diff --git "a/checkpoint-2518560/trainer_state.json" "b/checkpoint-2518560/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2518560/trainer_state.json" @@ -0,0 +1,29803 @@ +{ + "best_metric": 3.843557357788086, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/4/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 2518560, + "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": 10.9889, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.826, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1945, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9797, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8194, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7109, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6086, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5346, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4515, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4029, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3415, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.2991, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2541, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2066, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1674, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1264, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0986, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0669, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0396, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0086, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9953, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9686, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 4.9364, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9247, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9133, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8768, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8566, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8456, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8303, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8075, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.7921, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7873, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.772, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7651, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7509, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.733, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7253, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6916, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6974, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6702, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6715, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6588, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6606, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6397, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6351, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6266, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6095, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6199, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5848, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5777, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5909, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.585, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5602, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5547, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5534, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5357, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5588, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5201, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.529, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5198, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5039, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5122, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.4933, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4904, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4817, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4954, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4681, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.471, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4498, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4588, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4722, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4604, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4448, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.456, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4573, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4323, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4382, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4204, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.41, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4094, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4092, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4153, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4218, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4106, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3863, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3926, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.3951, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3863, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3776, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3724, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3695, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3761, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3633, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3694, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3596, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3599, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3432, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3462, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3428, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3486, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3486, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3269, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3327, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3241, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3291, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.317, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.314, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3204, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3096, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3077, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3009, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.2963, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3112, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.2977, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.298, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3003, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3063, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2924, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2799, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2859, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2904, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2767, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2757, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2736, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2743, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2677, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2739, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.266, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2654, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2597, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2753, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2598, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2521, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2481, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2585, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2519, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2587, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2438, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2511, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2427, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.246, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2361, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2457, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2328, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2206, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2409, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2298, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2271, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2335, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2157, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.188263893127441, + "eval_runtime": 314.831, + "eval_samples_per_second": 1212.05, + "eval_steps_per_second": 37.877, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2057, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2093, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2168, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2107, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2172, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.2046, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.2042, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.1978, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2108, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.1915, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.1916, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.196, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1914, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1829, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1821, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1661, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1782, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1709, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1649, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1926, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1684, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1728, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1688, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1831, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.156, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1587, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1634, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1604, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.152, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1512, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1591, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1587, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1594, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1523, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1456, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1538, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1277, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1499, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1268, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1367, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1327, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1424, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1344, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1294, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1334, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1252, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1366, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1112, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1133, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.128, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1287, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.1131, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1099, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1172, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1017, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1243, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1058, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.82647640174716e-05, + "loss": 4.1143, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1101, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.0958, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.1119, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.0964, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.0977, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.0935, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1111, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.0918, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.0929, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.0835, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.0901, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1061, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1018, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.0896, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.1005, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.1033, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.0897, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0936, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.0849, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.074, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0778, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.0804, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0851, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806359955004151e-05, + "loss": 4.0989, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805521360253099e-05, + "loss": 4.0872, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.066, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0762, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030072138803156e-05, + "loss": 4.082, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021686191292636e-05, + "loss": 4.0772, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0676, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0688, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0698, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0728, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0639, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0725, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.0664, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.071, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0543, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0646, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.0606, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.0639, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0663, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0535, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.0547, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0561, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.0594, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0441, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0478, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0572, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0443, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0473, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0414, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0385, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0594, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780371707123404e-05, + "loss": 4.0419, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0492, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0477, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0598, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777018965999569e-05, + "loss": 4.0483, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0333, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0416, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0476, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0333, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772829268005055e-05, + "loss": 4.0369, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771990673254003e-05, + "loss": 4.032, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771152078502951e-05, + "loss": 4.0434, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0297, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0398, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0339, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767799337379116e-05, + "loss": 4.0352, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0275, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0493, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0386, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0217, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763606363623857e-05, + "loss": 4.0257, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762767768872805e-05, + "loss": 4.0331, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761929174121753e-05, + "loss": 4.0335, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.042, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760253622500022e-05, + "loss": 4.0256, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.75941502774897e-05, + "loss": 4.0334, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758576432997918e-05, + "loss": 4.0267, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0335, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0246, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560622866251346e-05, + "loss": 4.0287, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552236918740826e-05, + "loss": 4.0216, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0135, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.0332, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527095455013e-05, + "loss": 4.0241, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751870950750248e-05, + "loss": 4.02, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0241, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0128, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.022622108459473, + "eval_runtime": 302.4683, + "eval_samples_per_second": 1261.59, + "eval_steps_per_second": 39.426, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0044, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0043, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0202, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0106, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0234, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0068, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0101, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0034, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0194, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 4.0023, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.0019, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0025, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392985810059604e-05, + "loss": 4.0035, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384599862549084e-05, + "loss": 3.9957, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737621391503856e-05, + "loss": 3.9983, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736782796752804e-05, + "loss": 3.9866, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 3.9911, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 3.9877, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 3.983, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.0163, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 3.992, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 3.9882, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 3.9942, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730075676624761e-05, + "loss": 4.0035, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.9803, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.9862, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9892, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 3.9914, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9779, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9818, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9856, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9901, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9956, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9834, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9779, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200174532532566e-05, + "loss": 3.9887, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9684, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9845, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9642, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166647121294215e-05, + "loss": 3.9719, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9742, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9831, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9749, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133119710055864e-05, + "loss": 3.9703, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.9734, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9704, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9785, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9586, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9561, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9752, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9715, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9607, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9603, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9637, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9502, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9723, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9585, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9662, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9606, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998993686298745e-05, + "loss": 3.9563, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699060773878822e-05, + "loss": 3.9566, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9541, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9518, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965466275060394e-05, + "loss": 3.9484, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9652, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9517, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9513, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9423, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9492, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9647, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9595, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9516, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689002550507317e-05, + "loss": 3.9604, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9645, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.9472, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.955, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685649809383482e-05, + "loss": 3.9504, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.68481121463243e-05, + "loss": 3.9412, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683972619881378e-05, + "loss": 3.9471, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9416, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.95, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9605, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806198787575436e-05, + "loss": 3.9566, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9309, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789443271358125e-05, + "loss": 3.9467, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781057323847605e-05, + "loss": 3.9476, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9475, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9395, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9337, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.9442, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.9383, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9343, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9437, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9371, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9462, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9301, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9335, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9343, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9427, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666370319511152e-05, + "loss": 3.9408, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655317247601e-05, + "loss": 3.9297, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664693130009048e-05, + "loss": 3.9314, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9307, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9374, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9191, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661340388885213e-05, + "loss": 3.9241, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9396, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.928, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9211, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9213, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657147415129953e-05, + "loss": 3.9198, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.9365, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655470225627849e-05, + "loss": 3.9258, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9252, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9281, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9426, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521174845040136e-05, + "loss": 3.9307, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9163, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650441932882283e-05, + "loss": 3.9246, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.9277, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.919, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9206, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9175, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.9279, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645412002256344e-05, + "loss": 3.9129, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644573407505292e-05, + "loss": 3.928, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.64373481275424e-05, + "loss": 3.9139, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9248, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9131, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9344, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9266, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395434768793536e-05, + "loss": 3.9163, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387048821283016e-05, + "loss": 3.9091, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378662873772496e-05, + "loss": 3.9229, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370276926261976e-05, + "loss": 3.9193, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9306, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.9122, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9254, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336765893827354e-05, + "loss": 3.918, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9287, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319993998806314e-05, + "loss": 3.9103, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311608051295794e-05, + "loss": 3.918, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303222103785274e-05, + "loss": 3.9135, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629485253507848e-05, + "loss": 3.9043, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628646658756797e-05, + "loss": 3.9245, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627808064005745e-05, + "loss": 3.9204, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626969469254693e-05, + "loss": 3.9076, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626132512384014e-05, + "loss": 3.9184, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625293917632962e-05, + "loss": 3.9058, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.949087142944336, + "eval_runtime": 302.9735, + "eval_samples_per_second": 1259.487, + "eval_steps_per_second": 39.36, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.62445532288191e-05, + "loss": 3.9043, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623616728130858e-05, + "loss": 3.8982, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.9107, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9081, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621102581758075e-05, + "loss": 3.9208, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620263987007023e-05, + "loss": 3.899, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619425392255971e-05, + "loss": 3.9062, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618586797504919e-05, + "loss": 3.8996, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9187, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616909608002815e-05, + "loss": 3.8961, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160726511321364e-05, + "loss": 3.8955, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9069, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.8972, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.8971, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.8962, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.8891, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8877, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.8896, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.8839, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.915, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607688341501989e-05, + "loss": 3.8928, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.8924, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.894, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9022, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8849, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.891, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.891, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601819816124998e-05, + "loss": 3.8927, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600981221373946e-05, + "loss": 3.8816, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600144264503267e-05, + "loss": 3.887, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599305669752215e-05, + "loss": 3.8922, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598468712881536e-05, + "loss": 3.8938, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976301181304846e-05, + "loss": 3.9006, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967915233794326e-05, + "loss": 3.8915, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959529286283806e-05, + "loss": 3.8824, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951143338773286e-05, + "loss": 3.893, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942757391262766e-05, + "loss": 3.8781, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934371443752246e-05, + "loss": 3.8863, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926001875045455e-05, + "loss": 3.8726, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917632306338664e-05, + "loss": 3.8781, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8783, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900860411317624e-05, + "loss": 3.8942, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892474463807104e-05, + "loss": 3.8856, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884088516296584e-05, + "loss": 3.8779, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8802, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.8791, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585894705256876e-05, + "loss": 3.8865, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585056110505824e-05, + "loss": 3.8701, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584219153635145e-05, + "loss": 3.8625, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583380558884093e-05, + "loss": 3.8854, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582541964133041e-05, + "loss": 3.8809, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581703369381989e-05, + "loss": 3.8671, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.58086641251131e-05, + "loss": 3.8738, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580027817760258e-05, + "loss": 3.8756, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579189223009206e-05, + "loss": 3.8617, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578350628258154e-05, + "loss": 3.8797, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577512033507102e-05, + "loss": 3.8682, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.8812, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.867, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574997887134319e-05, + "loss": 3.876, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741592923832666e-05, + "loss": 3.8636, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573322335512588e-05, + "loss": 3.8687, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572483740761536e-05, + "loss": 3.8605, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571645146010484e-05, + "loss": 3.8627, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708065512594315e-05, + "loss": 3.8818, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699679565083795e-05, + "loss": 3.8618, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691293617573275e-05, + "loss": 3.8662, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568292404886649e-05, + "loss": 3.8543, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567453810135597e-05, + "loss": 3.8641, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566615215384545e-05, + "loss": 3.8767, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565776620633493e-05, + "loss": 3.8722, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564938025882441e-05, + "loss": 3.8679, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564099431131389e-05, + "loss": 3.8767, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563260836380337e-05, + "loss": 3.8754, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562423879509658e-05, + "loss": 3.8657, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561585284758606e-05, + "loss": 3.8682, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560746690007554e-05, + "loss": 3.8686, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559908095256502e-05, + "loss": 3.8609, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.55906950050545e-05, + "loss": 3.8618, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558232543634771e-05, + "loss": 3.8605, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557393948883719e-05, + "loss": 3.8655, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556555354132667e-05, + "loss": 3.8744, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557167593816156e-05, + "loss": 3.8716, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548781646305635e-05, + "loss": 3.8469, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540412077598845e-05, + "loss": 3.8679, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5532026130088325e-05, + "loss": 3.8643, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523640182577804e-05, + "loss": 3.8641, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515254235067284e-05, + "loss": 3.8579, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506868287556764e-05, + "loss": 3.85, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498498718849973e-05, + "loss": 3.8633, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490112771339453e-05, + "loss": 3.8562, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548174320263266e-05, + "loss": 3.8564, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547335725512214e-05, + "loss": 3.8612, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546497130761162e-05, + "loss": 3.8576, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545658536010111e-05, + "loss": 3.8685, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544819941259059e-05, + "loss": 3.8537, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543981346508007e-05, + "loss": 3.8509, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543142751756955e-05, + "loss": 3.853, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542304157005903e-05, + "loss": 3.8659, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541467200135224e-05, + "loss": 3.8579, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540628605384172e-05, + "loss": 3.8494, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.53979001063312e-05, + "loss": 3.85, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538951415882068e-05, + "loss": 3.8535, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538112821131015e-05, + "loss": 3.8615, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537275864260337e-05, + "loss": 3.8458, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536437269509285e-05, + "loss": 3.8427, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535598674758233e-05, + "loss": 3.8597, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534760080007181e-05, + "loss": 3.8471, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533923123136502e-05, + "loss": 3.8431, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.53308452838545e-05, + "loss": 3.8422, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322459336343976e-05, + "loss": 3.8464, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314073388833456e-05, + "loss": 3.8588, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305687441322936e-05, + "loss": 3.8443, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297301493812416e-05, + "loss": 3.8494, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288915546301896e-05, + "loss": 3.8522, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280529598791376e-05, + "loss": 3.8645, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272160030084585e-05, + "loss": 3.859, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263774082574065e-05, + "loss": 3.8379, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255388135063545e-05, + "loss": 3.8507, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524700218755303e-05, + "loss": 3.8469, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523861624004251e-05, + "loss": 3.8459, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523024667133572e-05, + "loss": 3.8456, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.52218607238252e-05, + "loss": 3.8387, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521347477631468e-05, + "loss": 3.8507, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520508882880416e-05, + "loss": 3.8399, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519670288129364e-05, + "loss": 3.8498, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518833331258685e-05, + "loss": 3.8411, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517994736507633e-05, + "loss": 3.8488, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517156141756581e-05, + "loss": 3.8365, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516317547005529e-05, + "loss": 3.8659, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.51548059013485e-05, + "loss": 3.8458, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146419953837985e-05, + "loss": 3.8447, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5138034006327465e-05, + "loss": 3.8347, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129648058816945e-05, + "loss": 3.8516, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121278490110154e-05, + "loss": 3.8447, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112892542599634e-05, + "loss": 3.8547, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104506595089114e-05, + "loss": 3.8408, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096120647578594e-05, + "loss": 3.8496, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087734700068074e-05, + "loss": 3.844, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507936513136128e-05, + "loss": 3.8575, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507097918385076e-05, + "loss": 3.8357, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506259323634024e-05, + "loss": 3.8462, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505420728882972e-05, + "loss": 3.8407, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504583772012293e-05, + "loss": 3.8372, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503745177261242e-05, + "loss": 3.848, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.50290658251019e-05, + "loss": 3.8464, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502067987759138e-05, + "loss": 3.8389, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501229393008086e-05, + "loss": 3.8437, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500392436137407e-05, + "loss": 3.8369, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9090492725372314, + "eval_runtime": 303.0153, + "eval_samples_per_second": 1259.313, + "eval_steps_per_second": 39.354, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499553841386355e-05, + "loss": 3.8298, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498715246635303e-05, + "loss": 3.8262, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497876651884251e-05, + "loss": 3.8405, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497038057133199e-05, + "loss": 