278, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154214954109868e-05, + "loss": 3.7178, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153376359358816e-05, + "loss": 3.702, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.704, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7079, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7158, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150023618234981e-05, + "loss": 3.7145, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.707, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148346428732877e-05, + "loss": 3.7102, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7146, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7107, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458306444797206e-05, + "loss": 3.7071, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449920497286686e-05, + "loss": 3.7144, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441534549776166e-05, + "loss": 3.7088, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.7126, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424779033558855e-05, + "loss": 3.7124, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416393086048335e-05, + "loss": 3.698, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140800713853782e-05, + "loss": 3.7093, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.13996211910273e-05, + "loss": 3.7177, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139123524351678e-05, + "loss": 3.7201, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138284929600626e-05, + "loss": 3.7142, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137446334849574e-05, + "loss": 3.714, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136609377978895e-05, + "loss": 3.7004, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135770783227843e-05, + "loss": 3.702, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134932188476791e-05, + "loss": 3.7098, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134093593725739e-05, + "loss": 3.7234, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7174, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.7077, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7014, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307424904822776e-05, + "loss": 3.7145, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299038957312256e-05, + "loss": 3.7081, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290653009801736e-05, + "loss": 3.7073, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282267062291215e-05, + "loss": 3.7262, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273881114780695e-05, + "loss": 3.7128, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265511546073905e-05, + "loss": 3.7051, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257125598563384e-05, + "loss": 3.711, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.9115793704986572, + "eval_runtime": 585.0666, + "eval_samples_per_second": 652.218, + "eval_steps_per_second": 20.382, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7165, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.7167, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.708, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223598187325033e-05, + "loss": 3.7027, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215212239814513e-05, + "loss": 3.7029, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120682629230399e-05, + "loss": 3.7054, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119844034479347e-05, + "loss": 3.7012, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119005439728296e-05, + "loss": 3.6964, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118168482857617e-05, + "loss": 3.705, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117329888106565e-05, + "loss": 3.7179, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116492931235886e-05, + "loss": 3.7004, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115654336484834e-05, + "loss": 3.6977, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114815741733782e-05, + "loss": 3.713, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.11397714698273e-05, + "loss": 3.6993, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113138552231678e-05, + "loss": 3.7094, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112301595360999e-05, + "loss": 3.6785, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111463000609947e-05, + "loss": 3.6862, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.7035, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.695, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7191, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1081086216057394e-05, + "loss": 3.7012, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107270026854687e-05, + "loss": 3.709, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106431432103635e-05, + "loss": 3.6953, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105594475232956e-05, + "loss": 3.7056, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104755880481904e-05, + "loss": 3.6869, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039172857308516e-05, + "loss": 3.7009, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103080328860173e-05, + "loss": 3.7026, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102241734109121e-05, + "loss": 3.6988, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014031393580685e-05, + "loss": 3.695, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005645446070165e-05, + "loss": 3.6898, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099727587736338e-05, + "loss": 3.6806, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7042, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098050398234234e-05, + "loss": 3.7006, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097211803483182e-05, + "loss": 3.6976, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963748466125036e-05, + "loss": 3.6978, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955362518614516e-05, + "loss": 3.7049, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094697657110399e-05, + "loss": 3.6971, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093859062359347e-05, + "loss": 3.6982, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930221054886685e-05, + "loss": 3.6953, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092183510737616e-05, + "loss": 3.6962, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091344915986564e-05, + "loss": 3.698, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090506321235512e-05, + "loss": 3.6835, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896693643648334e-05, + "loss": 3.7068, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888307696137814e-05, + "loss": 3.6943, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879921748627294e-05, + "loss": 3.7031, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871535801116774e-05, + "loss": 3.6981, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086316623240999e-05, + "loss": 3.6858, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085478028489946e-05, + "loss": 3.7064, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084639433738894e-05, + "loss": 3.6846, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083800838987842e-05, + "loss": 3.6924, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082963882117163e-05, + "loss": 3.6847, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082125287366111e-05, + "loss": 3.6969, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081286692615059e-05, + "loss": 3.6915, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080448097864007e-05, + "loss": 3.6923, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079611140993329e-05, + "loss": 3.6893, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.0787741841226504e-05, + "loss": 3.6888, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.0779355893715984e-05, + "loss": 3.6947, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770969946205464e-05, + "loss": 3.6895, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076258399869494e-05, + "loss": 3.7026, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075419805118442e-05, + "loss": 3.6983, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.07458121036739e-05, + "loss": 3.6864, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073742615616338e-05, + "loss": 3.6783, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072904020865286e-05, + "loss": 3.6874, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.0720670639946066e-05, + "loss": 3.7031, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.0712284692435546e-05, + "loss": 3.6873, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.0703898744925026e-05, + "loss": 3.6839, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695512797414506e-05, + "loss": 3.6827, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068714322870772e-05, + "loss": 3.6916, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.06787572811972e-05, + "loss": 3.6804, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067037133368668e-05, + "loss": 3.6867, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066198538617616e-05, + "loss": 3.691, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065361581746937e-05, + "loss": 3.6834, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064522986995885e-05, + "loss": 3.6896, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063684392244833e-05, + "loss": 3.6948, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062847435374154e-05, + "loss": 3.6974, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062008840623102e-05, + "loss": 3.6887, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.06117024587205e-05, + "loss": 3.6859, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060331651120998e-05, + "loss": 3.6907, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594946942503195e-05, + "loss": 3.684, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586560994992675e-05, + "loss": 3.699, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578175047482155e-05, + "loss": 3.6925, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569789099971635e-05, + "loss": 3.6916, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.6726, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6869, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6754, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0536261688733284e-05, + "loss": 3.6903, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.052789212002649e-05, + "loss": 3.6882, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.051950617251597e-05, + "loss": 3.6873, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.051112022500545e-05, + "loss": 3.6895, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.6912, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049436470878815e-05, + "loss": 3.6809, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.048597876127763e-05, + "loss": 3.6855, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047759281376711e-05, + "loss": 3.688, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046920686625659e-05, + "loss": 3.6778, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046082091874607e-05, + "loss": 3.6788, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045243497123555e-05, + "loss": 3.6814, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044404902372503e-05, + "loss": 3.6824, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043567945501824e-05, + "loss": 3.7032, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6797, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.6826, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041053799129041e-05, + "loss": 3.6788, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.6918, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039376609626937e-05, + "loss": 3.6865, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0385380148758853e-05, + "loss": 3.6791, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0376994201248333e-05, + "loss": 3.6907, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036860825373781e-05, + "loss": 3.6706, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036023868503102e-05, + "loss": 3.6716, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.03518527375205e-05, + "loss": 3.687, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.6766, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033509722130319e-05, + "loss": 3.684, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032671127379267e-05, + "loss": 3.6839, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031832532628215e-05, + "loss": 3.6588, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030993937877163e-05, + "loss": 3.6815, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030156981006484e-05, + "loss": 3.6938, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029318386255432e-05, + "loss": 3.6842, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028479791504381e-05, + "loss": 3.673, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027641196753329e-05, + "loss": 3.6743, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026802602002277e-05, + "loss": 3.675, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025964007251224e-05, + "loss": 3.6856, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251270503805456e-05, + "loss": 3.6837, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242884556294936e-05, + "loss": 3.676, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234498608784416e-05, + "loss": 3.6766, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022611266127389e-05, + "loss": 3.6867, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.6796, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209357145056585e-05, + "loss": 3.6715, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200971197546065e-05, + "loss": 3.6861, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192585250035545e-05, + "loss": 3.6781, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.0184199302525025e-05, + "loss": 3.6781, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175813355014505e-05, + "loss": 3.6884, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167427407503985e-05, + "loss": 3.6648, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159041459993465e-05, + "loss": 3.6789, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150671891286674e-05, + "loss": 3.6889, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.0142285943776154e-05, + "loss": 3.6833, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013391637506936e-05, + "loss": 3.6797, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012553042755884e-05, + "loss": 3.6836, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011714448004832e-05, + "loss": 3.6711, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.01087585325378e-05, + "loss": 3.6694, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010037258502728e-05, + "loss": 3.6819, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009198663751676e-05, + "loss": 3.6885, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008360069000624e-05, + "loss": 3.6885, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007521474249572e-05, + "loss": 3.6775, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6712, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.6834, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.00500732787679e-05, + "loss": 3.6747, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004168733125738e-05, + "loss": 3.6804, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.0033334141354317e-05, + "loss": 3.6893, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.0024948193843797e-05, + "loss": 3.6867, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.0016562246333276e-05, + "loss": 3.673, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008176298822756e-05, + "loss": 3.6829, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.9047582149505615, + "eval_runtime": 576.6312, + "eval_samples_per_second": 661.759, + "eval_steps_per_second": 20.68, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.6828, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991404403801716e-05, + "loss": 3.6886, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983018456291196e-05, + "loss": 3.6768, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974632508780676e-05, + "loss": 3.6775, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996624656127016e-05, + "loss": 3.6695, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995786061375964e-05, + "loss": 3.6752, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994947466624912e-05, + "loss": 3.6748, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.99410887187386e-05, + "loss": 3.6603, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6726, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6903, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.99159636338145e-05, + "loss": 3.6705, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990757768630398e-05, + "loss": 3.6679, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.6826, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6686, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6784, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987405027506563e-05, + "loss": 3.6526, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986566432755512e-05, + "loss": 3.6549, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857278380044597e-05, + "loss": 3.6758, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.6647, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.6885, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983212053751303e-05, + "loss": 3.6727, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982373459000251e-05, + "loss": 3.6785, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981534864249199e-05, + "loss": 3.664, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9806995452588935e-05, + "loss": 3.6767, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798609505078415e-05, + "loss": 3.6592, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790223557567895e-05, + "loss": 3.6683, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978183761005737e-05, + "loss": 3.6646, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773451662546854e-05, + "loss": 3.6712, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765065715036334e-05, + "loss": 3.6677, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.6583, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6534, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6712, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973155468260172e-05, + "loss": 3.6735, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.97231687350912e-05, + "loss": 3.6671, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971478278758067e-05, + "loss": 3.6689, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970639684007015e-05, + "loss": 3.6727, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969801089255963e-05, + "loss": 3.6689, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968962494504911e-05, + "loss": 3.6714, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.667, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6671, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966448348132129e-05, + "loss": 3.6704, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965609753381077e-05, + "loss": 3.6545, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.673, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963934201759346e-05, + "loss": 3.672, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963095607008294e-05, + "loss": 3.6723, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962257012257242e-05, + "loss": 3.6709, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.96141841750619e-05, + "loss": 3.6539, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605814606355106e-05, + "loss": 3.6785, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597428658844586e-05, + "loss": 3.6571, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589042711334066e-05, + "loss": 3.6624, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6555, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957228719511676e-05, + "loss": 3.6618, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956391762640997e-05, + "loss": 3.6709, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955553167889945e-05, + "loss": 3.6572, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954714573138893e-05, + "loss": 3.6642, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953875978387841e-05, + "loss": 3.658, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953037383636789e-05, + "loss": 3.6705, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952198788885737e-05, + "loss": 3.6595, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951361832015058e-05, + "loss": 3.6739, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950523237264006e-05, + "loss": 3.6659, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949684642512954e-05, + "loss": 3.6602, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948846047761902e-05, + "loss": 3.6535, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6594, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6678, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6621, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6581, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.6561, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438177550163364e-05, + "loss": 3.6591, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429791602652844e-05, + "loss": 3.6553, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421405655142324e-05, + "loss": 3.6562, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.6583, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.657, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6592, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.6711, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379475917589724e-05, + "loss": 3.6654, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6594, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6612, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935435083266563e-05, + "loss": 3.6631, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6544, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6687, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6668, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.6629, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931242109511303e-05, + "loss": 3.6464, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.93040351476025e-05, + "loss": 3.6578, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6443, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6654, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.6617, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927050773636415e-05, + "loss": 3.656, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6609, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6642, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6538, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.656, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6602, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6508, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6522, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203452913887456e-05, + "loss": 3.6493, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6568, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6742, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.6521, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6542, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916155593394232e-05, + "loss": 3.6547, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.91531699864318e-05, + "loss": 3.6612, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914478403892128e-05, + "loss": 3.6603, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913639809141076e-05, + "loss": 3.6514, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912801214390024e-05, + "loss": 3.6617, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911962619638972e-05, + "loss": 3.643, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911125662768293e-05, + "loss": 3.648, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102887058976145e-05, + "loss": 3.6589, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.652, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.65, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907772921644458e-05, + "loss": 3.6551, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906934326893406e-05, + "loss": 3.6337, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906095732142354e-05, + "loss": 3.6569, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052587752716754e-05, + "loss": 3.6619, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6566, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.645, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027429910185194e-05, + "loss": 3.6486, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019043962674674e-05, + "loss": 3.6458, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6582, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.6548, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899390249894684e-05, + "loss": 3.6511, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898551655143632e-05, + "loss": 3.6481, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.89771306039258e-05, + "loss": 3.6606, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896876103521901e-05, + "loss": 3.6538, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896037508770849e-05, + "loss": 3.6487, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895198914019798e-05, + "loss": 3.6513, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894360319268746e-05, + "loss": 3.6534, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893521724517694e-05, + "loss": 3.6526, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6576, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6418, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6491, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890168983393859e-05, + "loss": 3.6635, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6529, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.6548, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6562, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6469, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.645, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.6512, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884298820136494e-05, + "loss": 3.6643, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.6605, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.6482, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6496, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6525, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880109122141981e-05, + "loss": 3.6517, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6548, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6615, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6601, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6457, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759177862670934e-05, + "loss": 3.6541, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.9011378288269043, + "eval_runtime": 568.9315, + "eval_samples_per_second": 670.715, + "eval_steps_per_second": 20.96, + "step": 686871 + }, + { + "epoch": 0.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.656, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.662, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.6509, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6475, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6448, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.648, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.6501, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.6349, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6465, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6616, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.6458, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6399, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6598, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6403, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633454165228064e-05, + "loss": 3.651, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625068217717544e-05, + "loss": 3.6267, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.8616682270207024e-05, + "loss": 3.6286, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6468, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.8599910375185983e-05, + "loss": 3.6396, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.6598, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6435, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6594, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856638296394763e-05, + "loss": 3.639, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855801339524084e-05, + "loss": 3.6471, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6335, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.85412415002198e-05, + "loss": 3.644, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853285555270929e-05, + "loss": 3.6428, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.85244859840025e-05, + "loss": 3.6462, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851610003649198e-05, + "loss": 3.6404, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850771408898146e-05, + "loss": 3.6359, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849932814147094e-05, + "loss": 3.626, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.849094219396042e-05, + "loss": 3.6477, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.84825562464499e-05, + "loss": 3.645, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.847417029893938e-05, + "loss": 3.6421, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465800730232586e-05, + "loss": 3.6424, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457414782722066e-05, + "loss": 3.6471, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6402, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6443, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.8432256940190506e-05, + "loss": 3.644, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.8423870992679986e-05, + "loss": 3.6391, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841548504516947e-05, + "loss": 3.642, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.8407099097658946e-05, + "loss": 3.6341, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839872952895216e-05, + "loss": 3.6405, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839034358144164e-05, + "loss": 3.6494, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6461, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.8373571686420595e-05, + "loss": 3.6449, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836520211771381e-05, + "loss": 3.6294, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835683254900702e-05, + "loss": 3.6515, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.83484466014965e-05, + "loss": 3.6335, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834006065398598e-05, + "loss": 3.6363, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833167470647546e-05, + "loss": 3.631, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.832328875896494e-05, + "loss": 3.6329, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.831490281145442e-05, + "loss": 3.6476, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.83065168639439e-05, + "loss": 3.6295, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.829813091643338e-05, + "loss": 3.6417, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289777726530324e-05, + "loss": 3.6268, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8281391779019804e-05, + "loss": 3.6431, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8273005831509284e-05, + "loss": 3.6344, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6506, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8256233936488244e-05, + "loss": 3.6416, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824784798897772e-05, + "loss": 3.6326, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.82394620414672e-05, + "loss": 3.6311, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823107609395668e-05, + "loss": 3.6325, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822270652524989e-05, + "loss": 3.6376, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821432057773937e-05, + "loss": 3.6385, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820593463022885e-05, + "loss": 3.6347, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819754868271833e-05, + "loss": 3.6302, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818919549281528e-05, + "loss": 3.634, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818080954530476e-05, + "loss": 3.6289, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817242359779424e-05, + "loss": 3.6337, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816403765028371e-05, + "loss": 3.6308, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815565170277319e-05, + "loss": 3.6279, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814726575526267e-05, + "loss": 3.6377, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813887980775215e-05, + "loss": 3.6446, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813049386024163e-05, + "loss": 3.6405, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.638, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811375472282806e-05, + "loss": 3.632, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810536877531754e-05, + "loss": 3.6423, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096982827807016e-05, + "loss": 3.6284, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8088596880296496e-05, + "loss": 3.6414, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8080210932785976e-05, + "loss": 3.6419, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6396, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8063439037764936e-05, + "loss": 3.6237, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8055069469058145e-05, + "loss": 3.6296, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046683521547625e-05, + "loss": 3.6184, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.641, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6355, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.80215420578198e-05, + "loss": 3.6327, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801315611030928e-05, + "loss": 3.6371, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800477016279876e-05, + "loss": 3.6377, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6268, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798801464658145e-05, + "loss": 3.631, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797962869907093e-05, + "loss": 3.6393, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797124275156041e-05, + "loss": 3.6225, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.627, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.79544872353431e-05, + "loss": 3.6291, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794610128783258e-05, + "loss": 3.6317, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793771534032206e-05, + "loss": 3.646, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.7929345771615274e-05, + "loss": 3.627, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.7920959824104754e-05, + "loss": 3.6328, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7912573876594234e-05, + "loss": 3.6306, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7904187929083714e-05, + "loss": 3.6362, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.7895801981573194e-05, + "loss": 3.6364, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.6293, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787904646535588e-05, + "loss": 3.6348, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787066051784536e-05, + "loss": 3.6208, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786227457033484e-05, + "loss": 3.623, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785388862282432e-05, + "loss": 3.632, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784551905411753e-05, + "loss": 3.6277, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783713310660701e-05, + "loss": 3.6241, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782874715909649e-05, + "loss": 3.6337, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782036121158597e-05, + "loss": 3.6106, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6299, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780360569536867e-05, + "loss": 3.6383, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779521974785815e-05, + "loss": 3.6329, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778683380034763e-05, + "loss": 3.6233, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.6236, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6225, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6317, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775330638910928e-05, + "loss": 3.631, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6336, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6181, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6387, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.7719762599067196e-05, + "loss": 3.6239, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.771139303036041e-05, + "loss": 3.6269, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.770300708284989e-05, + "loss": 3.6245, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.769462113533937e-05, + "loss": 3.6323, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.768623518782885e-05, + "loss": 3.6252, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7677849240318325e-05, + "loss": 3.6314, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669463292807805e-05, + "loss": 3.6194, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661077345297285e-05, + "loss": 3.6253, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652707776590494e-05, + "loss": 3.6399, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644321829079974e-05, + "loss": 3.6274, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7635935881569454e-05, + "loss": 3.6289, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627549934058934e-05, + "loss": 3.6353, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761918036535215e-05, + "loss": 3.6216, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761079441784163e-05, + "loss": 3.623, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760240847033111e-05, + "loss": 3.627, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759402252282059e-05, + "loss": 3.6322, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.75856529541138e-05, + "loss": 3.6408, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757726700660328e-05, + "loss": 3.6236, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756888105909276e-05, + "loss": 3.6266, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756049511158224e-05, + "loss": 3.6265, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755210916407172e-05, + "loss": 3.6267, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754373959536493e-05, + "loss": 3.6314, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753535364785441e-05, + "loss": 3.6358, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752696770034389e-05, + "loss": 3.6361, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751858175283337e-05, + "loss": 3.6227, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751019580532285e-05, + "loss": 3.63, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8989105224609375, + "eval_runtime": 316.6879, + "eval_samples_per_second": 1204.943, + "eval_steps_per_second": 37.655, + "step": 763190 + }, + { + "epoch": 1.0, + "learning_rate": 3.7501826236616064e-05, + "loss": 3.6338, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7493440289105544e-05, + "loss": 3.6341, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7485054341595024e-05, + "loss": 3.6305, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7476668394084504e-05, + "loss": 3.6226, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7468282446573984e-05, + "loss": 3.6237, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459896499063463e-05, + "loss": 3.6228, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.7451510551552943e-05, + "loss": 3.6275, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744314098284615e-05, + "loss": 3.6064, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743475503533563e-05, + "loss": 3.6234, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742636908782511e-05, + "loss": 3.6392, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741799951911832e-05, + "loss": 3.6236, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.74096135716078e-05, + "loss": 3.6188, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740122762409728e-05, + "loss": 3.6316, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739284167658677e-05, + "loss": 3.6168, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738445572907625e-05, + "loss": 3.6258, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737606978156573e-05, + "loss": 3.6022, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736768383405521e-05, + "loss": 3.6021, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735929788654468e-05, + "loss": 3.6265, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.735091193903416e-05, + "loss": 3.6176, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734252599152364e-05, + "loss": 3.6365, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733414004401312e-05, + "loss": 3.6184, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.732577047530633e-05, + "loss": 3.635, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317400906599546e-05, + "loss": 3.6193, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7309014959089026e-05, + "loss": 3.6217, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300629011578506e-05, + "loss": 3.6093, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292243064067986e-05, + "loss": 3.6231, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.72838734953612e-05, + "loss": 3.6202, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.727548754785068e-05, + "loss": 3.6224, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7267101600340155e-05, + "loss": 3.6141, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7258715652829635e-05, + "loss": 3.6173, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7250329705319115e-05, + "loss": 3.5995, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724196013661233e-05, + "loss": 3.6269, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7233574189101804e-05, + "loss": 3.6221, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7225188241591284e-05, + "loss": 3.6191, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216802294080764e-05, + "loss": 3.6202, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.7208416346570244e-05, + "loss": 3.6241, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.720004677786346e-05, + "loss": 3.6186, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719166083035294e-05, + "loss": 3.6207, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718327488284242e-05, + "loss": 3.6205, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.71748889353319e-05, + "loss": 3.6173, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716650298782138e-05, + "loss": 3.618, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715813341911459e-05, + "loss": 3.6137, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714974747160407e-05, + "loss": 3.6169, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714136152409355e-05, + "loss": 3.6236, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713297557658303e-05, + "loss": 3.6205, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712458962907251e-05, + "loss": 3.6229, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711622006036572e-05, + "loss": 3.6076, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.71078341128552e-05, + "loss": 3.6273, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709944816534468e-05, + "loss": 3.6125, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709106221783416e-05, + "loss": 3.6101, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7082676270323644e-05, + "loss": 3.6117, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7074290322813124e-05, + "loss": 3.6111, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7065904375302604e-05, + "loss": 3.6218, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705753480659581e-05, + "loss": 3.6093, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704914885908529e-05, + "loss": 3.6189, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704076291157477e-05, + "loss": 3.6039, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703237696406425e-05, + "loss": 3.6235, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702399101655373e-05, + "loss": 3.6109, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701560506904321e-05, + "loss": 3.6241, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700723550033642e-05, + "loss": 3.6206, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.69988495528259e-05, + "loss": 3.6124, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699046360531538e-05, + "loss": 3.6098, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698207765780486e-05, + "loss": 3.6065, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697370808909808e-05, + "loss": 3.6128, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696532214158756e-05, + "loss": 3.6185, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695693619407704e-05, + "loss": 