3.8399, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496199462382146e-05, + "loss": 3.8496, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495360867631094e-05, + "loss": 3.8319, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494522272880042e-05, + "loss": 3.8325, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368367812899e-05, + "loss": 3.8305, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928467212583116e-05, + "loss": 3.8456, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920081265072596e-05, + "loss": 3.8321, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911695317562076e-05, + "loss": 3.8255, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903309370051556e-05, + "loss": 3.834, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.48949561801485e-05, + "loss": 3.8291, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488657023263798e-05, + "loss": 3.8262, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487818428512746e-05, + "loss": 3.8333, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869798337616934e-05, + "loss": 3.8175, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861412390106414e-05, + "loss": 3.8197, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853026442595894e-05, + "loss": 3.8211, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844640495085374e-05, + "loss": 3.8164, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836254547574854e-05, + "loss": 3.8404, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482788497886807e-05, + "loss": 3.8288, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481949903135755e-05, + "loss": 3.8237, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481111308384703e-05, + "loss": 3.8255, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480272713633651e-05, + "loss": 3.8365, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479434118882599e-05, + "loss": 3.8173, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.47859716201192e-05, + "loss": 3.8238, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477758567260868e-05, + "loss": 3.8204, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476919972509816e-05, + "loss": 3.8232, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476081377758764e-05, + "loss": 3.8158, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475244420888085e-05, + "loss": 3.8208, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474405826137033e-05, + "loss": 3.8249, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473567231385981e-05, + "loss": 3.8272, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727286366349295e-05, + "loss": 3.8333, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718916797642504e-05, + "loss": 3.8266, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710530850131984e-05, + "loss": 3.8142, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702144902621464e-05, + "loss": 3.8244, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693758955110944e-05, + "loss": 3.8159, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468538938640415e-05, + "loss": 3.8178, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467700343889363e-05, + "loss": 3.8065, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466861749138311e-05, + "loss": 3.8132, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466023154387259e-05, + "loss": 3.8161, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46518619751658e-05, + "loss": 3.8259, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464347602765528e-05, + "loss": 3.8191, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463509008014476e-05, + "loss": 3.8154, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462670413263425e-05, + "loss": 3.8146, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461831818512373e-05, + "loss": 3.8148, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460994861641694e-05, + "loss": 3.8235, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460156266890642e-05, + "loss": 3.8085, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.45931767213959e-05, + "loss": 3.7974, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458479077388538e-05, + "loss": 3.8207, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576421205178586e-05, + "loss": 3.8179, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568035257668066e-05, + "loss": 3.802, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559649310157546e-05, + "loss": 3.8094, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551263362647026e-05, + "loss": 3.8153, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542893793940235e-05, + "loss": 3.7961, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534507846429715e-05, + "loss": 3.8162, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.45261218989192e-05, + "loss": 3.8076, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451773595140868e-05, + "loss": 3.8158, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450935000389816e-05, + "loss": 3.8068, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450098043519137e-05, + "loss": 3.8119, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449259448768085e-05, + "loss": 3.8031, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448420854017033e-05, + "loss": 3.8103, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447582259265981e-05, + "loss": 3.7966, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446745302395302e-05, + "loss": 3.805, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.44590670764425e-05, + "loss": 3.8153, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445068112893198e-05, + "loss": 3.8033, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444229518142146e-05, + "loss": 3.8018, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443392561271467e-05, + "loss": 3.7936, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425539665204156e-05, + "loss": 3.8018, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.4417153717693636e-05, + "loss": 3.8122, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.4408767770183116e-05, + "loss": 3.8151, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400398201476325e-05, + "loss": 3.8082, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392012253965805e-05, + "loss": 3.8175, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383626306455285e-05, + "loss": 3.817, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375240358944764e-05, + "loss": 3.8018, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366870790237974e-05, + "loss": 3.8061, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358484842727454e-05, + "loss": 3.809, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350098895216933e-05, + "loss": 3.7994, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341712947706413e-05, + "loss": 3.7993, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433334337899962e-05, + "loss": 3.8026, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.43249574314891e-05, + "loss": 3.8015, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431657148397859e-05, + "loss": 3.8174, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430818553646807e-05, + "loss": 3.8118, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429979958895754e-05, + "loss": 3.7884, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429141364144702e-05, + "loss": 3.8041, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428304407274024e-05, + "loss": 3.8069, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427465812522971e-05, + "loss": 3.8055, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426627217771919e-05, + "loss": 3.801, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425788623020867e-05, + "loss": 3.7906, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424951666150189e-05, + "loss": 3.8027, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424113071399136e-05, + "loss": 3.7966, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423274476648084e-05, + "loss": 3.7978, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422435881897033e-05, + "loss": 3.7972, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421598925026354e-05, + "loss": 3.8034, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420761968155675e-05, + "loss": 3.806, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419923373404623e-05, + "loss": 3.8025, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419084778653571e-05, + "loss": 3.787, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182461839025185e-05, + "loss": 3.7985, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174075891514665e-05, + "loss": 3.8018, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165689944004145e-05, + "loss": 3.8054, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157303996493625e-05, + "loss": 3.7903, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148918048983105e-05, + "loss": 3.7932, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140548480276314e-05, + "loss": 3.7964, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132162532765794e-05, + "loss": 3.803, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412377658525528e-05, + "loss": 3.7906, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411539063774476e-05, + "loss": 3.7874, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410702106903797e-05, + "loss": 3.7967, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409863512152745e-05, + "loss": 3.7904, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409026555282066e-05, + "loss": 3.787, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408187960531014e-05, + "loss": 3.7867, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407349365779962e-05, + "loss": 3.7875, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.40651077102891e-05, + "loss": 3.8023, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405672176277858e-05, + "loss": 3.7906, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404833581526806e-05, + "loss": 3.79, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.403994986775754e-05, + "loss": 3.7973, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403156392024702e-05, + "loss": 3.8095, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023194351540234e-05, + "loss": 3.8016, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014808404029714e-05, + "loss": 3.7839, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006422456519194e-05, + "loss": 3.7911, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3998036509008674e-05, + "loss": 3.7907, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398966694030188e-05, + "loss": 3.7879, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398129737159509e-05, + "loss": 3.7901, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397291142408457e-05, + "loss": 3.7825, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396452547657405e-05, + "loss": 3.7936, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395613952906353e-05, + "loss": 3.7886, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394775358155301e-05, + "loss": 3.7928, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393936763404249e-05, + "loss": 3.7831, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393098168653197e-05, + "loss": 3.7898, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392259573902145e-05, + "loss": 3.7888, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391420979151093e-05, + "loss": 3.8022, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390584022280415e-05, + "loss": 3.7883, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389745427529363e-05, + "loss": 3.7944, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388906832778311e-05, + "loss": 3.7787, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388068238027259e-05, + "loss": 3.7995, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.38723128115658e-05, + "loss": 3.7924, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386392686405528e-05, + "loss": 3.7979, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385554091654476e-05, + "loss": 3.7853, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384715496903424e-05, + "loss": 3.7995, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838785400327446e-05, + "loss": 3.7853, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830399452816926e-05, + "loss": 3.8058, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822013505306406e-05, + "loss": 3.7831, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813627557795886e-05, + "loss": 3.7935, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.38052579890891e-05, + "loss": 3.787, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379687204157858e-05, + "loss": 3.7832, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378848609406806e-05, + "loss": 3.7954, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378010014655754e-05, + "loss": 3.7933, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377171419904702e-05, + "loss": 3.7844, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376334463034023e-05, + "loss": 3.7852, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375495868282971e-05, + "loss": 3.7874, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.884556293487549, + "eval_runtime": 303.9185, + "eval_samples_per_second": 1255.57, + "eval_steps_per_second": 39.237, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.374657273531919e-05, + "loss": 3.7776, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.373818678780867e-05, + "loss": 3.7737, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729800840298144e-05, + "loss": 3.7882, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721414892787624e-05, + "loss": 3.785, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371302894527711e-05, + "loss": 3.7961, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370464299776659e-05, + "loss": 3.779, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369625705025607e-05, + "loss": 3.7778, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.368787110274555e-05, + "loss": 3.7789, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367950153403876e-05, + "loss": 3.795, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.367111558652824e-05, + "loss": 3.7782, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366272963901772e-05, + "loss": 3.7747, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.36543436915072e-05, + "loss": 3.7795, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.3645990501604144e-05, + "loss": 3.7795, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363760455409362e-05, + "loss": 3.7739, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.36292186065831e-05, + "loss": 3.7808, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362083265907258e-05, + "loss": 3.7675, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.3612446711562064e-05, + "loss": 3.7663, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.3604060764051544e-05, + "loss": 3.772, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.3595674816541024e-05, + "loss": 3.7639, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.3587288869030504e-05, + "loss": 3.7885, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357891930032371e-05, + "loss": 3.7795, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357053335281319e-05, + "loss": 3.7741, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356214740530267e-05, + "loss": 3.7709, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.355376145779215e-05, + "loss": 3.7834, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.354539188908536e-05, + "loss": 3.768, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353700594157484e-05, + "loss": 3.7768, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352861999406432e-05, + "loss": 3.7684, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.35202340465538e-05, + "loss": 3.7726, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351186447784701e-05, + "loss": 3.7684, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.35034785303365e-05, + "loss": 3.7679, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.349509258282598e-05, + "loss": 3.7751, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348670663531546e-05, + "loss": 3.7767, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3478337066608667e-05, + "loss": 3.7823, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3469951119098146e-05, + "loss": 3.7782, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461565171587626e-05, + "loss": 3.7636, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453179224077106e-05, + "loss": 3.7756, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444809655370316e-05, + "loss": 3.7696, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436423707859795e-05, + "loss": 3.7605, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428037760349275e-05, + "loss": 3.7637, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419651812838755e-05, + "loss": 3.7639, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411282244131964e-05, + "loss": 3.7658, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.340289629662145e-05, + "loss": 3.779, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339451034911093e-05, + "loss": 3.7659, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338612440160041e-05, + "loss": 3.7645, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337775483289362e-05, + "loss": 3.7698, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.33693688853831e-05, + "loss": 3.7657, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336098293787258e-05, + "loss": 3.7694, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335259699036206e-05, + "loss": 3.7605, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334422742165527e-05, + "loss": 3.7467, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333584147414475e-05, + "loss": 3.7752, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332745552663423e-05, + "loss": 3.7662, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331906957912371e-05, + "loss": 3.7598, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331070001041692e-05, + "loss": 3.7597, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.3302314062906405e-05, + "loss": 3.7624, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3293928115395885e-05, + "loss": 3.7483, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285542167885365e-05, + "loss": 3.7638, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277172599178574e-05, + "loss": 3.7637, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.3268786651668054e-05, + "loss": 3.7659, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3260400704157534e-05, + "loss": 3.7618, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.3252014756647014e-05, + "loss": 3.7615, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.3243628809136494e-05, + "loss": 3.7538, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.32352592404297e-05, + "loss": 3.7645, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322687329291918e-05, + "loss": 3.7501, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321848734540866e-05, + "loss": 3.7554, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321010139789814e-05, + "loss": 3.7676, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320173182919136e-05, + "loss": 3.7577, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319334588168084e-05, + "loss": 3.7524, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318495993417032e-05, + "loss": 3.7509, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.31765739866598e-05, + "loss": 3.7518, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316818803914928e-05, + "loss": 3.7623, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315981847044249e-05, + "loss": 3.7668, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315143252293197e-05, + "loss": 3.7594, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314304657542145e-05, + "loss": 3.7702, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313466062791092e-05, + "loss": 3.7686, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126291059204136e-05, + "loss": 3.7629, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3117905111693616e-05, + "loss": 3.7563, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109519164183096e-05, + "loss": 3.7589, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101133216672576e-05, + "loss": 3.7566, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.309276364796579e-05, + "loss": 3.7496, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.308437770045527e-05, + "loss": 3.7632, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.307599175294475e-05, + "loss": 3.7517, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067605805434225e-05, + "loss": 3.7668, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305923623672744e-05, + "loss": 3.7688, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.305085028921692e-05, + "loss": 3.7401, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042464341706394e-05, + "loss": 3.759, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034078394195874e-05, + "loss": 3.7545, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302570882548909e-05, + "loss": 3.7595, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301732287797857e-05, + "loss": 3.7535, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300893693046805e-05, + "loss": 3.7454, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300055098295753e-05, + "loss": 3.7569, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.2992181414250746e-05, + "loss": 3.7496, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.2983795466740226e-05, + "loss": 3.7541, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.29754095192297e-05, + "loss": 3.7494, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296702357171918e-05, + "loss": 3.7601, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958654003012395e-05, + "loss": 3.7595, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.295026805550187e-05, + "loss": 3.7557, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294188210799135e-05, + "loss": 3.7417, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293349616048083e-05, + "loss": 3.7551, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.2925126591774044e-05, + "loss": 3.7542, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291674064426352e-05, + "loss": 3.7625, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.2908354696753004e-05, + "loss": 3.7454, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.2899968749242484e-05, + "loss": 3.7525, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.28915991805357e-05, + "loss": 3.7479, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288321323302517e-05, + "loss": 3.7576, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287482728551465e-05, + "loss": 3.743, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286644133800413e-05, + "loss": 3.7477, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285807176929734e-05, + "loss": 3.7518, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284968582178682e-05, + "loss": 3.7475, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284131625308004e-05, + "loss": 3.7398, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283293030556952e-05, + "loss": 3.7461, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282454435805899e-05, + "loss": 3.7442, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281615841054847e-05, + "loss": 3.7517, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.280777246303796e-05, + "loss": 3.7507, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.279938651552744e-05, + "loss": 3.741, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.279100056801692e-05, + "loss": 3.7538, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.27826146205064e-05, + "loss": 3.7648, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774245051799606e-05, + "loss": 3.7578, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765859104289086e-05, + "loss": 3.7388, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757473156778566e-05, + "loss": 3.7494, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749087209268046e-05, + "loss": 3.7466, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740717640561255e-05, + "loss": 3.7422, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732331693050735e-05, + "loss": 3.7458, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2723945745540215e-05, + "loss": 3.7376, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715559798029695e-05, + "loss": 3.7526, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707190229322904e-05, + "loss": 3.7441, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269880428181239e-05, + "loss": 3.7533, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.269041833430187e-05, + "loss": 3.7426, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268203238679135e-05, + "loss": 3.7409, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267366281808456e-05, + "loss": 3.7511, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266527687057404e-05, + "loss": 3.756, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265689092306352e-05, + "loss": 3.7465, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.2648504975553e-05, + "loss": 3.7486, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264013540684621e-05, + "loss": 3.7376, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263174945933569e-05, + "loss": 3.7553, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262336351182517e-05, + "loss": 3.7468, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261497756431465e-05, + "loss": 3.7559, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260660799560786e-05, + "loss": 3.7411, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2598222048097345e-05, + "loss": 3.7544, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.2589836100586825e-05, + "loss": 3.7418, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.2581450153076305e-05, + "loss": 3.766, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.2573080584369514e-05, + "loss": 3.7372, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.2564694636858994e-05, + "loss": 3.7529, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.2556308689348474e-05, + "loss": 3.7439, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2547922741837953e-05, + "loss": 3.7401, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253955317313116e-05, + "loss": 3.7492, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253116722562064e-05, + "loss": 3.7465, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252278127811012e-05, + "loss": 3.7487, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.25143953305996e-05, + "loss": 3.7389, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250600938308908e-05, + "loss": 3.746, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.869255781173706, + "eval_runtime": 304.294, + "eval_samples_per_second": 1254.021, + "eval_steps_per_second": 39.189, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.24976398143823e-05, + "loss": 3.738, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.248925386687178e-05, + "loss": 3.7318, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.248086791936126e-05, + "loss": 3.74, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.247249835065447e-05, + "loss": 3.7456, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.246411240314395e-05, + "loss": 3.7506, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245572645563343e-05, + "loss": 3.7398, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.244734050812291e-05, + "loss": 3.7318, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243895456061239e-05, + "loss": 3.7411, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.2430584991905596e-05, + "loss": 3.7502, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.2422199044395076e-05, + "loss": 3.7389, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.2413813096884556e-05, + "loss": 3.7338, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.2405427149374036e-05, + "loss": 3.7356, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.239707395947098e-05, + "loss": 3.74, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.238868801196046e-05, + "loss": 3.7308, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.238030206444994e-05, + "loss": 3.739, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.237191611693942e-05, + "loss": 3.7264, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.236354654823263e-05, + "loss": 3.7238, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.235516060072211e-05, + "loss": 3.7292, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234677465321159e-05, + "loss": 3.7236, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233838870570107e-05, + "loss": 3.7462, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.233000275819055e-05, + "loss": 3.7414, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232161681068003e-05, + "loss": 3.7342, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.231323086316951e-05, + "loss": 3.7296, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230484491565899e-05, + "loss": 3.7394, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.2296475346952206e-05, + "loss": 3.7288, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.2288089399441686e-05, + "loss": 3.7367, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.2279703451931166e-05, + "loss": 3.7264, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.2271317504420645e-05, + "loss": 3.7338, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.2262947935713855e-05, + "loss": 3.7286, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.2254561988203335e-05, + "loss": 3.728, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.2246176040692814e-05, + "loss": 3.7336, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.2237790093182294e-05, + "loss": 3.738, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.2229420524475504e-05, + "loss": 3.7354, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.2221034576964983e-05, + "loss": 3.738, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.2212648629454463e-05, + "loss": 3.7245, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.2204262681943943e-05, + "loss": 3.74, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.219589311323716e-05, + "loss": 3.7291, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.218750716572664e-05, + "loss": 3.7208, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217912121821612e-05, + "loss": 3.7225, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.21707352707056e-05, + "loss": 3.723, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216236570199881e-05, + "loss": 3.7268, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.215397975448829e-05, + "loss": 3.735, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.214559380697777e-05, + "loss": 3.7259, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.213720785946725e-05, + "loss": 3.7272, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.212883829076046e-05, + "loss": 3.7303, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.212045234324994e-05, + "loss": 3.7256, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211206639573942e-05, + "loss": 3.7301, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.21036804482289e-05, + "loss": 3.7195, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.209531087952211e-05, + "loss": 3.7076, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208692493201159e-05, + "loss": 3.7338, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.207853898450107e-05, + "loss": 3.7304, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.2070153036990546e-05, + "loss": 3.7168, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.206178346828376e-05, + "loss": 3.7263, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.205339752077324e-05, + "loss": 3.7215, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.204502795206645e-05, + "loss": 3.7107, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.203664200455593e-05, + "loss": 3.7228, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.202825605704541e-05, + "loss": 3.7268, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.201987010953489e-05, + "loss": 3.7263, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.2011484162024364e-05, + "loss": 3.721, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200309821451385e-05, + "loss": 3.7231, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.199471226700333e-05, + "loss": 3.7145, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.1986342698296547e-05, + "loss": 3.7285, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197795675078602e-05, + "loss": 3.7121, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.19695708032755e-05, + "loss": 3.7144, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.196118485576498e-05, + "loss": 3.7291, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195281528705819e-05, + "loss": 3.719, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.194442933954767e-05, + "loss": 3.7157, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193604339203715e-05, + "loss": 3.7134, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192765744452663e-05, + "loss": 3.7121, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.191928787581984e-05, + "loss": 3.7203, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191090192830932e-05, + "loss": 3.7325, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.1902515980798804e-05, + "loss": 3.7202, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.1894130033288284e-05, + "loss": 3.7311, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.1885760464581493e-05, + "loss": 3.7265, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.1877374517070973e-05, + "loss": 3.7274, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186898856956045e-05, + "loss": 3.72, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186060262204993e-05, + "loss": 3.72, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185223305334314e-05, + "loss": 3.7194, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.184384710583262e-05, + "loss": 3.7087, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.18354611583221e-05, + "loss": 3.7245, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182707521081158e-05, + "loss": 3.7163, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181870564210479e-05, + "loss": 3.7278, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.181031969459427e-05, + "loss": 3.7268, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180193374708375e-05, + "loss": 3.7019, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.179354779957324e-05, + "loss": 3.7241, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.178517823086645e-05, + "loss": 3.7181, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.177679228335593e-05, + "loss": 3.7221, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.176840633584541e-05, + "loss": 3.7149, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.176002038833489e-05, + "loss": 3.7092, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.1751650819628096e-05, + "loss": 3.7201, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.1743264872117576e-05, + "loss": 3.7123, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.1734878924607056e-05, + "loss": 3.7142, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.1726492977096536e-05, + "loss": 3.713, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.1718123408389745e-05, + "loss": 3.7217, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.1709737460879225e-05, + "loss": 3.7269, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.1701351513368705e-05, + "loss": 3.7111, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.169296556585819e-05, + "loss": 3.7092, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.16845959971514e-05, + "loss": 3.7153, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.167621004964088e-05, + "loss": 3.7156, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.166782410213036e-05, + "loss": 3.7274, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.165943815461984e-05, + "loss": 3.7098, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.165106858591305e-05, + "loss": 3.7145, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.164268263840253e-05, + "loss": 3.7117, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.163429669089201e-05, + "loss": 3.7222, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.162591074338149e-05, + "loss": 3.7038, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.16175411746747e-05, + "loss": 3.7102, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160915522716418e-05, + "loss": 3.7128, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160076927965366e-05, + "loss": 3.7114, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.1592399710946875e-05, + "loss": 3.7028, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.1584013763436354e-05, + "loss": 3.7102, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.1575627815925834e-05, + "loss": 3.7061, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.1567241868415314e-05, + "loss": 3.7151, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.1558855920904794e-05, + "loss": 3.7138, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.1550469973394274e-05, + "loss": 3.709, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.1542084025883754e-05, + "loss": 3.7127, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.1533698078373234e-05, + "loss": 3.729, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.152532850966644e-05, + "loss": 3.7257, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151694256215592e-05, + "loss": 3.7042, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.15085566146454e-05, + "loss": 3.7117, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.150017066713488e-05, + "loss": 3.7108, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.14918010984281e-05, + "loss": 3.7023, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148341515091758e-05, + "loss": 3.7128, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147502920340706e-05, + "loss": 3.6959, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146664325589654e-05, + "loss": 3.7189, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.145827368718975e-05, + "loss": 3.7033, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.144988773967923e-05, + "loss": 3.717, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.144150179216871e-05, + "loss": 3.708, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143311584465819e-05, + "loss": 3.7075, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.14247462759514e-05, + "loss": 3.7124, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.141636032844088e-05, + "loss": 3.7204, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140797438093036e-05, + "loss": 3.7073, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139958843341984e-05, + "loss": 3.7144, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139121886471305e-05, + "loss": 3.7015, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138283291720253e-05, + "loss": 3.7227, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137444696969201e-05, + "loss": 3.71, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136606102218149e-05, + "loss": 3.7171, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.13576914534747e-05, + "loss": 3.7099, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.134930550596418e-05, + "loss": 3.718, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.134091955845366e-05, + "loss": 3.7082, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133253361094314e-05, + "loss": 3.7269, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132416404223635e-05, + "loss": 3.7022, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131577809472583e-05, + "loss": 3.7158, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.130739214721531e-05, + "loss": 3.7103, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.129900619970479e-05, + "loss": 3.709, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.1290636630998006e-05, + "loss": 3.7075, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.1282250683487486e-05, + "loss": 3.7121, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.1273864735976966e-05, + "loss": 3.7123, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.1265478788466446e-05, + "loss": 3.7034, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.1257109219759655e-05, + "loss": 3.7159, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.85919451713562, + "eval_runtime": 303.67, + "eval_samples_per_second": 1256.598, + "eval_steps_per_second": 39.27, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248723272249135e-05, + "loss": 3.7031, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240337324738615e-05, + "loss": 3.6984, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231951377228095e-05, + "loss": 3.7073, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122356542971757e-05, + "loss": 3.7067, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121517948220705e-05, + "loss": 3.7155, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120679353469653e-05, + "loss": 3.7068, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119840758718601e-05, + "loss": 3.7008, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119002163967549e-05, + "loss": 3.7021, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.1181652070968704e-05, + "loss": 3.7152, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.1173266123458184e-05, + "loss": 3.706, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.1164880175947664e-05, + "loss": 3.698, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156494228437144e-05, + "loss": 3.7004, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114814103853409e-05, + "loss": 3.7053, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.113975509102357e-05, + "loss": 3.6952, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113136914351304e-05, + "loss": 3.7035, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112298319600252e-05, + "loss": 3.6907, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111461362729574e-05, + "loss": 3.6904, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110622767978521e-05, + "loss": 3.6947, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.10978417322747e-05, + "loss": 3.6916, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108945578476418e-05, + "loss": 3.709, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108106983725366e-05, + "loss": 3.7067, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107268388974314e-05, + "loss": 3.6987, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106429794223262e-05, + "loss": 3.6956, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.10559119947221e-05, + "loss": 3.7039, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104754242601531e-05, + "loss": 3.6943, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103915647850479e-05, + "loss": 3.701, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103077053099427e-05, + "loss": 3.6882, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022384583483747e-05, + "loss": 3.7037, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014015014776956e-05, + "loss": 3.7011, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005629067266436e-05, + "loss": 3.691, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997243119755916e-05, + "loss": 3.6976, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988857172245396e-05, + "loss": 3.7051, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098048760353861e-05, + "loss": 3.6984, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097210165602809e-05, + "loss": 3.7086, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096371570851757e-05, + "loss": 3.6897, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095532976100705e-05, + "loss": 3.7011, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094696019230026e-05, + "loss": 3.6981, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093857424478974e-05, + "loss": 3.6899, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093018829727922e-05, + "loss": 3.6893, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.09218023497687e-05, + "loss": 3.6879, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091343278106191e-05, + "loss": 3.691, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090504683355139e-05, + "loss": 3.7022, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.089666088604087e-05, + "loss": 3.6933, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888291317334085e-05, + "loss": 3.6944, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879905369823565e-05, + "loss": 3.6994, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871519422313045e-05, + "loss": 3.6924, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863133474802525e-05, + "loss": 3.6942, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854763906095734e-05, + "loss": 3.6899, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846377958585214e-05, + "loss": 3.6682, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0837992011074694e-05, + "loss": 3.7072, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.0829606063564174e-05, + "loss": 3.6929, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082123649485738e-05, + "loss": 3.6916, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081285054734686e-05, + "loss": 3.6893, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080446459983634e-05, + "loss": 3.6889, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079609503112955e-05, + "loss": 3.6789, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078770908361904e-05, + "loss": 3.6866, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077932313610852e-05, + "loss": 3.6938, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770937188598e-05, + "loss": 3.6936, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076255124108748e-05, + "loss": 3.6948, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075416529357696e-05, + "loss": 3.683, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074577934606644e-05, + "loss": 3.6815, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073740977735965e-05, + "loss": 3.7006, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072902382984913e-05, + "loss": 3.6745, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072063788233861e-05, + "loss": 3.6827, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071225193482809e-05, + "loss": 3.6925, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.07038823661213e-05, + "loss": 3.6885, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695496418610777e-05, + "loss": 3.6838, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.0687110471100257e-05, + "loss": 3.6833, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678724523589736e-05, + "loss": 3.677, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067035495488295e-05, + "loss": 3.6869, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066198538617616e-05, + "loss": 3.7012, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065359943866564e-05, + "loss": 3.6897, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064521349115512e-05, + "loss": 3.7005, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.06368275436446e-05, + "loss": 3.6946, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062844159613408e-05, + "loss": 3.6982, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062005564862356e-05, + "loss": 3.6841, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061166970111304e-05, + "loss": 3.6915, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060328375360252e-05, + "loss": 3.6883, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059491418489573e-05, + "loss": 3.6743, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058652823738521e-05, + "loss": 3.6929, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.057814228987469e-05, + "loss": 3.6847, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056975634236418e-05, + "loss": 3.6944, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561386773657386e-05, + "loss": 3.6984, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553000826146866e-05, + "loss": 3.6724, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544614878636346e-05, + "loss": 3.6891, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0536245309929555e-05, + "loss": 3.6846, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.0527859362419035e-05, + "loss": 3.6923, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519473414908515e-05, + "loss": 3.6821, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511087467397995e-05, + "loss": 3.6789, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502717898691204e-05, + "loss": 3.6843, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494331951180684e-05, + "loss": 3.6811, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485946003670164e-05, + "loss": 3.6836, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477560056159644e-05, + "loss": 3.681, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046919048745286e-05, + "loss": 3.6954, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046080453994234e-05, + "loss": 3.6932, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045241859243182e-05, + "loss": 3.6798, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044403264492129e-05, + "loss": 3.6758, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043566307621451e-05, + "loss": 3.684, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042727712870399e-05, + "loss": 3.6886, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041889118119347e-05, + "loss": 3.6903, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041050523368294e-05, + "loss": 3.6827, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040213566497616e-05, + "loss": 3.6833, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039374971746564e-05, + "loss": 3.6799, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038536376995512e-05, + "loss": 3.6923, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.03769778224446e-05, + "loss": 3.6691, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036860825373781e-05, + "loss": 3.6822, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036022230622729e-05, + "loss": 3.676, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351836358716766e-05, + "loss": 3.6823, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034346679000998e-05, + "loss": 3.6726, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033508084249946e-05, + "loss": 3.6829, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.032669489498894e-05, + "loss": 3.673, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318308947478415e-05, + "loss": 3.6874, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0309922999967895e-05, + "loss": 3.6849, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301537052457375e-05, + "loss": 3.6769, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293151104946855e-05, + "loss": 3.6841, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284765157436335e-05, + "loss": 3.6993, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027639558872955e-05, + "loss": 3.6862, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026800964121903e-05, + "loss": 3.68, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025962369370851e-05, + "loss": 3.6747, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025123774619799e-05, + "loss": 3.6805, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242884556294936e-05, + "loss": 3.68, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234498608784416e-05, + "loss": 3.6785, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022611266127389e-05, + "loss": 3.6669, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021772671376337e-05, + "loss": 3.686, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020934076625285e-05, + "loss": 3.6741, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020095481874233e-05, + "loss": 3.6843, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019256887123181e-05, + "loss": 3.6769, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018418292372129e-05, + "loss": 3.6792, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175813355014505e-05, + "loss": 3.677, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167427407503985e-05, + "loss": 3.692, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159041459993465e-05, + "loss": 3.6791, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150655512482945e-05, + "loss": 3.6828, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.0142285943776154e-05, + "loss": 3.6677, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133899996265634e-05, + "loss": 3.6912, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125514048755114e-05, + "loss": 3.6818, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0117128101244594e-05, + "loss": 3.6872, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.01087585325378e-05, + "loss": 3.6796, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010037258502728e-05, + "loss": 3.6854, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009198663751676e-05, + "loss": 3.6747, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008360069000624e-05, + "loss": 3.6958, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007523112129946e-05, + "loss": 3.6734, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6877, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.682, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.00500732787679e-05, + "loss": 3.6765, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004170371006111e-05, + "loss": 3.676, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003331776255059e-05, + "loss": 3.6824, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002493181504007e-05, + "loss": 3.684, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001654586752955e-05, + "loss": 3.6743, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.0008176298822756e-05, + "loss": 3.6869, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8534765243530273, + "eval_runtime": 303.8653, + "eval_samples_per_second": 1255.79, + "eval_steps_per_second": 39.244, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.6718, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991404403801716e-05, + "loss": 3.6687, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983018456291196e-05, + "loss": 3.6762, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974632508780676e-05, + "loss": 3.6791, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996624656127016e-05, + "loss": 3.6867, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995786061375964e-05, + "loss": 3.6732, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994947466624912e-05, + "loss": 3.6765, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.99410887187386e-05, + "loss": 3.6724, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6811, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6802, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.6674, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990756130750025e-05, + "loss": 3.6678, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989920811759719e-05, + "loss": 3.6818, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989082217008667e-05, + "loss": 3.6647, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988243622257615e-05, + "loss": 3.6705, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987405027506563e-05, + "loss": 3.6645, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865680706358846e-05, + "loss": 3.6592, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857294758848326e-05, + "loss": 3.6687, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848908811337806e-05, + "loss": 3.659, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840522863827286e-05, + "loss": 3.6783, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832136916316766e-05, + "loss": 3.678, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823750968806246e-05, + "loss": 3.6724, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815365021295726e-05, + "loss": 3.6652, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.98069790737852e-05, + "loss": 3.6701, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798609505078415e-05, + "loss": 3.6693, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790223557567895e-05, + "loss": 3.67, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978183761005737e-05, + "loss": 3.6632, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773451662546854e-05, + "loss": 3.6744, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976508209384007e-05, + "loss": 3.6653, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975669614632955e-05, + "loss": 3.6637, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748310198819023e-05, + "loss": 3.6649, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.6794, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973155468260172e-05, + "loss": 3.6738, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.97231687350912e-05, + "loss": 3.6774, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971478278758067e-05, + "loss": 3.6602, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970639684007015e-05, + "loss": 3.6666, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.675, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968964132385284e-05, + "loss": 3.6606, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968125537634232e-05, + "loss": 3.6595, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6598, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664499860125024e-05, + "loss": 3.6635, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.6665, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964772796510398e-05, + "loss": 3.6726, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963935839639719e-05, + "loss": 3.6684, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963097244888667e-05, + "loss": 3.6637, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622586501376146e-05, + "loss": 3.6682, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614200553865626e-05, + "loss": 3.6631, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960583098515884e-05, + "loss": 3.6636, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597445037648315e-05, + "loss": 3.6356, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589059090137795e-05, + "loss": 3.6795, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580673142627275e-05, + "loss": 3.6623, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957230357392049e-05, + "loss": 3.6687, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956393400521371e-05, + "loss": 3.6605, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955554805770319e-05, + "loss": 3.6602, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954716211019267e-05, + "loss": 3.6507, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953877616268215e-05, + "loss": 3.6572, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953039021517162e-05, + "loss": 3.6687, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.95220042676611e-05, + "loss": 3.6624, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951361832015058e-05, + "loss": 3.6692, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950524875144379e-05, + "loss": 3.6596, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949686280393327e-05, + "loss": 3.6514, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948847685642275e-05, + "loss": 3.6724, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948009090891223e-05, + "loss": 3.6451, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471721340205445e-05, + "loss": 3.6508, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463335392694925e-05, + "loss": 3.6662, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454949445184404e-05, + "loss": 3.6649, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446563497673884e-05, + "loss": 3.6486, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438193928967094e-05, + "loss": 3.6607, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429807981456573e-05, + "loss": 3.6461, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421422033946053e-05, + "loss": 3.6648, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941305246523926e-05, + "loss": 3.6673, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940466651772874e-05, + "loss": 3.6649, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939628057021822e-05, + "loss": 3.666, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.93878946227077e-05, + "loss": 3.6679, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937950867519718e-05, + "loss": 3.675, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937112272768666e-05, + "loss": 3.6553, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6635, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935435083266563e-05, + "loss": 3.6624, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934598126395884e-05, + "loss": 3.6403, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933759531644832e-05, + "loss": 3.6664, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.93292093689378e-05, + "loss": 3.6599, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932082342142728e-05, + "loss": 3.6635, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931245385272049e-05, + "loss": 3.6747, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304084284013696e-05, + "loss": 3.6487, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295698336503176e-05, + "loss": 3.6522, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287312388992656e-05, + "loss": 3.6579, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9278926441482136e-05, + "loss": 3.666, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270540493971616e-05, + "loss": 3.6522, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621545464611e-05, + "loss": 3.6557, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925376859895058e-05, + "loss": 3.6558, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924539903024379e-05, + "loss": 3.6571, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923701308273327e-05, + "loss": 3.6525, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922862713522275e-05, + "loss": 3.6574, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922025756651596e-05, + "loss": 3.6675, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.6593, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920348567149492e-05, + "loss": 3.6615, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.91950997239844e-05, + "loss": 3.645, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918671377647388e-05, + "loss": 3.6571, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917832782896336e-05, + "loss": 3.659, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916994188145284e-05, + "loss": 3.6662, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161572312746056e-05, + "loss": 3.6552, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153186365235536e-05, + "loss": 3.6529, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144800417725016e-05, + "loss": 3.6565, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136414470214496e-05, + "loss": 3.6584, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128044901507705e-05, + "loss": 3.6465, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119675332800914e-05, + "loss": 3.6559, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111289385290394e-05, + "loss": 3.644, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102903437779874e-05, + "loss": 3.6621, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094517490269354e-05, + "loss": 3.6442, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086131542758834e-05, + "loss": 3.6524, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077745595248314e-05, + "loss": 3.6478, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9069359647737794e-05, + "loss": 3.6573, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060973700227274e-05, + "loss": 3.6585, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905260413152049e-05, + "loss": 3.6498, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904421818400997e-05, + "loss": 3.6537, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903583223649945e-05, + "loss": 3.6692, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902744628898892e-05, + "loss": 3.6618, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901907672028214e-05, + "loss": 3.6504, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901069077277162e-05, + "loss": 3.6478, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.90023048252611e-05, + "loss": 3.6517, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899393525655431e-05, + "loss": 3.6565, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898554930904379e-05, + "loss": 3.6466, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897716336153327e-05, + "loss": 3.6426, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896877741402275e-05, + "loss": 3.6592, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896039146651223e-05, + "loss": 3.652, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895200551900171e-05, + "loss": 3.6566, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943635950294924e-05, + "loss": 3.651, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352500027844e-05, + "loss": 3.6515, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892686405527388e-05, + "loss": 3.6513, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891847810776336e-05, + "loss": 3.6638, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891009216025284e-05, + "loss": 3.6559, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890170621274232e-05, + "loss": 3.6538, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.8893320265231797e-05, + "loss": 3.6419, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.8884934317721277e-05, + "loss": 3.6666, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.8876564749014486e-05, + "loss": 3.6538, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.88681951803077e-05, + "loss": 3.6614, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885980923279718e-05, + "loss": 3.6534, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885142328528666e-05, + "loss": 3.6546, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884303733777614e-05, + "loss": 3.6517, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883465139026562e-05, + "loss": 3.6698, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.88262654427551e-05, + "loss": 3.6479, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881787949524458e-05, + "loss": 3.6605, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880949354773406e-05, + "loss": 3.6555, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880112397902727e-05, + "loss": 3.6481, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879275441032048e-05, + "loss": 3.6532, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878436846280996e-05, + "loss": 3.6556, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877598251529944e-05, + "loss": 3.6552, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876759656778892e-05, + "loss": 3.6528, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.87592106202784e-05, + "loss": 3.6567, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8486855030059814, + "eval_runtime": 316.2396, + "eval_samples_per_second": 1206.652, + "eval_steps_per_second": 37.709, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875082467276788e-05, + "loss": 3.6427, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742438725257366e-05, + "loss": 3.64, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734069156550575e-05, + "loss": 3.6464, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725683209040055e-05, + "loss": 3.656, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717297261529535e-05, + "loss": 3.6604, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708911314019015e-05, + "loss": 3.6456, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.8700541745312224e-05, + "loss": 3.6501, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.8692155797801704e-05, + "loss": 3.6486, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.8683769850291184e-05, + "loss": 3.6527, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8675383902780664e-05, + "loss": 3.6586, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866701433407387e-05, + "loss": 3.639, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865862838656335e-05, + "loss": 3.6409, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865025881785657e-05, + "loss": 3.6591, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864187287034605e-05, + "loss": 3.6375, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863348692283553e-05, + "loss": 3.6427, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862510097532501e-05, + "loss": 3.6374, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861673140661822e-05, + "loss": 3.636, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.86083454591077e-05, + "loss": 3.6416, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859995951159718e-05, + "loss": 3.6348, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859157356408666e-05, + "loss": 3.6502, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858318761657614e-05, + "loss": 3.6526, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857481804786935e-05, + "loss": 3.6498, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566432100358827e-05, + "loss": 3.6391, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558046152848307e-05, + "loss": 3.6422, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549660205337787e-05, + "loss": 3.6473, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854127425782727e-05, + "loss": 3.6413, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853288831031675e-05, + "loss": 3.6395, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852450236280623e-05, + "loss": 3.6529, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.8516116415295706e-05, + "loss": 3.6378, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850774684658892e-05, + "loss": 3.6372, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.84993608990784e-05, + "loss": 3.638, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849097495156788e-05, + "loss": 3.6503, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482589004057355e-05, + "loss": 3.6488, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847421943535057e-05, + "loss": 3.6572, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846583348784005e-05, + "loss": 3.6339, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457447540329524e-05, + "loss": 3.6438, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844906159281901e-05, + "loss": 3.6524, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844069202411223e-05, + "loss": 3.629, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432322455405436e-05, + "loss": 3.6371, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423936507894916e-05, + "loss": 3.6366, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415550560384396e-05, + "loss": 3.6406, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407164612873876e-05, + "loss": 3.6404, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398778665363356e-05, + "loss": 3.6438, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839039271785283e-05, + "loss": 3.6445, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838200677034231e-05, + "loss": 3.6375, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373637201635525e-05, + "loss": 3.6403, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365251254125e-05, + "loss": 3.6396, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835686530661448e-05, + "loss": 3.6401, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348479359103965e-05, + "loss": 3.6113, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834010979039718e-05, + "loss": 3.655, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833174022169039e-05, + "loss": 3.6356, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832335427417987e-05, + "loss": 3.6444, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831496832666935e-05, + "loss": 3.6335, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830658237915883e-05, + "loss": 3.6372, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829821281045204e-05, + "loss": 3.6245, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828982686294152e-05, + "loss": 3.6306, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281440915431e-05, + "loss": 3.6472, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827305496792047e-05, + "loss": 3.6307, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826466902040995e-05, + "loss": 3.6441, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825628307289943e-05, + "loss": 3.6384, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824791350419265e-05, + "loss": 3.6246, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823952755668213e-05, + "loss": 3.6483, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823114160917161e-05, + "loss": 3.6227, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822275566166109e-05, + "loss": 3.6276, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821436971415057e-05, + "loss": 3.6417, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820598376664005e-05, + "loss": 3.6355, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819759781912953e-05, + "loss": 3.6239, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818921187161901e-05, + "loss": 3.6379, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180842302912216e-05, + "loss": 3.6195, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172456355401696e-05, + "loss": 3.6415, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164086786694905e-05, + "loss": 3.6423, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155700839184385e-05, + "loss": 3.6359, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814731489167387e-05, + "loss": 3.6407, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813892894416335e-05, + "loss": 3.643, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813054299665283e-05, + "loss": 3.6512, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812215704914231e-05, + "loss": 3.6299, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811377110163179e-05, + "loss": 3.6372, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810538515412127e-05, + "loss": 3.642, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809701558541448e-05, + "loss": 3.6125, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808862963790396e-05, + "loss": 3.6405, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808024369039344e-05, + "loss": 3.6395, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807185774288292e-05, + "loss": 3.6381, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806348817417613e-05, + "loss": 3.65, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805511860546934e-05, + "loss": 3.6243, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046732657958826e-05, + "loss": 3.6298, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038346710448306e-05, + "loss": 3.6346, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029960762937786e-05, + "loss": 3.6385, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021574815427266e-05, + "loss": 3.6337, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013188867916746e-05, + "loss": 3.6296, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004802920406225e-05, + "loss": 3.6282, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996433351699435e-05, + "loss": 3.6358, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7988047404188915e-05, + "loss": 3.6291, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979661456678394e-05, + "loss": 3.6315, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971291887971604e-05, + "loss": 3.6438, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962905940461084e-05, + "loss": 3.635, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954519992950563e-05, + "loss": 3.637, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946134045440043e-05, + "loss": 3.6235, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937748097929523e-05, + "loss": 3.6319, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929362150419e-05, + "loss": 3.6322, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792099258171222e-05, + "loss": 3.6395, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.79126066342017e-05, + "loss": 3.6313, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790422068669118e-05, + "loss": 3.6309, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789583473918066e-05, + "loss": 3.6335, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788744879167013e-05, + "loss": 3.6347, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787906284415961e-05, + "loss": 3.6206, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787067689664909e-05, + "loss": 3.6335, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786229094913857e-05, + "loss": 3.62, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785392138043178e-05, + "loss": 3.6378, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845551811725e-05, + "loss": 3.6248, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783716586421448e-05, + "loss": 3.6263, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782877991670396e-05, + "loss": 3.6194, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782039396919344e-05, + "loss": 3.6374, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781200802168292e-05, + "loss": 3.6314, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.78036220741724e-05, + "loss": 3.6252, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779523612666188e-05, + "loss": 3.6343, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778685017915136e-05, + "loss": 3.6425, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77784969892483e-05, + "loss": 3.6399, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777011104173778e-05, + "loss": 3.6258, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761725094227255e-05, + "loss": 3.6213, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753339146716735e-05, + "loss": 3.631, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774496957800995e-05, + "loss": 3.6323, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773658363049943e-05, + "loss": 3.6189, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772819768298891e-05, + "loss": 3.6202, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771981173547839e-05, + "loss": 3.637, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771142578796787e-05, + "loss": 3.6297, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770303984045735e-05, + "loss": 3.6296, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769467027175056e-05, + "loss": 3.6287, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768628432424004e-05, + "loss": 3.6283, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767789837672952e-05, + "loss": 3.6248, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669512429219e-05, + "loss": 3.6404, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766112648170848e-05, + "loss": 3.6259, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765274053419796e-05, + "loss": 3.6346, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764435458668744e-05, + "loss": 3.618, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763596863917692e-05, + "loss": 3.6452, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627599070470135e-05, + "loss": 3.6238, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619213122959615e-05, + "loss": 3.6431, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610843554252824e-05, + "loss": 3.629, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602457606742304e-05, + "loss": 3.6338, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594071659231784e-05, + "loss": 3.6235, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585685711721264e-05, + "loss": 3.6488, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577299764210744e-05, + "loss": 3.6244, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568913816700224e-05, + "loss": 3.6364, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560527869189704e-05, + "loss": 3.6336, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755215830048291e-05, + "loss": 3.6249, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754378873177612e-05, + "loss": 3.6308, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.75354027842656e-05, + "loss": 3.6304, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752701683675509e-05, + "loss": 3.6308, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751863088924457e-05, + "loss": 3.6309, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751024494173405e-05, + "loss": 3.6334, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8458807468414307, + "eval_runtime": 315.3201, + "eval_samples_per_second": 1210.17, + "eval_steps_per_second": 37.819, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750185899422353e-05, + "loss": 3.6245, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749347304671301e-05, + "loss": 3.6185, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748508709920249e-05, + "loss": 3.6247, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747670115169197e-05, + "loss": 3.6301, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746831520418144e-05, + "loss": 3.64, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745992925667092e-05, + "loss": 3.623, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74515433091604e-05, + "loss": 3.6248, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744315736164988e-05, + "loss": 3.6256, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743478779294309e-05, + "loss": 3.6283, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742640184543257e-05, + "loss": 3.6329, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741801589792206e-05, + "loss": 3.6187, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740962995041154e-05, + "loss": 3.6213, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740127676050848e-05, + "loss": 3.6372, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739289081299796e-05, + "loss": 3.6126, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738450486548744e-05, + "loss": 3.6215, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376118917976916e-05, + "loss": 3.6112, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736774934927013e-05, + "loss": 3.6154, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735936340175961e-05, + "loss": 3.6184, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735097745424909e-05, + "loss": 3.6102, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342591506738564e-05, + "loss": 3.6278, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334205559228044e-05, + "loss": 3.6292, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732583599052126e-05, + "loss": 3.6265, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731745004301074e-05, + "loss": 3.6181, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730906409550022e-05, + "loss": 3.6219, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.73006781479897e-05, + "loss": 3.626, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729229220047918e-05, + "loss": 3.6166, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728390625296866e-05, + "loss": 3.6121, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727552030545814e-05, + "loss": 3.6323, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726713435794762e-05, + "loss": 3.6175, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725876478924083e-05, + "loss": 3.6168, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725037884173031e-05, + "loss": 