3.6145, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694855024656652e-05, + "loss": 3.607, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694018067785973e-05, + "loss": 3.609, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693179473034921e-05, + "loss": 3.6079, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.6923408782838687e-05, + "loss": 3.6094, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.6915022835328167e-05, + "loss": 3.6095, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906653266621376e-05, + "loss": 3.6099, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898267319110856e-05, + "loss": 3.6119, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.6889881371600336e-05, + "loss": 3.6232, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6881495424089815e-05, + "loss": 3.6178, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687312585538303e-05, + "loss": 3.6122, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.686473990787251e-05, + "loss": 3.6119, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.685635396036199e-05, + "loss": 3.6169, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847968012851464e-05, + "loss": 3.6107, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6839582065340944e-05, + "loss": 3.6161, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683121249663416e-05, + "loss": 3.6232, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682282654912364e-05, + "loss": 3.6176, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814440601613113e-05, + "loss": 3.6038, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680605465410259e-05, + "loss": 3.6034, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679766870659207e-05, + "loss": 3.597, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678929913788529e-05, + "loss": 3.6183, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678091319037477e-05, + "loss": 3.6112, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677252724286425e-05, + "loss": 3.6144, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676414129535373e-05, + "loss": 3.6136, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675575534784321e-05, + "loss": 3.616, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674736940033269e-05, + "loss": 3.6065, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673898345282217e-05, + "loss": 3.6075, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673059750531165e-05, + "loss": 3.6179, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672222793660486e-05, + "loss": 3.5987, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671384198909434e-05, + "loss": 3.6033, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670545604158382e-05, + "loss": 3.6042, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669708647287703e-05, + "loss": 3.6127, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668870052536651e-05, + "loss": 3.6179, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668031457785599e-05, + "loss": 3.6117, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667192863034547e-05, + "loss": 3.6119, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.6663542682834954e-05, + "loss": 3.6051, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.6655156735324434e-05, + "loss": 3.6149, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6646770787813914e-05, + "loss": 3.6112, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6638384840303393e-05, + "loss": 3.6119, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.66300152715966e-05, + "loss": 3.6102, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662162932408608e-05, + "loss": 3.5961, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661324337657556e-05, + "loss": 3.5994, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.660485742906504e-05, + "loss": 3.6105, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659648786035825e-05, + "loss": 3.6082, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658810191284773e-05, + "loss": 3.6015, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657971596533721e-05, + "loss": 3.6145, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657133001782669e-05, + "loss": 3.5905, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656294407031617e-05, + "loss": 3.6036, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655457450160939e-05, + "loss": 3.6132, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654618855409887e-05, + "loss": 3.6154, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653780260658835e-05, + "loss": 3.6023, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652941665907783e-05, + "loss": 3.6056, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.65210307115673e-05, + "loss": 3.5948, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6512661142860516e-05, + "loss": 3.6081, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6504275195349996e-05, + "loss": 3.6101, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6495889247839476e-05, + "loss": 3.6084, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648750330032895e-05, + "loss": 3.5966, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647911735281843e-05, + "loss": 3.6148, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.6470747784111645e-05, + "loss": 3.6046, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.6462361836601125e-05, + "loss": 3.6046, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6453975889090605e-05, + "loss": 3.6003, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6445589941580085e-05, + "loss": 3.6152, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.6437203994069565e-05, + "loss": 3.6042, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6428834425362774e-05, + "loss": 3.6081, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6420448477852254e-05, + "loss": 3.6011, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6412062530341734e-05, + "loss": 3.6015, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6403676582831214e-05, + "loss": 3.6135, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.6097, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.63869210666139e-05, + "loss": 3.6076, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637853511910338e-05, + "loss": 3.6164, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637014917159286e-05, + "loss": 3.6006, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.5977, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635339365537556e-05, + "loss": 3.6068, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634500770786504e-05, + "loss": 3.6121, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633662176035452e-05, + "loss": 3.6202, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.6328235812844e-05, + "loss": 3.6024, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631984986533348e-05, + "loss": 3.6072, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631148029662669e-05, + "loss": 3.6019, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630309434911617e-05, + "loss": 3.6057, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629470840160565e-05, + "loss": 3.609, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.628632245409513e-05, + "loss": 3.6133, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627793650658461e-05, + "loss": 3.6198, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6269566937877816e-05, + "loss": 3.5988, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6261180990367296e-05, + "loss": 3.6103, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8982067108154297, + "eval_runtime": 324.2015, + "eval_samples_per_second": 1177.018, + "eval_steps_per_second": 36.783, + "step": 839509 + }, + { + "epoch": 0.0, + "learning_rate": 3.6252795042856776e-05, + "loss": 3.6162, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624440909534626e-05, + "loss": 3.6078, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623602314783574e-05, + "loss": 3.6104, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622763720032522e-05, + "loss": 3.6127, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.62192512528147e-05, + "loss": 3.6191, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621088168410791e-05, + "loss": 3.6064, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620249573659739e-05, + "loss": 3.6085, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619410978908687e-05, + "loss": 3.6034, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618572384157635e-05, + "loss": 3.6081, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617733789406583e-05, + "loss": 3.6128, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616896832535904e-05, + "loss": 3.6056, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616058237784852e-05, + "loss": 3.6075, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615221280914173e-05, + "loss": 3.6163, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614382686163122e-05, + "loss": 3.5956, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.61354409141207e-05, + "loss": 3.6037, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612705496661018e-05, + "loss": 3.5978, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611866901909966e-05, + "loss": 3.5953, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110283071589137e-05, + "loss": 3.6046, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610189712407861e-05, + "loss": 3.5981, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609351117656809e-05, + "loss": 3.6217, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608512522905757e-05, + "loss": 3.6158, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607675566035078e-05, + "loss": 3.6078, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606836971284026e-05, + "loss": 3.6045, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605998376532974e-05, + "loss": 3.6072, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605159781781922e-05, + "loss": 3.5952, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.60432118703087e-05, + "loss": 3.6105, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034825922798185e-05, + "loss": 3.6056, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6026456354091394e-05, + "loss": 3.5898, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6018070406580874e-05, + "loss": 3.6013, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6009684459070354e-05, + "loss": 3.5984, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6001298511559834e-05, + "loss": 3.6052, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5992928942853043e-05, + "loss": 3.6025, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598454299534252e-05, + "loss": 3.6046, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.5976157047832e-05, + "loss": 3.609, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596777110032148e-05, + "loss": 3.5966, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595940153161469e-05, + "loss": 3.6105, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595101558410417e-05, + "loss": 3.6109, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594262963659365e-05, + "loss": 3.5965, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.593424368908314e-05, + "loss": 3.6009, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592585774157262e-05, + "loss": 3.599, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.59174717940621e-05, + "loss": 3.5962, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590910222535531e-05, + "loss": 3.607, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590071627784479e-05, + "loss": 3.6047, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589233033033427e-05, + "loss": 3.608, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588394438282375e-05, + "loss": 3.6041, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587557481411696e-05, + "loss": 3.604, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586718886660644e-05, + "loss": 3.6057, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585880291909592e-05, + "loss": 3.6051, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.58504169715854e-05, + "loss": 3.5788, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5842047402878606e-05, + "loss": 3.6114, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583366145536809e-05, + "loss": 3.5947, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582527550785757e-05, + "loss": 3.6095, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581688956034705e-05, + "loss": 3.6055, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580851999164026e-05, + "loss": 3.5957, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580013404412974e-05, + "loss": 3.5873, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579174809661922e-05, + "loss": 3.5984, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.57833621491087e-05, + "loss": 3.616, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577499258040191e-05, + "loss": 3.5968, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576660663289139e-05, + "loss": 3.6155, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.575822068538087e-05, + "loss": 3.601, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574983473787035e-05, + "loss": 3.5774, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574144879035983e-05, + "loss": 3.6173, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.5733079221653046e-05, + "loss": 3.5944, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.5724693274142526e-05, + "loss": 3.5868, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5716307326632006e-05, + "loss": 3.6006, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5707921379121486e-05, + "loss": 3.6002, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699551810414695e-05, + "loss": 3.5868, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5691165862904175e-05, + "loss": 3.594, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5682779915393655e-05, + "loss": 3.5858, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.5674393967883135e-05, + "loss": 3.5922, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.5666008020372615e-05, + "loss": 3.606, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.5657638451665824e-05, + "loss": 3.5988, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.5649252504155304e-05, + "loss": 3.5979, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640866556644784e-05, + "loss": 3.591, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632480609134264e-05, + "loss": 3.6069, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.562411104042748e-05, + "loss": 3.6018, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561572509291696e-05, + "loss": 3.6076, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560733914540644e-05, + "loss": 3.5923, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559895319789591e-05, + "loss": 3.5896, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559058362918913e-05, + "loss": 3.6007, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558219768167861e-05, + "loss": 3.6078, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557381173416809e-05, + "loss": 3.5957, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556542578665756e-05, + "loss": 3.603, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555703983914704e-05, + "loss": 3.5838, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554867027044026e-05, + "loss": 3.5936, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554028432292974e-05, + "loss": 3.597, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553189837541922e-05, + "loss": 3.6058, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.55235124279087e-05, + "loss": 3.5908, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.5515142859201914e-05, + "loss": 3.5912, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550675691169139e-05, + "loss": 3.596, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549837096418087e-05, + "loss": 3.596, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548998501667035e-05, + "loss": 3.5988, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.548159906915983e-05, + "loss": 3.586, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473229500453036e-05, + "loss": 3.5992, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464843552942516e-05, + "loss": 3.6086, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456457605431996e-05, + "loss": 3.6031, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5448071657921476e-05, + "loss": 3.577, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439702089214685e-05, + "loss": 3.59, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.543131614170417e-05, + "loss": 3.5905, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542293019419365e-05, + "loss": 3.6045, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541454424668313e-05, + "loss": 3.6035, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540617467797634e-05, + "loss": 3.5937, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539778873046582e-05, + "loss": 3.5868, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.53894027829553e-05, + "loss": 3.5987, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538101683544478e-05, + "loss": 3.5837, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537264726673799e-05, + "loss": 3.5933, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536426131922747e-05, + "loss": 3.5893, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535587537171695e-05, + "loss": 3.5976, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534748942420643e-05, + "loss": 3.5898, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533910347669591e-05, + "loss": 3.5781, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.5330733907989125e-05, + "loss": 3.5855, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.5322347960478605e-05, + "loss": 3.5826, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5313962012968085e-05, + "loss": 3.5964, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5305576065457565e-05, + "loss": 3.5883, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5297206496750774e-05, + "loss": 3.5959, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5288820549240254e-05, + "loss": 3.5954, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5280434601729734e-05, + "loss": 3.589, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5272048654219214e-05, + "loss": 3.6004, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263662706708694e-05, + "loss": 3.5919, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.52552931380019e-05, + "loss": 3.5912, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524690719049138e-05, + "loss": 3.5871, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523852124298086e-05, + "loss": 3.5846, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.523013529547034e-05, + "loss": 3.5944, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522174934795982e-05, + "loss": 3.5879, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521337977925304e-05, + "loss": 3.5947, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520499383174252e-05, + "loss": 3.5915, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.5196607884232e-05, + "loss": 3.5911, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518822193672148e-05, + "loss": 3.5879, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517985236801469e-05, + "loss": 3.5768, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517146642050417e-05, + "loss": 3.5971, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516308047299365e-05, + "loss": 3.588, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.515469452548313e-05, + "loss": 3.6058, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146324956776337e-05, + "loss": 3.5869, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5137939009265817e-05, + "loss": 3.5979, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5129553061755297e-05, + "loss": 3.5966, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5121167114244776e-05, + "loss": 3.5858, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511278116673426e-05, + "loss": 3.5915, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510441159802747e-05, + "loss": 3.5862, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509602565051695e-05, + "loss": 3.5986, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508763970300643e-05, + "loss": 3.5979, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507925375549591e-05, + "loss": 3.5867, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.507088418678912e-05, + "loss": 3.5872, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.50624982392786e-05, + "loss": 3.591, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505411229176808e-05, + "loss": 3.5956, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504572634425756e-05, + "loss": 3.5831, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503735677555077e-05, + "loss": 3.6079, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.5883, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502058488052973e-05, + "loss": 3.5971, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501219893301922e-05, + "loss": 3.5887, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.89139986038208, + "eval_runtime": 303.6857, + "eval_samples_per_second": 1256.533, + "eval_steps_per_second": 39.268, + "step": 915829 + }, + { + "epoch": 1.0, + "learning_rate": 3.5003829364312426e-05, + "loss": 3.5919, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.4995443416801906e-05, + "loss": 3.5856, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.4987057469291386e-05, + "loss": 3.5901, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.4978671521780866e-05, + "loss": 3.5921, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.4970285574270346e-05, + "loss": 3.5962, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.4961916005563555e-05, + "loss": 3.5876, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.4953530058053035e-05, + "loss": 3.5881, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.4945144110542515e-05, + "loss": 3.5864, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493675816303199e-05, + "loss": 3.5855, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492837221552147e-05, + "loss": 3.5848, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.5895, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.4911616699304164e-05, + "loss": 3.5869, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.4903230751793644e-05, + "loss": 3.5948, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4894844804283124e-05, + "loss": 3.5747, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488647523557634e-05, + "loss": 3.5799, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487808928806582e-05, + "loss": 3.574, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486970334055529e-05, + "loss": 3.5744, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486131739304477e-05, + "loss": 3.5832, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485294782433799e-05, + "loss": 3.577, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484456187682746e-05, + "loss": 3.5973, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.5949, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.5859, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.5836, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481103446558912e-05, + "loss": 3.587, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.5715, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.5922, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5805, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.4777507054350766e-05, + "loss": 3.5683, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.4769121106840246e-05, + "loss": 3.5818, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5762, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.5816, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4743979643112415e-05, + "loss": 3.58, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735593695601895e-05, + "loss": 3.5875, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.5819, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5769, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471045223187407e-05, + "loss": 3.5883, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470206628436355e-05, + "loss": 3.5878, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469368033685303e-05, + "loss": 3.5787, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468529438934251e-05, + "loss": 3.5761, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467692482063572e-05, + "loss": 3.578, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.46685388731252e-05, + "loss": 3.5742, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.466015292561468e-05, + "loss": 3.5852, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.465176697810416e-05, + "loss": 3.5853, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464339740939737e-05, + "loss": 3.5884, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463501146188685e-05, + "loss": 3.583, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462662551437633e-05, + "loss": 3.5785, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461823956686581e-05, + "loss": 3.5843, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.4609869998159025e-05, + "loss": 3.5831, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.4601484050648505e-05, + "loss": 3.5588, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.4593098103137985e-05, + "loss": 3.5884, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.4584712155627465e-05, + "loss": 3.5741, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.4576342586920674e-05, + "loss": 3.5858, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.4567956639410154e-05, + "loss": 3.5827, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.4559570691899634e-05, + "loss": 3.5781, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.4551184744389114e-05, + "loss": 3.5653, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454281517568232e-05, + "loss": 3.5754, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.45344292281718e-05, + "loss": 3.5964, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452604328066128e-05, + "loss": 3.5781, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451765733315076e-05, + "loss": 3.5925, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450928776444398e-05, + "loss": 3.5788, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.450090181693346e-05, + "loss": 3.5583, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.449251586942294e-05, + "loss": 3.5976, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448412992191242e-05, + "loss": 3.5746, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.44757439744019e-05, + "loss": 3.5667, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446737440569511e-05, + "loss": 3.5791, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445898845818459e-05, + "loss": 3.5769, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445060251067407e-05, + "loss": 3.5671, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444221656316355e-05, + "loss": 3.569, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.4433846994456756e-05, + "loss": 3.5669, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.4425461046946236e-05, + "loss": 3.5721, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.4417075099435716e-05, + "loss": 3.5834, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.44086891519252e-05, + "loss": 3.5791, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440030320441468e-05, + "loss": 3.5779, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439193363570789e-05, + "loss": 3.5672, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438354768819737e-05, + "loss": 3.5871, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437516174068685e-05, + "loss": 3.5809, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436677579317633e-05, + "loss": 3.5876, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435840622446954e-05, + "loss": 3.5731, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.435002027695902e-05, + "loss": 3.5719, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.43416343294485e-05, + "loss": 3.5815, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433324838193798e-05, + "loss": 3.5816, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.432487881323119e-05, + "loss": 3.577, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.431649286572067e-05, + "loss": 3.5822, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.430810691821016e-05, + "loss": 3.5651, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4299720970699637e-05, + "loss": 3.5722, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291351401992846e-05, + "loss": 3.5764, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.4282965454482326e-05, + "loss": 3.5861, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.4274579506971806e-05, + "loss": 3.5673, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.4266193559461286e-05, + "loss": 3.5751, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.4257807611950765e-05, + "loss": 3.5744, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.4249438043243975e-05, + "loss": 3.5754, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.4241052095733455e-05, + "loss": 3.5771, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.4232666148222934e-05, + "loss": 3.5684, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.4224280200712414e-05, + "loss": 3.5776, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.4215910632005624e-05, + "loss": 3.5855, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420752468449511e-05, + "loss": 3.5866, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419913873698459e-05, + "loss": 3.5544, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419075278947407e-05, + "loss": 3.5719, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418238322076728e-05, + "loss": 3.5679, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.417399727325676e-05, + "loss": 3.5844, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.416561132574624e-05, + "loss": 3.5841, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.415722537823572e-05, + "loss": 3.5724, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.414883943072519e-05, + "loss": 3.5657, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414046986201841e-05, + "loss": 3.5752, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413208391450789e-05, + "loss": 3.5688, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.412369796699737e-05, + "loss": 3.5705, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.411531201948685e-05, + "loss": 3.5667, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4106942450780064e-05, + "loss": 3.5762, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.4098556503269544e-05, + "loss": 3.5726, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409017055575902e-05, + "loss": 3.5593, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.40817846082485e-05, + "loss": 3.5621, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407341503954171e-05, + "loss": 3.5645, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406502909203119e-05, + "loss": 3.5756, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.4056643144520666e-05, + "loss": 3.5657, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404827357581388e-05, + "loss": 3.5755, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403988762830336e-05, + "loss": 3.573, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403150168079284e-05, + "loss": 3.5725, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.4023115733282315e-05, + "loss": 3.5737, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401474616457553e-05, + "loss": 3.574, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400636021706501e-05, + "loss": 3.574, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399797426955449e-05, + "loss": 3.5658, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398958832204397e-05, + "loss": 3.5625, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.398120237453345e-05, + "loss": 3.5756, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3972832805826667e-05, + "loss": 3.5685, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.396444685831614e-05, + "loss": 3.5745, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395606091080562e-05, + "loss": 3.5689, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.39476749632951e-05, + "loss": 3.5698, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3939305394588316e-05, + "loss": 3.5715, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.393091944707779e-05, + "loss": 3.5596, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.392253349956727e-05, + "loss": 3.5725, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.391414755205675e-05, + "loss": 3.5708, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.3905777983349965e-05, + "loss": 3.5847, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.3897392035839444e-05, + "loss": 3.5664, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.3889006088328924e-05, + "loss": 3.5746, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.3880620140818404e-05, + "loss": 3.5783, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.3872250572111613e-05, + "loss": 3.5674, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.3863864624601093e-05, + "loss": 3.5689, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385547867709057e-05, + "loss": 3.5708, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384709272958005e-05, + "loss": 3.5783, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383872316087326e-05, + "loss": 3.5785, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383033721336274e-05, + "loss": 3.5721, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382195126585222e-05, + "loss": 3.565, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.38135653183417e-05, + "loss": 3.5716, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380519574963492e-05, + "loss": 3.5768, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.37968098021244e-05, + "loss": 3.5587, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378842385461388e-05, + "loss": 3.5906, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.378003790710336e-05, + "loss": 3.569, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377166833839657e-05, + "loss": 3.5742, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376328239088605e-05, + "loss": 3.569, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.893287420272827, + "eval_runtime": 413.8322, + "eval_samples_per_second": 922.091, + "eval_steps_per_second": 28.816, + "step": 992149 + }, + { + "epoch": 0.0, + "learning_rate": 3.375489644337553e-05, + "loss": 3.5917, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374651049586501e-05, + "loss": 3.5664, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373812454835449e-05, + "loss": 3.569, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372973860084397e-05, + "loss": 3.575, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372135265333345e-05, + "loss": 3.5742, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.3712983084626656e-05, + "loss": 3.5718, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370459713711614e-05, + "loss": 3.5663, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369621118960562e-05, + "loss": 3.5647, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368784162089883e-05, + "loss": 3.5666, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367945567338831e-05, + "loss": 3.5702, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367106972587779e-05, + "loss": 3.5693, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366268377836727e-05, + "loss": 3.5705, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365431420966048e-05, + "loss": 3.5745, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364592826214996e-05, + "loss": 3.5569, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363754231463944e-05, + "loss": 3.5626, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.362915636712892e-05, + "loss": 3.5543, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.36207704196184e-05, + "loss": 3.5521, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361240085091161e-05, + "loss": 3.5663, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.3604014903401096e-05, + "loss": 3.5563, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3595628955890576e-05, + "loss": 3.576, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3587243008380056e-05, + "loss": 3.5786, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578873439673265e-05, + "loss": 3.5672, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570487492162745e-05, + "loss": 3.5651, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562101544652225e-05, + "loss": 3.5683, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553715597141705e-05, + "loss": 3.5496, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545329649631185e-05, + "loss": 3.5746, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3536960080924394e-05, + "loss": 3.5612, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528574133413874e-05, + "loss": 3.5573, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520188185903354e-05, + "loss": 3.5609, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511802238392834e-05, + "loss": 3.554, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350343266968605e-05, + "loss": 3.5622, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349504672217553e-05, + "loss": 3.5633, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348666077466501e-05, + "loss": 3.5706, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347827482715449e-05, + "loss": 3.5649, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346988887964397e-05, + "loss": 3.5584, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346151931093718e-05, + "loss": 3.562, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345313336342666e-05, + "loss": 3.5721, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344474741591614e-05, + "loss": 3.5579, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343636146840562e-05, + "loss": 3.56, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342799189969883e-05, + "loss": 3.5578, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341960595218831e-05, + "loss": 3.5617, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341122000467779e-05, + "loss": 3.5604, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340283405716727e-05, + "loss": 3.5668, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394464488460484e-05, + "loss": 3.5706, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386078540949964e-05, + "loss": 3.5623, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377692593439444e-05, + "loss": 3.5633, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369306645928924e-05, + "loss": 3.5605, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336093707722213e-05, + "loss": 3.567, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335255112971161e-05, + "loss": 3.5397, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334416518220109e-05, + "loss": 3.5684, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.3335779234690566e-05, + "loss": 3.5563, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.3327393287180046e-05, + "loss": 3.5664, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331902371847326e-05, + "loss": 3.5639, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331063777096274e-05, + "loss": 3.558, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330225182345222e-05, + "loss": 3.5538, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329388225474544e-05, + "loss": 3.5537, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328549630723492e-05, + "loss": 3.5774, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.32771103597244e-05, + "loss": 3.5552, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326872441221387e-05, + "loss": 3.5761, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.3260354843507086e-05, + "loss": 3.5587, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.3251968895996566e-05, + "loss": 3.5455, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324358294848604e-05, + "loss": 3.5758, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323519700097552e-05, + "loss": 3.5588, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226811053465e-05, + "loss": 3.5435, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218441484758215e-05, + "loss": 3.5564, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3210055537247695e-05, + "loss": 3.5632, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201669589737175e-05, + "loss": 3.5477, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193283642226655e-05, + "loss": 3.5535, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184914073519864e-05, + "loss": 3.5516, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176528126009344e-05, + "loss": 3.5473, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3168142178498824e-05, + "loss": 3.5661, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3159756230988304e-05, + "loss": 3.5624, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315138666228151e-05, + "loss": 3.5591, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314300071477099e-05, + "loss": 3.549, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313461476726047e-05, + "loss": 3.5667, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312622881974995e-05, + "loss": 3.5615, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311785925104316e-05, + "loss": 3.5688, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310947330353264e-05, + "loss": 3.5525, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310108735602213e-05, + "loss": 3.5544, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309270140851161e-05, + "loss": 3.5638, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308433183980482e-05, + "loss": 3.5601, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.30759458922943e-05, + "loss": 3.5594, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306755994478378e-05, + "loss": 3.5646, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305917399727326e-05, + "loss": 3.5505, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305080442856647e-05, + "loss": 3.5495, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.304241848105595e-05, + "loss": 3.5603, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303403253354543e-05, + "loss": 3.5639, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302564658603491e-05, + "loss": 3.5552, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017277017328116e-05, + "loss": 3.5528, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3008891069817596e-05, + "loss": 3.5571, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300050512230708e-05, + "loss": 3.5601, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299211917479656e-05, + "loss": 3.5538, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298374960608977e-05, + "loss": 3.5548, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297536365857925e-05, + "loss": 3.5579, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296697771106873e-05, + "loss": 3.5686, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295859176355821e-05, + "loss": 3.5681, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295022219485142e-05, + "loss": 3.5379, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.29418362473409e-05, + "loss": 3.5528, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293345029983038e-05, + "loss": 3.5502, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292506435231986e-05, + "loss": 3.5655, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291669478361307e-05, + "loss": 3.5623, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290830883610255e-05, + "loss": 3.5591, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.2899922888592036e-05, + "loss": 3.5443, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891536941081516e-05, + "loss": 3.5624, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883167372374725e-05, + "loss": 3.5508, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2874781424864205e-05, + "loss": 3.5516, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2866395477353685e-05, + "loss": 3.5503, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.2858009529843165e-05, + "loss": 3.5561, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849639961136374e-05, + "loss": 3.5575, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2841254013625854e-05, + "loss": 3.5407, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2832868066115334e-05, + "loss": 3.5485, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824482118604814e-05, + "loss": 3.5407, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2816096171094294e-05, + "loss": 3.5594, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.28077266023875e-05, + "loss": 3.5507, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279934065487699e-05, + "loss": 3.5542, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279095470736647e-05, + "loss": 3.5563, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278256875985595e-05, + "loss": 3.5561, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.277419919114916e-05, + "loss": 3.5554, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276581324363864e-05, + "loss": 3.5545, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275742729612812e-05, + "loss": 3.5588, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.27490413486176e-05, + "loss": 3.5486, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274067177991081e-05, + "loss": 3.5398, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273228583240029e-05, + "loss": 3.5583, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272389988488977e-05, + "loss": 3.5528, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271551393737925e-05, + "loss": 3.555, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270714436867246e-05, + "loss": 