3.6165, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724199289421979e-05, + "loss": 3.6272, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723360694670927e-05, + "loss": 3.6197, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722523737800248e-05, + "loss": 3.6372, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721685143049196e-05, + "loss": 3.6139, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208465482981445e-05, + "loss": 3.6161, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200079535470925e-05, + "loss": 3.6342, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191709966764134e-05, + "loss": 3.6035, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718334039805734e-05, + "loss": 3.616, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717495445054682e-05, + "loss": 3.6154, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.71665685030363e-05, + "loss": 3.6123, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715818255552578e-05, + "loss": 3.619, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714979660801526e-05, + "loss": 3.6202, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714141066050474e-05, + "loss": 3.6246, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713302471299422e-05, + "loss": 3.6132, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246387654837e-05, + "loss": 3.622, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711626919677691e-05, + "loss": 3.6113, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.71078832492664e-05, + "loss": 3.6211, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709949730175588e-05, + "loss": 3.5892, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709112773304909e-05, + "loss": 3.6269, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082758164342297e-05, + "loss": 3.6148, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074372216831777e-05, + "loss": 3.6218, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065986269321256e-05, + "loss": 3.6138, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057600321810736e-05, + "loss": 3.6142, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7049230753103946e-05, + "loss": 3.6009, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040844805593425e-05, + "loss": 3.6076, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032458858082905e-05, + "loss": 3.6271, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024072910572385e-05, + "loss": 3.6056, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015686963061865e-05, + "loss": 3.6201, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700730101555135e-05, + "loss": 3.6211, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699893144684456e-05, + "loss": 3.5983, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699054549933404e-05, + "loss": 3.6237, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698215955182352e-05, + "loss": 3.6054, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973773604313e-05, + "loss": 3.6051, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696538765680248e-05, + "loss": 3.6176, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695700170929196e-05, + "loss": 3.6137, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694861576178144e-05, + "loss": 3.6031, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694022981427092e-05, + "loss": 3.6149, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693186024556413e-05, + "loss": 3.6016, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692347429805361e-05, + "loss": 3.615, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691510472934682e-05, + "loss": 3.6191, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906718781836306e-05, + "loss": 3.6158, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898332834325786e-05, + "loss": 3.6188, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889946886815266e-05, + "loss": 3.6214, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881560939304746e-05, + "loss": 3.6283, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873191370597955e-05, + "loss": 3.6086, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864805423087435e-05, + "loss": 3.6193, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856419475576915e-05, + "loss": 3.616, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6848033528066395e-05, + "loss": 3.5953, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839663959359604e-05, + "loss": 3.6169, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831278011849084e-05, + "loss": 3.6181, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822892064338564e-05, + "loss": 3.614, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814506116828044e-05, + "loss": 3.6283, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806120169317523e-05, + "loss": 3.6008, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797734221807003e-05, + "loss": 3.6048, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789348274296483e-05, + "loss": 3.6144, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678096232678596e-05, + "loss": 3.6155, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677259275807917e-05, + "loss": 3.6142, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676420681056865e-05, + "loss": 3.6075, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675582086305813e-05, + "loss": 3.6021, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674743491554761e-05, + "loss": 3.6119, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673906534684082e-05, + "loss": 3.6114, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.67306793993303e-05, + "loss": 3.6087, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672230983062352e-05, + "loss": 3.619, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713923883113e-05, + "loss": 3.6199, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670553793560248e-05, + "loss": 3.6096, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669715198809196e-05, + "loss": 3.6034, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668876604058144e-05, + "loss": 3.6092, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668038009307092e-05, + "loss": 3.6091, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672010524364126e-05, + "loss": 3.6193, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663624576853606e-05, + "loss": 3.6103, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655238629343086e-05, + "loss": 3.6079, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646852681832566e-05, + "loss": 3.6104, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638466734322046e-05, + "loss": 3.6064, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630080786811526e-05, + "loss": 3.6045, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621694839301006e-05, + "loss": 3.6096, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613308891790486e-05, + "loss": 3.5969, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604939323083695e-05, + "loss": 3.6188, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659656975437691e-05, + "loss": 3.6052, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658818380686639e-05, + "loss": 3.601, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657979785935587e-05, + "loss": 3.5995, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657141191184535e-05, + "loss": 3.6163, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656302596433483e-05, + "loss": 3.612, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655464001682431e-05, + "loss": 3.6028, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654627044811752e-05, + "loss": 3.6142, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537884500607e-05, + "loss": 3.6222, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652949855309648e-05, + "loss": 3.6163, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652111260558596e-05, + "loss": 3.605, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651274303687917e-05, + "loss": 3.6035, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650435708936865e-05, + "loss": 3.6076, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649597114185813e-05, + "loss": 3.6144, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487585194347615e-05, + "loss": 3.5971, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479199246837095e-05, + "loss": 3.5985, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470813299326575e-05, + "loss": 3.6165, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462427351816055e-05, + "loss": 3.6081, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454041404305535e-05, + "loss": 3.6072, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445671835598744e-05, + "loss": 3.6112, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437285888088224e-05, + "loss": 3.6044, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428899940577704e-05, + "loss": 3.6068, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642051399306718e-05, + "loss": 3.6195, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641214442436039e-05, + "loss": 3.6054, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640375847684987e-05, + "loss": 3.6134, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639537252933935e-05, + "loss": 3.5956, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638698658182883e-05, + "loss": 3.6152, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637860063431831e-05, + "loss": 3.6112, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637021468680779e-05, + "loss": 3.6175, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636184511810101e-05, + "loss": 3.6103, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635345917059048e-05, + "loss": 3.6086, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634507322307996e-05, + "loss": 3.6099, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633668727556944e-05, + "loss": 3.6222, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632830132805892e-05, + "loss": 3.6054, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631993175935213e-05, + "loss": 3.6125, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631154581184161e-05, + "loss": 3.6156, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630315986433109e-05, + "loss": 3.6038, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629477391682057e-05, + "loss": 3.6082, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628640434811379e-05, + "loss": 3.613, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627801840060327e-05, + "loss": 3.6088, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269632453092747e-05, + "loss": 3.6092, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261246505582227e-05, + "loss": 3.6091, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8445067405700684, + "eval_runtime": 306.7063, + "eval_samples_per_second": 1244.158, + "eval_steps_per_second": 38.881, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252860558071707e-05, + "loss": 3.5972, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244474610561186e-05, + "loss": 3.5997, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236088663050666e-05, + "loss": 3.6045, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227719094343876e-05, + "loss": 3.6094, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219333146833355e-05, + "loss": 3.6153, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210947199322835e-05, + "loss": 3.604, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202561251812315e-05, + "loss": 3.6023, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194175304301795e-05, + "loss": 3.6043, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185789356791275e-05, + "loss": 3.6069, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177403409280755e-05, + "loss": 3.6099, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616903384057397e-05, + "loss": 3.6023, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616064789306345e-05, + "loss": 3.5974, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615226194555293e-05, + "loss": 3.6139, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614387599804241e-05, + "loss": 3.5942, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613549005053189e-05, + "loss": 3.6023, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.61271204818251e-05, + "loss": 3.5877, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611873453431458e-05, + "loss": 3.597, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611034858680406e-05, + "loss": 3.599, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610196263929354e-05, + "loss": 3.5872, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609357669178301e-05, + "loss": 3.606, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608519074427249e-05, + "loss": 3.606, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607682117556571e-05, + "loss": 3.6008, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606843522805519e-05, + "loss": 3.5974, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606004928054467e-05, + "loss": 3.6005, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605166333303415e-05, + "loss": 3.6069, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604327738552363e-05, + "loss": 3.5996, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603489143801311e-05, + "loss": 3.5869, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602650549050259e-05, + "loss": 3.6137, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601811954299207e-05, + "loss": 3.594, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600974997428528e-05, + "loss": 3.5935, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600136402677476e-05, + "loss": 3.6018, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599299445806797e-05, + "loss": 3.6036, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598460851055745e-05, + "loss": 3.5989, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597622256304693e-05, + "loss": 3.6151, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596783661553641e-05, + "loss": 3.5932, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595946704682962e-05, + "loss": 3.5977, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.59510810993191e-05, + "loss": 3.6113, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594269515180858e-05, + "loss": 3.5827, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593430920429806e-05, + "loss": 3.5939, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592593963559127e-05, + "loss": 3.5956, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591755368808075e-05, + "loss": 3.5923, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590916774057023e-05, + "loss": 3.6005, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590078179305971e-05, + "loss": 3.5982, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589239584554919e-05, + "loss": 3.6016, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588400989803867e-05, + "loss": 3.5956, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587562395052815e-05, + "loss": 3.6, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586723800301763e-05, + "loss": 3.5906, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585886843431085e-05, + "loss": 3.6036, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850498865604056e-05, + "loss": 3.5692, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842112918093536e-05, + "loss": 3.5998, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833726970583016e-05, + "loss": 3.5967, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825341023072496e-05, + "loss": 3.6043, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816955075561976e-05, + "loss": 3.5883, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808585506855185e-05, + "loss": 3.5966, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800199559344665e-05, + "loss": 3.5825, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791813611834145e-05, + "loss": 3.5865, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783427664323625e-05, + "loss": 3.6088, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775041716813105e-05, + "loss": 3.5817, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766655769302585e-05, + "loss": 3.6001, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758269821792065e-05, + "loss": 3.6019, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574990025308528e-05, + "loss": 3.5731, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574151430557476e-05, + "loss": 3.6068, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573312835806424e-05, + "loss": 3.5863, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572474241055372e-05, + "loss": 3.5847, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571637284184693e-05, + "loss": 3.5958, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570798689433641e-05, + "loss": 3.5964, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569960094682589e-05, + "loss": 3.5826, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569121499931537e-05, + "loss": 3.5948, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568282905180485e-05, + "loss": 3.5794, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567444310429432e-05, + "loss": 3.5974, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566607353558754e-05, + "loss": 3.6007, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565768758807702e-05, + "loss": 3.5969, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.56493016405665e-05, + "loss": 3.5971, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564091569305598e-05, + "loss": 3.5972, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632546124349194e-05, + "loss": 3.61, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.5624160176838674e-05, + "loss": 3.586, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561577422932815e-05, + "loss": 3.6016, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560738828181763e-05, + "loss": 3.5903, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559900233430711e-05, + "loss": 3.5814, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559063276560032e-05, + "loss": 3.5959, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582246818089796e-05, + "loss": 3.5976, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573860870579276e-05, + "loss": 3.5957, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565474923068756e-05, + "loss": 3.6102, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557088975558236e-05, + "loss": 3.5789, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554870302804772e-05, + "loss": 3.5884, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.55403170805372e-05, + "loss": 3.5949, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553193113302668e-05, + "loss": 3.5961, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552356156431989e-05, + "loss": 3.5912, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551517561680937e-05, + "loss": 3.5844, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550678966929885e-05, + "loss": 3.5876, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549842010059206e-05, + "loss": 3.5913, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549003415308154e-05, + "loss": 3.5931, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548164820557102e-05, + "loss": 3.5874, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.54732622580605e-05, + "loss": 3.6007, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546487631054998e-05, + "loss": 3.5994, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545649036303946e-05, + "loss": 3.5917, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544810441552894e-05, + "loss": 3.5851, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439734846822157e-05, + "loss": 3.5919, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431348899311636e-05, + "loss": 3.5897, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422962951801116e-05, + "loss": 3.5961, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414577004290596e-05, + "loss": 3.5898, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406191056780076e-05, + "loss": 3.5867, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397821488073285e-05, + "loss": 3.5931, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389435540562765e-05, + "loss": 3.5885, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381049593052245e-05, + "loss": 3.5892, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372663645541725e-05, + "loss": 3.5872, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364294076834934e-05, + "loss": 3.5802, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355908129324414e-05, + "loss": 3.5951, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347522181813894e-05, + "loss": 3.5882, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339136234303374e-05, + "loss": 3.5798, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330750286792854e-05, + "loss": 3.5785, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322364339282334e-05, + "loss": 3.5929, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313978391771814e-05, + "loss": 3.5938, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305592444261294e-05, + "loss": 3.5839, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529723925435824e-05, + "loss": 3.5955, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528885330684772e-05, + "loss": 3.6048, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.52804673593372e-05, + "loss": 3.5911, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527208141182668e-05, + "loss": 3.5863, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526371184311989e-05, + "loss": 3.5854, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525532589560937e-05, + "loss": 3.5883, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524693994809885e-05, + "loss": 3.5965, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523855400058833e-05, + "loss": 3.5798, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523016805307781e-05, + "loss": 3.5786, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221798484371024e-05, + "loss": 3.5928, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213412536860504e-05, + "loss": 3.5857, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205026589349984e-05, + "loss": 3.5901, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519664064183946e-05, + "loss": 3.5904, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518825469432894e-05, + "loss": 3.584, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517988512562215e-05, + "loss": 3.5847, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517149917811163e-05, + "loss": 3.5997, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163113230601106e-05, + "loss": 3.5861, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154727283090586e-05, + "loss": 3.5958, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146341335580066e-05, + "loss": 3.5795, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137955388069546e-05, + "loss": 3.5934, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512958581936276e-05, + "loss": 3.5933, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512119987185224e-05, + "loss": 3.5942, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511281392434172e-05, + "loss": 3.5964, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.51044279768312e-05, + "loss": 3.588, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509604202932068e-05, + "loss": 3.5912, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508765608181016e-05, + "loss": 3.6029, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507927013429964e-05, + "loss": 3.5867, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507090056559285e-05, + "loss": 3.5916, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506251461808233e-05, + "loss": 3.5945, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505412867057181e-05, + "loss": 3.5842, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504574272306129e-05, + "loss": 3.5865, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.50373731543545e-05, + "loss": 3.598, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028987206843986e-05, + "loss": 3.5847, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020601259333466e-05, + "loss": 3.5923, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012215311822946e-05, + "loss": 3.5914, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.843557357788086, + "eval_runtime": 306.1211, + "eval_samples_per_second": 1246.536, + "eval_steps_per_second": 38.955, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003829364312426e-05, + "loss": 3.592, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995443416801906e-05, + "loss": 3.5776, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987057469291386e-05, + "loss": 3.5841, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978671521780866e-05, + "loss": 3.5932, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970301953074075e-05, + "loss": 3.5898, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961916005563555e-05, + "loss": 3.5883, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953530058053035e-05, + "loss": 3.5884, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945144110542515e-05, + "loss": 3.5852, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493675816303199e-05, + "loss": 3.585, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492837221552147e-05, + "loss": 3.5912, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.5874, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911616699304164e-05, + "loss": 3.576, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903230751793644e-05, + "loss": 3.5959, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894844804283124e-05, + "loss": 3.5759, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886458856772604e-05, + "loss": 3.5791, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487808928806582e-05, + "loss": 3.5718, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486970334055529e-05, + "loss": 3.5777, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486131739304477e-05, + "loss": 3.5765, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485293144553425e-05, + "loss": 3.5714, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484454549802373e-05, + "loss": 3.5804, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.5909, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.5839, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.5745, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481101808678539e-05, + "loss": 3.5831, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480263213927487e-05, + "loss": 3.59, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479424619176435e-05, + "loss": 3.5765, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478586024425383e-05, + "loss": 3.5715, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477747429674331e-05, + "loss": 3.5942, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476910472803652e-05, + "loss": 3.577, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760718780526e-05, + "loss": 3.5738, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475233283301548e-05, + "loss": 3.5802, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474394688550496e-05, + "loss": 3.584, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735577316798166e-05, + "loss": 3.5858, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727191369287646e-05, + "loss": 3.5991, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718805421777126e-05, + "loss": 3.5704, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710419474266606e-05, + "loss": 3.5863, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702033526756086e-05, + "loss": 3.5923, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.46936639580493e-05, + "loss": 3.561, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468527801053878e-05, + "loss": 3.5783, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467689206302826e-05, + "loss": 3.5791, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466850611551774e-05, + "loss": 3.5701, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466012016800722e-05, + "loss": 3.5859, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465175059930043e-05, + "loss": 3.5771, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464336465178991e-05, + "loss": 3.5849, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463497870427939e-05, + "loss": 3.5751, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462659275676887e-05, + "loss": 3.5811, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461820680925835e-05, + "loss": 3.5706, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609820861747824e-05, + "loss": 3.5872, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460143491423731e-05, + "loss": 3.5535, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459304896672679e-05, + "loss": 3.582, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584679398020006e-05, + "loss": 3.5772, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457629345050948e-05, + "loss": 3.588, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456790750299896e-05, + "loss": 3.5687, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455952155548844e-05, + "loss": 3.5726, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551151986781655e-05, + "loss": 3.5683, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454276603927113e-05, + "loss": 3.5692, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453438009176061e-05, + "loss": 3.5911, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452599414425009e-05, + "loss": 3.5621, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451760819673957e-05, + "loss": 3.586, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450923862803278e-05, + "loss": 3.5828, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4500852680522264e-05, + "loss": 3.5578, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492466733011744e-05, + "loss": 3.5865, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484080785501224e-05, + "loss": 3.5646, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447571121679443e-05, + "loss": 3.5662, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446732526928391e-05, + "loss": 3.5769, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445893932177339e-05, + "loss": 3.5796, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445055337426287e-05, + "loss": 3.5637, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444218380555608e-05, + "loss": 3.5786, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443379785804556e-05, + "loss": 3.5605, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442541191053504e-05, + "loss": 3.5752, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441702596302452e-05, + "loss": 3.5846, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440865639431773e-05, + "loss": 3.5764, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440027044680722e-05, + "loss": 3.5813, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.43918844992967e-05, + "loss": 3.5777, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438349855178618e-05, + "loss": 3.5913, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437511260427566e-05, + "loss": 3.5699, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436672665676514e-05, + "loss": 3.5835, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435835708805835e-05, + "loss": 3.5721, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434997114054783e-05, + "loss": 3.5592, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434158519303731e-05, + "loss": 3.5775, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433319924552679e-05, + "loss": 3.5802, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324813298016267e-05, + "loss": 3.58, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316443729309476e-05, + "loss": 3.589, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308057781798956e-05, + "loss": 3.5666, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299671834288436e-05, + "loss": 3.5652, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291285886777916e-05, + "loss": 3.5735, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282899939267396e-05, + "loss": 3.5841, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427453037056061e-05, + "loss": 3.5731, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426614442305009e-05, + "loss": 3.5667, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425775847553957e-05, + "loss": 3.5716, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424937252802905e-05, + "loss": 3.573, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424100295932226e-05, + "loss": 3.5725, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423261701181174e-05, + "loss": 3.5717, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422423106430122e-05, + "loss": 3.5813, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.42158451167907e-05, + "loss": 3.5801, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420747554808391e-05, + "loss": 3.5743, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419908960057339e-05, + "loss": 3.5667, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419070365306287e-05, + "loss": 3.5713, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418231770555235e-05, + "loss": 3.5731, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173948136845565e-05, + "loss": 3.5827, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165562189335045e-05, + "loss": 3.5695, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157176241824525e-05, + "loss": 3.5697, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148790294314005e-05, + "loss": 3.5754, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140420725607214e-05, + "loss": 3.5692, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132034778096694e-05, + "loss": 3.5741, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123648830586174e-05, + "loss": 3.57, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115262883075654e-05, + "loss": 3.5597, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106876935565134e-05, + "loss": 3.5797, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409850736685834e-05, + "loss": 3.568, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409012141934782e-05, + "loss": 3.5657, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.40817354718373e-05, + "loss": 3.5594, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407334952432679e-05, + "loss": 3.5753, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406496357681626e-05, + "loss": 3.5768, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405657762930574e-05, + "loss": 3.5625, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404820806059896e-05, + "loss": 3.5784, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403982211308843e-05, + "loss": 3.5818, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403143616557791e-05, + "loss": 3.5803, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402305021806739e-05, + "loss": 3.5699, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401466427055687e-05, + "loss": 3.5678, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400629470185008e-05, + "loss": 3.5687, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790875433956e-05, + "loss": 3.5794, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398952280682904e-05, + "loss": 3.5602, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398113685931853e-05, + "loss": 3.5668, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397275091180801e-05, + "loss": 3.5676, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3964381343101216e-05, + "loss": 3.5707, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955995395590696e-05, + "loss": 3.5726, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947609448080176e-05, + "loss": 3.5744, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939223500569656e-05, + "loss": 3.5633, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930853931862865e-05, + "loss": 3.5674, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922467984352345e-05, + "loss": 3.5843, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914082036841825e-05, + "loss": 3.5673, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905696089331305e-05, + "loss": 3.5782, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897326520624514e-05, + "loss": 3.5577, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888940573113994e-05, + "loss": 3.5773, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388055462560348e-05, + "loss": 3.5755, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387216867809296e-05, + "loss": 3.5754, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386378273058244e-05, + "loss": 3.5781, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385541316187565e-05, + "loss": 3.5672, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384702721436513e-05, + "loss": 3.577, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383864126685461e-05, + "loss": 3.5842, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383025531934409e-05, + "loss": 3.5699, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.38218857506373e-05, + "loss": 3.5724, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381349980312678e-05, + "loss": 3.5776, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380511385561626e-05, + "loss": 3.5673, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379672790810574e-05, + "loss": 3.5693, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378835833939895e-05, + "loss": 3.5833, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779972391888435e-05, + "loss": 3.568, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771586444377915e-05, + "loss": 3.5749, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763200496867395e-05, + "loss": 3.5693, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8437399864196777, + "eval_runtime": 304.1822, + "eval_samples_per_second": 1254.482, + "eval_steps_per_second": 39.203, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3754814549356875e-05, + "loss": 3.5642, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746444980650084e-05, + "loss": 3.5599, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738059033139564e-05, + "loss": 3.5685, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729673085629044e-05, + "loss": 3.5759, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721287138118524e-05, + "loss": 3.5726, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371291756941173e-05, + "loss": 3.5723, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370453162190121e-05, + "loss": 3.5653, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369614567439069e-05, + "loss": 3.5691, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368775972688017e-05, + "loss": 3.5679, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367939015817339e-05, + "loss": 3.5796, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367100421066287e-05, + "loss": 3.564, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366261826315235e-05, + "loss": 3.5599, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365423231564183e-05, + "loss": 3.5783, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364584636813131e-05, + "loss": 3.5548, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363747679942452e-05, + "loss": 3.5625, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629090851914e-05, + "loss": 3.554, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362070490440348e-05, + "loss": 3.5624, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361231895689296e-05, + "loss": 3.5587, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360393300938244e-05, + "loss": 3.5585, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359554706187192e-05, + "loss": 3.5603, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587177493165126e-05, + "loss": 3.5758, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357880792445834e-05, + "loss": 3.5654, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357042197694782e-05, + "loss": 3.5599, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.35620360294373e-05, + "loss": 3.5662, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355365008192678e-05, + "loss": 3.5727, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354526413441626e-05, + "loss": 3.5579, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353687818690574e-05, + "loss": 3.5556, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528492239395215e-05, + "loss": 3.5775, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520106291884695e-05, + "loss": 3.5577, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351173672317791e-05, + "loss": 3.5574, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350335077566739e-05, + "loss": 3.5623, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3494964828156864e-05, + "loss": 3.5608, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486578880646344e-05, + "loss": 3.5723, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347820931193956e-05, + "loss": 3.5759, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346982336442904e-05, + "loss": 3.5589, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346143741691852e-05, + "loss": 3.5631, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453051469408e-05, + "loss": 3.575, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344466552189748e-05, + "loss": 3.5466, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343629595319069e-05, + "loss": 3.5668, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342791000568017e-05, + "loss": 3.5567, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341952405816965e-05, + "loss": 3.5518, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341113811065913e-05, + "loss": 3.5669, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340276854195234e-05, + "loss": 3.5668, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339438259444182e-05, + "loss": 3.565, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.33859966469313e-05, + "loss": 3.5568, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337761069942078e-05, + "loss": 