3.5483, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698758421161943e-05, + "loss": 3.5538, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690372473651423e-05, + "loss": 3.5561, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.26819865261409e-05, + "loss": 3.5445, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267361695743411e-05, + "loss": 3.5476, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266523100992359e-05, + "loss": 3.5579, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265684506241307e-05, + "loss": 3.5699, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264845911490255e-05, + "loss": 3.5505, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.264007316739203e-05, + "loss": 3.5482, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263170359868524e-05, + "loss": 3.5638, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262331765117472e-05, + "loss": 3.5523, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.26149317036642e-05, + "loss": 3.5494, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260654575615368e-05, + "loss": 3.5498, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.25981761874469e-05, + "loss": 3.5628, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258979023993638e-05, + "loss": 3.5614, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258140429242586e-05, + "loss": 3.5538, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257301834491534e-05, + "loss": 3.5474, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.2564648776208546e-05, + "loss": 3.5556, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2556262828698026e-05, + "loss": 3.5558, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.2547876881187506e-05, + "loss": 3.5448, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.2539490933676986e-05, + "loss": 3.5727, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.2531121364970195e-05, + "loss": 3.5505, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522735417459675e-05, + "loss": 3.5578, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2514349469949155e-05, + "loss": 3.552, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8943638801574707, + "eval_runtime": 302.8082, + "eval_samples_per_second": 1260.174, + "eval_steps_per_second": 39.381, + "step": 1068469 + }, + { + "epoch": 1.0, + "learning_rate": 3.2505963522438635e-05, + "loss": 3.5571, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2497577574928115e-05, + "loss": 3.5467, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.248920800622133e-05, + "loss": 3.5509, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248082205871081e-05, + "loss": 3.56, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247243611120029e-05, + "loss": 3.5537, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246405016368977e-05, + "loss": 3.5567, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245568059498298e-05, + "loss": 3.5491, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.244729464747246e-05, + "loss": 3.546, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243890869996194e-05, + "loss": 3.5481, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243052275245141e-05, + "loss": 3.5562, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242215318374463e-05, + "loss": 3.551, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.241376723623411e-05, + "loss": 3.5543, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240538128872359e-05, + "loss": 3.5582, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239699534121307e-05, + "loss": 3.5362, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.2388625772506284e-05, + "loss": 3.5464, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.2380239824995764e-05, + "loss": 3.5357, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.2371853877485244e-05, + "loss": 3.5351, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.236346792997472e-05, + "loss": 3.5515, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.235509836126793e-05, + "loss": 3.5386, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234671241375741e-05, + "loss": 3.5596, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.2338326466246887e-05, + "loss": 3.5626, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.2329940518736366e-05, + "loss": 3.5467, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232157095002958e-05, + "loss": 3.5507, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.231318500251906e-05, + "loss": 3.5541, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230479905500854e-05, + "loss": 3.5354, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229641310749802e-05, + "loss": 3.5551, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228804353879124e-05, + "loss": 3.5431, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227965759128072e-05, + "loss": 3.5423, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227127164377019e-05, + "loss": 3.5433, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226288569625967e-05, + "loss": 3.5362, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225451612755289e-05, + "loss": 3.5413, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224613018004236e-05, + "loss": 3.5513, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223774423253184e-05, + "loss": 3.553, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.222935828502132e-05, + "loss": 3.5432, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.2220988716314536e-05, + "loss": 3.5406, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221260276880401e-05, + "loss": 3.544, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.220421682129349e-05, + "loss": 3.5587, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2195830873782976e-05, + "loss": 3.5393, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.218746130507619e-05, + "loss": 3.5429, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2179075357565665e-05, + "loss": 3.5418, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.2170689410055145e-05, + "loss": 3.5395, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.2162303462544625e-05, + "loss": 3.5438, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.2153933893837834e-05, + "loss": 3.5505, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.2145547946327314e-05, + "loss": 3.5544, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.2137161998816794e-05, + "loss": 3.5459, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.2128776051306274e-05, + "loss": 3.5452, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212040648259948e-05, + "loss": 3.5433, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211202053508896e-05, + "loss": 3.5526, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210363458757844e-05, + "loss": 3.5224, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.209524864006793e-05, + "loss": 3.5498, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208687907136114e-05, + "loss": 3.5459, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207849312385062e-05, + "loss": 3.5506, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.20701071763401e-05, + "loss": 3.5417, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.206172122882958e-05, + "loss": 3.5382, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.205335166012279e-05, + "loss": 3.5392, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.204496571261227e-05, + "loss": 3.5367, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.203657976510175e-05, + "loss": 3.5571, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.202819381759123e-05, + "loss": 3.5424, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.201980787008071e-05, + "loss": 3.5591, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2011438301373917e-05, + "loss": 3.541, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.2003052353863396e-05, + "loss": 3.5276, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199466640635288e-05, + "loss": 3.5634, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198628045884236e-05, + "loss": 3.5385, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197791089013557e-05, + "loss": 3.5296, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196952494262505e-05, + "loss": 3.5397, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196113899511453e-05, + "loss": 3.5456, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195275304760401e-05, + "loss": 3.5302, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194438347889722e-05, + "loss": 3.5365, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.19359975313867e-05, + "loss": 3.5343, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192761158387618e-05, + "loss": 3.5328, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191922563636566e-05, + "loss": 3.5492, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191085606765887e-05, + "loss": 3.5465, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190247012014835e-05, + "loss": 3.5414, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189408417263784e-05, + "loss": 3.5351, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188569822512732e-05, + "loss": 3.5522, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.1877328656420526e-05, + "loss": 3.5431, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.1868942708910006e-05, + "loss": 3.5525, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.1860556761399486e-05, + "loss": 3.5382, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.1852170813888966e-05, + "loss": 3.5366, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.1843801245182175e-05, + "loss": 3.5437, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.1835415297671655e-05, + "loss": 3.5455, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.1827029350161135e-05, + "loss": 3.5431, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.1818643402650615e-05, + "loss": 3.5473, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.1810273833943824e-05, + "loss": 3.539, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.1801887886433304e-05, + "loss": 3.5296, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179350193892279e-05, + "loss": 3.543, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178511599141227e-05, + "loss": 3.5493, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177674642270548e-05, + "loss": 3.5364, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176836047519496e-05, + "loss": 3.5407, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.175997452768444e-05, + "loss": 3.536, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.175158858017392e-05, + "loss": 3.5421, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.174321901146713e-05, + "loss": 3.5378, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.173483306395661e-05, + "loss": 3.5378, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.172644711644609e-05, + "loss": 3.5447, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.171806116893557e-05, + "loss": 3.5451, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.170969160022878e-05, + "loss": 3.5538, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.170130565271826e-05, + "loss": 3.519, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1692919705207744e-05, + "loss": 3.538, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1684533757697224e-05, + "loss": 3.5342, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.167616418899043e-05, + "loss": 3.5463, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166777824147991e-05, + "loss": 3.5476, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165939229396939e-05, + "loss": 3.5404, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165100634645887e-05, + "loss": 3.5287, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164263677775208e-05, + "loss": 3.5435, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163425083024156e-05, + "loss": 3.5378, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162586488273104e-05, + "loss": 3.5342, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.161747893522052e-05, + "loss": 3.5296, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160910936651373e-05, + "loss": 3.5369, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160072341900321e-05, + "loss": 3.5412, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.15923374714927e-05, + "loss": 3.5277, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158395152398218e-05, + "loss": 3.5364, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157558195527539e-05, + "loss": 3.5198, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156719600776487e-05, + "loss": 3.545, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.155881006025435e-05, + "loss": 3.5319, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.155042411274383e-05, + "loss": 3.5373, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1542054544037036e-05, + "loss": 3.542, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1533668596526516e-05, + "loss": 3.5448, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.1525282649015996e-05, + "loss": 3.5327, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.1516896701505476e-05, + "loss": 3.5401, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.1508527132798685e-05, + "loss": 3.5441, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1500141185288165e-05, + "loss": 3.5279, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.1491755237777645e-05, + "loss": 3.5237, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.148336929026713e-05, + "loss": 3.5419, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147499972156034e-05, + "loss": 3.5369, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146661377404982e-05, + "loss": 3.5388, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.14582278265393e-05, + "loss": 3.5332, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144984187902878e-05, + "loss": 3.5367, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144147231032199e-05, + "loss": 3.5381, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143308636281147e-05, + "loss": 3.525, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.142470041530095e-05, + "loss": 3.5294, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.141631446779043e-05, + "loss": 3.5457, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140794489908364e-05, + "loss": 3.5506, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139955895157312e-05, + "loss": 3.5345, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.13911730040626e-05, + "loss": 3.532, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1382787056552085e-05, + "loss": 3.5425, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.1374417487845294e-05, + "loss": 3.5351, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1366031540334774e-05, + "loss": 3.5336, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.1357645592824254e-05, + "loss": 3.5343, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1349259645313734e-05, + "loss": 3.548, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.134089007660694e-05, + "loss": 3.5414, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.133250412909642e-05, + "loss": 3.5381, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.13241181815859e-05, + "loss": 3.5296, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131573223407538e-05, + "loss": 3.5385, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130736266536859e-05, + "loss": 3.5397, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129897671785807e-05, + "loss": 3.5264, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129059077034755e-05, + "loss": 3.5567, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.128220482283704e-05, + "loss": 3.5355, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127383525413025e-05, + "loss": 3.5423, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126544930661973e-05, + "loss": 3.535, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.896198272705078, + "eval_runtime": 302.5794, + "eval_samples_per_second": 1261.127, + "eval_steps_per_second": 39.411, + "step": 1144789 + }, + { + "epoch": 0.0, + "learning_rate": 3.125706335910921e-05, + "loss": 3.5659, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124867741159869e-05, + "loss": 3.5322, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124029146408816e-05, + "loss": 3.5368, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123190551657764e-05, + "loss": 3.5429, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.122351956906712e-05, + "loss": 3.5391, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121515000036033e-05, + "loss": 3.5393, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.120676405284981e-05, + "loss": 3.5333, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.119837810533929e-05, + "loss": 3.5347, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.118999215782878e-05, + "loss": 3.5317, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181622589121986e-05, + "loss": 3.5374, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.1173236641611466e-05, + "loss": 3.5343, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.1164850694100946e-05, + "loss": 3.5353, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.1156464746590426e-05, + "loss": 3.5433, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.1148095177883635e-05, + "loss": 3.5207, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.1139709230373115e-05, + "loss": 3.5319, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.1131323282862595e-05, + "loss": 3.5169, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.1122937335352075e-05, + "loss": 3.522, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.1114567766645284e-05, + "loss": 3.5303, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.1106181819134764e-05, + "loss": 3.5241, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.1097795871624244e-05, + "loss": 3.5375, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.108940992411373e-05, + "loss": 3.5468, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108104035540694e-05, + "loss": 3.5324, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107265440789642e-05, + "loss": 3.5338, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.10642684603859e-05, + "loss": 3.5373, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.105588251287538e-05, + "loss": 3.5236, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.104751294416859e-05, + "loss": 3.5359, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.103912699665807e-05, + "loss": 3.5213, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.103074104914755e-05, + "loss": 3.5297, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.102235510163703e-05, + "loss": 3.5256, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.101398553293024e-05, + "loss": 3.5217, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.100559958541972e-05, + "loss": 3.5276, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.09972136379092e-05, + "loss": 3.5278, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0988827690398684e-05, + "loss": 3.5377, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.0980441742888164e-05, + "loss": 3.5326, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097207217418137e-05, + "loss": 3.5219, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096368622667085e-05, + "loss": 3.5263, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095530027916033e-05, + "loss": 3.5455, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094691433164981e-05, + "loss": 3.5233, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.093854476294302e-05, + "loss": 3.5286, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.09301588154325e-05, + "loss": 3.5235, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092177286792198e-05, + "loss": 3.5231, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091338692041146e-05, + "loss": 3.5254, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090501735170467e-05, + "loss": 3.5415, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089663140419415e-05, + "loss": 3.537, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088824545668364e-05, + "loss": 3.5317, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.087985950917312e-05, + "loss": 3.5316, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.087148994046633e-05, + "loss": 3.5234, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.086310399295581e-05, + "loss": 3.5391, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854718045445287e-05, + "loss": 3.5097, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.0846332097934767e-05, + "loss": 3.5311, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.0837962529227976e-05, + "loss": 3.529, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.0829576581717456e-05, + "loss": 3.5367, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.0821190634206936e-05, + "loss": 3.5303, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.0812804686696416e-05, + "loss": 3.5168, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.0804435117989625e-05, + "loss": 3.5291, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.0796049170479105e-05, + "loss": 3.5152, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078766322296859e-05, + "loss": 3.5454, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077927727545807e-05, + "loss": 3.5265, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077090770675128e-05, + "loss": 3.5444, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076252175924076e-05, + "loss": 3.5255, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075413581173024e-05, + "loss": 3.5137, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.074574986421972e-05, + "loss": 3.5413, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.073738029551293e-05, + "loss": 3.5213, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.072899434800241e-05, + "loss": 3.5206, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.072060840049189e-05, + "loss": 3.5183, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.071222245298137e-05, + "loss": 3.5323, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.070385288427458e-05, + "loss": 3.5158, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.069546693676406e-05, + "loss": 3.5196, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0687080989253545e-05, + "loss": 3.5191, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0678695041743025e-05, + "loss": 3.5157, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0670325473036234e-05, + "loss": 3.5341, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0661939525525714e-05, + "loss": 3.5315, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.0653553578015194e-05, + "loss": 3.5208, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.0645167630504674e-05, + "loss": 3.5236, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063679806179788e-05, + "loss": 3.5348, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062841211428736e-05, + "loss": 3.5256, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.062002616677684e-05, + "loss": 3.532, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061164021926632e-05, + "loss": 3.5269, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060327065055953e-05, + "loss": 3.5225, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059488470304901e-05, + "loss": 3.5266, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058649875553849e-05, + "loss": 3.5293, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057811280802798e-05, + "loss": 3.525, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056974323932119e-05, + "loss": 3.5339, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056135729181067e-05, + "loss": 3.5268, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.055297134430015e-05, + "loss": 3.5107, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054458539678963e-05, + "loss": 3.5268, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053621582808284e-05, + "loss": 3.5319, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.0527829880572317e-05, + "loss": 3.5242, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.0519443933061797e-05, + "loss": 3.5222, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511057985551277e-05, + "loss": 3.5218, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.050268841684449e-05, + "loss": 3.5255, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.049430246933397e-05, + "loss": 3.5198, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.048591652182345e-05, + "loss": 3.5254, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.047753057431293e-05, + "loss": 3.5236, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469161005606138e-05, + "loss": 3.5265, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.046077505809562e-05, + "loss": 3.5416, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.04523891105851e-05, + "loss": 3.508, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.044400316307458e-05, + "loss": 3.5195, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.043563359436779e-05, + "loss": 3.5208, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.042724764685727e-05, + "loss": 3.5291, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.041886169934675e-05, + "loss": 3.5307, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.041047575183623e-05, + "loss": 3.5282, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402089804325707e-05, + "loss": 3.513, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393720235618923e-05, + "loss": 3.5252, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385334288108403e-05, + "loss": 3.5264, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.0376948340597883e-05, + "loss": 3.518, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.036856239308736e-05, + "loss": 3.515, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360192824380575e-05, + "loss": 3.5241, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.0351806876870055e-05, + "loss": 3.5297, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343420929359535e-05, + "loss": 3.5067, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0335034981849008e-05, + "loss": 3.521, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.0326665413142224e-05, + "loss": 3.5057, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318279465631704e-05, + "loss": 3.5287, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030989351812118e-05, + "loss": 3.5205, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030150757061066e-05, + "loss": 3.5204, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.0293138001903876e-05, + "loss": 3.5252, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284752054393356e-05, + "loss": 3.526, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.027636610688283e-05, + "loss": 3.5177, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267980159372313e-05, + "loss": 3.5267, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.025961059066553e-05, + "loss": 3.5263, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.025122464315501e-05, + "loss": 3.5145, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.0242838695644482e-05, + "loss": 3.51, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.0234452748133962e-05, + "loss": 3.5241, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226083179427178e-05, + "loss": 3.5234, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217697231916654e-05, + "loss": 3.5263, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209311284406134e-05, + "loss": 3.5127, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200925336895614e-05, + "loss": 3.5221, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.019255576818883e-05, + "loss": 3.5232, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.0184169820678303e-05, + "loss": 3.511, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175783873167783e-05, + "loss": 3.5101, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.0167397925657266e-05, + "loss": 3.5292, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015902835695048e-05, + "loss": 3.5349, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.0150642409439955e-05, + "loss": 3.5205, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.0142256461929435e-05, + "loss": 3.5181, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.013388689322265e-05, + "loss": 3.5285, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.0125500945712128e-05, + "loss": 3.5209, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.0117114998201608e-05, + "loss": 3.519, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.0108729050691088e-05, + "loss": 3.5194, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.0100359481984304e-05, + "loss": 3.5326, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091973534473777e-05, + "loss": 3.5253, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083587586963257e-05, + "loss": 3.5206, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075201639452737e-05, + "loss": 3.5173, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066832070745953e-05, + "loss": 3.5219, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.005844612323543e-05, + "loss": 3.5201, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.005006017572491e-05, + "loss": 3.5113, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.004167422821439e-05, + "loss": 3.5428, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033304659507598e-05, + "loss": 3.5232, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024918711997078e-05, + "loss": 3.5256, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.001653276448656e-05, + "loss": 3.5188, + "step": 1220608 + }, + { + "epoch": 0.03, + "eval_loss": 3.897986650466919, + "eval_runtime": 305.1095, + "eval_samples_per_second": 1250.669, + "eval_steps_per_second": 39.084, + "step": 1221109 + }, + { + "epoch": 1.0, + "learning_rate": 3.000814681697604e-05, + "loss": 3.5203, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.999976086946552e-05, + "loss": 3.5186, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.999139130075873e-05, + "loss": 3.5213, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.998300535324821e-05, + "loss": 3.5295, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.997461940573769e-05, + "loss": 3.525, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.996623345822717e-05, + "loss": 3.5263, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957863889520383e-05, + "loss": 3.5176, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949477942009863e-05, + "loss": 3.5195, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941091994499343e-05, + "loss": 3.5152, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.9932706046988823e-05, + "loss": 3.5245, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.9924336478282032e-05, + "loss": 3.5189, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.9915950530771515e-05, + "loss": 3.5238, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.9907564583260995e-05, + "loss": 3.5276, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899178635750475e-05, + "loss": 3.5092, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.9890809067043684e-05, + "loss": 3.5119, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.9882423119533164e-05, + "loss": 3.5051, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.9874037172022644e-05, + "loss": 3.507, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.9865651224512124e-05, + "loss": 3.518, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.9857281655805337e-05, + "loss": 3.5128, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.9848895708294816e-05, + "loss": 3.5178, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840509760784296e-05, + "loss": 3.5343, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832123813273776e-05, + "loss": 3.5186, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823754244566985e-05, + "loss": 3.519, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.981536829705647e-05, + "loss": 3.5174, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.980698234954595e-05, + "loss": 3.5138, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979859640203543e-05, + "loss": 3.521, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790226833328638e-05, + "loss": 3.5081, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781840885818118e-05, + "loss": 3.5132, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773454938307598e-05, + "loss": 3.511, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765068990797078e-05, + "loss": 3.5044, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.975669942209029e-05, + "loss": 3.5179, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.974831347457977e-05, + "loss": 3.5101, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.973992752706925e-05, + "loss": 3.5183, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.973154157955873e-05, + "loss": 3.5188, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.972317201085194e-05, + "loss": 3.5126, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714786063341422e-05, + "loss": 3.5128, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706400115830902e-05, + "loss": 3.5279, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9698014168320382e-05, + "loss": 3.5089, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.968964459961359e-05, + "loss": 3.5129, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.968125865210307e-05, + "loss": 3.5142, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.967287270459255e-05, + "loss": 3.5034, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.966448675708203e-05, + "loss": 3.5109, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656117188375244e-05, + "loss": 3.5294, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647731240864724e-05, + "loss": 3.5197, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639345293354204e-05, + "loss": 3.5132, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.9630959345843684e-05, + "loss": 3.523, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.9622589777136893e-05, + "loss": 3.5103, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.9614203829626376e-05, + "loss": 3.5216, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.9605817882115856e-05, + "loss": 3.4951, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.9597431934605336e-05, + "loss": 3.5125, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9589062365898545e-05, + "loss": 3.5208, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580676418388025e-05, + "loss": 3.5151, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572290470877505e-05, + "loss": 3.517, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.9563904523366985e-05, + "loss": 3.5014, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.9555534954660198e-05, + "loss": 3.516, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.9547149007149677e-05, + "loss": 3.4997, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.9538763059639157e-05, + "loss": 3.5308, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530377112128637e-05, + "loss": 3.5104, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9522007543421846e-05, + "loss": 3.5294, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.951362159591133e-05, + "loss": 3.5082, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.950523564840081e-05, + "loss": 3.5056, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.949684970089029e-05, + "loss": 3.5192, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.94884801321835e-05, + "loss": 3.5074, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.948009418467298e-05, + "loss": 3.5073, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.947170823716246e-05, + "loss": 3.5053, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.946332228965194e-05, + "loss": 3.5146, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.945495272094515e-05, + "loss": 3.5017, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.944656677343463e-05, + "loss": 3.5065, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.943818082592411e-05, + "loss": 3.4993, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.942979487841359e-05, + "loss": 3.5013, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.94214253097068e-05, + "loss": 3.5179, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9413039362196283e-05, + "loss": 3.5204, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404653414685763e-05, + "loss": 3.5069, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396267467175243e-05, + "loss": 3.5076, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387897898468453e-05, + "loss": 3.5152, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.9379511950957932e-05, + "loss": 3.5125, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371126003447412e-05, + "loss": 3.5113, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362740055936892e-05, + "loss": 3.5165, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354370487230105e-05, + "loss": 3.5094, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9345984539719585e-05, + "loss": 3.5125, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337598592209065e-05, + "loss": 3.5153, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.9329212644698545e-05, + "loss": 3.5158, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.9320843075991754e-05, + "loss": 3.5209, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.9312457128481237e-05, + "loss": 3.5089, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.9304071180970717e-05, + "loss": 3.494, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295685233460197e-05, + "loss": 3.5146, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.9287315664753406e-05, + "loss": 3.5152, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278929717242886e-05, + "loss": 3.5129, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270543769732366e-05, + "loss": 3.5095, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262157822221846e-05, + "loss": 3.5049, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.925378825351506e-05, + "loss": 3.517, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.924540230600454e-05, + "loss": 3.504, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.923701635849402e-05, + "loss": 3.5093, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.92286304109835e-05, + "loss": 3.5107, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220260842276707e-05, + "loss": 3.5114, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211874894766187e-05, + "loss": 3.526, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.920348894725567e-05, + "loss": 3.4998, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.919510299974515e-05, + "loss": 3.4978, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.918673343103836e-05, + "loss": 3.5127, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.917834748352784e-05, + "loss": 3.5119, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.916996153601732e-05, + "loss": 3.5188, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.91615755885068e-05, + "loss": 3.5128, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9153206019800012e-05, + "loss": 3.4945, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9144820072289492e-05, + "loss": 3.5099, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136434124778972e-05, + "loss": 3.5131, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9128048177268445e-05, + "loss": 3.4993, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.911967860856166e-05, + "loss": 3.4986, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.911129266105114e-05, + "loss": 3.5111, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102906713540624e-05, + "loss": 3.5146, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094520766030098e-05, + "loss": 3.4942, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086151197323314e-05, + "loss": 3.4997, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077765249812793e-05, + "loss": 3.4964, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.9069379302302273e-05, + "loss": 3.5146, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.906099335479175e-05, + "loss": 3.5055, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.9052623786084966e-05, + "loss": 3.5051, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044237838574446e-05, + "loss": 3.5102, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.903585189106392e-05, + "loss": 3.5154, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.90274659435534e-05, + "loss": 3.5018, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.9019096374846615e-05, + "loss": 3.5126, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010710427336095e-05, + "loss": 3.5112, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.900232447982557e-05, + "loss": 3.5056, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.899393853231505e-05, + "loss": 3.4901, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985568963608267e-05, + "loss": 3.5087, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977183016097747e-05, + "loss": 3.508, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8968797068587224e-05, + "loss": 3.5152, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960411121076704e-05, + "loss": 3.4999, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.895204155236992e-05, + "loss": 3.5084, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.8943655604859393e-05, + "loss": 3.507, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935269657348873e-05, + "loss": 3.4975, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8926883709838353e-05, + "loss": 3.4948, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891851414113157e-05, + "loss": 3.5171, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.8910128193621045e-05, + "loss": 3.5203, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901742246110525e-05, + "loss": 3.5128, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.8893356298600005e-05, + "loss": 3.4961, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888498672989322e-05, + "loss": 3.5135, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.8876600782382694e-05, + "loss": 3.5044, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868214834872177e-05, + "loss": 3.5085, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.8859828887361657e-05, + "loss": 3.5052, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.8851459318654866e-05, + "loss": 3.517, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8843073371144346e-05, + "loss": 3.5069, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.8834687423633826e-05, + "loss": 3.5089, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826301476123306e-05, + "loss": 3.5018, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.881793190741652e-05, + "loss": 3.506, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809545959906e-05, + "loss": 3.5066, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.880116001239548e-05, + "loss": 3.496, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.879277406488496e-05, + "loss": 3.5277, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784404496178168e-05, + "loss": 3.5085, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8776018548667648e-05, + "loss": 3.5088, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.876763260115713e-05, + "loss": 3.5071, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.875924665364661e-05, + "loss": 3.5028, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.9002740383148193, + "eval_runtime": 303.9087, + "eval_samples_per_second": 1255.611, + "eval_steps_per_second": 39.239, + "step": 1297429 + }, + { + "epoch": 0.0, + "learning_rate": 2.875086070613609e-05, + "loss": 3.502, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.874247475862557e-05, + "loss": 3.507, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.873408881111505e-05, + "loss": 3.5138, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.872571924240826e-05, + "loss": 3.5081, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.871733329489774e-05, + "loss": 3.5129, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708947347387223e-05, + "loss": 3.4995, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700561399876703e-05, + "loss": 3.5059, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692191831169912e-05, + "loss": 3.4976, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683805883659392e-05, + "loss": 3.5133, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675419936148872e-05, + "loss": 3.5005, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8667033988638352e-05, + "loss": 3.511, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658664419931565e-05, + "loss": 3.5089, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650278472421045e-05, + "loss": 3.4981, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641892524910525e-05, + "loss": 3.4972, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633506577400005e-05, + "loss": 3.491, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625137008693214e-05, + "loss": 3.4987, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616751061182694e-05, + "loss": 3.4973, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608365113672177e-05, + "loss": 3.4978, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.8599979166161657e-05, + "loss": 3.5025, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591609597454866e-05, + "loss": 3.522, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583223649944346e-05, + "loss": 3.502, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574837702433826e-05, + "loss": 3.5041, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566451754923306e-05, + "loss": 3.5074, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855808218621652e-05, + "loss": 3.4997, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.8549696238705998e-05, + "loss": 3.5039, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.8541310291195478e-05, + "loss": 3.4922, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532924343684958e-05, + "loss": 3.501, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524554774978167e-05, + "loss": 3.4997, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516168827467647e-05, + "loss": 3.4883, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850778287995713e-05, + "loss": 3.5023, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.849939693244661e-05, + "loss": 3.4966, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.849102736373982e-05, + "loss": 3.5068, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.84826414162293e-05, + "loss": 3.5037, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.847425546871878e-05, + "loss": 3.4943, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.846586952120826e-05, + "loss": 3.503, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457499952501472e-05, + "loss": 3.5127, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449114004990952e-05, + "loss": 3.4904, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440728057480432e-05, + "loss": 3.5028, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432342109969912e-05, + "loss": 3.4966, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842397254126312e-05, + "loss": 3.4933, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.84155865937526e-05, + "loss": 3.4953, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.840720064624208e-05, + "loss": 3.5136, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398814698731564e-05, + "loss": 3.506, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390445130024773e-05, + "loss": 3.4969, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382059182514253e-05, + "loss": 3.509, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373673235003733e-05, + "loss": 3.4982, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365287287493213e-05, + "loss": 3.5036, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356917718786426e-05, + "loss": 3.4843, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348531771275906e-05, + "loss": 3.4959, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340145823765386e-05, + "loss": 3.506, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331759876254866e-05, + "loss": 3.5032, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323390307548075e-05, + "loss": 3.5005, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315004360037555e-05, + "loss": 3.4889, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306618412527035e-05, + "loss": 3.5031, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298232465016518e-05, + "loss": 3.4857, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289862896309727e-05, + "loss": 3.5139, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281476948799207e-05, + "loss": 3.4954, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273091001288687e-05, + "loss": 3.5139, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264705053778167e-05, + "loss": 3.4949, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.825633548507138e-05, + "loss": 3.4946, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824794953756086e-05, + "loss": 3.499, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823956359005034e-05, + "loss": 3.5005, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.823117764253982e-05, + "loss": 3.4923, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222808073833028e-05, + "loss": 3.4864, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214422126322508e-05, + "loss": 3.5027, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206036178811988e-05, + "loss": 3.4898, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.819765023130147e-05, + "loss": 3.4849, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.818928066259468e-05, + "loss": 3.4895, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.818089471508416e-05, + "loss": 3.4905, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.817250876757364e-05, + "loss": 3.5063, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816412282006312e-05, + "loss": 3.5068, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155753251356333e-05, + "loss": 3.4922, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147367303845813e-05, + "loss": 3.4929, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138981356335293e-05, + "loss": 3.5002, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130595408824773e-05, + "loss": 3.4973, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122225840117982e-05, + "loss": 3.4994, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113839892607462e-05, + "loss": 3.5041, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105453945096942e-05, + "loss": 3.496, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809706799758642e-05, + "loss": 3.4999, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.8088698428879634e-05, + "loss": 3.4985, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.8080312481369114e-05, + "loss": 3.5042, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.8071926533858594e-05, + "loss": 3.5024, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806354058634807e-05, + "loss": 3.4953, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055171017641287e-05, + "loss": 3.4808, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8046785070130767e-05, + "loss": 3.5007, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.8038399122620247e-05, + "loss": 3.4994, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803001317510972e-05, + "loss": 3.4961, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021643606402936e-05, + "loss": 3.4987, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013257658892416e-05, + "loss": 3.4893, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004871711381892e-05, + "loss": 3.4988, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996485763871372e-05, + "loss": 3.4895, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988116195164588e-05, + "loss": 3.5001, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979730247654068e-05, + "loss": 3.4902, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.797134430014354e-05, + "loss": 3.5005, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962958352633024e-05, + "loss": 3.507, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.795458878392624e-05, + "loss": 3.4955, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946202836415714e-05, + "loss": 3.4796, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937816888905193e-05, + "loss": 3.4971, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929430941394673e-05, + "loss": 3.5012, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792106137268789e-05, + "loss": 3.5035, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912675425177366e-05, + "loss": 3.4985, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904289477666846e-05, + "loss": 3.4873, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7895903530156326e-05, + "loss": 3.4902, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.788753396144954e-05, + "loss": 3.5013, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879148013939015e-05, + "loss": 3.4837, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870762066428495e-05, + "loss": 3.4867, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862376118917978e-05, + "loss": 3.4984, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7854006550211187e-05, + "loss": 3.5006, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845620602700667e-05, + "loss": 3.4776, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837234655190147e-05, + "loss": 3.4907, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828848707679627e-05, + "loss": 3.4805, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.782047913897284e-05, + "loss": 3.497, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781209319146232e-05, + "loss": 3.4953, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.78037072439518e-05, + "loss": 3.484, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779532129644128e-05, + "loss": 3.5024, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.778695172773449e-05, + "loss": 3.4995, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777856578022397e-05, + "loss": 3.4868, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.777017983271345e-05, + "loss": 3.4959, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761793885202932e-05, + "loss": 3.4956, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775342431649614e-05, + "loss": 3.4902, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.774503836898562e-05, + "loss": 3.4799, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.77366524214751e-05, + "loss": 3.4976, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.772826647396458e-05, + "loss": 3.4931, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719896905257793e-05, + "loss": 3.5004, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711510957747273e-05, + "loss": 3.486, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703125010236753e-05, + "loss": 3.4955, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694739062726233e-05, + "loss": 3.4957, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686369494019442e-05, + "loss": 3.4831, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7677983546508922e-05, + "loss": 3.477, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669597598998402e-05, + "loss": 3.5057, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661211651487885e-05, + "loss": 3.5046, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652842082781095e-05, + "loss": 3.495, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644456135270575e-05, + "loss": 3.4825, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636070187760054e-05, + "loss": 3.5026, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627684240249534e-05, + "loss": 3.4938, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619314671542747e-05, + "loss": 3.492, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7610928724032227e-05, + "loss": 3.4899, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.7602542776521707e-05, + "loss": 3.5016, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.7594156829011187e-05, + "loss": 3.4923, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585787260304396e-05, + "loss": 3.4991, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577401312793876e-05, + "loss": 3.4872, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569015365283356e-05, + "loss": 3.4959, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.756062941777284e-05, + "loss": 3.4942, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552259849066048e-05, + "loss": 3.4871, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543873901555528e-05, + "loss": 3.5099, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535487954045008e-05, + "loss": 3.4975, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527102006534488e-05, + "loss": 3.4951, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.75187324378277e-05, + "loss": 3.4914, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751034649031718e-05, + "loss": 3.4894, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.901305675506592, + "eval_runtime": 308.4832, + "eval_samples_per_second": 1236.991, + "eval_steps_per_second": 38.657, + "step": 1373749 + }, + { + "epoch": 1.0, + "learning_rate": 2.750196054280666e-05, + "loss": 3.4881, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.749357459529614e-05, + "loss": 3.4949, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.748520502658935e-05, + "loss": 3.5004, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.747681907907883e-05, + "loss": 3.4962, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.746843313156831e-05, + "loss": 3.5044, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.746004718405779e-05, + "loss": 3.4836, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451677615351002e-05, + "loss": 3.4915, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443291667840482e-05, + "loss": 3.4862, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7434905720329962e-05, + "loss": 3.498, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426519772819442e-05, + "loss": 3.4924, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7418150204112654e-05, + "loss": 3.4944, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409764256602134e-05, + "loss": 3.497, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401378309091614e-05, + "loss": 3.4827, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392992361581094e-05, + "loss": 3.4842, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384622792874303e-05, + "loss": 3.4753, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376236845363783e-05, + "loss": 3.4854, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7367850897853263e-05, + "loss": 3.4832, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359464950342743e-05, + "loss": 3.4837, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7351095381635956e-05, + "loss": 3.4888, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342709434125436e-05, + "loss": 3.5104, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334323486614915e-05, + "loss": 3.4903, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7325937539104395e-05, + "loss": 3.487, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317567970397605e-05, + "loss": 3.4939, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309182022887088e-05, + "loss": 3.487, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.7300796075376568e-05, + "loss": 3.4873, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.7292410127866048e-05, + "loss": 3.48, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284040559159257e-05, + "loss": 3.4893, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275654611648737e-05, + "loss": 3.4828, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267268664138217e-05, + "loss": 3.4763, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258882716627697e-05, + "loss": 3.4907, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.725051314792091e-05, + "loss": 3.4803, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.724212720041039e-05, + "loss": 3.4939, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.723374125289987e-05, + "loss": 3.4879, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722535530538935e-05, + "loss": 3.4815, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216985736682558e-05, + "loss": 3.4878, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720859978917204e-05, + "loss": 3.5011, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.720021384166152e-05, + "loss": 3.4751, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191827894151e-05, + "loss": 3.49, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.718345832544421e-05, + "loss": 3.4801, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.717507237793369e-05, + "loss": 3.4808, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.716668643042317e-05, + "loss": 3.4827, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.715830048291265e-05, + "loss": 3.5016, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149930914205863e-05, + "loss": 3.4918, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141544966695343e-05, + "loss": 3.4856, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133159019184823e-05, + "loss": 3.4952, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7124789450478032e-05, + "loss": 3.4807, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116403502967512e-05, + "loss": 3.4928, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.7108017555456995e-05, + "loss": 3.4763, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099631607946475e-05, + "loss": 3.4788, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091262039239684e-05, + "loss": 3.4948, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.7082876091729164e-05, + "loss": 3.4874, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.7074490144218644e-05, + "loss": 3.4844, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066104196708124e-05, + "loss": 3.4774, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057734628001337e-05, + "loss": 3.4915, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049348680490817e-05, + "loss": 3.4705, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7040962732980297e-05, + "loss": 3.497, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032576785469776e-05, + "loss": 3.4879, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024207216762986e-05, + "loss": 3.4978, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015821269252466e-05, + "loss": 3.4858, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.700743532174195e-05, + "loss": 3.4799, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699904937423143e-05, + "loss": 3.4863, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990679805524638e-05, + "loss": 3.4903, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982293858014118e-05, + "loss": 3.4785, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973907910503598e-05, + "loss": 3.472, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965521962993078e-05, + "loss": 3.489, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.695715239428629e-05, + "loss": 3.4795, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.694876644677577e-05, + "loss": 3.4688, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.694038049926525e-05, + "loss": 3.4806, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.693199455175473e-05, + "loss": 3.4734, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692362498304794e-05, + "loss": 3.4888, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.691523903553742e-05, + "loss": 3.4952, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906853088026903e-05, + "loss": 3.4779, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898467140516382e-05, + "loss": 3.4827, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.689009757180959e-05, + "loss": 3.4849, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.688171162429907e-05, + "loss": 3.4844, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.687332567678855e-05, + "loss": 3.4855, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686493972927803e-05, + "loss": 3.4906, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856570160571244e-05, + "loss": 3.4828, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848184213060724e-05, + "loss": 3.4863, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839798265550204e-05, + "loss": 3.4817, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.6831412318039684e-05, + "loss": 3.4876, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.6823042749332893e-05, + "loss": 3.4884, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.6814656801822373e-05, + "loss": 3.4849, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806270854311856e-05, + "loss": 3.4704, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6797884906801336e-05, + "loss": 3.4859, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789515338094545e-05, + "loss": 3.488, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781129390584025e-05, + "loss": 3.4848, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772743443073505e-05, + "loss": 3.4864, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764357495562985e-05, + "loss": 3.4699, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6755987926856198e-05, + "loss": 3.485, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747601979345678e-05, + "loss": 3.4781, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739216031835158e-05, + "loss": 3.4883, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.673083008432463e-05, + "loss": 3.4708, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722460515617847e-05, + "loss": 3.489, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714074568107327e-05, + "loss": 3.4968, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.670568862059681e-05, + "loss": 3.4823, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697302673086283e-05, + "loss": 3.4663, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.66889331043795e-05, + "loss": 3.4845, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668054715686898e-05, + "loss": 3.4861, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667216120935846e-05, + "loss": 3.487, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663775261847935e-05, + "loss": 3.4843, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665540569314115e-05, + "loss": 3.4736, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664701974563063e-05, + "loss": 3.4763, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638633798120104e-05, + "loss": 3.4907, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630247850609584e-05, + "loss": 3.4705, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.66218782819028e-05, + "loss": 3.4743, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661349233439228e-05, + "loss": 3.4845, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605106386881757e-05, + "loss": 3.4893, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596720439371237e-05, + "loss": 3.4636, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588350870664453e-05, + "loss": 3.4794, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579964923153926e-05, + "loss": 3.467, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657157897564341e-05, + "loss": 3.4814, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656319302813289e-05, + "loss": 3.4836, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554823459426105e-05, + "loss": 3.4724, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546437511915578e-05, + "loss": 3.4872, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538051564405058e-05, + "loss": 3.4873, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529665616894538e-05, + "loss": 3.4702, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521296048187754e-05, + "loss": 3.4858, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651291010067723e-05, + "loss": 3.4818, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.650452415316671e-05, + "loss": 3.4808, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.649613820565619e-05, + "loss": 3.4629, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.64877686369494e-05, + "loss": 3.4827, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.647938268943888e-05, + "loss": 3.4798, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6470996741928363e-05, + "loss": 3.4844, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462610794417843e-05, + "loss": 3.4768, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454241225711052e-05, + "loss": 3.4825, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445855278200532e-05, + "loss": 3.4788, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437469330690012e-05, + "loss": 3.4699, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642908338317949e-05, + "loss": 3.4661, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420713814472704e-05, + "loss": 3.4927, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412327866962184e-05, + "loss": 3.4864, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403941919451664e-05, + "loss": 3.486, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395555971941144e-05, + "loss": 3.4726, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387186403234353e-05, + "loss": 3.4868, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6378800455723833e-05, + "loss": 3.4809, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370414508213313e-05, + "loss": 3.4765, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6362028560702796e-05, + "loss": 3.4776, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353658991996005e-05, + "loss": 3.4839, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345273044485485e-05, + "loss": 3.4808, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336887096974965e-05, + "loss": 3.4878, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328501149464445e-05, + "loss": 3.4731, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320131580757658e-05, + "loss": 3.4847, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311745633247138e-05, + "loss": 3.4796, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303359685736618e-05, + "loss": 3.4725, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6294973738226098e-05, + "loss": 3.4977, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286604169519307e-05, + "loss": 3.4832, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278218222008787e-05, + "loss": 3.484, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269832274498267e-05, + "loss": 3.4775, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626144632698775e-05, + "loss": 3.4769, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.9045493602752686, + "eval_runtime": 307.5273, + "eval_samples_per_second": 1240.836, + "eval_steps_per_second": 38.777, + "step": 1450069 + }, + { + "epoch": 0.0, + "learning_rate": 2.625307675828096e-05, + "loss": 3.4752, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.624469081077044e-05, + "loss": 3.4827, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.623630486325992e-05, + "loss": 3.4844, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.62279189157494e-05, + "loss": 3.4827, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.621954934704261e-05, + "loss": 3.4907, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.621116339953209e-05, + "loss": 3.4736, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620277745202157e-05, + "loss": 3.4758, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619439150451105e-05, + "loss": 3.4703, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.618602193580426e-05, + "loss": 3.4883, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.617763598829374e-05, + "loss": 3.4782, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.616925004078322e-05, + "loss": 3.4826, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160864093272704e-05, + "loss": 3.4851, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152494524565913e-05, + "loss": 3.4705, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144108577055393e-05, + "loss": 3.4657, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135722629544873e-05, + "loss": 3.4687, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127336682034353e-05, + "loss": 3.4682, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118950734523833e-05, + "loss": 3.4741, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110564787013313e-05, + "loss": 3.4698, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102178839502796e-05, + "loss": 3.4766, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093792891992276e-05, + "loss": 3.4929, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085423323285485e-05, + "loss": 3.4775, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077037375774965e-05, + "loss": 3.4749, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068651428264445e-05, + "loss": 3.4799, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060265480753925e-05, + "loss": 3.4784, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051895912047137e-05, + "loss": 3.4717, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043509964536617e-05, + "loss": 3.4659, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035124017026097e-05, + "loss": 3.4804, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026738069515577e-05, + "loss": 3.4629, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018368500808786e-05, + "loss": 3.4675, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009982553298266e-05, + "loss": 3.4743, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.600159660578775e-05, + "loss": 3.4724, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.599321065827723e-05, + "loss": 3.4759, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598484108957044e-05, + "loss": 3.4746, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597645514205992e-05, + "loss": 3.4696, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.59680691945494e-05, + "loss": 3.4784, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595968324703888e-05, + "loss": 3.4859, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.595131367833209e-05, + "loss": 3.464, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594292773082157e-05, + "loss": 3.4802, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.593454178331105e-05, + "loss": 3.463, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.592615583580053e-05, + "loss": 3.4735, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591778626709374e-05, + "loss": 3.4671, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590940031958322e-05, + "loss": 3.4869, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901014372072703e-05, + "loss": 3.4759, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892628424562183e-05, + "loss": 3.4769, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884258855855392e-05, + "loss": 3.4787, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875872908344872e-05, + "loss": 3.4699, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867486960834352e-05, + "loss": 3.4818, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859101013323832e-05, + "loss": 3.4618, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850731444617045e-05, + "loss": 3.4648, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842345497106525e-05, + "loss": 3.4787, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833959549596005e-05, + "loss": 3.4725, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825573602085478e-05, + "loss": 3.4752, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817204033378694e-05, + "loss": 3.4652, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808818085868174e-05, + "loss": 3.4736, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800432138357657e-05, + "loss": 3.4602, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579204619084713e-05, + "loss": 3.4791, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783676622140346e-05, + "loss": 3.4774, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775290674629826e-05, + "loss": 3.4826, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766904727119306e-05, + "loss": 3.4754, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758518779608782e-05, + "loss": 3.4707, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750149210902e-05, + "loss": 3.4676, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741763263391478e-05, + "loss": 3.4785, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.573337731588095e-05, + "loss": 3.4639, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.572499136837043e-05, + "loss": 3.462, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716621799663647e-05, + "loss": 3.472, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708235852153127e-05, + "loss": 3.4719, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699849904642604e-05, + "loss": 3.4568, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691463957132084e-05, + "loss": 3.462, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.56830943884253e-05, + "loss": 3.462, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.567470844091478e-05, + "loss": 3.478, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666322493404256e-05, + "loss": 3.4795, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5657936545893736e-05, + "loss": 3.4669, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649566977186952e-05, + "loss": 3.4716, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641181029676425e-05, + "loss": 3.4673, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632795082165905e-05, + "loss": 3.4834, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624409134655385e-05, + "loss": 3.4661, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.56160395659486e-05, + "loss": 3.4826, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607653618438078e-05, + "loss": 3.4681, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599284049731293e-05, + "loss": 3.4713, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590898102220773e-05, + "loss": 3.4724, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.5582512154710253e-05, + "loss": 3.4723, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574126207199727e-05, + "loss": 3.4802, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556574025968921e-05, + "loss": 3.4696, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555735431217869e-05, + "loss": 3.4592, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554896836466817e-05, + "loss": 3.4699, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.554058241715765e-05, + "loss": 3.4723, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.553221284845086e-05, + "loss": 3.4757, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552382690094034e-05, + "loss": 3.4713, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.551544095342982e-05, + "loss": 3.4595, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.55070550059193e-05, + "loss": 3.474, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.549868543721251e-05, + "loss": 3.4627, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.549029948970199e-05, + "loss": 3.4754, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.548191354219147e-05, + "loss": 3.4577, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.547352759468095e-05, + "loss": 3.4762, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.546515802597416e-05, + "loss": 3.4842, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456772078463643e-05, + "loss": 3.4682, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448386130953123e-05, + "loss": 3.4528, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440000183442603e-05, + "loss": 3.4729, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431630614735812e-05, + "loss": 3.4699, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423244667225292e-05, + "loss": 3.4775, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5414858719714772e-05, + "loss": 3.471, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406472772204252e-05, + "loss": 3.4607, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398103203497465e-05, + "loss": 3.4664, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389717255986945e-05, + "loss": 3.476, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381331308476425e-05, + "loss": 3.4554, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5372945360965905e-05, + "loss": 3.4648, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364575792259114e-05, + "loss": 3.4683, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356189844748597e-05, + "loss": 3.4773, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347803897238077e-05, + "loss": 3.4482, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339417949727557e-05, + "loss": 3.4651, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331048381020766e-05, + "loss": 3.4595, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322662433510246e-05, + "loss": 3.4643, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314276485999726e-05, + "loss": 3.4696, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305890538489206e-05, + "loss": 3.4581, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529752096978242e-05, + "loss": 3.4801, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.52891350222719e-05, + "loss": 3.4718, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.528074907476138e-05, + "loss": 3.4578, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527236312725086e-05, + "loss": 3.4727, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263993558544067e-05, + "loss": 3.47, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525560761103355e-05, + "loss": 3.4673, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.524722166352303e-05, + "loss": 3.4489, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.523883571601251e-05, + "loss": 3.4738, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.523046614730572e-05, + "loss": 3.4657, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.52220801997952e-05, + "loss": 3.4704, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.521369425228468e-05, + "loss": 3.4645, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.520530830477416e-05, + "loss": 3.4713, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196938736067372e-05, + "loss": 3.4658, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188552788556852e-05, + "loss": 3.4584, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180166841046332e-05, + "loss": 3.4557, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171780893535812e-05, + "loss": 3.4746, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.516341132482902e-05, + "loss": 3.4766, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155025377318504e-05, + "loss": 3.4724, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146639429807984e-05, + "loss": 3.4605, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138253482297464e-05, + "loss": 3.4721, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129883913590673e-05, + "loss": 3.471, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121497966080153e-05, + "loss": 3.4615, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113112018569633e-05, + "loss": 3.467, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104726071059113e-05, + "loss": 3.4689, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096356502352326e-05, + "loss": 3.4728, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087970554841806e-05, + "loss": 3.4742, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079584607331286e-05, + "loss": 3.4613, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071198659820766e-05, + "loss": 3.4686, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062829091113975e-05, + "loss": 3.4672, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054443143603458e-05, + "loss": 3.4592, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5046057196092938e-05, + "loss": 3.4848, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037687627386147e-05, + "loss": 3.4713, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029301679875627e-05, + "loss": 3.4721, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020915732365107e-05, + "loss": 3.4628, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012529784854587e-05, + "loss": 3.4689, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.9050183296203613, + "eval_runtime": 301.377, + "eval_samples_per_second": 1266.158, + "eval_steps_per_second": 39.568, + "step": 1526389 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004143837344067e-05, + "loss": 3.4584, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995757889833547e-05, + "loss": 3.4687, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987371942323027e-05, + "loss": 3.4692, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978985994812507e-05, + "loss": 3.4707, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970616426105716e-05, + "loss": 3.4789, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962230478595196e-05, + "loss": 3.4613, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953844531084676e-05, + "loss": 3.4648, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494545858357416e-05, + "loss": 3.4528, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493708901486737e-05, + "loss": 3.4767, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928703067356848e-05, + "loss": 3.4654, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920317119846328e-05, + "loss": 3.4688, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911931172335808e-05, + "loss": 3.4662, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903577982432753e-05, + "loss": 3.4648, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895192034922233e-05, + "loss": 3.45, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886806087411713e-05, + "loss": 3.4581, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487842013990119e-05, + "loss": 3.4526, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487003419239067e-05, + "loss": 3.4623, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486164824488015e-05, + "loss": 3.461, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485326229736963e-05, + "loss": 3.4579, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844876349859113e-05, + "loss": 3.486, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836506781152322e-05, + "loss": 3.463, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828120833641802e-05, + "loss": 3.4628, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819734886131282e-05, + "loss": 3.4683, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811348938620762e-05, + "loss": 3.4638, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802979369913974e-05, + "loss": 3.4593, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794593422403454e-05, + "loss": 3.4548, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786207474892934e-05, + "loss": 3.4672, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777821527382414e-05, + "loss": 3.446, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769451958675623e-05, + "loss": 3.4605, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761066011165103e-05, + "loss": 3.4581, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752680063654583e-05, + "loss": 3.4587, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744294116144067e-05, + "loss": 3.4666, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735924547437276e-05, + "loss": 3.4589, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727538599926756e-05, + "loss": 3.4582, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719152652416236e-05, + "loss": 3.4626, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710766704905716e-05, + "loss": 3.4718, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702397136198928e-05, + "loss": 3.4529, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4694011188688408e-05, + "loss": 3.4648, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685625241177888e-05, + "loss": 3.4528, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677239293667364e-05, + "loss": 3.4639, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668869724960577e-05, + "loss": 3.4516, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660483777450057e-05, + "loss": 3.4754, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652097829939537e-05, + "loss": 3.4654, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643711882429017e-05, + "loss": 3.4604, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463534231372223e-05, + "loss": 3.4693, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462695636621171e-05, + "loss": 3.4571, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461857041870119e-05, + "loss": 3.4663, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610184471190666e-05, + "loss": 3.4518, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460181490248388e-05, + "loss": 3.4501, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459342895497336e-05, + "loss": 3.4705, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585043007462838e-05, + "loss": 3.4576, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576657059952318e-05, + "loss": 3.4646, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456828749124553e-05, + "loss": 3.4528, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.455990154373501e-05, + "loss": 3.4639, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455151559622449e-05, + "loss": 3.4484, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.454312964871397e-05, + "loss": 3.4655, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534760080007183e-05, + "loss": 3.4629, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526374132496663e-05, + "loss": 3.4724, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451798818498614e-05, + "loss": 3.4634, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509618616279352e-05, + "loss": 3.4553, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501232668768835e-05, + "loss": 3.4562, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492846721258312e-05, + "loss": 3.4662, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484460773747792e-05, + "loss": 3.4512, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476091205041004e-05, + "loss": 3.4509, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467705257530484e-05, + "loss": 3.458, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445931931001996e-05, + "loss": 3.4616, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450933362509444e-05, + "loss": 3.4413, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442563793802657e-05, + "loss": 3.4521, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434177846292137e-05, + "loss": 3.4492, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425791898781613e-05, + "loss": 3.4649, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417405951271093e-05, + "loss": 3.4627, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409036382564306e-05, + "loss": 3.4557, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400650435053786e-05, + "loss": 3.4587, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392264487543266e-05, + "loss": 3.455, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383878540032746e-05, + "loss": 3.4713, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375508971325958e-05, + "loss": 3.4524, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367123023815435e-05, + "loss": 3.4661, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358737076304915e-05, + "loss": 3.4613, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435036750759813e-05, + "loss": 3.4571, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434198156008761e-05, + "loss": 3.463, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333595612577087e-05, + "loss": 3.4619, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325209665066567e-05, + "loss": 