3.5608, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369241130713993e-05, + "loss": 3.5598, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336085518320347e-05, + "loss": 3.565, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335246923569295e-05, + "loss": 3.5396, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334408328818243e-05, + "loss": 3.563, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333569734067191e-05, + "loss": 3.5615, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332732777196512e-05, + "loss": 3.5698, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.33189418244546e-05, + "loss": 3.5531, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331055587694408e-05, + "loss": 3.5565, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330216992943356e-05, + "loss": 3.549, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329380036072677e-05, + "loss": 3.5535, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328541441321625e-05, + "loss": 3.573, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327702846570573e-05, + "loss": 3.5408, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326864251819521e-05, + "loss": 3.5713, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.32602565706847e-05, + "loss": 3.5655, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325188700197791e-05, + "loss": 3.5438, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324350105446739e-05, + "loss": 3.5683, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323511510695687e-05, + "loss": 3.545, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322672915944635e-05, + "loss": 3.5475, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218359590739556e-05, + "loss": 3.558, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3209973643229036e-05, + "loss": 3.5632, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201587695718516e-05, + "loss": 3.5444, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193201748207996e-05, + "loss": 3.5671, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184815800697476e-05, + "loss": 3.5418, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176429853186956e-05, + "loss": 3.5561, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168060284480165e-05, + "loss": 3.5685, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315967433696965e-05, + "loss": 3.5598, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315128838945913e-05, + "loss": 3.5657, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314290244194861e-05, + "loss": 3.5652, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313453287324182e-05, + "loss": 3.5734, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.31261469257313e-05, + "loss": 3.5536, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311776097822078e-05, + "loss": 3.5671, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310937503071026e-05, + "loss": 3.5504, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310100546200347e-05, + "loss": 3.5483, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309261951449295e-05, + "loss": 3.5599, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308423356698243e-05, + "loss": 3.558, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307584761947191e-05, + "loss": 3.5634, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306746167196139e-05, + "loss": 3.5728, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3059092103254605e-05, + "loss": 3.5544, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050706155744085e-05, + "loss": 3.5436, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042320208233565e-05, + "loss": 3.5558, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3033934260723045e-05, + "loss": 3.5673, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025564692016254e-05, + "loss": 3.5539, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017178744505734e-05, + "loss": 3.5493, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3008792796995214e-05, + "loss": 3.5559, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000406849484694e-05, + "loss": 3.5512, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.29920372807779e-05, + "loss": 3.5575, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298365133326738e-05, + "loss": 3.5531, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297526538575686e-05, + "loss": 3.5656, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296687943824634e-05, + "loss": 3.5667, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295850986953956e-05, + "loss": 3.5545, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295012392202904e-05, + "loss": 3.5516, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294173797451852e-05, + "loss": 3.5548, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933352027008e-05, + "loss": 3.5591, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292498245830121e-05, + "loss": 3.5645, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291659651079069e-05, + "loss": 3.5543, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290821056328017e-05, + "loss": 3.55, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289982461576964e-05, + "loss": 3.5623, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289145504706286e-05, + "loss": 3.5529, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288306909955234e-05, + "loss": 3.5526, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287468315204182e-05, + "loss": 3.554, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.28662972045313e-05, + "loss": 3.547, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285792763582451e-05, + "loss": 3.5605, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284954168831399e-05, + "loss": 3.555, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284115574080347e-05, + "loss": 3.548, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2832769793292946e-05, + "loss": 3.543, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824383845782426e-05, + "loss": 3.5569, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281601427707564e-05, + "loss": 3.5632, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807628329565115e-05, + "loss": 3.5503, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799242382054595e-05, + "loss": 3.5589, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2790856434544075e-05, + "loss": 3.5614, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278248686583729e-05, + "loss": 3.5661, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774100918326764e-05, + "loss": 3.5552, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276571497081625e-05, + "loss": 3.5479, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275732902330573e-05, + "loss": 3.5536, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748959454598946e-05, + "loss": 3.5608, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274057350708842e-05, + "loss": 3.5428, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.27321875595779e-05, + "loss": 3.5497, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272380161206738e-05, + "loss": 3.5506, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271543204336059e-05, + "loss": 3.5523, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270704609585007e-05, + "loss": 3.5542, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269866014833955e-05, + "loss": 3.5623, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269027420082903e-05, + "loss": 3.5442, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268190463212224e-05, + "loss": 3.5503, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267351868461172e-05, + "loss": 3.568, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.26651327371012e-05, + "loss": 3.5556, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656746789590684e-05, + "loss": 3.5603, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264837722088389e-05, + "loss": 3.5419, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.263999127337337e-05, + "loss": 3.5598, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263160532586285e-05, + "loss": 3.5595, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262321937835233e-05, + "loss": 3.5582, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261484980964554e-05, + "loss": 3.5573, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260646386213502e-05, + "loss": 3.5535, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.25980779146245e-05, + "loss": 3.566, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258969196711398e-05, + "loss": 3.5601, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258132239840719e-05, + "loss": 3.5596, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257293645089667e-05, + "loss": 3.553, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256455050338615e-05, + "loss": 3.5639, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255616455587564e-05, + "loss": 3.5541, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254779498716885e-05, + "loss": 3.5483, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253940903965833e-05, + "loss": 3.5676, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253102309214781e-05, + "loss": 3.5493, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522637144637287e-05, + "loss": 3.5645, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514267575930496e-05, + "loss": 3.5499, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8446083068847656, + "eval_runtime": 304.1942, + "eval_samples_per_second": 1254.432, + "eval_steps_per_second": 39.202, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505881628419976e-05, + "loss": 3.5417, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497495680909456e-05, + "loss": 3.5471, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489109733398936e-05, + "loss": 3.5516, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480723785888416e-05, + "loss": 3.5573, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472337838377895e-05, + "loss": 3.5574, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463968269671105e-05, + "loss": 3.5555, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245558232216059e-05, + "loss": 3.5466, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244719637465007e-05, + "loss": 3.55, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243881042713955e-05, + "loss": 3.5531, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243044085843276e-05, + "loss": 3.5617, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242205491092224e-05, + "loss": 3.5487, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241366896341172e-05, + "loss": 3.5488, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240529939470493e-05, + "loss": 3.5604, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239691344719441e-05, + "loss": 3.5415, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238852749968389e-05, + "loss": 3.545, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238014155217337e-05, + "loss": 3.5417, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237177198346658e-05, + "loss": 3.5497, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236338603595606e-05, + "loss": 3.5371, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355000088445545e-05, + "loss": 3.5404, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346614140935025e-05, + "loss": 3.5467, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338228193424505e-05, + "loss": 3.556, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2329858624717714e-05, + "loss": 3.5526, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321472677207194e-05, + "loss": 3.54, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2313086729696674e-05, + "loss": 3.5541, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2304700782186154e-05, + "loss": 3.5576, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229633121347936e-05, + "loss": 3.5416, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228794526596884e-05, + "loss": 3.5374, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227955931845832e-05, + "loss": 3.5583, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.22711733709478e-05, + "loss": 3.5377, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226280380224101e-05, + "loss": 3.545, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22544178547305e-05, + "loss": 3.5443, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224603190721998e-05, + "loss": 3.5478, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223764595970946e-05, + "loss": 3.5531, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222927639100267e-05, + "loss": 3.5591, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222089044349215e-05, + "loss": 3.5464, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221250449598163e-05, + "loss": 3.5481, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220411854847111e-05, + "loss": 3.5575, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219573260096059e-05, + "loss": 3.5325, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187363032253797e-05, + "loss": 3.5512, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2178977084743277e-05, + "loss": 3.5378, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170591137232756e-05, + "loss": 3.5405, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162205189722236e-05, + "loss": 3.5482, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215383562101545e-05, + "loss": 3.554, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214544967350493e-05, + "loss": 3.5456, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213706372599441e-05, + "loss": 3.5438, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212867777848389e-05, + "loss": 3.5454, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.21203082097771e-05, + "loss": 3.5416, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211192226226658e-05, + "loss": 3.5501, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210353631475606e-05, + "loss": 3.525, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209515036724554e-05, + "loss": 3.5462, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208678079853875e-05, + "loss": 3.5479, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207839485102823e-05, + "loss": 3.5551, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207000890351771e-05, + "loss": 3.5371, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206162295600719e-05, + "loss": 3.5389, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053253387300406e-05, + "loss": 3.5353, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044867439789886e-05, + "loss": 3.5351, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036481492279366e-05, + "loss": 3.5596, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028095544768846e-05, + "loss": 3.5296, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019725976062055e-05, + "loss": 3.5511, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011340028551535e-05, + "loss": 3.5487, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002954081041015e-05, + "loss": 3.5318, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994568133530495e-05, + "loss": 3.5495, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986198564823704e-05, + "loss": 3.5295, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977812617313184e-05, + "loss": 3.5317, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969426669802664e-05, + "loss": 3.5416, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961040722292144e-05, + "loss": 3.5487, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195267115358535e-05, + "loss": 3.5306, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194428520607484e-05, + "loss": 3.5534, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193589925856432e-05, + "loss": 3.5241, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192751331105379e-05, + "loss": 3.5428, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191914374234701e-05, + "loss": 3.5546, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191075779483649e-05, + "loss": 3.546, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190237184732596e-05, + "loss": 3.5466, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189398589981544e-05, + "loss": 3.5479, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188561633110866e-05, + "loss": 3.5576, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187723038359814e-05, + "loss": 3.5398, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186884443608761e-05, + "loss": 3.5542, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186045848857709e-05, + "loss": 3.5344, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852088919870307e-05, + "loss": 3.5308, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184370297235979e-05, + "loss": 3.5434, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835317024849266e-05, + "loss": 3.5447, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1826931077338746e-05, + "loss": 3.5465, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181856150863196e-05, + "loss": 3.5604, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810175561121435e-05, + "loss": 3.5423, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801789613610915e-05, + "loss": 3.5256, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793403666100395e-05, + "loss": 3.5431, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178503409739361e-05, + "loss": 3.5469, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776648149883084e-05, + "loss": 3.5397, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768262202372564e-05, + "loss": 3.5344, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759876254862044e-05, + "loss": 3.5423, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175150668615526e-05, + "loss": 3.5341, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174312073864474e-05, + "loss": 3.5454, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173473479113422e-05, + "loss": 3.5354, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17263488436237e-05, + "loss": 3.5477, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171797927491691e-05, + "loss": 3.5523, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170959332740639e-05, + "loss": 3.5414, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170120737989587e-05, + "loss": 3.5325, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169282143238535e-05, + "loss": 3.5403, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168445186367856e-05, + "loss": 3.5393, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167606591616804e-05, + "loss": 3.5493, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166767996865752e-05, + "loss": 3.5406, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659294021147e-05, + "loss": 3.536, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1650924452440214e-05, + "loss": 3.5421, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642538504929694e-05, + "loss": 3.5389, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634152557419174e-05, + "loss": 3.5399, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625766609908654e-05, + "loss": 3.5386, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161739704120186e-05, + "loss": 3.534, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160901109369134e-05, + "loss": 3.5416, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160062514618082e-05, + "loss": 3.5406, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.15922391986703e-05, + "loss": 3.5299, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158386962996351e-05, + "loss": 3.5279, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157548368245299e-05, + "loss": 3.5362, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156709773494247e-05, + "loss": 3.5516, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155871178743195e-05, + "loss": 3.5365, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155034221872517e-05, + "loss": 3.5416, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154195627121465e-05, + "loss": 3.5407, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153357032370413e-05, + "loss": 3.5557, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152518437619361e-05, + "loss": 3.5387, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516814807486816e-05, + "loss": 3.5331, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508428859976296e-05, + "loss": 3.5403, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500042912465776e-05, + "loss": 3.5413, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491656964955256e-05, + "loss": 3.5248, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483287396248465e-05, + "loss": 3.5351, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1474901448737945e-05, + "loss": 3.5368, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466515501227425e-05, + "loss": 3.5367, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458129553716905e-05, + "loss": 3.5328, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144975998501012e-05, + "loss": 3.5451, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.14413740374996e-05, + "loss": 3.5344, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143298808998908e-05, + "loss": 3.5374, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142460214247856e-05, + "loss": 3.5487, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141621619496804e-05, + "loss": 3.5405, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140784662626125e-05, + "loss": 3.5434, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139946067875073e-05, + "loss": 3.53, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139107473124021e-05, + "loss": 3.5428, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138268878372969e-05, + "loss": 3.5492, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.13743192150229e-05, + "loss": 3.5401, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136593326751238e-05, + "loss": 3.5452, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135754732000186e-05, + "loss": 3.5359, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349161372491346e-05, + "loss": 3.551, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1340791803784555e-05, + "loss": 3.5437, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332405856274035e-05, + "loss": 3.5436, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324019908763515e-05, + "loss": 3.5388, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315633961252995e-05, + "loss": 3.5448, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307264392546204e-05, + "loss": 3.5371, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298878445035684e-05, + "loss": 3.5332, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290492497525164e-05, + "loss": 3.5544, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282106550014644e-05, + "loss": 3.5332, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127373698130785e-05, + "loss": 3.5476, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126535103379733e-05, + "loss": 3.5373, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.845421314239502, + "eval_runtime": 304.8939, + "eval_samples_per_second": 1251.554, + "eval_steps_per_second": 39.112, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125696508628681e-05, + "loss": 3.5294, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.12485791387763e-05, + "loss": 3.5303, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124020957006951e-05, + "loss": 3.5348, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123182362255899e-05, + "loss": 3.5432, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122343767504847e-05, + "loss": 3.5407, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121505172753795e-05, + "loss": 3.5437, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120668215883116e-05, + "loss": 3.5316, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119829621132064e-05, + "loss": 3.5338, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118991026381012e-05, + "loss": 3.5377, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11815243162996e-05, + "loss": 3.548, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173154747592806e-05, + "loss": 3.5269, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164768800082286e-05, + "loss": 3.5342, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156382852571766e-05, + "loss": 3.5433, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114799690506125e-05, + "loss": 3.5302, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113962733635446e-05, + "loss": 3.5292, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113124138884394e-05, + "loss": 3.5287, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112285544133342e-05, + "loss": 3.5286, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.11144694938229e-05, + "loss": 3.5268, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110609992511611e-05, + "loss": 3.5284, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109771397760559e-05, + "loss": 3.5288, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108932803009507e-05, + "loss": 3.5438, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108094208258455e-05, + "loss": 3.5327, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107257251387776e-05, + "loss": 3.5287, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106418656636724e-05, + "loss": 3.5361, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105580061885672e-05, + "loss": 3.5463, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.10474146713462e-05, + "loss": 3.5245, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103902872383569e-05, + "loss": 3.5274, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103064277632517e-05, + "loss": 3.5393, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102225682881464e-05, + "loss": 3.5277, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1013887260107856e-05, + "loss": 3.5291, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005501312597336e-05, + "loss": 3.5271, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997115365086816e-05, + "loss": 3.5331, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098872941757629e-05, + "loss": 3.5371, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980359848869505e-05, + "loss": 3.5434, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0971973901358985e-05, + "loss": 3.5337, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096358795384846e-05, + "loss": 3.5304, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095520200633794e-05, + "loss": 3.5405, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946816058827424e-05, + "loss": 3.5203, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093844649012064e-05, + "loss": 3.5396, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930060542610114e-05, + "loss": 3.522, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921674595099593e-05, + "loss": 3.5256, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913288647589073e-05, + "loss": 3.53, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090491907888229e-05, + "loss": 3.5387, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089653313137176e-05, + "loss": 3.5317, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088814718386124e-05, + "loss": 3.5305, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087976123635072e-05, + "loss": 3.5282, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087139166764393e-05, + "loss": 3.5284, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086300572013341e-05, + "loss": 3.5367, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085461977262289e-05, + "loss": 3.5057, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084623382511238e-05, + "loss": 3.5253, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083786425640559e-05, + "loss": 3.5394, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082947830889507e-05, + "loss": 3.5355, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082109236138455e-05, + "loss": 3.5189, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081270641387403e-05, + "loss": 3.5262, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804336845167236e-05, + "loss": 3.5221, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795950897656716e-05, + "loss": 3.5174, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787564950146196e-05, + "loss": 3.547, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779179002635676e-05, + "loss": 3.5139, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770809433928885e-05, + "loss": 3.5355, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762423486418365e-05, + "loss": 3.5298, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754037538907845e-05, + "loss": 3.521, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074565159139733e-05, + "loss": 3.5324, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073728202269054e-05, + "loss": 3.5158, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072889607518002e-05, + "loss": 3.5195, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.07205101276695e-05, + "loss": 3.5219, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071212418015898e-05, + "loss": 3.537, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070375461145219e-05, + "loss": 3.514, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069536866394167e-05, + "loss": 3.533, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068698271643115e-05, + "loss": 3.5114, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067859676892063e-05, + "loss": 3.5259, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067022720021384e-05, + "loss": 3.537, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066184125270332e-05, + "loss": 3.5365, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.06534553051928e-05, + "loss": 3.5286, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645069357682285e-05, + "loss": 3.5314, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636699788975495e-05, + "loss": 3.5431, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628313841464975e-05, + "loss": 3.5236, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0619927893954454e-05, + "loss": 3.5391, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611541946443934e-05, + "loss": 3.5222, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603172377737144e-05, + "loss": 3.5207, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0594786430226623e-05, + "loss": 3.5251, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586400482716103e-05, + "loss": 3.53, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578014535205583e-05, + "loss": 3.5332, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056964496649879e-05, + "loss": 3.5395, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056125901898827e-05, + "loss": 3.5335, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055287307147775e-05, + "loss": 3.5103, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054448712396724e-05, + "loss": 3.5252, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053611755526045e-05, + "loss": 3.5336, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052773160774993e-05, + "loss": 3.5271, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051934566023941e-05, + "loss": 3.5203, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510959712728888e-05, + "loss": 3.527, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502590144022097e-05, + "loss": 3.5191, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494204196511577e-05, + "loss": 3.5306, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485818249001057e-05, + "loss": 3.5245, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477432301490537e-05, + "loss": 3.5302, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046906273278375e-05, + "loss": 3.5339, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046067678527323e-05, + "loss": 3.5296, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.045229083776271e-05, + "loss": 3.518, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044390489025219e-05, + "loss": 3.5284, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.04355353215454e-05, + "loss": 3.5245, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042714937403488e-05, + "loss": 3.5336, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418763426524362e-05, + "loss": 3.5272, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410377479013842e-05, + "loss": 3.5191, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040200791030705e-05, + "loss": 3.5267, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039362196279653e-05, + "loss": 3.525, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038523601528601e-05, + "loss": 3.5268, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037685006777549e-05, + "loss": 3.523, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368480499068703e-05, + "loss": 3.5159, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360094551558183e-05, + "loss": 3.5296, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351708604047663e-05, + "loss": 3.5243, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0343322656537143e-05, + "loss": 3.5137, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334953087830352e-05, + "loss": 3.5171, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326567140319832e-05, + "loss": 3.5165, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318181192809315e-05, + "loss": 3.5349, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309795245298795e-05, + "loss": 3.5235, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301425676592005e-05, + "loss": 3.5278, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293039729081484e-05, + "loss": 3.5323, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284653781570964e-05, + "loss": 3.5409, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276267834060444e-05, + "loss": 3.5235, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267898265353657e-05, + "loss": 3.5146, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259512317843137e-05, + "loss": 3.5302, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251126370332617e-05, + "loss": 3.5219, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242740422822097e-05, + "loss": 3.5152, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234370854115306e-05, + "loss": 3.516, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225984906604786e-05, + "loss": 3.5236, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021759895909427e-05, + "loss": 3.5246, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020921301158375e-05, + "loss": 3.519, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200843442876958e-05, + "loss": 3.5327, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192457495366438e-05, + "loss": 3.5198, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184071547855918e-05, + "loss": 3.5255, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175685600345398e-05, + "loss": 3.5246, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016731603163861e-05, + "loss": 3.5336, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015893008412809e-05, + "loss": 3.5306, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015054413661757e-05, + "loss": 3.5132, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014215818910705e-05, + "loss": 3.5253, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013378862040026e-05, + "loss": 3.5336, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012540267288974e-05, + "loss": 3.5251, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117016725379223e-05, + "loss": 3.5328, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108647156672432e-05, + "loss": 3.5238, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100261209161912e-05, + "loss": 3.537, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091875261651392e-05, + "loss": 3.5283, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083489314140872e-05, + "loss": 3.5298, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075119745434084e-05, + "loss": 3.5226, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066733797923564e-05, + "loss": 3.5319, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058347850413044e-05, + "loss": 3.5224, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049961902902524e-05, + "loss": 3.5145, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041592334195733e-05, + "loss": 3.5412, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033206386685213e-05, + "loss": 3.5254, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024820439174693e-05, + "loss": 3.53, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016434491664176e-05, + "loss": 3.523, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008064922957386e-05, + "loss": 3.5171, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8467257022857666, + "eval_runtime": 305.208, + "eval_samples_per_second": 1250.265, + "eval_steps_per_second": 39.072, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999678975446866e-05, + "loss": 3.517, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991293027936345e-05, + "loss": 3.5198, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982907080425825e-05, + "loss": 3.5288, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974537511719038e-05, + "loss": 3.5249, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966151564208518e-05, + "loss": 3.5313, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957765616697998e-05, + "loss": 3.518, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949379669187478e-05, + "loss": 3.5212, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941010100480687e-05, + "loss": 3.5199, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932624152970167e-05, + "loss": 3.5384, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924238205459647e-05, + "loss": 3.5159, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991585225794913e-05, + "loss": 3.5206, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990748268924234e-05, + "loss": 3.5282, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989911312053555e-05, + "loss": 3.5188, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890727173025028e-05, + "loss": 3.5139, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882341225514508e-05, + "loss": 3.5124, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987395527800399e-05, + "loss": 3.5106, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986556933049347e-05, + "loss": 3.5128, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985718338298295e-05, + "loss": 3.5149, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984879743547243e-05, + "loss": 3.5114, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840411487961905e-05, + "loss": 3.5322, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.983204191925512e-05, + "loss": 3.5188, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.98236559717446e-05, + "loss": 3.514, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981527002423408e-05, + "loss": 3.5205, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806884076723557e-05, + "loss": 3.5326, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798514508016773e-05, + "loss": 3.5092, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790128560506253e-05, + "loss": 3.5159, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978174261299573e-05, + "loss": 3.5188, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977335666548521e-05, + "loss": 3.5204, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764987096778425e-05, + "loss": 3.5111, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756601149267905e-05, + "loss": 3.5102, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974821520175738e-05, + "loss": 3.5236, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973982925424686e-05, + "loss": 3.5231, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731459685540074e-05, + "loss": 3.5264, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723073738029554e-05, + "loss": 3.5232, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971468779051903e-05, + "loss": 3.5188, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970630184300851e-05, + "loss": 3.5231, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697932274301727e-05, + "loss": 3.5074, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.96895463267912e-05, + "loss": 3.5238, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681160379280683e-05, + "loss": 3.5102, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672774431770163e-05, + "loss": 3.513, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966440486306338e-05, + "loss": 3.5136, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656018915552852e-05, + "loss": 3.5275, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647632968042332e-05, + "loss": 3.5152, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639247020531812e-05, + "loss": 3.5153, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630877451825028e-05, + "loss": 3.5173, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622491504314504e-05, + "loss": 3.5123, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614105556803984e-05, + "loss": 3.5233, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605719609293464e-05, + "loss": 3.4959, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597350040586673e-05, + "loss": 3.5089, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588964093076153e-05, + "loss": 3.5229, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580578145565633e-05, + "loss": 3.5213, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572192198055117e-05, + "loss": 3.5077, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563822629348326e-05, + "loss": 3.5097, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555436681837806e-05, + "loss": 3.5105, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547050734327286e-05, + "loss": 3.4991, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538664786816766e-05, + "loss": 3.5302, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530295218109978e-05, + "loss": 3.5064, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521909270599458e-05, + "loss": 