3.4663, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316823717556047e-05, + "loss": 3.4565, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308437770045527e-05, + "loss": 3.4459, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300051822535007e-05, + "loss": 3.461, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429166587502449e-05, + "loss": 3.4546, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.42832963063177e-05, + "loss": 3.4641, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427491035880718e-05, + "loss": 3.4581, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.426652441129666e-05, + "loss": 3.4473, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.425813846378614e-05, + "loss": 3.4614, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424976889507935e-05, + "loss": 3.4521, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424138294756883e-05, + "loss": 3.4616, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423299700005831e-05, + "loss": 3.4454, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422461105254779e-05, + "loss": 3.4658, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216241483841e-05, + "loss": 3.471, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.420785553633048e-05, + "loss": 3.4578, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419946958881996e-05, + "loss": 3.4381, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.419108364130944e-05, + "loss": 3.4606, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182714072602653e-05, + "loss": 3.4577, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174328125092133e-05, + "loss": 3.4631, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165942177581613e-05, + "loss": 3.4623, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415755623007109e-05, + "loss": 3.4516, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149186661364305e-05, + "loss": 3.4518, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140800713853785e-05, + "loss": 3.4643, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132414766343265e-05, + "loss": 3.4432, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124028818832742e-05, + "loss": 3.4526, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115659250125954e-05, + "loss": 3.4536, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107273302615434e-05, + "loss": 3.462, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098887355104914e-05, + "loss": 3.4357, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090501407594394e-05, + "loss": 3.4548, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082131838887607e-05, + "loss": 3.4467, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073745891377086e-05, + "loss": 3.4519, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065359943866563e-05, + "loss": 3.4562, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056973996356043e-05, + "loss": 3.4487, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404860442764926e-05, + "loss": 3.465, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040218480138735e-05, + "loss": 3.4618, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031832532628215e-05, + "loss": 3.447, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023446585117695e-05, + "loss": 3.4585, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015077016410908e-05, + "loss": 3.4578, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006691068900384e-05, + "loss": 3.456, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998305121389868e-05, + "loss": 3.4372, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989919173879348e-05, + "loss": 3.4606, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398154960517256e-05, + "loss": 3.4515, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973163657662037e-05, + "loss": 3.4596, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964777710151517e-05, + "loss": 3.4485, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956391762640997e-05, + "loss": 3.4627, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.394802219393421e-05, + "loss": 3.4607, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393963624642369e-05, + "loss": 3.4455, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393125029891317e-05, + "loss": 3.4433, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.392286435140265e-05, + "loss": 3.4641, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914494782695858e-05, + "loss": 3.4583, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906108835185338e-05, + "loss": 3.4626, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.389772288767482e-05, + "loss": 3.45, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.38893369401643e-05, + "loss": 3.4579, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388096737145751e-05, + "loss": 3.4599, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387258142394699e-05, + "loss": 3.4497, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386419547643647e-05, + "loss": 3.4528, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385580952892595e-05, + "loss": 3.4598, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847439960219163e-05, + "loss": 3.4573, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839054012708643e-05, + "loss": 3.4623, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830668065198123e-05, + "loss": 3.447, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822282117687603e-05, + "loss": 3.4572, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813912548980812e-05, + "loss": 3.4525, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805526601470292e-05, + "loss": 3.4522, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797140653959775e-05, + "loss": 3.4658, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788771085252984e-05, + "loss": 3.4551, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780385137742464e-05, + "loss": 3.4637, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771999190231944e-05, + "loss": 3.4441, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763613242721424e-05, + "loss": 3.4588, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.9080393314361572, + "eval_runtime": 313.068, + "eval_samples_per_second": 1218.876, + "eval_steps_per_second": 38.091, + "step": 1602709 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755243674014637e-05, + "loss": 3.4517, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746857726504117e-05, + "loss": 3.4576, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738471778993596e-05, + "loss": 3.4595, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3730085831483076e-05, + "loss": 3.4547, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721716262776286e-05, + "loss": 3.4632, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713330315265765e-05, + "loss": 3.454, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704944367755245e-05, + "loss": 3.4469, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369655842024473e-05, + "loss": 3.4476, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3688188851537938e-05, + "loss": 3.4612, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679802904027418e-05, + "loss": 3.457, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671416956516898e-05, + "loss": 3.4566, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3663031009006378e-05, + "loss": 3.4529, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365466144029959e-05, + "loss": 3.4505, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364627549278907e-05, + "loss": 3.4422, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363788954527855e-05, + "loss": 3.4488, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362950359776803e-05, + "loss": 3.4375, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362111765025751e-05, + "loss": 3.4496, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612731702746987e-05, + "loss": 3.4482, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604345755236467e-05, + "loss": 3.4452, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595959807725947e-05, + "loss": 3.4799, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587590239019162e-05, + "loss": 3.4493, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357920429150864e-05, + "loss": 3.4533, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357081834399812e-05, + "loss": 3.4554, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.35624323964876e-05, + "loss": 3.4515, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3554062827780808e-05, + "loss": 3.4438, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.354567688027029e-05, + "loss": 3.4465, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.353729093275977e-05, + "loss": 3.4539, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352890498524925e-05, + "loss": 3.4352, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352053541654246e-05, + "loss": 3.4468, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351214946903194e-05, + "loss": 3.4421, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.350376352152142e-05, + "loss": 3.4491, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.34953775740109e-05, + "loss": 3.4504, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3487008005304113e-05, + "loss": 3.4503, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478622057793593e-05, + "loss": 3.4517, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470236110283073e-05, + "loss": 3.4501, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461850162772553e-05, + "loss": 3.4559, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345348059406576e-05, + "loss": 3.4428, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3445094646555245e-05, + "loss": 3.4545, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436708699044725e-05, + "loss": 3.4396, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428322751534205e-05, + "loss": 3.4515, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419953182827414e-05, + "loss": 3.4401, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411567235316894e-05, + "loss": 3.4644, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403181287806374e-05, + "loss": 3.4547, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394811719099586e-05, + "loss": 3.4483, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386425771589066e-05, + "loss": 3.4574, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3378039824078546e-05, + "loss": 3.4521, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369653876568026e-05, + "loss": 3.4526, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361267929057506e-05, + "loss": 3.4386, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352898360350715e-05, + "loss": 3.4349, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.33445124128402e-05, + "loss": 3.4604, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333612646532968e-05, + "loss": 3.4471, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327756896622888e-05, + "loss": 3.4549, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319370949112368e-05, + "loss": 3.4455, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310985001601848e-05, + "loss": 3.4458, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330261543289506e-05, + "loss": 3.4388, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329422948538454e-05, + "loss": 3.45, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.328584353787402e-05, + "loss": 3.4512, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.32774575903635e-05, + "loss": 3.4605, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.326907164285298e-05, + "loss": 3.452, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.326068569534246e-05, + "loss": 3.4413, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252299747831936e-05, + "loss": 3.4452, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243913800321416e-05, + "loss": 3.4533, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235544231614632e-05, + "loss": 3.4386, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227158284104112e-05, + "loss": 3.4418, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321877233659359e-05, + "loss": 3.4452, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321038638908307e-05, + "loss": 3.4486, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.320201682037628e-05, + "loss": 3.4311, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319363087286576e-05, + "loss": 3.4428, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318524492535524e-05, + "loss": 3.4344, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317685897784472e-05, + "loss": 3.4527, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168489409137934e-05, + "loss": 3.4505, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.316010346162741e-05, + "loss": 3.4449, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315171751411689e-05, + "loss": 3.4465, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143347945410106e-05, + "loss": 3.4436, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134961997899586e-05, + "loss": 3.4628, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126576050389063e-05, + "loss": 3.4382, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118190102878542e-05, + "loss": 3.4552, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109820534171755e-05, + "loss": 3.4473, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101450965464967e-05, + "loss": 3.4448, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3093065017954447e-05, + "loss": 3.4506, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084679070443927e-05, + "loss": 3.4489, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076293122933407e-05, + "loss": 3.4544, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067907175422884e-05, + "loss": 3.4464, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059521227912364e-05, + "loss": 3.432, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051135280401844e-05, + "loss": 3.4493, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042749332891324e-05, + "loss": 3.445, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034379764184536e-05, + "loss": 3.4521, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025993816674016e-05, + "loss": 3.4475, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017607869163496e-05, + "loss": 3.4345, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009221921652976e-05, + "loss": 3.4475, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000852352946185e-05, + "loss": 3.4466, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299246640543567e-05, + "loss": 3.4465, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298408045792515e-05, + "loss": 3.4321, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297569451041463e-05, + "loss": 3.4524, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967324941707838e-05, + "loss": 3.4618, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958938994197317e-05, + "loss": 3.4457, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950553046686797e-05, + "loss": 3.4294, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942167099176277e-05, + "loss": 3.4475, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293379753046949e-05, + "loss": 3.4456, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292541158295897e-05, + "loss": 3.4504, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291702563544845e-05, + "loss": 3.4511, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.290863968793793e-05, + "loss": 3.4398, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.290027011923114e-05, + "loss": 3.4416, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891884171720622e-05, + "loss": 3.4509, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883498224210102e-05, + "loss": 3.4324, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875112276699582e-05, + "loss": 3.4411, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286674270799279e-05, + "loss": 3.4395, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285835676048227e-05, + "loss": 3.4515, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.284997081297175e-05, + "loss": 3.4261, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284158486546123e-05, + "loss": 3.4408, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833215296754444e-05, + "loss": 3.4374, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824829349243924e-05, + "loss": 3.4406, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816443401733403e-05, + "loss": 3.4482, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2808057454222883e-05, + "loss": 3.4343, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799687885516093e-05, + "loss": 3.4496, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791301938005576e-05, + "loss": 3.4505, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782915990495056e-05, + "loss": 3.4363, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774530042984536e-05, + "loss": 3.4484, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766160474277745e-05, + "loss": 3.4412, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757774526767225e-05, + "loss": 3.4486, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749388579256705e-05, + "loss": 3.4285, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2741002631746185e-05, + "loss": 3.4458, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732633063039397e-05, + "loss": 3.4375, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724247115528877e-05, + "loss": 3.4464, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715861168018357e-05, + "loss": 3.4379, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707475220507834e-05, + "loss": 3.447, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699105651801046e-05, + "loss": 3.4452, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269071970429053e-05, + "loss": 3.4389, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268233375678001e-05, + "loss": 3.4242, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673947809269486e-05, + "loss": 3.4568, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.26655782405627e-05, + "loss": 3.4431, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.265719229305218e-05, + "loss": 3.4523, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648806345541655e-05, + "loss": 3.4362, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264042039803114e-05, + "loss": 3.4494, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263205082932435e-05, + "loss": 3.4464, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262366488181383e-05, + "loss": 3.4421, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615278934303307e-05, + "loss": 3.4407, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606892986792787e-05, + "loss": 3.4465, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598523418086e-05, + "loss": 3.447, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.259013747057548e-05, + "loss": 3.4559, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258175152306496e-05, + "loss": 3.4333, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257336557555444e-05, + "loss": 3.4457, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564996006847652e-05, + "loss": 3.4372, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255661005933713e-05, + "loss": 3.4447, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.254822411182661e-05, + "loss": 3.4491, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539838164316092e-05, + "loss": 3.4408, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531468595609305e-05, + "loss": 3.4545, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252308264809878e-05, + "loss": 3.4386, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251469670058826e-05, + "loss": 3.4454, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.9094295501708984, + "eval_runtime": 305.1185, + "eval_samples_per_second": 1250.632, + "eval_steps_per_second": 39.083, + "step": 1679029 + }, + { + "epoch": 0.0, + "learning_rate": 2.250631075307774e-05, + "loss": 3.4351, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249792480556722e-05, + "loss": 3.4459, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.24895388580567e-05, + "loss": 3.4474, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481152910546184e-05, + "loss": 3.4464, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472783341839393e-05, + "loss": 3.4525, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464397394328873e-05, + "loss": 3.4465, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2456011446818353e-05, + "loss": 3.4334, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2447625499307833e-05, + "loss": 3.4352, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439255930601046e-05, + "loss": 3.4493, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430869983090526e-05, + "loss": 3.4473, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422484035580006e-05, + "loss": 3.441, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414098088069486e-05, + "loss": 3.4462, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405728519362695e-05, + "loss": 3.4302, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397342571852175e-05, + "loss": 3.4342, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388956624341655e-05, + "loss": 3.4369, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380570676831138e-05, + "loss": 3.4263, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372201108124347e-05, + "loss": 3.4397, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363815160613827e-05, + "loss": 3.4308, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355429213103307e-05, + "loss": 3.4342, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347043265592784e-05, + "loss": 3.4675, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338673696886e-05, + "loss": 3.44, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233028774937548e-05, + "loss": 3.4377, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232190180186496e-05, + "loss": 3.4441, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313515854354436e-05, + "loss": 3.4424, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.230514628564765e-05, + "loss": 3.427, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.229676033813713e-05, + "loss": 3.4397, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288374390626608e-05, + "loss": 3.4376, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279988443116088e-05, + "loss": 3.427, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.22716188744093e-05, + "loss": 3.4363, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226323292689878e-05, + "loss": 3.428, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254846979388257e-05, + "loss": 3.4413, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246461031877737e-05, + "loss": 3.4407, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238091463170953e-05, + "loss": 3.4381, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229705515660433e-05, + "loss": 3.4393, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222131956814991e-05, + "loss": 3.4384, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212949999443122e-05, + "loss": 3.4413, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204564051932602e-05, + "loss": 3.4301, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196178104422082e-05, + "loss": 3.4459, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187792156911562e-05, + "loss": 3.4243, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179422588204774e-05, + "loss": 3.4403, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171036640694254e-05, + "loss": 3.4225, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216265069318373e-05, + "loss": 3.4537, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215426474567321e-05, + "loss": 3.4417, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145895176966423e-05, + "loss": 3.4416, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137509229455903e-05, + "loss": 3.442, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129123281945383e-05, + "loss": 3.4401, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120737334434863e-05, + "loss": 3.4377, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112367765728076e-05, + "loss": 3.432, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103981818217552e-05, + "loss": 3.4184, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095595870707032e-05, + "loss": 3.4511, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087209923196516e-05, + "loss": 3.4325, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078840354489728e-05, + "loss": 3.4437, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070454406979205e-05, + "loss": 3.4315, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2062068459468685e-05, + "loss": 3.4351, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053698890761897e-05, + "loss": 3.4224, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045312943251377e-05, + "loss": 3.4429, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036926995740857e-05, + "loss": 3.4413, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028541048230337e-05, + "loss": 3.447, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2020155100719817e-05, + "loss": 3.4411, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011769153209297e-05, + "loss": 3.427, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003383205698777e-05, + "loss": 3.4355, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994997258188257e-05, + "loss": 3.4453, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198662768948147e-05, + "loss": 3.4255, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197824174197095e-05, + "loss": 3.4296, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196985579446043e-05, + "loss": 3.4318, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196146984694991e-05, + "loss": 3.4416, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953100278243118e-05, + "loss": 3.416, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944714330732598e-05, + "loss": 3.4303, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936328383222078e-05, + "loss": 3.4275, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192794243571156e-05, + "loss": 3.4334, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191957286700477e-05, + "loss": 3.4392, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191118691949425e-05, + "loss": 3.4347, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190280097198373e-05, + "loss": 3.4382, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894415024473207e-05, + "loss": 3.4273, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886045455766423e-05, + "loss": 3.4532, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877659508255903e-05, + "loss": 3.4259, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869273560745383e-05, + "loss": 3.4428, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186088761323486e-05, + "loss": 3.433, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852518044528072e-05, + "loss": 3.4328, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844148475821284e-05, + "loss": 3.4426, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835762528310764e-05, + "loss": 3.4386, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827376580800244e-05, + "loss": 3.439, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818990633289724e-05, + "loss": 3.4363, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810604685779204e-05, + "loss": 3.4222, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180221873826868e-05, + "loss": 3.4337, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179383279075816e-05, + "loss": 3.4361, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785463222051373e-05, + "loss": 3.4411, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777077274540857e-05, + "loss": 3.4298, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768691327030333e-05, + "loss": 3.4253, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760305379519813e-05, + "loss": 3.432, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751935810813026e-05, + "loss": 3.437, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743549863302506e-05, + "loss": 3.4346, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1735163915791985e-05, + "loss": 3.4231, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726777968281465e-05, + "loss": 3.4382, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718408399574678e-05, + "loss": 3.4494, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1710022452064154e-05, + "loss": 3.4323, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701636504553634e-05, + "loss": 3.4155, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693250557043114e-05, + "loss": 3.4362, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684880988336327e-05, + "loss": 3.4335, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676495040825807e-05, + "loss": 3.4377, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668109093315287e-05, + "loss": 3.4427, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659723145804767e-05, + "loss": 3.4293, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.165135357709798e-05, + "loss": 3.4279, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642967629587456e-05, + "loss": 3.4386, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163458168207694e-05, + "loss": 3.4204, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162619573456642e-05, + "loss": 3.4309, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617826165859628e-05, + "loss": 3.4256, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609440218349108e-05, + "loss": 3.444, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601054270838588e-05, + "loss": 3.4172, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592668323328068e-05, + "loss": 3.4253, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.158429875462128e-05, + "loss": 3.4255, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.157591280711076e-05, + "loss": 3.4316, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156752685960024e-05, + "loss": 3.4342, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155914091208972e-05, + "loss": 3.4267, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.15507549645792e-05, + "loss": 3.4355, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154236901706868e-05, + "loss": 3.4407, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153398306955816e-05, + "loss": 3.4244, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.152559712204764e-05, + "loss": 3.4418, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517227553340853e-05, + "loss": 3.4301, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508841605830333e-05, + "loss": 3.4356, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150045565831981e-05, + "loss": 3.421, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1492086089613022e-05, + "loss": 3.429, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.14837001421025e-05, + "loss": 3.4272, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475314194591985e-05, + "loss": 3.4337, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146692824708146e-05, + "loss": 3.4327, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458558678374674e-05, + "loss": 3.4297, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450172730864154e-05, + "loss": 3.4352, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144178678335363e-05, + "loss": 3.4282, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143340083584311e-05, + "loss": 3.4166, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1425031267136326e-05, + "loss": 3.4415, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416645319625806e-05, + "loss": 3.4301, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408259372115283e-05, + "loss": 3.4402, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399873424604763e-05, + "loss": 3.4259, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391503855897975e-05, + "loss": 3.44, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1383117908387455e-05, + "loss": 3.4328, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374731960876935e-05, + "loss": 3.4275, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366346013366415e-05, + "loss": 3.4282, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357976444659628e-05, + "loss": 3.4343, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349590497149104e-05, + "loss": 3.4354, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341204549638584e-05, + "loss": 3.4482, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332818602128064e-05, + "loss": 3.417, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132444903342128e-05, + "loss": 3.4362, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316063085910757e-05, + "loss": 3.4257, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307677138400237e-05, + "loss": 3.4341, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299291190889717e-05, + "loss": 3.4322, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.129092162218293e-05, + "loss": 3.4297, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.128253567467241e-05, + "loss": 3.447, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127414972716189e-05, + "loss": 3.4252, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126576377965137e-05, + "loss": 3.4345, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.9128286838531494, + "eval_runtime": 302.7502, + "eval_samples_per_second": 1260.415, + "eval_steps_per_second": 39.389, + "step": 1755349 + }, + { + "epoch": 0.0, + "learning_rate": 2.125737783214085e-05, + "loss": 3.4319, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124899188463033e-05, + "loss": 3.4289, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.124060593711981e-05, + "loss": 3.4365, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232219989609285e-05, + "loss": 3.4368, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.12238504209025e-05, + "loss": 3.4394, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.121546447339198e-05, + "loss": 3.4329, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120707852588146e-05, + "loss": 3.4223, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198692578370938e-05, + "loss": 3.4216, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119032300966415e-05, + "loss": 3.4397, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.118193706215363e-05, + "loss": 3.4344, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.117355111464311e-05, + "loss": 3.426, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.116516516713259e-05, + "loss": 3.4346, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156811977229532e-05, + "loss": 3.4248, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114842602971901e-05, + "loss": 3.4216, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114004008220849e-05, + "loss": 3.4251, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113165413469797e-05, + "loss": 3.4183, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123268187187455e-05, + "loss": 3.4259, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114882239676935e-05, + "loss": 3.42, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110649629216641e-05, + "loss": 3.4215, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.109811034465589e-05, + "loss": 3.4545, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089740775949104e-05, + "loss": 3.4288, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081354828438584e-05, + "loss": 3.4281, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072968880928064e-05, + "loss": 3.4301, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064582933417544e-05, + "loss": 3.4329, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056213364710756e-05, + "loss": 3.4143, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047827417200233e-05, + "loss": 3.428, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039441469689713e-05, + "loss": 3.4274, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031055522179193e-05, + "loss": 3.4184, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022685953472405e-05, + "loss": 3.422, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014300005961885e-05, + "loss": 3.4182, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005914058451365e-05, + "loss": 3.4275, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997528110940845e-05, + "loss": 3.4312, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989158542234058e-05, + "loss": 3.4258, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980772594723534e-05, + "loss": 3.4253, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972386647213017e-05, + "loss": 3.4264, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964000699702497e-05, + "loss": 3.4283, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955631130995707e-05, + "loss": 3.4204, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947245183485186e-05, + "loss": 3.434, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938859235974666e-05, + "loss": 3.415, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.093048966726788e-05, + "loss": 3.4275, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.092210371975736e-05, + "loss": 3.4142, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091371777224684e-05, + "loss": 3.4417, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090533182473632e-05, + "loss": 3.4273, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089696225602953e-05, + "loss": 3.4296, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888576308519008e-05, + "loss": 3.4334, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880190361008488e-05, + "loss": 3.427, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087180441349797e-05, + "loss": 3.4291, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086343484479118e-05, + "loss": 3.4224, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085504889728066e-05, + "loss": 3.4039, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084666294977014e-05, + "loss": 3.4413, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083827700225962e-05, + "loss": 3.421, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829907433552833e-05, + "loss": 3.437, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821521486042313e-05, + "loss": 3.4189, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813135538531792e-05, + "loss": 3.4228, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804749591021272e-05, + "loss": 3.411, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079638002231448e-05, + "loss": 3.4296, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.078799407480396e-05, + "loss": 3.4325, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077960812729344e-05, + "loss": 3.4306, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771222179782925e-05, + "loss": 3.4342, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762852611076134e-05, + "loss": 3.4154, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754466663565614e-05, + "loss": 3.4201, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746080716055094e-05, + "loss": 3.4355, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737694768544574e-05, + "loss": 3.4165, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729325199837786e-05, + "loss": 3.4156, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720939252327266e-05, + "loss": 3.4209, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712553304816746e-05, + "loss": 3.4309, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704167357306226e-05, + "loss": 3.4077, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695797788599435e-05, + "loss": 3.418, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687411841088915e-05, + "loss": 3.4162, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679025893578395e-05, + "loss": 3.4215, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067063994606788e-05, + "loss": 3.4285, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662270377361088e-05, + "loss": 3.4253, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653884429850568e-05, + "loss": 3.4221, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645498482340047e-05, + "loss": 3.4197, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637112534829527e-05, + "loss": 3.4391, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062874296612274e-05, + "loss": 3.416, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.062035701861222e-05, + "loss": 3.4322, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.06119710711017e-05, + "loss": 3.4222, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060358512359118e-05, + "loss": 3.4198, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059521555488439e-05, + "loss": 3.4291, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058682960737387e-05, + "loss": 3.427, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057844365986335e-05, + "loss": 3.4233, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.057005771235283e-05, + "loss": 3.4271, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056167176484231e-05, + "loss": 3.4134, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055328581733179e-05, + "loss": 3.4224, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054489986982127e-05, + "loss": 3.4234, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053653030111448e-05, + "loss": 3.4325, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528144353603958e-05, + "loss": 3.4188, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051975840609344e-05, + "loss": 3.4154, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.051137245858292e-05, + "loss": 3.4202, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050300288987613e-05, + "loss": 3.4278, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049461694236561e-05, + "loss": 3.4249, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048623099485509e-05, + "loss": 3.4102, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047784504734457e-05, + "loss": 3.4318, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469475478637782e-05, + "loss": 3.4356, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461089531127262e-05, + "loss": 3.4244, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452703583616742e-05, + "loss": 3.4047, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444317636106222e-05, + "loss": 3.4255, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043594806739943e-05, + "loss": 3.4172, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042756211988891e-05, + "loss": 3.4307, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419176172378395e-05, + "loss": 3.4312, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410790224867875e-05, + "loss": 3.4145, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402420656161084e-05, + "loss": 3.419, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394034708650564e-05, + "loss": 3.425, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385648761140044e-05, + "loss": 3.4114, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377262813629524e-05, + "loss": 3.4221, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368893244922736e-05, + "loss": 3.4129, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360507297412216e-05, + "loss": 3.4341, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352121349901696e-05, + "loss": 3.4052, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343735402391176e-05, + "loss": 3.4122, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335365833684385e-05, + "loss": 3.4153, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0326979886173865e-05, + "loss": 3.4246, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031859393866335e-05, + "loss": 3.4181, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310207991152828e-05, + "loss": 3.4143, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301822043642308e-05, + "loss": 3.4251, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293436096131785e-05, + "loss": 3.4284, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285050148621265e-05, + "loss": 3.4129, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276664201110745e-05, + "loss": 3.4294, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268294632403957e-05, + "loss": 3.4181, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259908684893437e-05, + "loss": 3.4192, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251522737382917e-05, + "loss": 3.4155, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024315316867613e-05, + "loss": 3.4178, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023476722116561e-05, + "loss": 3.4152, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226381273655086e-05, + "loss": 3.4225, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217995326144566e-05, + "loss": 3.4236, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209625757437782e-05, + "loss": 3.4204, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020123980992726e-05, + "loss": 3.4191, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.019285386241674e-05, + "loss": 3.4177, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.018446791490622e-05, + "loss": 3.4063, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.017609834619943e-05, + "loss": 3.4313, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.016771239868891e-05, + "loss": 3.4213, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015932645117839e-05, + "loss": 3.4262, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.015094050366787e-05, + "loss": 3.4162, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.014257093496108e-05, + "loss": 3.4297, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013418498745056e-05, + "loss": 3.421, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.012579903994004e-05, + "loss": 3.4168, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011741309242952e-05, + "loss": 3.4197, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109043523722732e-05, + "loss": 