3.5201, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513523323088938e-05, + "loss": 3.5156, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505137375578418e-05, + "loss": 3.5061, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496767806871627e-05, + "loss": 3.5153, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488381859361107e-05, + "loss": 3.5048, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479995911850587e-05, + "loss": 3.508, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.94716263431438e-05, + "loss": 3.5052, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946324039563328e-05, + "loss": 3.5239, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945485444812276e-05, + "loss": 3.5048, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944646850061224e-05, + "loss": 3.5144, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943809893190545e-05, + "loss": 3.4955, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429712984394932e-05, + "loss": 3.5152, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421327036884412e-05, + "loss": 3.5209, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412941089373892e-05, + "loss": 3.5186, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.94045715206671e-05, + "loss": 3.5138, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939618557315658e-05, + "loss": 3.5211, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938779962564606e-05, + "loss": 3.5298, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937941367813554e-05, + "loss": 3.5114, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371044109428753e-05, + "loss": 3.5222, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362658161918233e-05, + "loss": 3.5118, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354272214407713e-05, + "loss": 3.5041, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345886266897193e-05, + "loss": 3.5129, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337516698190402e-05, + "loss": 3.5135, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329130750679885e-05, + "loss": 3.5203, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320744803169365e-05, + "loss": 3.5297, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312358855658845e-05, + "loss": 3.5205, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303989286952054e-05, + "loss": 3.4959, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295603339441534e-05, + "loss": 3.5138, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287217391931014e-05, + "loss": 3.5168, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278831444420494e-05, + "loss": 3.5133, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270461875713707e-05, + "loss": 3.5072, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262075928203187e-05, + "loss": 3.5111, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253689980692667e-05, + "loss": 3.508, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245304033182147e-05, + "loss": 3.5145, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236934464475356e-05, + "loss": 3.5105, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922854851696484e-05, + "loss": 3.5205, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922016256945432e-05, + "loss": 3.5177, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.92117766219438e-05, + "loss": 3.5204, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203407053237008e-05, + "loss": 3.5002, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195021105726488e-05, + "loss": 3.5133, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186635158215968e-05, + "loss": 3.5137, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178249210705448e-05, + "loss": 3.5184, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916987964199866e-05, + "loss": 3.5175, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916149369448814e-05, + "loss": 3.5045, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915310774697762e-05, + "loss": 3.5117, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.91447217994671e-05, + "loss": 3.5086, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913635223076031e-05, + "loss": 3.5147, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127966283249793e-05, + "loss": 3.5063, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119580335739273e-05, + "loss": 3.5054, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111194388228753e-05, + "loss": 3.5188, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102824819521962e-05, + "loss": 3.508, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094438872011442e-05, + "loss": 3.5012, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086052924500922e-05, + "loss": 3.5039, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.90776669769904e-05, + "loss": 3.5042, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069297408283614e-05, + "loss": 3.5209, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060911460773094e-05, + "loss": 3.5079, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052525513262574e-05, + "loss": 3.5119, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044139565752054e-05, + "loss": 3.5183, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035769997045263e-05, + "loss": 3.5274, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027384049534746e-05, + "loss": 3.5071, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018998102024226e-05, + "loss": 3.5055, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010612154513706e-05, + "loss": 3.5115, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002242585806915e-05, + "loss": 3.5123, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993856638296395e-05, + "loss": 3.5002, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985470690785875e-05, + "loss": 3.5057, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977084743275355e-05, + "loss": 3.5092, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968715174568568e-05, + "loss": 3.51, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960329227058048e-05, + "loss": 3.5074, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951943279547528e-05, + "loss": 3.5154, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943557332037008e-05, + "loss": 3.5082, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935187763330217e-05, + "loss": 3.5076, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.89268018158197e-05, + "loss": 3.5092, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891841586830918e-05, + "loss": 3.5246, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891002992079866e-05, + "loss": 3.5149, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890166035209187e-05, + "loss": 3.5074, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889327440458135e-05, + "loss": 3.5029, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888488845707083e-05, + "loss": 3.5213, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887650250956031e-05, + "loss": 3.5111, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886813294085352e-05, + "loss": 3.5199, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859746993343e-05, + "loss": 3.5083, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885136104583248e-05, + "loss": 3.5213, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884297509832196e-05, + "loss": 3.5118, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883460552961517e-05, + "loss": 3.5144, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826219582104654e-05, + "loss": 3.5107, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817833634594134e-05, + "loss": 3.5201, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809447687083614e-05, + "loss": 3.512, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801078118376823e-05, + "loss": 3.4992, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792692170866303e-05, + "loss": 3.5232, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784306223355783e-05, + "loss": 3.5135, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775936654648995e-05, + "loss": 3.5138, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767550707138475e-05, + "loss": 3.5113, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759164759627955e-05, + "loss": 3.502, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.84841251373291, + "eval_runtime": 307.2252, + "eval_samples_per_second": 1242.056, + "eval_steps_per_second": 38.815, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750778812117435e-05, + "loss": 3.5025, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742409243410644e-05, + "loss": 3.5081, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734023295900124e-05, + "loss": 3.517, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725637348389604e-05, + "loss": 3.5071, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717251400879087e-05, + "loss": 3.5192, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708881832172297e-05, + "loss": 3.5032, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700495884661776e-05, + "loss": 3.5072, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692109937151256e-05, + "loss": 3.5059, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683723989640736e-05, + "loss": 3.5223, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867535442093395e-05, + "loss": 3.5073, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866696847342343e-05, + "loss": 3.5017, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865858252591291e-05, + "loss": 3.512, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.865019657840239e-05, + "loss": 3.5062, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641827009695598e-05, + "loss": 3.5016, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633441062185078e-05, + "loss": 3.5047, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625055114674558e-05, + "loss": 3.4919, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861666916716404e-05, + "loss": 3.5013, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860829959845725e-05, + "loss": 3.4999, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859991365094673e-05, + "loss": 3.495, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859152770343621e-05, + "loss": 3.5247, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858314175592569e-05, + "loss": 3.5022, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574772187218903e-05, + "loss": 3.5069, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566386239708382e-05, + "loss": 3.5029, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8558000292197862e-05, + "loss": 3.5198, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549614344687342e-05, + "loss": 3.4952, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.854124477598055e-05, + "loss": 3.5013, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.853285882847003e-05, + "loss": 3.5064, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852447288095951e-05, + "loss": 3.5088, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516086933448995e-05, + "loss": 3.499, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507717364742204e-05, + "loss": 3.4974, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499331417231684e-05, + "loss": 3.5089, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490945469721164e-05, + "loss": 3.5099, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482559522210644e-05, + "loss": 3.5134, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474189953503856e-05, + "loss": 3.5089, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465804005993336e-05, + "loss": 3.4997, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457418058482816e-05, + "loss": 3.5123, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449032110972296e-05, + "loss": 3.492, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440662542265505e-05, + "loss": 3.5126, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432276594754985e-05, + "loss": 3.4936, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423890647244465e-05, + "loss": 3.5031, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841550469973394e-05, + "loss": 3.5004, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407135131027158e-05, + "loss": 3.5136, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398749183516637e-05, + "loss": 3.5045, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390363236006117e-05, + "loss": 3.4993, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381977288495594e-05, + "loss": 3.5042, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837360771978881e-05, + "loss": 3.5019, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836522177227829e-05, + "loss": 3.5084, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835683582476777e-05, + "loss": 3.4858, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348449877257243e-05, + "loss": 3.4941, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.834008030855046e-05, + "loss": 3.5073, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833169436103994e-05, + "loss": 3.5111, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323308413529415e-05, + "loss": 3.4952, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314922466018895e-05, + "loss": 3.4912, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830655289731211e-05, + "loss": 3.5018, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829816694980159e-05, + "loss": 3.4839, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289781002291064e-05, + "loss": 3.5133, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281395054780548e-05, + "loss": 3.4982, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273025486073764e-05, + "loss": 3.5046, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264639538563243e-05, + "loss": 3.5031, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256253591052717e-05, + "loss": 3.4921, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247867643542197e-05, + "loss": 3.5034, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239498074835413e-05, + "loss": 3.495, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823111212732489e-05, + "loss": 3.4916, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822272617981437e-05, + "loss": 3.4905, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821434023230385e-05, + "loss": 3.5106, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205970663597065e-05, + "loss": 3.4953, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197584716086538e-05, + "loss": 3.4969, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189198768576018e-05, + "loss": 3.4857, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.81808128210655e-05, + "loss": 3.4996, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172443252358717e-05, + "loss": 3.5069, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816405730484819e-05, + "loss": 3.507, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815567135733767e-05, + "loss": 3.5002, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814728540982715e-05, + "loss": 3.5081, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138915841120363e-05, + "loss": 3.5125, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130529893609843e-05, + "loss": 3.5009, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122143946099323e-05, + "loss": 3.5074, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113757998588803e-05, + "loss": 3.5007, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105388429882012e-05, + "loss": 3.4903, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097002482371492e-05, + "loss": 3.4983, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.808861653486097e-05, + "loss": 3.5032, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080230587350455e-05, + "loss": 3.5026, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071861018643664e-05, + "loss": 3.5144, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063475071133144e-05, + "loss": 3.5054, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055089123622624e-05, + "loss": 3.4847, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046703176112104e-05, + "loss": 3.4965, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038333607405316e-05, + "loss": 3.5041, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029947659894796e-05, + "loss": 3.5032, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021561712384276e-05, + "loss": 3.4933, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013175764873756e-05, + "loss": 3.4977, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004806196166965e-05, + "loss": 3.4973, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996420248656445e-05, + "loss": 3.4993, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988034301145925e-05, + "loss": 3.4952, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797964835363541e-05, + "loss": 3.5076, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971278784928618e-05, + "loss": 3.505, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962892837418098e-05, + "loss": 3.5066, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954506889907578e-05, + "loss": 3.4877, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946120942397058e-05, + "loss": 3.5023, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793775137369027e-05, + "loss": 3.502, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792936542617975e-05, + "loss": 3.5033, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.792097947866923e-05, + "loss": 3.5014, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791259353115871e-05, + "loss": 3.496, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790422396245192e-05, + "loss": 3.4965, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.78958380149414e-05, + "loss": 3.4996, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788745206743088e-05, + "loss": 3.501, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787908249872409e-05, + "loss": 3.4903, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.787069655121357e-05, + "loss": 3.4926, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786231060370305e-05, + "loss": 3.5066, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785392465619253e-05, + "loss": 3.4927, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784555508748574e-05, + "loss": 3.4901, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837169139975224e-05, + "loss": 3.4902, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828783192464704e-05, + "loss": 3.491, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820397244954184e-05, + "loss": 3.5101, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812027676247393e-05, + "loss": 3.4931, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803641728736873e-05, + "loss": 3.5032, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795255781226353e-05, + "loss": 3.5018, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786869833715833e-05, + "loss": 3.5142, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778500265009045e-05, + "loss": 3.4958, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770114317498525e-05, + "loss": 3.4901, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761728369988005e-05, + "loss": 3.4985, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753342422477485e-05, + "loss": 3.4984, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744972853770694e-05, + "loss": 3.4874, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736586906260174e-05, + "loss": 3.4933, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728200958749657e-05, + "loss": 3.4929, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719815011239137e-05, + "loss": 3.5024, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711445442532346e-05, + "loss": 3.4873, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703059495021826e-05, + "loss": 3.5051, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694673547511306e-05, + "loss": 3.4975, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686287600000786e-05, + "loss": 3.4962, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677918031294e-05, + "loss": 3.493, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766953208378348e-05, + "loss": 3.5122, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766114613627296e-05, + "loss": 3.5035, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765276018876244e-05, + "loss": 3.4904, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644390620055648e-05, + "loss": 3.4923, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636004672545128e-05, + "loss": 3.5052, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762761872503461e-05, + "loss": 3.5013, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761923277752409e-05, + "loss": 3.5084, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.76108632088173e-05, + "loss": 3.4938, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760247726130678e-05, + "loss": 3.508, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759409131379626e-05, + "loss": 3.4961, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758570536628574e-05, + "loss": 3.5056, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577335797578952e-05, + "loss": 3.4986, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568949850068432e-05, + "loss": 3.5042, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560563902557912e-05, + "loss": 3.5, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552177955047392e-05, + "loss": 3.4902, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.75438083863406e-05, + "loss": 3.5098, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753542243883008e-05, + "loss": 3.503, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527036491319565e-05, + "loss": 3.5006, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518650543809045e-05, + "loss": 3.4955, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510280975102254e-05, + "loss": 3.4884, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.85058856010437, + "eval_runtime": 309.0742, + "eval_samples_per_second": 1234.626, + "eval_steps_per_second": 38.583, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501895027591734e-05, + "loss": 3.4905, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493509080081214e-05, + "loss": 3.4934, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485123132570694e-05, + "loss": 3.5043, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476737185060174e-05, + "loss": 3.4924, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468367616353386e-05, + "loss": 3.5102, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459981668842866e-05, + "loss": 3.4891, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451612100136075e-05, + "loss": 3.4941, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443226152625555e-05, + "loss": 3.4939, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434840205115035e-05, + "loss": 3.5096, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742645425760452e-05, + "loss": 3.4945, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418068310094e-05, + "loss": 3.488, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.740968236258348e-05, + "loss": 3.4964, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401296415072958e-05, + "loss": 3.4941, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392910467562438e-05, + "loss": 3.4877, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384540898855647e-05, + "loss": 3.4931, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376154951345127e-05, + "loss": 3.4832, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736776900383461e-05, + "loss": 3.4874, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735938305632409e-05, + "loss": 3.4859, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.73510134876173e-05, + "loss": 3.4818, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734262754010678e-05, + "loss": 3.5141, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733424159259626e-05, + "loss": 3.4916, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325872023889472e-05, + "loss": 3.4878, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317486076378952e-05, + "loss": 3.4932, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309100128868432e-05, + "loss": 3.5039, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300714181357912e-05, + "loss": 3.483, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729234461265112e-05, + "loss": 3.4909, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.72839586651406e-05, + "loss": 3.4921, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727557271763008e-05, + "loss": 3.4969, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267186770119564e-05, + "loss": 3.4826, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258817201412773e-05, + "loss": 3.487, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250431253902253e-05, + "loss": 3.4914, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242045306391733e-05, + "loss": 3.4964, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723365935888121e-05, + "loss": 3.5039, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225289790174426e-05, + "loss": 3.4967, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216903842663906e-05, + "loss": 3.4855, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208517895153386e-05, + "loss": 3.4989, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720013194764286e-05, + "loss": 3.4826, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191762378936075e-05, + "loss": 3.496, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183376431425555e-05, + "loss": 3.4823, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174990483915035e-05, + "loss": 3.487, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.716660453640451e-05, + "loss": 3.4879, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158234967697727e-05, + "loss": 3.5019, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149849020187207e-05, + "loss": 3.4915, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714146307267668e-05, + "loss": 3.4844, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133077125166164e-05, + "loss": 3.4898, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712470755645938e-05, + "loss": 3.4904, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711632160894886e-05, + "loss": 3.4955, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107935661438333e-05, + "loss": 3.4757, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099549713927812e-05, + "loss": 3.4795, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709118014522103e-05, + "loss": 3.4953, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708279419771051e-05, + "loss": 3.4962, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074408250199985e-05, + "loss": 3.4828, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066022302689465e-05, + "loss": 3.4826, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705765273398268e-05, + "loss": 3.4892, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049266786472154e-05, + "loss": 3.4723, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040880838961634e-05, + "loss": 3.4969, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032494891451117e-05, + "loss": 3.4867, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024125322744333e-05, + "loss": 3.4923, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015739375233806e-05, + "loss": 3.4877, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007353427723286e-05, + "loss": 3.4864, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998983859016502e-05, + "loss": 3.4833, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990597911505982e-05, + "loss": 3.4834, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698221196399546e-05, + "loss": 3.4794, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697382601648494e-05, + "loss": 3.4774, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696544006897442e-05, + "loss": 3.4968, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.69570541214639e-05, + "loss": 3.4858, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694866817395338e-05, + "loss": 3.4854, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694028222644286e-05, + "loss": 3.4756, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693191265773607e-05, + "loss": 3.4863, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692352671022555e-05, + "loss": 3.4972, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691514076271503e-05, + "loss": 3.494, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690677119400824e-05, + "loss": 3.4896, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689838524649772e-05, + "loss": 3.4947, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.68899992989872e-05, + "loss": 3.4965, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688161335147668e-05, + "loss": 3.4867, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873243782769892e-05, + "loss": 3.4928, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864857835259372e-05, + "loss": 3.4873, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856471887748852e-05, + "loss": 3.4822, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848085940238332e-05, + "loss": 3.4895, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683971637153154e-05, + "loss": 3.4873, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831346802824754e-05, + "loss": 3.4902, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822960855314234e-05, + "loss": 3.4979, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814574907803714e-05, + "loss": 3.4969, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806188960293194e-05, + "loss": 3.4715, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797803012782673e-05, + "loss": 3.4879, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789417065272153e-05, + "loss": 3.4908, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781031117761633e-05, + "loss": 3.4896, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772661549054846e-05, + "loss": 3.483, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764275601544326e-05, + "loss": 3.4784, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755889654033806e-05, + "loss": 3.4893, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747503706523286e-05, + "loss": 3.4834, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739134137816495e-05, + "loss": 3.4818, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730748190305975e-05, + "loss": 3.4948, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722362242795458e-05, + "loss": 3.4897, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713976295284938e-05, + "loss": 3.4946, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705606726578147e-05, + "loss": 3.4794, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697220779067627e-05, + "loss": 3.4858, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688834831557107e-05, + "loss": 3.4889, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680448884046587e-05, + "loss": 3.4925, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.66720793153398e-05, + "loss": 3.489, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666369336782928e-05, + "loss": 3.4825, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665530742031876e-05, + "loss": 3.4842, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664692147280824e-05, + "loss": 3.4861, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663855190410145e-05, + "loss": 3.4907, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663016595659093e-05, + "loss": 3.4747, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621780009080412e-05, + "loss": 3.4774, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613394061569892e-05, + "loss": 3.4977, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.66050244928631e-05, + "loss": 3.4842, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659663854535258e-05, + "loss": 3.4766, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658825259784206e-05, + "loss": 3.4791, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657986665033154e-05, + "loss": 3.4794, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571497081624753e-05, + "loss": 3.4944, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563111134114233e-05, + "loss": 3.4847, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554725186603713e-05, + "loss": 3.4869, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546339239093193e-05, + "loss": 3.4862, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537969670386402e-05, + "loss": 3.5019, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529583722875882e-05, + "loss": 3.4862, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521197775365365e-05, + "loss": 3.4774, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512811827854845e-05, + "loss": 3.4888, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504442259148055e-05, + "loss": 3.4831, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496056311637534e-05, + "loss": 3.4794, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487670364127014e-05, + "loss": 3.4794, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479284416616494e-05, + "loss": 3.4785, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470914847909707e-05, + "loss": 3.4906, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462528900399187e-05, + "loss": 3.4763, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454142952888667e-05, + "loss": 3.496, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445757005378147e-05, + "loss": 3.4783, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437387436671356e-05, + "loss": 3.4851, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429001489160836e-05, + "loss": 3.4799, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642061554165032e-05, + "loss": 3.5002, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.64122295941398e-05, + "loss": 3.4925, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403860025433008e-05, + "loss": 3.4831, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395474077922488e-05, + "loss": 3.4753, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387088130411968e-05, + "loss": 3.4936, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378702182901448e-05, + "loss": 3.4858, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637033261419466e-05, + "loss": 3.4959, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636194666668414e-05, + "loss": 3.4815, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635356071917362e-05, + "loss": 3.4963, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.63451747716631e-05, + "loss": 3.4844, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633680520295631e-05, + "loss": 3.4969, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632841925544579e-05, + "loss": 3.4818, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320033307935273e-05, + "loss": 3.4893, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311647360424753e-05, + "loss": 3.4883, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303277791717962e-05, + "loss": 3.4794, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294891844207442e-05, + "loss": 3.4946, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286505896696922e-05, + "loss": 3.4952, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278119949186402e-05, + "loss": 3.4842, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269750380479614e-05, + "loss": 3.4854, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261364432969094e-05, + "loss": 3.4765, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.851364850997925, + "eval_runtime": 313.6911, + "eval_samples_per_second": 1216.455, + "eval_steps_per_second": 38.015, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6252978485458574e-05, + "loss": 3.479, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244592537948054e-05, + "loss": 3.4804, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236206590437534e-05, + "loss": 3.4867, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622782064292701e-05, + "loss": 3.4849, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219451074220226e-05, + "loss": 3.4996, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211065126709706e-05, + "loss": 3.4754, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202695558002916e-05, + "loss": 3.482, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194309610492395e-05, + "loss": 3.4815, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185923662981875e-05, + "loss": 3.4984, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177537715471355e-05, + "loss": 3.4821, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169151767960832e-05, + "loss": 3.4738, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160765820450312e-05, + "loss": 3.4885, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152379872939792e-05, + "loss": 3.4776, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6143993925429272e-05, + "loss": 3.4784, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613562435672248e-05, + "loss": 3.4786, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127238409211964e-05, + "loss": 3.4733, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6118852461701444e-05, + "loss": 3.47, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110466514190924e-05, + "loss": 3.4741, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102096945484133e-05, + "loss": 3.4716, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6093710997973613e-05, + "loss": 3.5, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085325050463093e-05, + "loss": 3.4773, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076939102952573e-05, + "loss": 3.4778, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068569534245786e-05, + "loss": 3.4813, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060183586735266e-05, + "loss": 3.4856, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051797639224746e-05, + "loss": 3.4737, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043428070517955e-05, + "loss": 3.4815, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035042123007435e-05, + "loss": 3.4784, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026656175496918e-05, + "loss": 3.4806, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018270227986398e-05, + "loss": 3.4705, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009900659279607e-05, + "loss": 3.4742, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001514711769087e-05, + "loss": 3.4813, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993128764258567e-05, + "loss": 3.4829, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984742816748047e-05, + "loss": 3.4907, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597637324804126e-05, + "loss": 3.4856, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596798730053074e-05, + "loss": 3.4736, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595960135302022e-05, + "loss": 3.4856, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.59512154055097e-05, + "loss": 3.4741, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594284583680291e-05, + "loss": 3.4814, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934459889292388e-05, + "loss": 3.4698, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926073941781868e-05, + "loss": 3.4742, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591768799427135e-05, + "loss": 3.4741, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590931842556456e-05, + "loss": 3.4902, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590093247805404e-05, + "loss": 3.4817, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589254653054352e-05, + "loss": 3.4725, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884160583033e-05, + "loss": 3.477, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5875791014326213e-05, + "loss": 3.4793, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867405066815693e-05, + "loss": 3.4823, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859019119305173e-05, + "loss": 3.4675, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850633171794653e-05, + "loss": 3.461, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842263603087862e-05, + "loss": 3.482, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833877655577342e-05, + "loss": 3.4849, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825491708066822e-05, + "loss": 3.4681, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817105760556305e-05, + "loss": 3.4726, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808736191849514e-05, + "loss": 3.4787, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800350244338994e-05, + "loss": 3.4603, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791964296828474e-05, + "loss": 3.4794, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783578349317954e-05, + "loss": 3.4725, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775208780611167e-05, + "loss": 3.4821, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766822833100647e-05, + "loss": 3.4716, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758436885590127e-05, + "loss": 3.4805, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750067316883336e-05, + "loss": 3.4689, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741681369372816e-05, + "loss": 3.4722, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733295421862296e-05, + "loss": 3.4622, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724909474351776e-05, + "loss": 3.4667, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571652352684126e-05, + "loss": 3.4869, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570813757933074e-05, + "loss": 3.4697, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569975163182022e-05, + "loss": 3.4744, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.56913656843097e-05, + "loss": 3.4637, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682996115602908e-05, + "loss": 3.4747, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674610168092388e-05, + "loss": 3.4847, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666224220581868e-05, + "loss": 3.4794, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565783827307135e-05, + "loss": 3.4777, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564946870436456e-05, + "loss": 3.4861, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564108275685404e-05, + "loss": 3.4822, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563269680934352e-05, + "loss": 3.476, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.562432724063673e-05, + "loss": 3.4791, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615941293126213e-05, + "loss": 3.4771, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607555345615693e-05, + "loss": 3.4718, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599169398105172e-05, + "loss": 3.4742, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559079982939838e-05, + "loss": 3.4766, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558243026069159e-05, + "loss": 3.4749, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.5574044313181074e-05, + "loss": 3.4864, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.5565658365670554e-05, + "loss": 3.4826, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557272418160034e-05, + "loss": 3.4568, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548886470649514e-05, + "loss": 3.479, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540500523138994e-05, + "loss": 3.4785, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532114575628474e-05, + "loss": 3.4776, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523728628117954e-05, + "loss": 3.4715, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515359059411166e-05, + "loss": 3.4669, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506973111900646e-05, + "loss": 3.4783, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498587164390126e-05, + "loss": 3.4698, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490201216879606e-05, + "loss": 3.4713, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481831648172815e-05, + "loss": 3.4795, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473445700662295e-05, + "loss": 3.4766, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465059753151775e-05, + "loss": 3.4844, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456690184444988e-05, + "loss": 3.4722, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448304236934468e-05, + "loss": 3.4707, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5439918289423948e-05, + "loss": 3.4745, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431532341913427e-05, + "loss": 3.4838, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423162773206637e-05, + "loss": 3.4739, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541477682569612e-05, + "loss": 3.4711, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.54063908781856e-05, + "loss": 3.4702, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539800493067508e-05, + "loss": 3.4726, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538963536196829e-05, + "loss": 3.4811, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538124941445777e-05, + "loss": 3.4671, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537286346694725e-05, + "loss": 3.4622, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536447751943673e-05, + "loss": 3.4827, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535610795072994e-05, + "loss": 3.469, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534772200321942e-05, + "loss": 3.4635, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.53393360557089e-05, + "loss": 3.4675, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533095010819838e-05, + "loss": 3.4692, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.532258053949159e-05, + "loss": 3.4824, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314194591981074e-05, + "loss": 3.4668, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305808644470554e-05, + "loss": 3.4726, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297422696960027e-05, + "loss": 3.4763, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289053128253243e-05, + "loss": 3.4882, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280667180742723e-05, + "loss": 3.4771, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272281233232202e-05, + "loss": 3.4633, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526389528572168e-05, + "loss": 3.4756, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255525717014895e-05, + "loss": 3.4683, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247139769504375e-05, + "loss": 3.4695, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238753821993855e-05, + "loss": 3.469, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230367874483328e-05, + "loss": 3.4642, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221998305776544e-05, + "loss": 3.4772, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213612358266024e-05, + "loss": 3.4661, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.52052264107555e-05, + "loss": 3.4792, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.519684046324498e-05, + "loss": 3.4695, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188470894538196e-05, + "loss": 3.4729, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180084947027676e-05, + "loss": 3.4646, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171698999517153e-05, + "loss": 3.489, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163313052006633e-05, + "loss": 3.4748, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.515494348329985e-05, + "loss": 3.4725, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146573914593058e-05, + "loss": 3.4647, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138187967082538e-05, + "loss": 3.4823, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5129802019572018e-05, + "loss": 3.4742, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121416072061498e-05, + "loss": 3.483, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113030124550974e-05, + "loss": 3.47, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104644177040454e-05, + "loss": 3.4811, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096258229529934e-05, + "loss": 3.4733, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087872282019414e-05, + "loss": 3.4876, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079502713312626e-05, + "loss": 3.4661, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071116765802106e-05, + "loss": 3.4771, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062730818291586e-05, + "loss": 3.4758, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054344870781066e-05, + "loss": 3.4705, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045975302074275e-05, + "loss": 3.4779, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037589354563755e-05, + "loss": 3.483, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029203407053235e-05, + "loss": 3.4734, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020833838346448e-05, + "loss": 3.4712, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012447890835928e-05, + "loss": 3.4688, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.853569269180298, + "eval_runtime": 310.4324, + "eval_samples_per_second": 1229.224, + "eval_steps_per_second": 38.414, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004061943325408e-05, + "loss": 3.4646, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499567599581489e-05, + "loss": 3.4673, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.49873064271081e-05, + "loss": 3.474, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.497892047959758e-05, + "loss": 3.4737, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.497053453208706e-05, + "loss": 3.4844, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.496214858457654e-05, + "loss": 3.4671, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.4953779015869753e-05, + "loss": 3.4681, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.4945393068359233e-05, + "loss": 3.4683, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.4937007120848712e-05, + "loss": 3.4832, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492862117333819e-05, + "loss": 3.4741, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492023522582767e-05, + "loss": 3.4625, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911849278317152e-05, + "loss": 3.4726, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903463330806632e-05, + "loss": 3.465, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895077383296112e-05, + "loss": 3.4649, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.488670781458932e-05, + "loss": 3.4728, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.48783218670788e-05, + "loss": 3.4576, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.486993591956828e-05, + "loss": 3.4603, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.486154997205776e-05, + "loss": 3.4613, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853180403350974e-05, + "loss": 3.4585, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4844794455840454e-05, + "loss": 3.4845, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836408508329934e-05, + "loss": 3.4712, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828022560819414e-05, + "loss": 3.4651, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4819652992112623e-05, + "loss": 3.467, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.4811267044602106e-05, + "loss": 3.4781, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4802881097091586e-05, + "loss": 3.4601, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794511528384795e-05, + "loss": 3.4696, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786125580874275e-05, + "loss": 3.4641, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4777739633363755e-05, + "loss": 3.4672, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769353685853235e-05, + "loss": 3.4576, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4760984117146447e-05, + "loss": 3.4675, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752598169635927e-05, + "loss": 3.4708, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744212222125407e-05, + "loss": 3.4709, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4735826274614887e-05, + "loss": 3.4783, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727456705908096e-05, + "loss": 3.4749, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719070758397576e-05, + "loss": 3.4609, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.471068481088706e-05, + "loss": 3.4704, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.470229886337654e-05, + "loss": 3.4672, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.469392929466975e-05, + "loss": 3.4668, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.468554334715923e-05, + "loss": 3.4598, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.467715739964871e-05, + "loss": 3.4625, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.466877145213819e-05, + "loss": 3.466, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.46604018834314e-05, + "loss": 3.4771, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465201593592088e-05, + "loss": 3.4694, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464362998841036e-05, + "loss": 3.4609, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463524404089984e-05, + "loss": 3.4634, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462687447219305e-05, + "loss": 3.4662, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.461848852468253e-05, + "loss": 3.4715, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610102577172013e-05, + "loss": 3.4565, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.460171662966149e-05, + "loss": 3.4481, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.4593347060954702e-05, + "loss": 3.4723, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.4584961113444182e-05, + "loss": 3.4711, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.4576575165933662e-05, + "loss": 3.4552, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456818921842314e-05, + "loss": 3.4593, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559819649716355e-05, + "loss": 3.4695, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551433702205835e-05, + "loss": 3.4469, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543047754695315e-05, + "loss": 3.4687, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.453466180718479e-05, + "loss": 3.4623, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526292238478004e-05, + "loss": 3.4683, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4517906290967484e-05, + "loss": 3.4602, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.4509520343456964e-05, + "loss": 3.466, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501150774750176e-05, + "loss": 3.456, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492764827239656e-05, + "loss": 3.4652, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.4484378879729136e-05, + "loss": 3.4503, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.4475992932218613e-05, + "loss": 3.4587, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467606984708093e-05, + "loss": 3.4711, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4459221037197576e-05, + "loss": 3.4633, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450835089687056e-05, + "loss": 3.4604, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442449142176536e-05, + "loss": 3.4505, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434079573469745e-05, + "loss": 3.4602, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4425693625959225e-05, + "loss": 3.4686, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417307678448705e-05, + "loss": 3.472, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4408921730938185e-05, + "loss": 3.4669, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400552162231397e-05, + "loss": 3.4743, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392166214720877e-05, + "loss": 3.4717, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4383780267210357e-05, + "loss": 3.4643, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375410698503566e-05, + "loss": 3.4648, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367024750993046e-05, + "loss": 3.4677, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.435863880348253e-05, + "loss": 3.4572, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.435025285597201e-05, + "loss": 3.4613, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.434188328726522e-05, + "loss": 3.4697, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.43334973397547e-05, + "loss": 3.4605, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.4325127771047908e-05, + "loss": 3.4766, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431674182353739e-05, + "loss": 3.4702, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.430835587602687e-05, + "loss": 3.4473, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.429996992851635e-05, + "loss": 3.4627, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.429158398100583e-05, + "loss": 3.4688, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.428319803349531e-05, + "loss": 3.4681, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.427481208598479e-05, + "loss": 3.4636, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266426138474267e-05, + "loss": 3.4534, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4258056569767483e-05, + "loss": 3.4636, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.4249670622256963e-05, + "loss": 3.4604, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.4241284674746443e-05, + "loss": 3.4599, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423289872723592e-05, + "loss": 3.4637, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.4224529158529132e-05, + "loss": 3.4692, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.4216143211018612e-05, + "loss": 3.4683, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.4207757263508092e-05, + "loss": 3.4679, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.4199371315997572e-05, + "loss": 3.4535, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4191001747290785e-05, + "loss": 3.4646, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4182615799780264e-05, + "loss": 3.4666, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.417422985226974e-05, + "loss": 3.4656, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.416584390475922e-05, + "loss": 3.4578, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.4157474336052437e-05, + "loss": 3.4607, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149088388541917e-05, + "loss": 3.4618, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140702441031393e-05, + "loss": 3.4698, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132316493520873e-05, + "loss": 3.4548, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4123946924814086e-05, + "loss": 3.4561, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4115560977303562e-05, + "loss": 3.4649, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4107175029793046e-05, + "loss": 3.4576, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4098789082282526e-05, + "loss": 3.4535, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090419513575738e-05, + "loss": 3.4556, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082033566065215e-05, + "loss": 3.4559, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073647618554695e-05, + "loss": 3.4705, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065261671044175e-05, + "loss": 3.4571, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4056892102337387e-05, + "loss": 3.459, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048506154826867e-05, + "loss": 3.4645, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4040120207316347e-05, + "loss": 3.4777, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031734259805827e-05, + "loss": 3.4651, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023364691099036e-05, + "loss": 3.4513, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4014978743588516e-05, + "loss": 3.4599, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006592796078e-05, + "loss": 3.4582, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.399820684856748e-05, + "loss": 3.4557, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.398983727986069e-05, + "loss": 3.4578, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.398145133235017e-05, + "loss": 3.4531, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397306538483965e-05, + "loss": 3.4639, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.396467943732913e-05, + "loss": 3.4581, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.395630986862234e-05, + "loss": 3.4644, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394792392111182e-05, + "loss": 3.4569, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.39395379736013e-05, + "loss": 3.4599, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.393115202609078e-05, + "loss": 3.4588, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.392278245738399e-05, + "loss": 3.4691, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.391439650987347e-05, + "loss": 3.4624, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3906010562362953e-05, + "loss": 3.4647, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897640993656162e-05, + "loss": 3.4533, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.3889255046145642e-05, + "loss": 3.4719, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.3880869098635122e-05, + "loss": 3.4637, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.3872483151124602e-05, + "loss": 3.4687, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.3864113582417815e-05, + "loss": 3.456, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.3855727634907294e-05, + "loss": 3.473, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.3847341687396774e-05, + "loss": 3.458, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3838955739886254e-05, + "loss": 3.4791, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830586171179463e-05, + "loss": 3.4557, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822200223668943e-05, + "loss": 3.4667, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.3813814276158423e-05, + "loss": 3.4614, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.3805428328647907e-05, + "loss": 3.4578, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797058759941116e-05, + "loss": 3.4673, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788672812430596e-05, + "loss": 3.4729, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780286864920076e-05, + "loss": 3.4609, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3771900917409556e-05, + "loss": 3.4563, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763531348702768e-05, + "loss": 3.4595, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8546502590179443, + "eval_runtime": 309.5532, + "eval_samples_per_second": 1232.715, + "eval_steps_per_second": 38.523, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755145401192248e-05, + "loss": 3.4572, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746759453681728e-05, + "loss": 3.4545, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738373506171208e-05, + "loss": 3.4641, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3729987558660688e-05, + "loss": 3.4605, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721617989953897e-05, + "loss": 3.4733, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713232042443377e-05, + "loss": 3.4543, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370486247373659e-05, + "loss": 3.4557, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369647652622607e-05, + "loss": 3.4592, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368809057871555e-05, + "loss": 3.4706, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.367970463120503e-05, + "loss": 3.4603, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367131868369451e-05, + "loss": 3.453, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3662932736183986e-05, + "loss": 3.4587, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365454678867347e-05, + "loss": 3.4557, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364616084116295e-05, + "loss": 3.4524, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637791272456162e-05, + "loss": 3.46, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629405324945638e-05, + "loss": 3.4459, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621019377435118e-05, + "loss": 3.4476, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612633429924598e-05, + "loss": 3.4522, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604263861217814e-05, + "loss": 3.4449, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.359587791370729e-05, + "loss": 3.4712, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358749196619677e-05, + "loss": 3.4619, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357910601868625e-05, + "loss": 3.4542, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.357073644997946e-05, + "loss": 3.4535, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356235050246894e-05, + "loss": 3.4646, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3553964554958423e-05, + "loss": 3.451, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545594986251635e-05, + "loss": 3.4597, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537209038741112e-05, + "loss": 3.4496, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528823091230592e-05, + "loss": 3.4592, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520437143720072e-05, + "loss": 3.4479, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3512067575013284e-05, + "loss": 3.4533, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503681627502764e-05, + "loss": 3.4583, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495295679992244e-05, + "loss": 3.4585, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486909732481724e-05, + "loss": 3.4652, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478540163774933e-05, + "loss": 3.4639, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470154216264413e-05, + "loss": 3.4473, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3461768268753893e-05, + "loss": 3.4602, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3453382321243377e-05, + "loss": 3.4563, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3445012752536586e-05, + "loss": 3.4498, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436626805026066e-05, + "loss": 3.4511, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428257236319278e-05, + "loss": 3.4507, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419871288808755e-05, + "loss": 3.4536, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411485341298238e-05, + "loss": 3.4652, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403099393787718e-05, + "loss": 3.4548, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394713446277198e-05, + "loss": 3.4496, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386327498766678e-05, + "loss": 3.4565, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377941551256158e-05, + "loss": 3.4562, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369571982549367e-05, + "loss": 3.4539, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361186035038847e-05, + "loss": 3.4454, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335280008752833e-05, + "loss": 3.435, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.334441414001781e-05, + "loss": 3.4626, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333604457131102e-05, + "loss": 3.4546, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.33276586238005e-05, + "loss": 3.4495, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331927267628998e-05, + "loss": 3.4458, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.331088672877946e-05, + "loss": 3.4561, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.330251716007267e-05, + "loss": 3.4357, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.329413121256215e-05, + "loss": 3.4542, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328574526505163e-05, + "loss": 3.4568, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327735931754111e-05, + "loss": 3.4562, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326898974883432e-05, + "loss": 3.4536, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.32606038013238e-05, + "loss": 3.4527, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252234232617013e-05, + "loss": 3.4445, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243848285106493e-05, + "loss": 3.4559, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235462337595973e-05, + "loss": 3.4392, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227076390085453e-05, + "loss": 3.4446, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3218690442574933e-05, + "loss": 3.4586, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321030449506441e-05, + "loss": 3.4528, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3201918547553893e-05, + "loss": 3.445, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193532600043373e-05, + "loss": 3.4445, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185163031336585e-05, + "loss": 3.4457, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3176777083826062e-05, + "loss": 3.4562, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168391136315542e-05, + "loss": 3.4593, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160005188805022e-05, + "loss": 3.4535, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151635620098238e-05, + "loss": 3.4641, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143249672587714e-05, + "loss": 3.46, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134880103880927e-05, + "loss": 3.4577, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126494156370407e-05, + "loss": 3.4518, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118108208859883e-05, + "loss": 3.4525, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109722261349363e-05, + "loss": 3.4509, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101336313838846e-05, + "loss": 3.4448, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3092950366328326e-05, + "loss": 3.462, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084564418817806e-05, + "loss": 3.4455, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076178471307286e-05, + "loss": 3.4613, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067808902600495e-05, + "loss": 3.4633, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059422955089975e-05, + "loss": 3.4354, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051037007579455e-05, + "loss": 3.4527, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304265106006894e-05, + "loss": 3.4507, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034281491362148e-05, + "loss": 3.4574, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025895543851628e-05, + "loss": 3.451, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017509596341108e-05, + "loss": 3.4419, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009123648830588e-05, + "loss": 3.4547, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.30007540801238e-05, + "loss": 3.448, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.299236813261328e-05, + "loss": 3.4509, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298398218510276e-05, + "loss": 3.4499, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297559623759224e-05, + "loss": 3.4593, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296722666888545e-05, + "loss": 3.4572, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295884072137493e-05, + "loss": 3.455, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.295045477386441e-05, + "loss": 3.4408, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942068826353892e-05, + "loss": 3.4563, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.29336992576471e-05, + "loss": 3.452, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292531331013658e-05, + "loss": 3.4583, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291692736262606e-05, + "loss": 3.4428, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290855779391927e-05, + "loss": 3.4527, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900171846408754e-05, + "loss": 3.4445, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891785898898234e-05, + "loss": 3.457, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883399951387714e-05, + "loss": 3.4401, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875030382680923e-05, + "loss": 3.4468, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866644435170403e-05, + "loss": 3.4517, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858258487659883e-05, + "loss": 3.4483, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2849872540149363e-05, + "loss": 3.4393, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841502971442575e-05, + "loss": 3.4485, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833117023932055e-05, + "loss": 3.4455, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824731076421535e-05, + "loss": 3.4535, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281634512891101e-05, + "loss": 3.4511, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2807975560204224e-05, + "loss": 3.4451, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799589612693707e-05, + "loss": 3.4563, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2791203665183187e-05, + "loss": 3.4657, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782817717672664e-05, + "loss": 3.4559, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774448148965877e-05, + "loss": 3.4398, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766062201455356e-05, + "loss": 3.4515, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757676253944833e-05, + "loss": 3.4467, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749290306434316e-05, + "loss": 3.4435, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274092073772753e-05, + "loss": 3.4477, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273253479021701e-05, + "loss": 3.4399, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724148842706485e-05, + "loss": 3.453, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715762895195965e-05, + "loss": 3.4443, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707393326489178e-05, + "loss": 3.4557, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269900737897866e-05, + "loss": 3.4497, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690621431468138e-05, + "loss": 3.4449, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682235483957618e-05, + "loss": 3.4535, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267386591525083e-05, + "loss": 3.455, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665479967740307e-05, + "loss": 3.451, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657094020229787e-05, + "loss": 3.4516, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264870807271927e-05, + "loss": 3.4431, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640338504012483e-05, + "loss": 3.4598, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263195255650196e-05, + "loss": 3.4512, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262356660899144e-05, + "loss": 3.4575, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.261518066148092e-05, + "loss": 3.4447, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260681109277413e-05, + "loss": 3.4599, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.259842514526361e-05, + "loss": 3.4449, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.259003919775309e-05, + "loss": 3.4705, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.258165325024257e-05, + "loss": 3.4419, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257328368153578e-05, + "loss": 3.4586, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256489773402526e-05, + "loss": 3.4495, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255651178651474e-05, + "loss": 3.4481, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548125839004224e-05, + "loss": 3.4527, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539756270297433e-05, + "loss": 3.4576, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531370322786913e-05, + "loss": 3.4547, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522984375276393e-05, + "loss": 3.4437, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514598427765873e-05, + "loss": 3.4525, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8556435108184814, + "eval_runtime": 306.4516, + "eval_samples_per_second": 1245.192, + "eval_steps_per_second": 38.913, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506228859059085e-05, + "loss": 3.4461, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2497842911548565e-05, + "loss": 3.4435, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489456964038045e-05, + "loss": 3.4464, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481071016527525e-05, + "loss": 3.4519, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472701447820734e-05, + "loss": 3.4613, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464315500310214e-05, + "loss": 3.4471, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2455945931603427e-05, + "loss": 3.438, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2447559984092907e-05, + "loss": 3.4514, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2439174036582386e-05, + "loss": 3.4571, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430788089071866e-05, + "loss": 3.4513, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422402141561346e-05, + "loss": 3.4421, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414016194050826e-05, + "loss": 3.4461, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405630246540306e-05, + "loss": 3.4468, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397244299029786e-05, + "loss": 3.4402, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2388874730323e-05, + "loss": 3.4491, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.238048878281248e-05, + "loss": 3.4375, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.237210283530196e-05, + "loss": 3.434, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363716887791435e-05, + "loss": 3.4394, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355347319084648e-05, + "loss": 3.4355, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.234696137157413e-05, + "loss": 3.4601, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.233857542406361e-05, + "loss": 3.4514, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330189476553088e-05, + "loss": 3.4445, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.23218199078463e-05, + "loss": 3.4419, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.231343396033578e-05, + "loss": 3.4495, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.230504801282526e-05, + "loss": 3.4388, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.229666206531474e-05, + "loss": 3.4508, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288292496607952e-05, + "loss": 3.4385, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2279906549097432e-05, + "loss": 3.4467, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.227152060158691e-05, + "loss": 3.4418, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226313465407639e-05, + "loss": 3.4397, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.22547650853696e-05, + "loss": 3.4457, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224637913785908e-05, + "loss": 3.4529, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223799319034856e-05, + "loss": 3.4486, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.2229623621641774e-05, + "loss": 3.4518, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2221237674131254e-05, + "loss": 3.4354, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2212851726620734e-05, + "loss": 3.454, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220446577911021e-05, + "loss": 3.4419, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2196096210403426e-05, + "loss": 3.4379, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2187710262892906e-05, + "loss": 3.4386, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.2179324315382383e-05, + "loss": 3.44, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2170938367871863e-05, + "loss": 3.4433, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162568799165075e-05, + "loss": 3.4499, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2154182851654555e-05, + "loss": 3.4439, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.2145796904144035e-05, + "loss": 3.4408, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2137410956633515e-05, + "loss": 3.4446, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2129041387926727e-05, + "loss": 3.4443, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120655440416204e-05, + "loss": 3.4439, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112269492905684e-05, + "loss": 3.4319, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.2103899924198896e-05, + "loss": 3.4224, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209551397668838e-05, + "loss": 3.4519, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.2087128029177856e-05, + "loss": 3.4498, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2078742081667336e-05, + "loss": 3.4362, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.2070356134156816e-05, + "loss": 3.4408, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2061970186646296e-05, + "loss": 3.4399, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053584239135776e-05, + "loss": 3.4266, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.204521467042899e-05, + "loss": 3.4408, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.203682872291847e-05, + "loss": 3.4452, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202844277540795e-05, + "loss": 3.4457, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202005682789743e-05, + "loss": 3.439, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011687259190638e-05, + "loss": 3.4423, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.200331769048385e-05, + "loss": 3.4327, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.199493174297333e-05, + "loss": 3.4447, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.198654579546281e-05, + "loss": 3.4276, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.197815984795229e-05, + "loss": 3.4322, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.196977390044177e-05, + "loss": 3.4481, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.196138795293125e-05, + "loss": 3.4394, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.195300200542073e-05, + "loss": 3.4361, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.194461605791021e-05, + "loss": 3.4328, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936246489203422e-05, + "loss": 3.4315, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1927860541692902e-05, + "loss": 3.4393, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919474594182382e-05, + "loss": 3.4513, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.191108864667186e-05, + "loss": 3.4422, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.190271907796507e-05, + "loss": 3.4519, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894333130454555e-05, + "loss": 3.4451, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1885947182944035e-05, + "loss": 3.451, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.187756123543351e-05, + "loss": 3.4418, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869191666726724e-05, + "loss": 3.4404, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860805719216204e-05, + "loss": 3.4401, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852419771705684e-05, + "loss": 3.4336, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844050202998896e-05, + "loss": 3.4492, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835680634292105e-05, + "loss": 