3.4216, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100657576212212e-05, + "loss": 3.4221, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092271628701692e-05, + "loss": 3.4385, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083885681191172e-05, + "loss": 3.4047, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007551611248438e-05, + "loss": 3.4264, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067130164973865e-05, + "loss": 3.4157, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058744217463344e-05, + "loss": 3.421, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050358269952824e-05, + "loss": 3.4202, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041988701246034e-05, + "loss": 3.4236, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033602753735514e-05, + "loss": 3.4292, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025216806224993e-05, + "loss": 3.4152, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016830858714473e-05, + "loss": 3.4239, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.9132137298583984, + "eval_runtime": 306.1314, + "eval_samples_per_second": 1246.494, + "eval_steps_per_second": 38.954, + "step": 1831669 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008461290007686e-05, + "loss": 3.4189, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.0000075342497166e-05, + "loss": 3.4195, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991689394986646e-05, + "loss": 3.4217, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983303447476126e-05, + "loss": 3.4242, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9974933878769335e-05, + "loss": 3.4306, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966547931258818e-05, + "loss": 3.4183, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.9958161983748298e-05, + "loss": 3.4125, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9949776036237778e-05, + "loss": 3.413, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941406467530987e-05, + "loss": 3.4259, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.9933020520020467e-05, + "loss": 3.4272, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924634572509947e-05, + "loss": 3.4152, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916248624999427e-05, + "loss": 3.4237, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9907895435096372e-05, + "loss": 3.4154, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899509487585852e-05, + "loss": 3.4107, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989112354007533e-05, + "loss": 3.4137, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988273759256481e-05, + "loss": 3.4051, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.987435164505429e-05, + "loss": 3.4142, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865965697543772e-05, + "loss": 3.4112, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857579750033252e-05, + "loss": 3.4104, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849193802522732e-05, + "loss": 3.4429, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984082423381594e-05, + "loss": 3.4213, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.983243828630542e-05, + "loss": 3.414, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.98240523387949e-05, + "loss": 3.4189, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981566639128438e-05, + "loss": 3.4226, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807296822577593e-05, + "loss": 3.4002, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798910875067073e-05, + "loss": 3.4167, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790524927556553e-05, + "loss": 3.4201, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782138980046033e-05, + "loss": 3.4047, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773769411339242e-05, + "loss": 3.4055, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765383463828726e-05, + "loss": 3.4108, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756997516318205e-05, + "loss": 3.4159, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748611568807682e-05, + "loss": 3.42, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740242000100895e-05, + "loss": 3.4149, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731856052590375e-05, + "loss": 3.4157, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723470105079854e-05, + "loss": 3.4158, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9715084157569334e-05, + "loss": 3.4171, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706714588862547e-05, + "loss": 3.4126, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698328641352027e-05, + "loss": 3.4201, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689942693841507e-05, + "loss": 3.4039, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681556746330983e-05, + "loss": 3.4143, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673187177624196e-05, + "loss": 3.4068, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664801230113676e-05, + "loss": 3.4283, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656415282603156e-05, + "loss": 3.4226, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648029335092636e-05, + "loss": 3.4141, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639659766385848e-05, + "loss": 3.423, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631273818875328e-05, + "loss": 3.4147, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622887871364805e-05, + "loss": 3.4199, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614501923854288e-05, + "loss": 3.4134, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.96061323551475e-05, + "loss": 3.3882, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959774640763698e-05, + "loss": 3.4299, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589360460126457e-05, + "loss": 3.4091, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9580974512615937e-05, + "loss": 3.4283, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957260494390915e-05, + "loss": 3.4071, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956421899639863e-05, + "loss": 3.4149, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955583304888811e-05, + "loss": 3.3976, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.9547463480181322e-05, + "loss": 3.4186, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.9539077532670802e-05, + "loss": 3.4228, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953069158516028e-05, + "loss": 3.4175, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952230563764976e-05, + "loss": 3.4251, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513936068942974e-05, + "loss": 3.4082, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950555012143245e-05, + "loss": 3.4082, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949716417392193e-05, + "loss": 3.4254, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948877822641141e-05, + "loss": 3.4035, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480408657704623e-05, + "loss": 3.4071, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472022710194103e-05, + "loss": 3.4087, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463636762683583e-05, + "loss": 3.4167, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455250815173063e-05, + "loss": 3.3985, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446881246466276e-05, + "loss": 3.408, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438495298955752e-05, + "loss": 3.4022, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430109351445232e-05, + "loss": 3.4084, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421723403934712e-05, + "loss": 3.419, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413353835227925e-05, + "loss": 3.4109, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404967887717405e-05, + "loss": 3.4109, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396581940206884e-05, + "loss": 3.4119, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388195992696364e-05, + "loss": 3.4283, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379826423989574e-05, + "loss": 3.4032, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371440476479057e-05, + "loss": 3.4211, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363054528968537e-05, + "loss": 3.4106, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354668581458017e-05, + "loss": 3.4067, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346299012751226e-05, + "loss": 3.421, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337913065240706e-05, + "loss": 3.4192, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329527117730186e-05, + "loss": 3.4147, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321141170219666e-05, + "loss": 3.413, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.931275522270915e-05, + "loss": 3.4038, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.930436927519863e-05, + "loss": 3.4072, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295983327688106e-05, + "loss": 3.4133, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287597380177586e-05, + "loss": 3.4231, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279227811470798e-05, + "loss": 3.4063, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9270841863960278e-05, + "loss": 3.4064, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262455916449758e-05, + "loss": 3.4059, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925408634774297e-05, + "loss": 3.4185, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924570040023245e-05, + "loss": 3.4139, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923731445272193e-05, + "loss": 3.3999, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228928505211407e-05, + "loss": 3.4184, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922055893650462e-05, + "loss": 3.4232, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.92121729889941e-05, + "loss": 3.4145, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920378704148358e-05, + "loss": 3.3971, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.919540109397306e-05, + "loss": 3.4103, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9187031525266272e-05, + "loss": 3.4055, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178645577755752e-05, + "loss": 3.4191, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170259630245228e-05, + "loss": 3.4166, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916187368273471e-05, + "loss": 3.4115, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153504114027924e-05, + "loss": 3.4053, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145118166517404e-05, + "loss": 3.4097, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913673221900688e-05, + "loss": 3.4045, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912834627149636e-05, + "loss": 3.4087, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119976702789573e-05, + "loss": 3.4018, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111590755279053e-05, + "loss": 3.422, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103204807768533e-05, + "loss": 3.3972, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094818860258013e-05, + "loss": 3.4009, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086449291551225e-05, + "loss": 3.4019, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078063344040702e-05, + "loss": 3.4077, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9069677396530182e-05, + "loss": 3.4102, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061291449019665e-05, + "loss": 3.4027, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052921880312878e-05, + "loss": 3.4133, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044535932802354e-05, + "loss": 3.4188, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036149985291834e-05, + "loss": 3.4019, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027764037781314e-05, + "loss": 3.4147, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019394469074527e-05, + "loss": 3.4118, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9011008521564007e-05, + "loss": 3.4112, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002622574053487e-05, + "loss": 3.4033, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994236626542967e-05, + "loss": 3.4046, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985867057836176e-05, + "loss": 3.4057, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977481110325656e-05, + "loss": 3.4155, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8969095162815136e-05, + "loss": 3.413, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896070921530462e-05, + "loss": 3.408, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952339646597828e-05, + "loss": 3.4117, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943953699087308e-05, + "loss": 3.4065, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893558413038052e-05, + "loss": 3.394, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927198182869997e-05, + "loss": 3.418, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891881223535948e-05, + "loss": 3.4058, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.891042628784896e-05, + "loss": 3.4194, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890204034033844e-05, + "loss": 3.406, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889365439282792e-05, + "loss": 3.4171, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.88852684453174e-05, + "loss": 3.4102, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887688249780688e-05, + "loss": 3.4085, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886851292910009e-05, + "loss": 3.408, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.886012698158957e-05, + "loss": 3.4071, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851741034079053e-05, + "loss": 3.4133, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884335508656853e-05, + "loss": 3.4261, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.883498551786174e-05, + "loss": 3.393, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882659957035122e-05, + "loss": 3.419, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.88182136228407e-05, + "loss": 3.4016, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880982767533018e-05, + "loss": 3.4098, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801458106623394e-05, + "loss": 3.4077, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793072159112874e-05, + "loss": 3.4133, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784686211602354e-05, + "loss": 3.4163, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.877630026409183e-05, + "loss": 3.411, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8767930695385043e-05, + "loss": 3.4088, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.916419267654419, + "eval_runtime": 306.7954, + "eval_samples_per_second": 1243.796, + "eval_steps_per_second": 38.87, + "step": 1907989 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759544747874523e-05, + "loss": 3.4091, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751158800364003e-05, + "loss": 3.4096, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742772852853483e-05, + "loss": 3.4139, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734386905342963e-05, + "loss": 3.4101, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726017336636175e-05, + "loss": 3.4175, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717631389125652e-05, + "loss": 3.4096, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709245441615135e-05, + "loss": 3.4044, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700859494104615e-05, + "loss": 3.4047, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692489925397828e-05, + "loss": 3.4107, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684103977887304e-05, + "loss": 3.4161, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675718030376784e-05, + "loss": 3.4078, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667332082866264e-05, + "loss": 3.41, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865897889296321e-05, + "loss": 3.4067, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865059294545269e-05, + "loss": 3.3992, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.864220699794217e-05, + "loss": 3.4013, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863382105043165e-05, + "loss": 3.3963, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625435102921126e-05, + "loss": 3.401, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617049155410605e-05, + "loss": 3.4002, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860866320790009e-05, + "loss": 3.4008, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860027726038957e-05, + "loss": 3.427, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591907691682778e-05, + "loss": 3.4135, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8583521744172258e-05, + "loss": 3.4059, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575135796661738e-05, + "loss": 3.407, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566749849151218e-05, + "loss": 3.409, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.855838028044443e-05, + "loss": 3.3896, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854999433293391e-05, + "loss": 3.4058, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854160838542339e-05, + "loss": 3.4076, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853322243791287e-05, + "loss": 3.3924, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852485286920608e-05, + "loss": 3.4, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851646692169556e-05, + "loss": 3.3985, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508080974185042e-05, + "loss": 3.4043, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499695026674522e-05, + "loss": 3.4061, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849132545796773e-05, + "loss": 3.4038, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848293951045721e-05, + "loss": 3.4125, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847455356294669e-05, + "loss": 3.4013, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846616761543617e-05, + "loss": 3.4029, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457798046729384e-05, + "loss": 3.4072, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449412099218864e-05, + "loss": 3.4045, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441026151708344e-05, + "loss": 3.3955, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432640204197824e-05, + "loss": 3.4043, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424270635491033e-05, + "loss": 3.3964, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415884687980513e-05, + "loss": 3.4136, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407498740469993e-05, + "loss": 3.4124, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399129171763205e-05, + "loss": 3.4016, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390743224252685e-05, + "loss": 3.4159, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382357276742165e-05, + "loss": 3.4044, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373971329231645e-05, + "loss": 3.4091, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365601760524858e-05, + "loss": 3.4038, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357215813014338e-05, + "loss": 3.3767, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348829865503818e-05, + "loss": 3.4164, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340443917993297e-05, + "loss": 3.4021, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332074349286507e-05, + "loss": 3.4118, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323688401775987e-05, + "loss": 3.4015, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315302454265466e-05, + "loss": 3.4003, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306916506754946e-05, + "loss": 3.3881, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829854693804816e-05, + "loss": 3.4074, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829016099053764e-05, + "loss": 3.4104, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.828177504302712e-05, + "loss": 3.4071, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.82733890955166e-05, + "loss": 3.4175, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265019526809808e-05, + "loss": 3.3974, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.825663357929929e-05, + "loss": 3.3952, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824824763178877e-05, + "loss": 3.4165, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.823986168427825e-05, + "loss": 3.3945, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823149211557146e-05, + "loss": 3.3918, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822310616806094e-05, + "loss": 3.4004, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821472022055042e-05, + "loss": 3.4075, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.82063342730399e-05, + "loss": 3.392, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197964704333113e-05, + "loss": 3.394, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189578756822593e-05, + "loss": 3.3935, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181192809312073e-05, + "loss": 3.3935, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817280686180155e-05, + "loss": 3.4092, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.816443729309476e-05, + "loss": 3.4018, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156051345584245e-05, + "loss": 3.4032, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147665398073725e-05, + "loss": 3.3957, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.81392794505632e-05, + "loss": 3.4192, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8130909881856414e-05, + "loss": 3.3938, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122523934345894e-05, + "loss": 3.4128, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114137986835374e-05, + "loss": 3.3989, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105752039324854e-05, + "loss": 3.3984, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097382470618066e-05, + "loss": 3.4056, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088996523107546e-05, + "loss": 3.4106, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080610575597023e-05, + "loss": 3.4017, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072224628086503e-05, + "loss": 3.4029, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063838680575983e-05, + "loss": 3.3947, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055452733065466e-05, + "loss": 3.3961, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047066785554946e-05, + "loss": 3.404, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038680838044426e-05, + "loss": 3.4046, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030311269337635e-05, + "loss": 3.3966, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021925321827115e-05, + "loss": 3.3993, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013539374316595e-05, + "loss": 3.396, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005153426806075e-05, + "loss": 3.4029, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996783858099287e-05, + "loss": 3.4046, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988397910588767e-05, + "loss": 3.3864, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980011963078247e-05, + "loss": 3.4104, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971642394371456e-05, + "loss": 3.4098, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963256446860936e-05, + "loss": 3.4077, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954870499350416e-05, + "loss": 3.3859, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.79464845518399e-05, + "loss": 3.398, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793811498313311e-05, + "loss": 3.3944, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792972903562259e-05, + "loss": 3.4096, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792134308811207e-05, + "loss": 3.4052, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.791295714060155e-05, + "loss": 3.4025, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790458757189476e-05, + "loss": 3.3955, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789620162438424e-05, + "loss": 3.3984, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788781567687372e-05, + "loss": 3.3911, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.78794297293632e-05, + "loss": 3.399, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.787106016065641e-05, + "loss": 3.3919, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.786267421314589e-05, + "loss": 3.4065, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785428826563537e-05, + "loss": 3.3906, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845902318124853e-05, + "loss": 3.3855, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837532749418062e-05, + "loss": 3.3951, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829146801907542e-05, + "loss": 3.3913, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820760854397022e-05, + "loss": 3.3999, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.78123749068865e-05, + "loss": 3.3948, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7804005338179715e-05, + "loss": 3.4053, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795619390669195e-05, + "loss": 3.4065, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787233443158675e-05, + "loss": 3.3918, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777884749564815e-05, + "loss": 3.4024, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770477926941364e-05, + "loss": 3.4005, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762091979430844e-05, + "loss": 3.3991, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753706031920324e-05, + "loss": 3.3943, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745320084409804e-05, + "loss": 3.3907, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736950515703016e-05, + "loss": 3.397, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728564568192496e-05, + "loss": 3.4004, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720178620681973e-05, + "loss": 3.402, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711792673171453e-05, + "loss": 3.3965, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770342310446467e-05, + "loss": 3.3972, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769503715695415e-05, + "loss": 3.399, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686667588247358e-05, + "loss": 3.3804, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678281640736837e-05, + "loss": 3.4095, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669895693226317e-05, + "loss": 3.3924, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661509745715797e-05, + "loss": 3.413, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653123798205277e-05, + "loss": 3.3925, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644737850694757e-05, + "loss": 3.4062, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636351903184237e-05, + "loss": 3.4024, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627965955673717e-05, + "loss": 3.3922, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619596386966926e-05, + "loss": 3.3974, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611210439456406e-05, + "loss": 3.3956, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760282449194589e-05, + "loss": 3.4046, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759443854443537e-05, + "loss": 3.4143, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758606897572858e-05, + "loss": 3.3807, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757768302821806e-05, + "loss": 3.4036, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756929708070754e-05, + "loss": 3.3936, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756091113319702e-05, + "loss": 3.4021, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.755254156449023e-05, + "loss": 3.397, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754415561697971e-05, + "loss": 3.4062, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753576966946919e-05, + "loss": 3.4033, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752738372195867e-05, + "loss": 3.3967, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751901415325188e-05, + "loss": 3.3977, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.918168783187866, + "eval_runtime": 309.3384, + "eval_samples_per_second": 1233.571, + "eval_steps_per_second": 38.55, + "step": 1984309 + }, + { + "epoch": 1.0, + "learning_rate": 1.751062820574136e-05, + "loss": 3.3959, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.750224225823084e-05, + "loss": 3.3997, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493856310720323e-05, + "loss": 3.4015, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485486742013532e-05, + "loss": 3.4019, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477100794503012e-05, + "loss": 3.4069, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468714846992492e-05, + "loss": 3.3955, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460328899481972e-05, + "loss": 3.3939, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451959330775185e-05, + "loss": 3.3939, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443573383264665e-05, + "loss": 3.3972, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435187435754145e-05, + "loss": 3.4047, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426801488243625e-05, + "loss": 3.3971, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418431919536834e-05, + "loss": 3.394, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410062350830046e-05, + "loss": 3.4015, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401676403319526e-05, + "loss": 3.3854, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393290455809006e-05, + "loss": 3.3947, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384904508298486e-05, + "loss": 3.3812, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376518560787966e-05, + "loss": 3.3875, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368132613277446e-05, + "loss": 3.3932, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7359746665766922e-05, + "loss": 3.3911, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351360718256406e-05, + "loss": 3.4106, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342991149549618e-05, + "loss": 3.4048, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334605202039098e-05, + "loss": 3.3989, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326219254528575e-05, + "loss": 3.3958, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317833307018055e-05, + "loss": 3.3977, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309463738311267e-05, + "loss": 3.3809, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7301077790800747e-05, + "loss": 3.3982, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292691843290227e-05, + "loss": 3.3945, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284305895779707e-05, + "loss": 3.3797, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727593632707292e-05, + "loss": 3.3887, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267550379562396e-05, + "loss": 3.387, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259164432051876e-05, + "loss": 3.3963, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.725077848454136e-05, + "loss": 3.3956, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242408915834572e-05, + "loss": 3.3906, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723402296832405e-05, + "loss": 3.4015, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722563702081353e-05, + "loss": 3.3894, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.721725107330301e-05, + "loss": 3.3958, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.720888150459622e-05, + "loss": 3.4023, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.72004955570857e-05, + "loss": 3.388, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.719210960957518e-05, + "loss": 3.3862, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.718372366206466e-05, + "loss": 3.3911, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717535409335787e-05, + "loss": 3.3871, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716696814584735e-05, + "loss": 3.4009, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715858219833683e-05, + "loss": 3.3985, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.715019625082631e-05, + "loss": 3.3958, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141826682119522e-05, + "loss": 3.4002, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133440734609002e-05, + "loss": 3.3961, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125054787098482e-05, + "loss": 3.3987, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116668839587962e-05, + "loss": 3.3961, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108299270881175e-05, + "loss": 3.3654, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099913323370655e-05, + "loss": 3.405, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091527375860134e-05, + "loss": 3.3888, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083157807153344e-05, + "loss": 3.401, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074771859642824e-05, + "loss": 3.3925, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066385912132303e-05, + "loss": 3.3898, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7057999964621783e-05, + "loss": 3.3791, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049630395914996e-05, + "loss": 3.3948, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041244448404476e-05, + "loss": 3.3997, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032858500893956e-05, + "loss": 3.3938, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024472553383436e-05, + "loss": 3.4078, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016102984676645e-05, + "loss": 3.3918, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007717037166125e-05, + "loss": 3.3764, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999331089655608e-05, + "loss": 3.4063, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6990945142145088e-05, + "loss": 3.3861, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982575573438297e-05, + "loss": 3.38, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974189625927777e-05, + "loss": 3.3916, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965803678417257e-05, + "loss": 3.3945, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957417730906737e-05, + "loss": 3.3799, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694904816219995e-05, + "loss": 3.3856, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694066221468943e-05, + "loss": 3.3846, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693227626717891e-05, + "loss": 3.3798, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692389031966839e-05, + "loss": 3.4008, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.69155207509616e-05, + "loss": 3.3942, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690713480345108e-05, + "loss": 3.3888, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898748855940562e-05, + "loss": 3.3879, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890362908430042e-05, + "loss": 3.4034, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688199333972325e-05, + "loss": 3.3875, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687360739221273e-05, + "loss": 3.4029, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686522144470221e-05, + "loss": 3.3877, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685683549719169e-05, + "loss": 3.3873, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848465928484903e-05, + "loss": 3.3947, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840079980974383e-05, + "loss": 3.3993, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831694033463863e-05, + "loss": 3.3902, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823308085953343e-05, + "loss": 3.3985, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681492213844282e-05, + "loss": 3.381, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.68065361909323e-05, + "loss": 3.3841, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798150243421783e-05, + "loss": 3.3941, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789764295911263e-05, + "loss": 3.3956, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781394727204472e-05, + "loss": 3.3872, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773008779693952e-05, + "loss": 3.3868, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764622832183432e-05, + "loss": 3.3886, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756236884672912e-05, + "loss": 3.3905, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747867315966124e-05, + "loss": 3.3928, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739481368455604e-05, + "loss": 3.3782, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731095420945084e-05, + "loss": 3.397, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722709473434564e-05, + "loss": 3.3995, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714339904727773e-05, + "loss": 3.3981, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705953957217253e-05, + "loss": 3.3691, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697568009706733e-05, + "loss": 3.3903, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689182062196217e-05, + "loss": 3.3888, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680812493489426e-05, + "loss": 3.3973, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672426545978906e-05, + "loss": 3.3954, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6664040598468386e-05, + "loss": 3.3893, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655654650957866e-05, + "loss": 3.3847, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647285082251078e-05, + "loss": 3.389, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6638899134740558e-05, + "loss": 3.3805, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630513187230038e-05, + "loss": 3.3898, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6622127239719518e-05, + "loss": 3.3823, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613757671012727e-05, + "loss": 3.3945, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605371723502207e-05, + "loss": 3.3809, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596985775991687e-05, + "loss": 3.3777, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.65886162072849e-05, + "loss": 3.379, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.658023025977438e-05, + "loss": 3.383, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657184431226386e-05, + "loss": 3.3901, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656345836475334e-05, + "loss": 3.3827, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655508879604655e-05, + "loss": 3.3912, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546702848536032e-05, + "loss": 3.3955, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538316901025512e-05, + "loss": 3.3834, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652993095351499e-05, + "loss": 3.3904, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.65215613848082e-05, + "loss": 3.391, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651317543729768e-05, + "loss": 3.3908, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650478948978716e-05, + "loss": 3.3868, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.649640354227664e-05, + "loss": 3.3779, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488033973569853e-05, + "loss": 3.3928, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479648026059333e-05, + "loss": 3.3863, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471262078548813e-05, + "loss": 3.3911, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6462876131038293e-05, + "loss": 3.3888, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454506562331502e-05, + "loss": 3.3858, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446120614820985e-05, + "loss": 3.3856, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437751046114195e-05, + "loss": 3.3712, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429365098603674e-05, + "loss": 3.3985, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420979151093154e-05, + "loss": 3.3839, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412593203582634e-05, + "loss": 3.4024, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404207256072114e-05, + "loss": 3.3805, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395821308561594e-05, + "loss": 3.396, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387435361051074e-05, + "loss": 3.3925, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379049413540554e-05, + "loss": 3.3813, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370679844833767e-05, + "loss": 3.3877, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362293897323247e-05, + "loss": 3.3809, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353907949812723e-05, + "loss": 3.3973, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345522002302207e-05, + "loss": 3.3979, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633715243359542e-05, + "loss": 3.3788, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328766486084896e-05, + "loss": 3.3906, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320380538574376e-05, + "loss": 3.3849, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6311994591063856e-05, + "loss": 3.3941, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303625022357068e-05, + "loss": 3.3848, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295239074846548e-05, + "loss": 3.4005, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6286853127336028e-05, + "loss": 3.3869, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278467179825508e-05, + "loss": 3.393, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6270097611118717e-05, + "loss": 3.3864, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.9208455085754395, + "eval_runtime": 311.1279, + "eval_samples_per_second": 1226.476, + "eval_steps_per_second": 38.328, + "step": 2060629 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261711663608197e-05, + "loss": 3.3846, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253325716097677e-05, + "loss": 3.3866, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244939768587157e-05, + "loss": 3.3895, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.623655382107664e-05, + "loss": 3.3942, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622818425236985e-05, + "loss": 3.4004, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621979830485933e-05, + "loss": 3.3853, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621141235734881e-05, + "loss": 3.3863, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620302640983829e-05, + "loss": 3.3833, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.61946568411315e-05, + "loss": 3.3877, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618627089362098e-05, + "loss": 3.3938, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617788494611046e-05, + "loss": 3.3843, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616949899859994e-05, + "loss": 3.385, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161145808696883e-05, + "loss": 3.3941, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152759861186363e-05, + "loss": 3.3742, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144373913675843e-05, + "loss": 3.3804, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135987966165323e-05, + "loss": 3.3751, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127602018654803e-05, + "loss": 3.3752, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119216071144283e-05, + "loss": 3.3838, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110830123633763e-05, + "loss": 3.3796, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102444176123243e-05, + "loss": 3.3973, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6094074607416455e-05, + "loss": 3.3953, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085688659905935e-05, + "loss": 3.3887, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077302712395415e-05, + "loss": 3.3872, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068916764884895e-05, + "loss": 3.3873, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060547196178104e-05, + "loss": 3.3709, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052161248667584e-05, + "loss": 3.3912, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043775301157064e-05, + "loss": 3.3825, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035389353646548e-05, + "loss": 3.3726, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6027019784939757e-05, + "loss": 3.379, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018633837429237e-05, + "loss": 3.3782, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010247889918717e-05, + "loss": 3.383, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001861942408196e-05, + "loss": 3.3837, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.599349237370141e-05, + "loss": 3.3848, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598510642619089e-05, + "loss": 3.3878, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597672047868037e-05, + "loss": 3.3751, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968334531169845e-05, + "loss": 3.3902, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959964962463058e-05, + "loss": 3.3914, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951579014952538e-05, + "loss": 3.3751, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5943193067442018e-05, + "loss": 3.3766, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934807119931498e-05, + "loss": 3.378, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592643755122471e-05, + "loss": 3.3784, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591805160371419e-05, + "loss": 3.3883, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.590966565620367e-05, + "loss": 3.3851, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901279708693147e-05, + "loss": 3.389, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892910139986363e-05, + "loss": 3.3885, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884524192475843e-05, + "loss": 3.3874, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587613824496532e-05, + "loss": 3.3865, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.58677522974548e-05, + "loss": 3.3824, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585938272874801e-05, + "loss": 3.3582, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.585099678123749e-05, + "loss": 3.3926, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.584261083372697e-05, + "loss": 3.3764, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.583422488621645e-05, + "loss": 3.3909, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825855317509664e-05, + "loss": 3.3837, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817469369999144e-05, + "loss": 3.3767, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580908342248862e-05, + "loss": 3.3695, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.58006974749781e-05, + "loss": 3.3828, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792327906271316e-05, + "loss": 3.3967, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783941958760793e-05, + "loss": 3.3791, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775556011250273e-05, + "loss": 3.3974, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767186442543485e-05, + "loss": 3.3825, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758800495032965e-05, + "loss": 3.3636, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750414547522442e-05, + "loss": 3.3972, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5742028600011925e-05, + "loss": 3.3782, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733659031305138e-05, + "loss": 3.3682, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725273083794618e-05, + "loss": 3.3822, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716887136284094e-05, + "loss": 3.3826, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708501188773574e-05, + "loss": 3.3664, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700131620066787e-05, + "loss": 3.3769, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691745672556267e-05, + "loss": 3.3696, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683359725045747e-05, + "loss": 3.3725, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674973777535226e-05, + "loss": 3.3878, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.566660420882844e-05, + "loss": 3.3818, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658218261317916e-05, + "loss": 3.3798, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5649832313807395e-05, + "loss": 3.3749, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564144636629688e-05, + "loss": 3.3925, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.5633076797590088e-05, + "loss": 3.3815, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.5624690850079568e-05, + "loss": 3.3915, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5616304902569048e-05, + "loss": 3.3763, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.5607918955058528e-05, + "loss": 3.3768, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.559954938635174e-05, + "loss": 3.3849, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.559116343884122e-05, + "loss": 3.3896, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.55827774913307e-05, + "loss": 3.3803, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557439154382018e-05, + "loss": 3.3884, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556600559630966e-05, + "loss": 3.3667, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555761964879914e-05, + "loss": 3.3773, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554923370128862e-05, + "loss": 3.3788, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.55408477537781e-05, + "loss": 3.3889, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532478185071312e-05, + "loss": 3.3773, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524092237560792e-05, + "loss": 3.3755, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551570629005027e-05, + "loss": 3.3794, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550732034253975e-05, + "loss": 3.3766, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549895077383296e-05, + "loss": 3.383, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.549056482632244e-05, + "loss": 3.371, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.548217887881192e-05, + "loss": 3.3828, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.54737929313014e-05, + "loss": 3.3925, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465423362594614e-05, + "loss": 3.3869, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457037415084094e-05, + "loss": 3.3619, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.544865146757357e-05, + "loss": 3.3774, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.544026552006305e-05, + "loss": 3.3755, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431895951356266e-05, + "loss": 3.3868, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423510003845743e-05, + "loss": 3.3871, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415124056335223e-05, + "loss": 3.3797, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406738108824703e-05, + "loss": 3.3743, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398368540117915e-05, + "loss": 3.3801, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389982592607395e-05, + "loss": 3.3689, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381596645096875e-05, + "loss": 3.3807, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373210697586355e-05, + "loss": 3.3761, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364841128879567e-05, + "loss": 3.381, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356455181369044e-05, + "loss": 3.3742, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348069233858524e-05, + "loss": 3.3654, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.533969966515174e-05, + "loss": 3.3729, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331313717641216e-05, + "loss": 3.3678, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322927770130696e-05, + "loss": 3.3814, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314541822620176e-05, + "loss": 3.3733, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530617225391339e-05, + "loss": 3.383, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297786306402865e-05, + "loss": 3.3818, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.528940035889235e-05, + "loss": 3.3758, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528101441138183e-05, + "loss": 3.3816, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527264484267504e-05, + "loss": 3.3802, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264258895164518e-05, + "loss": 3.3795, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255872947654e-05, + "loss": 3.3736, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.524748700014348e-05, + "loss": 3.3684, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239117431436688e-05, + "loss": 3.3801, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523073148392617e-05, + "loss": 3.3765, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.522234553641565e-05, + "loss": 3.3813, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.521395958890513e-05, + "loss": 3.3781, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.520559002019834e-05, + "loss": 3.3761, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.519720407268782e-05, + "loss": 3.3718, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188834503981033e-05, + "loss": 3.3648, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180448556470513e-05, + "loss": 3.3861, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172062608959991e-05, + "loss": 3.3757, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163676661449471e-05, + "loss": 3.3915, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155290713938951e-05, + "loss": 3.3738, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146904766428433e-05, + "loss": 3.3824, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138518818917913e-05, + "loss": 3.3804, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130132871407393e-05, + "loss": 3.3699, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121763302700604e-05, + "loss": 3.3757, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113377355190084e-05, + "loss": 3.3727, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104991407679564e-05, + "loss": 3.3871, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096605460169044e-05, + "loss": 3.3857, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088235891462254e-05, + "loss": 3.3721, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079849943951734e-05, + "loss": 3.3733, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071463996441216e-05, + "loss": 3.3791, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063078048930696e-05, + "loss": 3.3836, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054708480223905e-05, + "loss": 3.3713, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046322532713387e-05, + "loss": 3.3916, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037936585202867e-05, + "loss": 3.3769, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029550637692343e-05, + "loss": 3.3837, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021181068985557e-05, + "loss": 3.376, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.9220192432403564, + "eval_runtime": 306.8369, + "eval_samples_per_second": 1243.628, + "eval_steps_per_second": 38.864, + "step": 2136949 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012795121475037e-05, + "loss": 3.3761, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004409173964517e-05, + "loss": 3.3725, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996023226453996e-05, + "loss": 3.3813, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987653657747208e-05, + "loss": 3.3832, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979267710236688e-05, + "loss": 3.3881, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970881762726166e-05, + "loss": 3.3759, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962495815215646e-05, + "loss": 3.3755, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954126246508859e-05, + "loss": 3.3762, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.494574029899834e-05, + "loss": 3.3771, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937354351487817e-05, + "loss": 3.3745, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928968403977297e-05, + "loss": 3.3772, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920598835270511e-05, + "loss": 3.3757, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.491222926656372e-05, + "loss": 3.3846, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903843319053202e-05, + "loss": 3.3656, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4895457371542682e-05, + "loss": 3.3679, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887071424032162e-05, + "loss": 3.3628, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.487868547652164e-05, + "loss": 3.3652, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.487029952901112e-05, + "loss": 3.3731, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.48619135815006e-05, + "loss": 3.37, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.485352763399008e-05, + "loss": 3.3875, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.484515806528329e-05, + "loss": 3.3851, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.483677211777277e-05, + "loss": 3.3775, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.482838617026225e-05, + "loss": 3.3734, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820000222751732e-05, + "loss": 3.3788, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811630654044941e-05, + "loss": 3.361, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803244706534423e-05, + "loss": 3.384, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794858759023903e-05, + "loss": 3.3696, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786472811513383e-05, + "loss": 3.3615, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778103242806594e-05, + "loss": 3.3737, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769717295296074e-05, + "loss": 3.3672, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761331347785554e-05, + "loss": 3.3731, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752945400275033e-05, + "loss": 3.3724, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744575831568244e-05, + "loss": 3.3783, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736189884057724e-05, + "loss": 3.3736, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727803936547204e-05, + "loss": 3.366, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719417989036686e-05, + "loss": 3.3776, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711048420329895e-05, + "loss": 3.3788, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702662472819375e-05, + "loss": 3.3702, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694276525308857e-05, + "loss": 3.3661, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685890577798336e-05, + "loss": 3.3689, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677521009091547e-05, + "loss": 3.3658, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669135061581027e-05, + "loss": 3.3773, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660749114070507e-05, + "loss": 3.3792, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652363166559987e-05, + "loss": 3.3801, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643993597853198e-05, + "loss": 3.3749, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635607650342678e-05, + "loss": 3.3727, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627221702832158e-05, + "loss": 3.3778, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.461883575532164e-05, + "loss": 3.3733, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610466186614849e-05, + "loss": 3.3489, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4602080239104329e-05, + "loss": 3.3798, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.459369429159381e-05, + "loss": 3.3669, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458530834408329e-05, + "loss": 3.3798, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576938775376501e-05, + "loss": 3.3711, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568552827865981e-05, + "loss": 3.3703, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4560166880355461e-05, + "loss": 3.3591, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.455178093284494e-05, + "loss": 3.3692, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543411364138152e-05, + "loss": 3.3888, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535025416627632e-05, + "loss": 3.3711, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526639469117112e-05, + "loss": 3.384, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518269900410322e-05, + "loss": 3.3722, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509883952899802e-05, + "loss": 3.3532, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501498005389282e-05, + "loss": 3.3881, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493112057878764e-05, + "loss": 3.3683, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484742489171973e-05, + "loss": 3.3612, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476356541661455e-05, + "loss": 3.3712, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467970594150935e-05, + "loss": 3.3713, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459584646640415e-05, + "loss": 3.3605, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451215077933625e-05, + "loss": 3.3642, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442829130423105e-05, + "loss": 3.3613, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434443182912585e-05, + "loss": 3.3641, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426057235402065e-05, + "loss": 3.3756, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417687666695276e-05, + "loss": 3.3715, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409301719184756e-05, + "loss": 3.372, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400915771674236e-05, + "loss": 3.3619, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392529824163714e-05, + "loss": 3.3815, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384160255456927e-05, + "loss": 3.3728, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375774307946408e-05, + "loss": 3.38, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367388360435888e-05, + "loss": 3.3661, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359002412925365e-05, + "loss": 3.368, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350632844218579e-05, + "loss": 3.3776, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342246896708059e-05, + "loss": 3.3748, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333860949197535e-05, + "loss": 3.373, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325475001687017e-05, + "loss": 3.3782, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4317089054176497e-05, + "loss": 3.3615, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308703106665977e-05, + "loss": 3.3635, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300317159155457e-05, + "loss": 3.3684, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291931211644937e-05, + "loss": 3.3795, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283561642938148e-05, + "loss": 3.365, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275175695427628e-05, + "loss": 3.3677, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.426678974791711e-05, + "loss": 3.3703, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425840380040659e-05, + "loss": 3.366, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250034231699798e-05, + "loss": 3.3707, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.424164828418928e-05, + "loss": 3.3619, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.423326233667876e-05, + "loss": 3.3721, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.422487638916824e-05, + "loss": 3.3788, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.421650682046145e-05, + "loss": 3.3812, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.420812087295093e-05, + "loss": 3.3493, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.419973492544041e-05, + "loss": 3.3696, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.419134897792989e-05, + "loss": 3.364, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4182979409223101e-05, + "loss": 3.3759, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174593461712581e-05, + "loss": 3.3774, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166207514202063e-05, + "loss": 3.3691, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157821566691543e-05, + "loss": 3.363, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149451997984752e-05, + "loss": 3.3685, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141066050474234e-05, + "loss": 3.3649, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132680102963714e-05, + "loss": 3.3682, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124310534256924e-05, + "loss": 3.3621, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115924586746404e-05, + "loss": 3.3709, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107538639235884e-05, + "loss": 3.3657, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099152691725364e-05, + "loss": 3.3553, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090783123018575e-05, + "loss": 3.3588, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082397175508055e-05, + "loss": 3.3598, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074011227997535e-05, + "loss": 3.3745, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065625280487017e-05, + "loss": 3.3632, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057255711780226e-05, + "loss": 3.3738, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048869764269706e-05, + "loss": 3.3714, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040483816759187e-05, + "loss": 3.3698, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4032097869248664e-05, + "loss": 3.3667, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023728300541878e-05, + "loss": 3.3679, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015342353031358e-05, + "loss": 3.3722, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006956405520838e-05, + "loss": 3.3614, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998570458010316e-05, + "loss": 3.3589, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990200889303529e-05, + "loss": 3.3679, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981814941793009e-05, + "loss": 3.3671, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973428994282489e-05, + "loss": 3.3717, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965043046771967e-05, + "loss": 3.3652, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.395667347806518e-05, + "loss": 3.3653, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.394828753055466e-05, + "loss": 3.3635, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.393991796184787e-05, + "loss": 3.3574, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.393153201433735e-05, + "loss": 3.3698, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923146066826832e-05, + "loss": 3.3691, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914760119316312e-05, + "loss": 3.3813, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906374171805788e-05, + "loss": 3.3618, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.389798822429527e-05, + "loss": 3.3683, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.388960227678475e-05, + "loss": 3.373, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.388121632927423e-05, + "loss": 3.3627, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.387284676056744e-05, + "loss": 3.3638, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.386446081305692e-05, + "loss": 3.3666, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.38560748655464e-05, + "loss": 3.3734, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.384768891803588e-05, + "loss": 3.3754, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839319349329091e-05, + "loss": 3.3654, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830933401818571e-05, + "loss": 3.3613, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822547454308051e-05, + "loss": 3.3688, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814161506797533e-05, + "loss": 3.3734, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805791938090742e-05, + "loss": 3.3589, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797405990580222e-05, + "loss": 3.3836, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789020043069704e-05, + "loss": 3.3648, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780634095559184e-05, + "loss": 3.3714, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772264526852394e-05, + "loss": 3.3652, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.924711227416992, + "eval_runtime": 306.2336, + "eval_samples_per_second": 1246.078, + "eval_steps_per_second": 38.941, + "step": 2213269 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763878579341874e-05, + "loss": 3.383, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755492631831354e-05, + "loss": 3.3633, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747106684320834e-05, + "loss": 3.3691, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738720736810314e-05, + "loss": 3.3741, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730351168103525e-05, + "loss": 3.374, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721965220593005e-05, + "loss": 3.3682, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713579273082487e-05, + "loss": 3.3651, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705193325571967e-05, + "loss": 3.3622, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696823756865176e-05, + "loss": 3.3668, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688437809354657e-05, + "loss": 3.3697, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3680051861844137e-05, + "loss": 3.3678, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671665914333614e-05, + "loss": 3.3681, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663312724430557e-05, + "loss": 3.3739, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654926776920037e-05, + "loss": 3.3548, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646540829409519e-05, + "loss": 3.3609, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638154881898999e-05, + "loss": 3.3537, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629768934388479e-05, + "loss": 3.3506, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621382986877959e-05, + "loss": 3.3663, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.361299703936744e-05, + "loss": 3.3586, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604611091856917e-05, + "loss": 3.3737, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359624152315013e-05, + "loss": 3.3792, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587855575639611e-05, + "loss": 3.3667, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579469628129088e-05, + "loss": 3.3651, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571083680618567e-05, + "loss": 3.3678, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562714111911782e-05, + "loss": 3.348, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554328164401262e-05, + "loss": 3.3734, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.354594221689074e-05, + "loss": 3.3564, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.353755626938022e-05, + "loss": 3.3553, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529186700673432e-05, + "loss": 3.3601, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520800753162912e-05, + "loss": 3.3528, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.351241480565239e-05, + "loss": 3.3623, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.350402885814187e-05, + "loss": 3.3613, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495659289435083e-05, + "loss": 3.3713, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487273341924561e-05, + "loss": 3.3636, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478887394414041e-05, + "loss": 3.3589, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470501446903521e-05, + "loss": 3.3609, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462131878196735e-05, + "loss": 3.3719, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453745930686212e-05, + "loss": 3.36, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445359983175692e-05, + "loss": 3.3582, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436974035665173e-05, + "loss": 3.3565, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428604466958386e-05, + "loss": 3.3628, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420234898251597e-05, + "loss": 3.3601, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411848950741077e-05, + "loss": 3.3698, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403463003230557e-05, + "loss": 3.37, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395077055720035e-05, + "loss": 3.3645, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386691108209515e-05, + "loss": 3.3651, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378305160698995e-05, + "loss": 3.3626, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369919213188475e-05, + "loss": 3.3678, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361533265677956e-05, + "loss": 3.3412, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353163696971166e-05, + "loss": 3.372, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344777749460646e-05, + "loss": 3.3597, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336391801950127e-05, + "loss": 3.3672, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328005854439607e-05, + "loss": 3.3606, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319636285732818e-05, + "loss": 3.3604, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3311250338222298e-05, + "loss": 3.3516, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302864390711778e-05, + "loss": 3.3561, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294478443201258e-05, + "loss": 3.3779, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3286108874494469e-05, + "loss": 3.356, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277722926983949e-05, + "loss": 3.3758, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269336979473428e-05, + "loss": 3.3608, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.326095103196291e-05, + "loss": 3.348, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325258146325612e-05, + "loss": 3.3758, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.32441955157456e-05, + "loss": 3.3601, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.323580956823508e-05, + "loss": 3.3477, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.322742362072456e-05, + "loss": 3.3555, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219054052017772e-05, + "loss": 3.365, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210668104507252e-05, + "loss": 3.3469, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202282156996731e-05, + "loss": 3.3557, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193896209486211e-05, + "loss": 3.3555, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185526640779422e-05, + "loss": 3.3493, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177140693268902e-05, + "loss": 3.3686, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168754745758382e-05, + "loss": 3.3643, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160368798247864e-05, + "loss": 3.3591, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151999229541073e-05, + "loss": 3.3519, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143613282030553e-05, + "loss": 3.3692, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135227334520034e-05, + "loss": 3.3617, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126857765813244e-05, + "loss": 3.372, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118471818302725e-05, + "loss": 3.3561, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110085870792205e-05, + "loss": 3.3584, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101716302085414e-05, + "loss": 3.3676, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093330354574896e-05, + "loss": 3.3619, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084944407064376e-05, + "loss": 3.3609, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076558459553856e-05, + "loss": 3.3665, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068172512043336e-05, + "loss": 3.3536, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059786564532814e-05, + "loss": 3.3529, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051400617022294e-05, + "loss": 3.3624, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3043014669511774e-05, + "loss": 3.3663, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034645100804985e-05, + "loss": 3.3606, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026259153294465e-05, + "loss": 3.3563, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017873205783945e-05, + "loss": 3.359, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009487258273426e-05, + "loss": 3.3605, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001117689566635e-05, + "loss": 3.3593, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992731742056115e-05, + "loss": 3.3592, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984345794545597e-05, + "loss": 3.3592, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975959847035077e-05, + "loss": 3.3678, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967590278328288e-05, + "loss": 3.3702, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2959204330817768e-05, + "loss": 3.343, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950818383307248e-05, + "loss": 3.3567, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942432435796728e-05, + "loss": 3.354, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2934062867089938e-05, + "loss": 3.3679, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925676919579418e-05, + "loss": 3.3633, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917290972068898e-05, + "loss": 3.3635, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.290890502455838e-05, + "loss": 3.3501, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900535455851589e-05, + "loss": 3.3645, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892149508341069e-05, + "loss": 3.3538, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.288376356083055e-05, + "loss": 3.3555, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.287539399212376e-05, + "loss": 3.3529, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867008044613241e-05, + "loss": 3.3602, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858622097102721e-05, + "loss": 3.3591, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850236149592201e-05, + "loss": 3.3438, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841866580885412e-05, + "loss": 3.3542, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833480633374892e-05, + "loss": 3.344, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825094685864372e-05, + "loss": 3.3623, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816708738353852e-05, + "loss": 3.3536, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808339169647063e-05, + "loss": 3.3591, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799953222136543e-05, + "loss": 3.3616, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791567274626023e-05, + "loss": 3.3621, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783181327115504e-05, + "loss": 3.3535, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774811758408713e-05, + "loss": 3.3581, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766425810898195e-05, + "loss": 3.3644, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758039863387675e-05, + "loss": 3.3511, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749653915877155e-05, + "loss": 3.3457, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741284347170366e-05, + "loss": 3.3597, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732898399659846e-05, + "loss": 3.3577, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724512452149326e-05, + "loss": 3.3599, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716126504638806e-05, + "loss": 3.3539, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707756935932016e-05, + "loss": 3.3581, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699370988421496e-05, + "loss": 3.357, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2691001419714707e-05, + "loss": 3.3482, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682615472204187e-05, + "loss": 3.3531, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674229524693667e-05, + "loss": 3.3635, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665843577183149e-05, + "loss": 3.3741, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657457629672629e-05, + "loss": 3.3543, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649071682162109e-05, + "loss": 3.353, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640685734651587e-05, + "loss": 3.366, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632299787141067e-05, + "loss": 3.355, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.262393021843428e-05, + "loss": 3.352, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.261554427092376e-05, + "loss": 3.3542, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607158323413238e-05, + "loss": 3.3659, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2598772375902718e-05, + "loss": 3.3676, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.259040280719593e-05, + "loss": 3.3567, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582016859685412e-05, + "loss": 3.3511, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573630912174888e-05, + "loss": 3.3583, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565244964664368e-05, + "loss": 3.3615, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556875395957582e-05, + "loss": 3.3495, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548489448447059e-05, + "loss": 3.3747, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540103500936539e-05, + "loss": 3.356, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.253171755342602e-05, + "loss": 3.3625, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523347984719233e-05, + "loss": 3.3569, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.926017999649048, + "eval_runtime": 321.6719, + "eval_samples_per_second": 1186.274, + "eval_steps_per_second": 37.072, + "step": 2289589 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514962037208711e-05, + "loss": 3.3596, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506576089698191e-05, + "loss": 3.3511, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498190142187671e-05, + "loss": 3.3569, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489820573480884e-05, + "loss": 3.3661, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481434625970364e-05, + "loss": 3.3609, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2473048678459842e-05, + "loss": 3.3616, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464662730949322e-05, + "loss": 3.3565, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456293162242534e-05, + "loss": 3.3524, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447907214732014e-05, + "loss": 3.3549, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439521267221493e-05, + "loss": 3.3632, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431135319710974e-05, + "loss": 3.3556, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422765751004185e-05, + "loss": 3.361, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414396182297398e-05, + "loss": 3.3631, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2406010234786876e-05, + "loss": 3.3424, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397624287276356e-05, + "loss": 3.3529, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389238339765836e-05, + "loss": 3.3385, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380852392255316e-05, + "loss": 3.3417, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372466444744796e-05, + "loss": 3.356, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364080497234276e-05, + "loss": 3.3459, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355694549723756e-05, + "loss": 3.3662, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347324981016966e-05, + "loss": 3.3688, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338939033506446e-05, + "loss": 3.3538, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330553085995928e-05, + "loss": 3.3568, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2322167138485406e-05, + "loss": 3.3597, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313797569778619e-05, + "loss": 3.3393, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305411622268099e-05, + "loss": 3.3629, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297025674757579e-05, + "loss": 3.3473, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288639727247057e-05, + "loss": 3.3473, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.228027015854027e-05, + "loss": 3.3495, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.227188421102975e-05, + "loss": 3.3422, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263498263519228e-05, + "loss": 3.3504, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.225511231600871e-05, + "loss": 3.3568, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.224674274730192e-05, + "loss": 3.3597, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.22383567997914e-05, + "loss": 3.3508, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.222997085228088e-05, + "loss": 3.3483, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.222158490477036e-05, + "loss": 3.3505, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213215336063572e-05, + "loss": 3.3658, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204829388553052e-05, + "loss": 3.3487, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.219644344104253e-05, + "loss": 3.3489, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.218805749353201e-05, + "loss": 3.3479, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179687924825223e-05, + "loss": 3.3486, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171318356118434e-05, + "loss": 3.3516, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162932408607914e-05, + "loss": 3.3599, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154546461097394e-05, + "loss": 3.3592, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146160513586874e-05, + "loss": 3.3544, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137774566076354e-05, + "loss": 3.3552, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129388618565834e-05, + "loss": 3.3518, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121002671055314e-05, + "loss": 3.3589, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112616723544792e-05, + "loss": 3.3303, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104247154838004e-05, + "loss": 3.3588, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095861207327484e-05, + "loss": 3.354, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087475259816964e-05, + "loss": 3.3588, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079089312306444e-05, + "loss": 3.3474, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070719743599655e-05, + "loss": 3.3472, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062333796089135e-05, + "loss": 3.3461, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053947848578617e-05, + "loss": 3.3453, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045578279871826e-05, + "loss": 3.3645, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037192332361307e-05, + "loss": 3.3511, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028822763654518e-05, + "loss": 3.3648, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020436816143998e-05, + "loss": 3.3501, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012050868633478e-05, + "loss": 3.3379, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003664921122958e-05, + "loss": 3.3708, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995278973612438e-05, + "loss": 3.3457, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986893026101916e-05, + "loss": 3.3409, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978507078591398e-05, + "loss": 3.3475, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970137509884609e-05, + "loss": 3.3524, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961751562374089e-05, + "loss": 3.3389, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953365614863568e-05, + "loss": 3.346, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944979667353048e-05, + "loss": 3.3433, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.193661009864626e-05, + "loss": 3.34, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.192822415113574e-05, + "loss": 3.3572, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919838203625219e-05, + "loss": 3.355, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911452256114699e-05, + "loss": 3.3466, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903082687407912e-05, + "loss": 3.3439, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.189469673989739e-05, + "loss": 3.3609, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.188631079238687e-05, + "loss": 3.3507, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1877924844876351e-05, + "loss": 3.3602, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869555276169562e-05, + "loss": 3.3488, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861169328659042e-05, + "loss": 3.3496, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852799759952253e-05, + "loss": 3.3536, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844413812441733e-05, + "loss": 3.3535, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836027864931213e-05, + "loss": 3.3529, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827641917420693e-05, + "loss": 3.3579, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819255969910173e-05, + "loss": 3.3479, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810870022399653e-05, + "loss": 3.3378, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802484074889133e-05, + "loss": 3.3484, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794098127378613e-05, + "loss": 3.3584, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785728558671823e-05, + "loss": 3.3462, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777342611161303e-05, + "loss": 3.346, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768956663650783e-05, + "loss": 3.3472, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760570716140263e-05, + "loss": 3.3469, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752201147433476e-05, + "loss": 3.3491, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743815199922954e-05, + "loss": 3.3481, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735429252412434e-05, + "loss": 3.3533, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727043304901916e-05, + "loss": 3.3518, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718673736195125e-05, + "loss": 3.3661, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710287788684605e-05, + "loss": 3.3295, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701901841174086e-05, + "loss": 3.3486, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693515893663566e-05, + "loss": 3.3445, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685146324956777e-05, + "loss": 3.3573, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676760377446257e-05, + "loss": 3.3553, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668374429935737e-05, + "loss": 3.3492, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1659988482425215e-05, + "loss": 3.3418, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651618913718428e-05, + "loss": 3.3522, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643232966207908e-05, + "loss": 3.3477, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634847018697388e-05, + "loss": 3.3445, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626477449990598e-05, + "loss": 3.3399, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1618091502480078e-05, + "loss": 3.3476, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609705554969558e-05, + "loss": 3.3504, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.160131960745904e-05, + "loss": 3.3375, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592950038752249e-05, + "loss": 3.3455, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.158456409124173e-05, + "loss": 3.3317, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.157617814373121e-05, + "loss": 3.357, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567792196220689e-05, + "loss": 3.3404, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559422627513902e-05, + "loss": 3.349, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551036680003381e-05, + "loss": 3.3513, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542650732492861e-05, + "loss": 3.3562, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.153426478498234e-05, + "loss": 3.3399, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525895216275552e-05, + "loss": 3.3515, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517509268765032e-05, + "loss": 3.3553, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509123321254512e-05, + "loss": 3.3386, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500737373743992e-05, + "loss": 3.3344, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492367805037203e-05, + "loss": 3.3497, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483981857526683e-05, + "loss": 3.3513, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475595910016163e-05, + "loss": 3.3509, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467209962505643e-05, + "loss": 3.3468, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458840393798855e-05, + "loss": 3.3479, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450454446288335e-05, + "loss": 3.3469, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1442084877581546e-05, + "loss": 3.3358, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433698930071026e-05, + "loss": 3.3414, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425312982560506e-05, + "loss": 3.3579, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416927035049986e-05, + "loss": 3.3621, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408541087539466e-05, + "loss": 3.3442, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400155140028946e-05, + "loss": 3.3425, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391769192518426e-05, + "loss": 3.3535, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383383245007904e-05, + "loss": 3.3447, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1375013676301116e-05, + "loss": 3.3457, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366627728790596e-05, + "loss": 3.3454, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358241781280076e-05, + "loss": 3.3593, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349855833769556e-05, + "loss": 3.3526, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341486265062767e-05, + "loss": 3.348, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333100317552247e-05, + "loss": 3.3388, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324714370041727e-05, + "loss": 3.3494, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316328422531207e-05, + "loss": 3.35, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1307958853824418e-05, + "loss": 3.3371, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.12995729063139e-05, + "loss": 3.3648, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291186958803378e-05, + "loss": 3.3481, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1282801011292858e-05, + "loss": 3.3528, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.127443144258607e-05, + "loss": 3.3449, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.9271461963653564, + "eval_runtime": 310.4445, + "eval_samples_per_second": 1229.176, + "eval_steps_per_second": 38.413, + "step": 2365909 + }, + { + "epoch": 0.0, + "learning_rate": 1.126604549507555e-05, + "loss": 3.3642, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257659547565028e-05, + "loss": 3.3405, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.124927360005451e-05, + "loss": 3.3494, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.124088765254399e-05, + "loss": 3.3544, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.12325180838372e-05, + "loss": 3.3532, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.122413213632668e-05, + "loss": 3.3497, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.121574618881616e-05, + "loss": 3.3463, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.120736024130564e-05, + "loss": 3.3453, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198990672598851e-05, + "loss": 3.3454, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190604725088331e-05, + "loss": 3.3511, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182218777577811e-05, + "loss": 3.3463, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173832830067291e-05, + "loss": 3.3486, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165479640164233e-05, + "loss": 3.3575, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157093692653714e-05, + "loss": 3.3349, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148707745143194e-05, + "loss": 3.3432, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140321797632673e-05, + "loss": 3.3266, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131935850122154e-05, + "loss": 3.3363, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123549902611634e-05, + "loss": 3.3442, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115163955101113e-05, + "loss": 3.339, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106778007590593e-05, + "loss": 3.3496, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098408438883805e-05, + "loss": 3.3589, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1090022491373285e-05, + "loss": 3.3463, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081636543862763e-05, + "loss": 3.3457, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073250596352245e-05, + "loss": 3.348, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064881027645456e-05, + "loss": 3.3378, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056495080134936e-05, + "loss": 3.3506, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048109132624416e-05, + "loss": 3.3343, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039723185113896e-05, + "loss": 3.3439, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031353616407106e-05, + "loss": 3.3398, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022967668896586e-05, + "loss": 3.3351, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014581721386066e-05, + "loss": 3.3431, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006195773875546e-05, + "loss": 3.34, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0997826205168759e-05, + "loss": 3.3516, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989440257658237e-05, + "loss": 3.3458, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981054310147717e-05, + "loss": 3.3354, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972668362637199e-05, + "loss": 3.3394, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.096429879393041e-05, + "loss": 3.3593, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.095591284641989e-05, + "loss": 3.3358, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.094752689890937e-05, + "loss": 3.3408, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.093914095139885e-05, + "loss": 3.3384, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.093077138269206e-05, + "loss": 3.3353, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.092238543518154e-05, + "loss": 3.3398, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.091399948767102e-05, + "loss": 3.3555, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.09056135401605e-05, + "loss": 3.3509, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.089724397145371e-05, + "loss": 3.3458, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.088885802394319e-05, + "loss": 3.3464, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.088047207643267e-05, + "loss": 3.3386, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.087208612892215e-05, + "loss": 3.3524, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863716560215361e-05, + "loss": 3.323, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855330612704841e-05, + "loss": 3.3456, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846944665194323e-05, + "loss": 3.3427, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838558717683801e-05, + "loss": 3.3494, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830189148977014e-05, + "loss": 3.3408, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0821803201466494e-05, + "loss": 3.3307, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813417253955974e-05, + "loss": 3.3424, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805031306445452e-05, + "loss": 3.3295, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796661737738664e-05, + "loss": 3.3581, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788275790228144e-05, + "loss": 3.3376, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779889842717624e-05, + "loss": 3.3585, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771503895207104e-05, + "loss": 3.3385, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763134326500315e-05, + "loss": 3.3311, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754748378989795e-05, + "loss": 3.3536, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746362431479275e-05, + "loss": 3.3342, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737976483968755e-05, + "loss": 3.3353, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729606915261967e-05, + "loss": 3.331, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721220967751447e-05, + "loss": 3.3477, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712835020240926e-05, + "loss": 3.3297, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704465451534138e-05, + "loss": 3.3367, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0696079504023618e-05, + "loss": 3.3333, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687693556513096e-05, + "loss": 3.3305, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0679307609002578e-05, + "loss": 3.3494, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670938040295789e-05, + "loss": 3.3444, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0662552092785269e-05, + "loss": 3.3362, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654166145274749e-05, + "loss": 3.3381, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645780197764229e-05, + "loss": 3.3508, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.063741062905744e-05, + "loss": 3.3399, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629024681546921e-05, + "loss": 3.3467, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.06206387340364e-05, + "loss": 3.3421, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061225278652588e-05, + "loss": 3.3394, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0603883217819092e-05, + "loss": 3.3442, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.059549727030857e-05, + "loss": 3.344, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.058711132279805e-05, + "loss": 3.3425, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.057872537528753e-05, + "loss": 3.3507, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570339427777012e-05, + "loss": 3.3434, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.056195348026649e-05, + "loss": 3.3243, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.055356753275597e-05, + "loss": 3.3413, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.054518158524545e-05, + "loss": 3.3476, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.053681201653866e-05, + "loss": 3.3397, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.052842606902814e-05, + "loss": 3.3372, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520040121517622e-05, + "loss": 3.3384, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511654174007102e-05, + "loss": 3.3384, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503284605300313e-05, + "loss": 3.3366, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494898657789793e-05, + "loss": 3.3408, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486512710279273e-05, + "loss": 3.3403, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478126762768751e-05, + "loss": 3.3413, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469757194061963e-05, + "loss": 3.3573, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461371246551443e-05, + "loss": 3.3244, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452985299040923e-05, + "loss": 3.3368, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444599351530403e-05, + "loss": 3.3372, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436229782823614e-05, + "loss": 3.343, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427843835313094e-05, + "loss": 3.345, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419457887802574e-05, + "loss": 3.3429, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411071940292054e-05, + "loss": 3.3281, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402702371585265e-05, + "loss": 3.3403, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394316424074746e-05, + "loss": 3.3421, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0385930476564225e-05, + "loss": 3.3331, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377544529053705e-05, + "loss": 3.3303, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369174960346917e-05, + "loss": 3.3409, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360789012836397e-05, + "loss": 3.3432, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352403065325875e-05, + "loss": 3.3216, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0344033496619088e-05, + "loss": 3.3363, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0335647549108568e-05, + "loss": 3.3218, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327261601598048e-05, + "loss": 3.3439, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0318875654087528e-05, + "loss": 3.3367, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310489706577008e-05, + "loss": 3.3387, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302103759066488e-05, + "loss": 3.3412, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293717811555968e-05, + "loss": 3.3453, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285348242849178e-05, + "loss": 3.3331, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0276962295338658e-05, + "loss": 3.3423, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0268576347828138e-05, + "loss": 3.3457, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260190400317618e-05, + "loss": 3.3292, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0251804452807098e-05, + "loss": 3.3281, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243418505296578e-05, + "loss": 3.3388, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235032557786058e-05, + "loss": 3.3408, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0226646610275538e-05, + "loss": 3.3432, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218277041568749e-05, + "loss": 3.3309, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209891094058229e-05, + "loss": 3.3389, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201505146547709e-05, + "loss": 3.339, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0193135577840921e-05, + "loss": 3.3285, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184749630330401e-05, + "loss": 3.3284, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.017636368281988e-05, + "loss": 3.3462, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.016797773530936e-05, + "loss": 3.3506, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159591787798841e-05, + "loss": 3.3356, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.015120584028832e-05, + "loss": 3.3346, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.01428198927778e-05, + "loss": 3.3411, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.013443394526728e-05, + "loss": 3.3364, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126064376560492e-05, + "loss": 3.3343, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.011767842904997e-05, + "loss": 3.3367, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.010929248153945e-05, + "loss": 3.3488, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100906534028932e-05, + "loss": 3.3415, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092536965322142e-05, + "loss": 3.3379, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084151017811622e-05, + "loss": 3.3314, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075765070301102e-05, + "loss": 3.3386, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067379122790582e-05, + "loss": 3.3377, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059009554083793e-05, + "loss": 3.3278, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050623606573273e-05, + "loss": 3.3568, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042237659062753e-05, + "loss": 3.3401, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033851711552233e-05, + "loss": 3.3424, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025482142845444e-05, + "loss": 3.3353, + "step": 2441728 + }, + { + "epoch": 0.03, + "eval_loss": 3.928295373916626, + "eval_runtime": 309.6067, + "eval_samples_per_second": 1232.502, + "eval_steps_per_second": 38.517, + "step": 2442229 + }, + { + "epoch": 1.0, + "learning_rate": 1.0017096195334924e-05, + "loss": 3.3366, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008710247824404e-05, + "loss": 3.3339, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000324300313884e-05, + "loss": 3.3398, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.991954731607094e-06, + "loss": 3.3458, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.983568784096576e-06, + "loss": 3.3434, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975182836586056e-06, + "loss": 3.3433, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966796889075534e-06, + "loss": 3.3337, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958427320368747e-06, + "loss": 3.3359, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950041372858227e-06, + "loss": 3.3316, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.941655425347707e-06, + "loss": 3.3435, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933269477837185e-06, + "loss": 3.3371, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.924899909130397e-06, + "loss": 3.342, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91653034042361e-06, + "loss": 3.3457, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.90814439291309e-06, + "loss": 3.3252, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.899758445402568e-06, + "loss": 3.3289, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891372497892048e-06, + "loss": 3.3206, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.88298655038153e-06, + "loss": 3.3249, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.874600602871008e-06, + "loss": 3.3373, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866214655360488e-06, + "loss": 3.3318, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857828707849968e-06, + "loss": 3.3355, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.84945913914318e-06, + "loss": 3.3513, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.841073191632659e-06, + "loss": 3.3373, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832687244122139e-06, + "loss": 3.3378, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.82430129661162e-06, + "loss": 3.3336, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.81593172790483e-06, + "loss": 3.3327, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.807545780394311e-06, + "loss": 3.3381, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799159832883791e-06, + "loss": 3.3229, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.79077388537327e-06, + "loss": 3.3316, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782404316666482e-06, + "loss": 3.3308, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774018369155962e-06, + "loss": 3.3237, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.765632421645442e-06, + "loss": 3.3364, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.75724647413492e-06, + "loss": 3.3308, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748876905428132e-06, + "loss": 3.3368, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740490957917612e-06, + "loss": 3.3364, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732105010407092e-06, + "loss": 3.3297, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723719062896572e-06, + "loss": 3.3304, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715349494189783e-06, + "loss": 3.3455, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.706963546679265e-06, + "loss": 3.3269, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698577599168743e-06, + "loss": 3.3298, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690191651658223e-06, + "loss": 3.3317, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681822082951435e-06, + "loss": 3.3246, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673436135440915e-06, + "loss": 3.33, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.665050187930394e-06, + "loss": 3.3505, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656664240419873e-06, + "loss": 3.3383, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648294671713086e-06, + "loss": 3.332, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.639908724202566e-06, + "loss": 3.3439, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631522776692046e-06, + "loss": 3.3292, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623136829181526e-06, + "loss": 3.3379, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614767260474737e-06, + "loss": 3.3136, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606381312964217e-06, + "loss": 3.3313, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.597995365453697e-06, + "loss": 3.341, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.589609417943176e-06, + "loss": 3.3345, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581239849236389e-06, + "loss": 3.3338, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572853901725867e-06, + "loss": 3.3204, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564467954215347e-06, + "loss": 3.3335, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.556082006704827e-06, + "loss": 3.3183, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.54771243799804e-06, + "loss": 3.3511, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539326490487518e-06, + "loss": 3.3286, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.530940542977e-06, + "loss": 3.3451, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.52255459546648e-06, + "loss": 3.3277, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514185026759689e-06, + "loss": 3.3276, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.50579907924917e-06, + "loss": 3.3371, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.49741313173865e-06, + "loss": 3.3266, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.48902718422813e-06, + "loss": 3.3267, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.480657615521341e-06, + "loss": 3.3244, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472271668010821e-06, + "loss": 3.3347, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.463885720500301e-06, + "loss": 3.3204, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.45549977298978e-06, + "loss": 3.328, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447130204282992e-06, + "loss": 3.3207, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438744256772472e-06, + "loss": 3.3227, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430358309261953e-06, + "loss": 3.3365, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.421988740555162e-06, + "loss": 3.341, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413602793044642e-06, + "loss": 3.3267, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405216845534124e-06, + "loss": 3.3298, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.396830898023604e-06, + "loss": 3.3351, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388461329316815e-06, + "loss": 3.3323, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380075381806295e-06, + "loss": 3.3319, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371689434295775e-06, + "loss": 3.337, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363303486785253e-06, + "loss": 3.3305, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.354933918078465e-06, + "loss": 3.3334, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346547970567945e-06, + "loss": 3.3343, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338162023057425e-06, + "loss": 3.3369, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329776075546905e-06, + "loss": 3.3402, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321390128036385e-06, + "loss": 3.328, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.313004180525865e-06, + "loss": 3.3162, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.304618233015343e-06, + "loss": 3.3335, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296232285504825e-06, + "loss": 3.3328, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287862716798036e-06, + "loss": 3.331, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279476769287516e-06, + "loss": 3.33, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271090821776996e-06, + "loss": 3.3239, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262704874266476e-06, + "loss": 3.3345, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254335305559688e-06, + "loss": 3.3267, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.245949358049168e-06, + "loss": 3.3298, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.237563410538646e-06, + "loss": 3.3323, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.229177463028126e-06, + "loss": 3.3298, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220807894321339e-06, + "loss": 3.3455, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212421946810817e-06, + "loss": 3.3196, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204035999300297e-06, + "loss": 3.3212, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.195650051789779e-06, + "loss": 3.3322, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.18728048308299e-06, + "loss": 3.3322, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.17889453557247e-06, + "loss": 3.3373, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.17050858806195e-06, + "loss": 3.3335, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.16212264055143e-06, + "loss": 3.3178, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.15375307184464e-06, + "loss": 3.3297, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.14536712433412e-06, + "loss": 3.3338, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.1369811768236e-06, + "loss": 3.3205, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.12859522931308e-06, + "loss": 3.3206, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.12022566060629e-06, + "loss": 3.3334, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.11183971309577e-06, + "loss": 3.3342, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.10345376558525e-06, + "loss": 3.3147, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.09506781807473e-06, + "loss": 3.3206, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.086698249367941e-06, + "loss": 3.3169, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078312301857423e-06, + "loss": 3.3349, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.069926354346903e-06, + "loss": 3.3247, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061556785640112e-06, + "loss": 3.3271, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053170838129594e-06, + "loss": 3.3304, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044784890619074e-06, + "loss": 3.3385, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036398943108554e-06, + "loss": 3.3199, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028029374401764e-06, + "loss": 3.3338, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.019643426891244e-06, + "loss": 3.3339, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011257479380724e-06, + "loss": 3.327, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002871531870204e-06, + "loss": 3.3125, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994501963163415e-06, + "loss": 3.3277, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986116015652895e-06, + "loss": 3.3294, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977730068142377e-06, + "loss": 3.3365, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969344120631855e-06, + "loss": 3.3227, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.960974551925066e-06, + "loss": 3.33, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.952588604414547e-06, + "loss": 3.3262, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.944219035707758e-06, + "loss": 3.319, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.935833088197238e-06, + "loss": 3.3169, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927447140686718e-06, + "loss": 3.3384, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.919061193176198e-06, + "loss": 3.3415, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.910675245665676e-06, + "loss": 3.3331, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902289298155158e-06, + "loss": 3.319, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.893903350644638e-06, + "loss": 3.3342, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885517403134118e-06, + "loss": 3.3267, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877147834427329e-06, + "loss": 3.3287, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868761886916809e-06, + "loss": 3.3287, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860375939406289e-06, + "loss": 3.3371, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.851989991895767e-06, + "loss": 3.3291, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.84362042318898e-06, + "loss": 3.3329, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.83523447567846e-06, + "loss": 3.3241, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.82684852816794e-06, + "loss": 3.3287, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.81846258065742e-06, + "loss": 3.3307, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.81009301195063e-06, + "loss": 3.3202, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801707064440112e-06, + "loss": 3.349, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793321116929592e-06, + "loss": 3.33, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.78493516941907e-06, + "loss": 3.3313, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776565600712282e-06, + "loss": 3.3283, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768179653201762e-06, + "loss": 3.3245, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.9299750328063965, + "eval_runtime": 306.896, + "eval_samples_per_second": 1243.389, + "eval_steps_per_second": 38.857, + "step": 2518549 + }, + { + "epoch": 0.0, + "learning_rate": 8.75979370569124e-06, + "loss": 3.323, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.75140775818072e-06, + "loss": 3.3332, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743021810670202e-06, + "loss": 3.3357, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.734652241963413e-06, + "loss": 3.3291, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726266294452893e-06, + "loss": 3.3355, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.717880346942373e-06, + "loss": 3.3213, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.709494399431853e-06, + "loss": 3.3266, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701124830725064e-06, + "loss": 3.3226, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.692738883214544e-06, + "loss": 3.3376, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684352935704024e-06, + "loss": 3.323, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.675966988193504e-06, + "loss": 3.3338, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.667597419486714e-06, + "loss": 3.3303, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659227850779927e-06, + "loss": 3.323, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.650841903269407e-06, + "loss": 3.3199, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.642455955758887e-06, + "loss": 3.3105, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634070008248365e-06, + "loss": 3.3202, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.625684060737847e-06, + "loss": 3.3223, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.617298113227327e-06, + "loss": 3.3224, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.608912165716805e-06, + "loss": 3.3272, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.600542597010017e-06, + "loss": 3.3443, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.592156649499497e-06, + "loss": 3.326, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.583770701988977e-06, + "loss": 3.3266, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.575384754478456e-06, + "loss": 3.3284, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.567015185771668e-06, + "loss": 3.3232, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.558629238261148e-06, + "loss": 3.327, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.550243290750628e-06, + "loss": 3.314, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.541857343240108e-06, + "loss": 3.3236, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.533487774533319e-06, + "loss": 3.3234, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.5251018270228e-06, + "loss": 3.31, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.516715879512279e-06, + "loss": 3.3247, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.508329932001759e-06, + "loss": 3.319, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.499960363294971e-06, + "loss": 3.3284, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.491574415784451e-06, + "loss": 3.3257, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.48318846827393e-06, + "loss": 3.3185, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.47480252076341e-06, + "loss": 3.3257, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.466432952056622e-06, + "loss": 3.3365, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.4580470045461e-06, + "loss": 3.3121, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.449661057035582e-06, + "loss": 3.3239, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441275109525062e-06, + "loss": 3.3187, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.432905540818272e-06, + "loss": 3.3166, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.424519593307752e-06, + "loss": 3.3192, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416133645797232e-06, + "loss": 3.338, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.407747698286712e-06, + "loss": 3.33, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399378129579925e-06, + "loss": 3.3214, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.390992182069403e-06, + "loss": 3.3343, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.382606234558883e-06, + "loss": 3.3229, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374220287048363e-06, + "loss": 3.3277, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.365850718341574e-06, + "loss": 3.307, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.357464770831054e-06, + "loss": 3.3201, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349078823320535e-06, + "loss": 3.3286, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.340692875810015e-06, + "loss": 3.3261, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332323307103224e-06, + "loss": 3.323, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.323937359592706e-06, + "loss": 3.3125, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.315551412082186e-06, + "loss": 3.3245, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307165464571664e-06, + "loss": 3.3102, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.298795895864877e-06, + "loss": 3.3392, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.290409948354357e-06, + "loss": 3.3219, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282024000843837e-06, + "loss": 3.3378, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.273638053333317e-06, + "loss": 3.3174, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.265268484626527e-06, + "loss": 3.3203, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.256882537116007e-06, + "loss": 3.3237, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.248496589605487e-06, + "loss": 3.3277, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240110642094967e-06, + "loss": 3.3175, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.231741073388178e-06, + "loss": 3.3118, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.22335512587766e-06, + "loss": 3.3273, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.214969178367138e-06, + "loss": 3.3135, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.206583230856618e-06, + "loss": 3.3107, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.19821366214983e-06, + "loss": 3.3164, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.18982771463931e-06, + "loss": 3.3128, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.181441767128789e-06, + "loss": 3.3299, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.173072198422001e-06, + "loss": 3.3294, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.164686250911481e-06, + "loss": 3.3168, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.156300303400961e-06, + "loss": 3.3179, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.147914355890441e-06, + "loss": 3.3252, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.139544787183652e-06, + "loss": 3.3222, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131158839673132e-06, + "loss": 3.3247, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.122772892162612e-06, + "loss": 3.3287, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114386944652092e-06, + "loss": 3.3215, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106017375945302e-06, + "loss": 3.3261, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.097631428434784e-06, + "loss": 3.3206, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089245480924262e-06, + "loss": 3.3285, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.080859533413742e-06, + "loss": 3.3274, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.072473585903224e-06, + "loss": 3.3191, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064087638392702e-06, + "loss": 3.3056, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.055701690882182e-06, + "loss": 3.3249, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.047315743371662e-06, + "loss": 3.324, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.038946174664875e-06, + "loss": 3.3237, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.030560227154353e-06, + "loss": 3.322, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022174279643833e-06, + "loss": 3.3147, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.013788332133314e-06, + "loss": 3.3238, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.005418763426525e-06, + "loss": 3.3158, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.997032815916005e-06, + "loss": 3.3252, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.988646868405485e-06, + "loss": 3.3149, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980260920894965e-06, + "loss": 3.322, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.971891352188176e-06, + "loss": 3.332, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.963505404677656e-06, + "loss": 3.3198, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955119457167136e-06, + "loss": 3.3067, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.946733509656616e-06, + "loss": 3.3235, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.938363940949826e-06, + "loss": 3.3251, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.929977993439306e-06, + "loss": 3.3262, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.921592045928786e-06, + "loss": 3.323, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913206098418266e-06, + "loss": 3.3141, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.904836529711477e-06, + "loss": 3.3179, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.896450582200959e-06, + "loss": 3.3277, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888064634690439e-06, + "loss": 3.309, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.879678687179917e-06, + "loss": 3.3121, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.87130911847313e-06, + "loss": 3.3234, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.86292317096261e-06, + "loss": 3.3271, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.854537223452088e-06, + "loss": 3.3019, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.8461676547453e-06, + "loss": 3.3146, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.83778170723478e-06, + "loss": 3.31, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.82939575972426e-06, + "loss": 3.3228, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.82100981221374e-06, + "loss": 3.3207, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.81262386470322e-06, + "loss": 3.3097, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.8042379171927e-06, + "loss": 3.3282, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.795851969682178e-06, + "loss": 3.3271, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78746602217166e-06, + "loss": 3.3097, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.77909645346487e-06, + "loss": 3.3225, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.77071050595435e-06, + "loss": 3.3237, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.76232455844383e-06, + "loss": 3.3158, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.75393861093331e-06, + "loss": 3.3053, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.745569042226521e-06, + "loss": 3.3196, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737183094716003e-06, + "loss": 3.3193, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.728797147205481e-06, + "loss": 3.3256, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.720411199694961e-06, + "loss": 3.3123, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712041630988174e-06, + "loss": 3.3202, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.703655683477652e-06, + "loss": 3.3208, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695269735967132e-06, + "loss": 3.3102, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.686900167260344e-06, + "loss": 3.3045, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.678514219749824e-06, + "loss": 3.33, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.670128272239303e-06, + "loss": 3.3297, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.661742324728784e-06, + "loss": 3.3217, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.653356377218264e-06, + "loss": 3.3095, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.644970429707742e-06, + "loss": 3.3282, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.636584482197222e-06, + "loss": 3.3182, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628214913490435e-06, + "loss": 3.3166, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.619828965979915e-06, + "loss": 3.3155, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.611443018469394e-06, + "loss": 3.3252, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603057070958875e-06, + "loss": 3.3173, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.594687502252086e-06, + "loss": 3.3224, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.586301554741566e-06, + "loss": 3.3107, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.5779156072310455e-06, + "loss": 3.3214, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.5695296597205254e-06, + "loss": 3.3208, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561160091013737e-06, + "loss": 3.3137, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.552774143503216e-06, + "loss": 3.3335, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.544388195992696e-06, + "loss": 3.3231, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536002248482177e-06, + "loss": 3.3204, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.5276326797753886e-06, + "loss": 3.3167, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519246732264868e-06, + "loss": 3.3165, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.930431365966797, + "eval_runtime": 306.3366, + "eval_samples_per_second": 1245.659, + "eval_steps_per_second": 38.928, + "step": 2594869 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.6831392281073377e+18, + "trial_name": null, + "trial_params": null +}