3.4391, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827294686781585e-05, + "loss": 3.4509, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1818908739271065e-05, + "loss": 3.4462, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810522791760545e-05, + "loss": 3.4236, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1802136844250025e-05, + "loss": 3.4443, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1793750896739505e-05, + "loss": 3.4403, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785364949228985e-05, + "loss": 3.446, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1776979001718465e-05, + "loss": 3.4388, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768609433011677e-05, + "loss": 3.4332, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760223485501157e-05, + "loss": 3.4429, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1751837537990634e-05, + "loss": 3.4345, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1743451590480117e-05, + "loss": 3.4383, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173508202177333e-05, + "loss": 3.438, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.1726696074262806e-05, + "loss": 3.4484, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.1718310126752286e-05, + "loss": 3.4513, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.1709924179241766e-05, + "loss": 3.4371, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.170155461053498e-05, + "loss": 3.4354, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169316866302446e-05, + "loss": 3.4434, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168478271551394e-05, + "loss": 3.4407, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167639676800342e-05, + "loss": 3.4481, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166802719929663e-05, + "loss": 3.435, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.1659641251786107e-05, + "loss": 3.4407, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.1651255304275587e-05, + "loss": 3.4368, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.1642885735568803e-05, + "loss": 3.4456, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163449978805828e-05, + "loss": 3.428, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162611384054776e-05, + "loss": 3.4371, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161772789303724e-05, + "loss": 3.4359, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160934194552672e-05, + "loss": 3.4374, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.16009559980162e-05, + "loss": 3.4295, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.159257005050568e-05, + "loss": 3.4358, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584184102995163e-05, + "loss": 3.4336, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575814534288372e-05, + "loss": 3.4445, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567428586777852e-05, + "loss": 3.4412, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559042639267332e-05, + "loss": 3.434, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.155065669175681e-05, + "loss": 3.4405, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542287123050024e-05, + "loss": 3.4548, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1533901175539504e-05, + "loss": 3.4476, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525515228028984e-05, + "loss": 3.4289, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.151712928051846e-05, + "loss": 3.4392, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508759711811673e-05, + "loss": 3.4378, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500373764301153e-05, + "loss": 3.4286, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1491987816790633e-05, + "loss": 3.44, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483601869280113e-05, + "loss": 3.4239, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475232300573326e-05, + "loss": 3.4449, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466846353062806e-05, + "loss": 3.4286, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458460405552282e-05, + "loss": 3.4453, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450074458041762e-05, + "loss": 3.4363, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441704889334978e-05, + "loss": 3.4351, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433318941824458e-05, + "loss": 3.4389, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1424932994313935e-05, + "loss": 3.4469, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416547046803415e-05, + "loss": 3.4374, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408177478096627e-05, + "loss": 3.4416, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399791530586107e-05, + "loss": 3.431, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391405583075587e-05, + "loss": 3.4515, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383019635565067e-05, + "loss": 3.4407, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.137465006685828e-05, + "loss": 3.4449, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366264119347756e-05, + "loss": 3.4374, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357878171837236e-05, + "loss": 3.4493, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349492224326716e-05, + "loss": 3.435, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.134112265561993e-05, + "loss": 3.4552, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.133273670810941e-05, + "loss": 3.4311, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132435076059889e-05, + "loss": 3.4472, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1315964813088368e-05, + "loss": 3.4404, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130759524438158e-05, + "loss": 3.4407, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1299209296871057e-05, + "loss": 3.4364, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129082334936054e-05, + "loss": 3.4431, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128243740185002e-05, + "loss": 3.4436, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127406783314323e-05, + "loss": 3.4314, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126568188563271e-05, + "loss": 3.4446, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8578267097473145, + "eval_runtime": 306.4911, + "eval_samples_per_second": 1245.031, + "eval_steps_per_second": 38.908, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.125729593812219e-05, + "loss": 3.4368, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124890999061167e-05, + "loss": 3.4329, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.124052404310115e-05, + "loss": 3.4356, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232138095590633e-05, + "loss": 3.4398, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223768526883842e-05, + "loss": 3.4463, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215382579373322e-05, + "loss": 3.44, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120701301066653e-05, + "loss": 3.4325, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119862706315601e-05, + "loss": 3.436, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190241115645494e-05, + "loss": 3.4489, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181855168134974e-05, + "loss": 3.4409, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173469220624454e-05, + "loss": 3.4303, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165083273113934e-05, + "loss": 3.4333, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.115669732560341e-05, + "loss": 3.4344, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114831137809289e-05, + "loss": 3.4302, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139941809386103e-05, + "loss": 3.4388, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131555861875587e-05, + "loss": 3.4237, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123169914365063e-05, + "loss": 3.4253, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114783966854543e-05, + "loss": 3.4295, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106414398147756e-05, + "loss": 3.425, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098028450637236e-05, + "loss": 3.4458, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089642503126712e-05, + "loss": 3.4409, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081256555616195e-05, + "loss": 3.4346, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072886986909408e-05, + "loss": 3.4305, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064501039398884e-05, + "loss": 3.4378, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056115091888364e-05, + "loss": 3.4306, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047729144377844e-05, + "loss": 3.4385, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039359575671057e-05, + "loss": 3.4244, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1030973628160537e-05, + "loss": 3.4391, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022587680650017e-05, + "loss": 3.4348, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014201733139497e-05, + "loss": 3.4238, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100583216443271e-05, + "loss": 3.4334, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997446216922186e-05, + "loss": 3.4428, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989060269411666e-05, + "loss": 3.435, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098069070070488e-05, + "loss": 3.4466, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972304753194358e-05, + "loss": 3.4266, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963918805683838e-05, + "loss": 3.4381, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955532858173318e-05, + "loss": 3.4335, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094716328946653e-05, + "loss": 3.4282, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093877734195601e-05, + "loss": 3.4285, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.093039139444549e-05, + "loss": 3.4289, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.092200544693497e-05, + "loss": 3.43, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913635878228183e-05, + "loss": 3.4399, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090524993071766e-05, + "loss": 3.4336, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089686398320714e-05, + "loss": 3.4292, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088847803569662e-05, + "loss": 3.4331, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880108466989832e-05, + "loss": 3.431, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871722519479312e-05, + "loss": 3.431, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863336571968792e-05, + "loss": 3.4246, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854950624458272e-05, + "loss": 3.4051, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084658105575148e-05, + "loss": 3.445, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838195108240964e-05, + "loss": 3.4318, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829809160730444e-05, + "loss": 3.4324, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821423213219924e-05, + "loss": 3.4267, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813053644513133e-05, + "loss": 3.4305, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804667697002613e-05, + "loss": 3.4178, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796281749492093e-05, + "loss": 3.4255, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787895801981573e-05, + "loss": 3.4352, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779526233274786e-05, + "loss": 3.4325, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771140285764266e-05, + "loss": 3.4361, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762754338253745e-05, + "loss": 3.4234, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754384769546955e-05, + "loss": 3.4225, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745998822036435e-05, + "loss": 3.4406, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737612874525918e-05, + "loss": 3.4128, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729226927015398e-05, + "loss": 3.4215, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720840979504878e-05, + "loss": 3.4342, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712455031994358e-05, + "loss": 3.4284, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704069084483834e-05, + "loss": 3.4241, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695683136973314e-05, + "loss": 3.4251, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687313568266527e-05, + "loss": 3.4196, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067892762075601e-05, + "loss": 3.4273, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670541673245487e-05, + "loss": 3.4384, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662155725734967e-05, + "loss": 3.4301, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065378615702818e-05, + "loss": 3.443, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.064540020951766e-05, + "loss": 3.4342, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637014262007136e-05, + "loss": 3.4441, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062862831449662e-05, + "loss": 3.4257, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.062025874578983e-05, + "loss": 3.4342, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611872798279308e-05, + "loss": 3.4292, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603486850768788e-05, + "loss": 3.418, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595100903258268e-05, + "loss": 3.4371, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058673133455148e-05, + "loss": 3.4293, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.057834538704096e-05, + "loss": 3.4375, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569975818334173e-05, + "loss": 3.4403, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561589870823653e-05, + "loss": 3.4157, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553203923313133e-05, + "loss": 3.4292, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.054481797580261e-05, + "loss": 3.4297, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053643202829209e-05, + "loss": 3.4357, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528046080781573e-05, + "loss": 3.4289, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519660133271053e-05, + "loss": 3.4232, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511274185760533e-05, + "loss": 3.4279, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050290461705374e-05, + "loss": 3.4254, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049451866954322e-05, + "loss": 3.4273, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.04861327220327e-05, + "loss": 3.4277, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477763153325914e-05, + "loss": 3.4418, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469377205815394e-05, + "loss": 3.4379, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0460991258304874e-05, + "loss": 3.4251, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452605310794354e-05, + "loss": 3.4216, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444235742087563e-05, + "loss": 3.4305, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435849794577043e-05, + "loss": 3.4334, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427463847066526e-05, + "loss": 3.4323, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419077899556006e-05, + "loss": 3.4273, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410708330849215e-05, + "loss": 3.4285, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402322383338695e-05, + "loss": 3.4244, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393936435828175e-05, + "loss": 3.4386, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385550488317655e-05, + "loss": 3.4152, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377180919610868e-05, + "loss": 3.4277, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0368794972100348e-05, + "loss": 3.4218, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360425403393557e-05, + "loss": 3.4295, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352039455883037e-05, + "loss": 3.4186, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343653508372517e-05, + "loss": 3.428, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335267560861997e-05, + "loss": 3.4198, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032688161335148e-05, + "loss": 3.4339, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031849566584096e-05, + "loss": 3.4304, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310109718330436e-05, + "loss": 3.4245, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301723770819916e-05, + "loss": 3.4301, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029335420211313e-05, + "loss": 3.446, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028496825460261e-05, + "loss": 3.4284, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027658230709209e-05, + "loss": 3.4262, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.026819635958157e-05, + "loss": 3.4213, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025982679087478e-05, + "loss": 3.4286, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251440843364258e-05, + "loss": 3.4248, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243054895853738e-05, + "loss": 3.426, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234668948343218e-05, + "loss": 3.4141, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226299379636434e-05, + "loss": 3.4331, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021791343212591e-05, + "loss": 3.4225, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020952748461539e-05, + "loss": 3.4318, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020114153710487e-05, + "loss": 3.4268, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192771968398083e-05, + "loss": 3.4257, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.018438602088756e-05, + "loss": 3.4244, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176000073377043e-05, + "loss": 3.4367, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167614125866522e-05, + "loss": 3.4255, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015924455715973e-05, + "loss": 3.4329, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150874988452944e-05, + "loss": 3.4176, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142489040942424e-05, + "loss": 3.4396, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134103093431904e-05, + "loss": 3.43, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125717145921384e-05, + "loss": 3.4336, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117331198410864e-05, + "loss": 3.4277, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108945250900344e-05, + "loss": 3.4354, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100575682193556e-05, + "loss": 3.4236, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092189734683033e-05, + "loss": 3.4457, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083803787172513e-05, + "loss": 3.4204, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0075417839661996e-05, + "loss": 3.4363, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067031892151476e-05, + "loss": 3.4331, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058645944640956e-05, + "loss": 3.4282, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050259997130436e-05, + "loss": 3.4231, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041874049619913e-05, + "loss": 3.4363, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033504480913125e-05, + "loss": 3.4329, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025118533402605e-05, + "loss": 3.424, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001673258589209e-05, + "loss": 3.4327, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.8597357273101807, + "eval_runtime": 305.1126, + "eval_samples_per_second": 1250.656, + "eval_steps_per_second": 39.084, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008346638381565e-05, + "loss": 3.4162, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999977069674777e-05, + "loss": 3.4228, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991591122164257e-05, + "loss": 3.4241, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983205174653737e-05, + "loss": 3.4324, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9974819227143214e-05, + "loss": 3.4381, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996644965843643e-05, + "loss": 3.4239, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995808008972964e-05, + "loss": 3.4268, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994969414221912e-05, + "loss": 3.423, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.99413081947086e-05, + "loss": 3.4334, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993292224719808e-05, + "loss": 3.4335, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992453629968756e-05, + "loss": 3.4191, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991615035217704e-05, + "loss": 3.4205, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990776440466652e-05, + "loss": 3.4283, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899378457156e-05, + "loss": 3.4144, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989100888844921e-05, + "loss": 3.4239, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882622940938688e-05, + "loss": 3.4157, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874236993428168e-05, + "loss": 3.4121, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986585104591765e-05, + "loss": 3.4227, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985748147721086e-05, + "loss": 3.4142, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984909552970034e-05, + "loss": 3.4344, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984070958218982e-05, + "loss": 3.4312, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.98323236346793e-05, + "loss": 3.4264, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823954065972512e-05, + "loss": 3.4187, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815568118461992e-05, + "loss": 3.4202, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807182170951472e-05, + "loss": 3.4229, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798796223440952e-05, + "loss": 3.4269, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979042665473416e-05, + "loss": 3.4182, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978204070722364e-05, + "loss": 3.4282, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977365475971312e-05, + "loss": 3.4196, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765268812202605e-05, + "loss": 3.4176, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756899243495814e-05, + "loss": 3.4199, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748513295985294e-05, + "loss": 3.4336, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740127348474774e-05, + "loss": 3.4273, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731741400964254e-05, + "loss": 3.4333, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723371832257466e-05, + "loss": 3.4153, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714985884746946e-05, + "loss": 3.4211, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706599937236426e-05, + "loss": 3.4309, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698230368529635e-05, + "loss": 3.4181, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689844421019115e-05, + "loss": 3.4166, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681458473508595e-05, + "loss": 3.415, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673072525998075e-05, + "loss": 3.4228, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664702957291287e-05, + "loss": 3.4219, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656317009780767e-05, + "loss": 3.4291, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647931062270247e-05, + "loss": 3.4221, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639545114759727e-05, + "loss": 3.416, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631175546052936e-05, + "loss": 3.4249, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.962278959854242e-05, + "loss": 3.4167, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.96144036510319e-05, + "loss": 3.4171, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960601770352138e-05, + "loss": 3.393, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959764813481459e-05, + "loss": 3.4352, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.958926218730407e-05, + "loss": 3.4185, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958087623979355e-05, + "loss": 3.4264, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957249029228303e-05, + "loss": 3.4167, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.956412072357624e-05, + "loss": 3.4174, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955573477606572e-05, + "loss": 3.4063, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.95473488285552e-05, + "loss": 3.4134, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953896288104468e-05, + "loss": 3.4263, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953059331233789e-05, + "loss": 3.4196, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522207364827373e-05, + "loss": 3.4276, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513821417316853e-05, + "loss": 3.4152, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505451848610062e-05, + "loss": 3.4087, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497065901099542e-05, + "loss": 3.4308, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9488679953589022e-05, + "loss": 3.4008, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480294006078502e-05, + "loss": 3.4094, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9471908058567982e-05, + "loss": 3.4241, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463522111057462e-05, + "loss": 3.422, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455136163546942e-05, + "loss": 3.4091, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446750216036422e-05, + "loss": 3.4211, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438380647329635e-05, + "loss": 3.4047, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942999469981911e-05, + "loss": 3.4213, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.942160875230859e-05, + "loss": 3.4239, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413222804798074e-05, + "loss": 3.4247, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404853236091284e-05, + "loss": 3.4267, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396467288580764e-05, + "loss": 3.425, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388081341070243e-05, + "loss": 3.4367, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379695393559723e-05, + "loss": 3.4162, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371325824852936e-05, + "loss": 3.4233, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9362939877342416e-05, + "loss": 3.4182, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354553929831896e-05, + "loss": 3.403, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346167982321376e-05, + "loss": 3.4279, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337814792418317e-05, + "loss": 3.42, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329428844907797e-05, + "loss": 3.4222, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321042897397277e-05, + "loss": 3.4326, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312656949886757e-05, + "loss": 3.4079, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304271002376237e-05, + "loss": 3.4129, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295885054865717e-05, + "loss": 3.4169, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287499107355197e-05, + "loss": 3.4263, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279113159844677e-05, + "loss": 3.4148, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927074359113789e-05, + "loss": 3.4172, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.926235764362737e-05, + "loss": 3.416, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.925397169611685e-05, + "loss": 3.418, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924558574860633e-05, + "loss": 3.4129, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923721617989954e-05, + "loss": 3.4194, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922883023238902e-05, + "loss": 3.4289, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.92204442848785e-05, + "loss": 3.4229, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212058337367982e-05, + "loss": 3.4239, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920368876866119e-05, + "loss": 3.4098, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.919530282115067e-05, + "loss": 3.4201, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918693325244388e-05, + "loss": 3.4203, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917854730493336e-05, + "loss": 3.4243, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170161357422843e-05, + "loss": 3.4151, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9161775409912323e-05, + "loss": 3.4167, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153389462401803e-05, + "loss": 3.418, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145003514891283e-05, + "loss": 3.4204, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136617567380763e-05, + "loss": 3.4073, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.912823161987024e-05, + "loss": 3.4188, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119862051163452e-05, + "loss": 3.4041, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111492482456665e-05, + "loss": 3.4251, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103106534946145e-05, + "loss": 3.4084, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094720587435625e-05, + "loss": 3.4162, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086334639925104e-05, + "loss": 3.41, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077948692414584e-05, + "loss": 3.4235, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.906956274490406e-05, + "loss": 3.4214, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061176797393544e-05, + "loss": 3.4133, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052790849883024e-05, + "loss": 3.4172, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044421281176237e-05, + "loss": 3.4307, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036035333665713e-05, + "loss": 3.4229, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9027649386155193e-05, + "loss": 3.4124, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019263438644673e-05, + "loss": 3.4111, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9010893869937886e-05, + "loss": 3.4144, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002507922427366e-05, + "loss": 3.4178, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994121974916846e-05, + "loss": 3.4105, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985736027406326e-05, + "loss": 3.405, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977366458699535e-05, + "loss": 3.4224, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.8968980511189015e-05, + "loss": 3.4123, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.8960594563678498e-05, + "loss": 3.4208, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.8952208616167978e-05, + "loss": 3.416, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8943839047461187e-05, + "loss": 3.4156, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935453099950667e-05, + "loss": 3.4129, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927067152440147e-05, + "loss": 3.4252, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918681204929627e-05, + "loss": 3.4179, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.891031163622284e-05, + "loss": 3.4197, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8901942067516052e-05, + "loss": 3.4077, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8893556120005532e-05, + "loss": 3.4317, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888517017249501e-05, + "loss": 3.4172, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887678422498449e-05, + "loss": 3.4252, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.886839827747397e-05, + "loss": 3.416, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.886001232996345e-05, + "loss": 3.4178, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.885164276125666e-05, + "loss": 3.4154, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.884325681374614e-05, + "loss": 3.4357, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.883487086623562e-05, + "loss": 3.4108, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.88264849187251e-05, + "loss": 3.426, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881809897121458e-05, + "loss": 3.4198, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.880971302370406e-05, + "loss": 3.4142, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.880132707619354e-05, + "loss": 3.4169, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.879294112868302e-05, + "loss": 3.4227, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784571559976233e-05, + "loss": 3.421, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776185612465713e-05, + "loss": 3.4191, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.876779966495519e-05, + "loss": 3.4217, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.859497547149658, + "eval_runtime": 304.3046, + "eval_samples_per_second": 1253.977, + "eval_steps_per_second": 39.188, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.875941371744467e-05, + "loss": 3.4159, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751027769934153e-05, + "loss": 3.4079, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742641822423633e-05, + "loss": 3.414, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734255874913113e-05, + "loss": 3.4208, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8725886306206322e-05, + "loss": 3.4279, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717500358695802e-05, + "loss": 3.4118, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709130789989014e-05, + "loss": 3.4149, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700744842478494e-05, + "loss": 3.4139, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692358894967974e-05, + "loss": 3.4191, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8683972947457454e-05, + "loss": 3.4267, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675586999946934e-05, + "loss": 3.4081, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667201052436414e-05, + "loss": 3.4082, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8658815104925894e-05, + "loss": 3.4244, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865042915741537e-05, + "loss": 3.4026, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642059588708586e-05, + "loss": 3.415, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633673641198066e-05, + "loss": 3.4048, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625287693687543e-05, + "loss": 3.403, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616901746177023e-05, + "loss": 3.4096, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608532177470235e-05, + "loss": 3.404, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600146229959715e-05, + "loss": 3.4204, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591760282449195e-05, + "loss": 3.4186, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8583374334938675e-05, + "loss": 3.418, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575004766231888e-05, + "loss": 3.4075, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566618818721368e-05, + "loss": 3.4108, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558232871210844e-05, + "loss": 3.4162, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8549846923700324e-05, + "loss": 3.4121, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854147735499354e-05, + "loss": 3.4079, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8533091407483017e-05, + "loss": 3.4215, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8524705459972497e-05, + "loss": 3.4069, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516319512461977e-05, + "loss": 3.4067, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850794994375519e-05, + "loss": 3.4078, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849956399624467e-05, + "loss": 3.419, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849117804873415e-05, + "loss": 3.4158, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848279210122363e-05, + "loss": 3.4263, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847442253251684e-05, + "loss": 3.4015, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466036585006318e-05, + "loss": 3.4146, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457650637495798e-05, + "loss": 3.4213, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449264689985278e-05, + "loss": 3.4018, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.844089512127849e-05, + "loss": 3.4068, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.843250917376797e-05, + "loss": 3.4084, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.842412322625745e-05, + "loss": 3.4105, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841573727874693e-05, + "loss": 3.4107, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.840736771004014e-05, + "loss": 3.4157, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8398981762529623e-05, + "loss": 3.4151, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390595815019103e-05, + "loss": 3.4069, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382226246312315e-05, + "loss": 3.4125, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837384029880179e-05, + "loss": 3.4092, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836545435129127e-05, + "loss": 3.4092, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835706840378075e-05, + "loss": 3.3792, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348698835073964e-05, + "loss": 3.4248, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340312887563444e-05, + "loss": 3.4048, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331926940052924e-05, + "loss": 3.4156, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323540992542404e-05, + "loss": 3.4038, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315171423835613e-05, + "loss": 3.4101, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306785476325093e-05, + "loss": 3.3949, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829841590761831e-05, + "loss": 3.4018, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8290029960107785e-05, + "loss": 3.4195, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281644012597265e-05, + "loss": 3.4035, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273258065086745e-05, + "loss": 3.4181, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264872117576225e-05, + "loss": 3.4098, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256502548869438e-05, + "loss": 3.3965, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8248116601358918e-05, + "loss": 3.4207, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239730653848398e-05, + "loss": 3.3912, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231344706337878e-05, + "loss": 3.4005, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8222958758827358e-05, + "loss": 3.4151, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214572811316838e-05, + "loss": 3.408, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206186863806318e-05, + "loss": 3.4003, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197800916295794e-05, + "loss": 3.4102, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.818943134758901e-05, + "loss": 3.3941, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818104540007849e-05, + "loss": 3.4137, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172659452567966e-05, + "loss": 3.4151, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164273505057446e-05, + "loss": 3.4066, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.815590393635066e-05, + "loss": 3.4152, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.814751798884014e-05, + "loss": 3.416, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813913204132962e-05, + "loss": 3.4252, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.81307460938191e-05, + "loss": 3.4061, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812237652511231e-05, + "loss": 3.4101, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.811399057760179e-05, + "loss": 3.4136, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105604630091268e-05, + "loss": 3.3885, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097218682580748e-05, + "loss": 3.418, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088865492677693e-05, + "loss": 3.415, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080479545167173e-05, + "loss": 3.4135, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072093597656653e-05, + "loss": 3.4218, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063707650146133e-05, + "loss": 3.3972, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055321702635613e-05, + "loss": 3.4014, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046935755125093e-05, + "loss": 3.4075, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038549807614572e-05, + "loss": 3.4147, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030163860104052e-05, + "loss": 3.4098, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8021794291397265e-05, + "loss": 3.4043, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801340834388674e-05, + "loss": 3.4009, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.800502239637622e-05, + "loss": 3.4096, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.79966364488657e-05, + "loss": 3.4053, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988266880158914e-05, + "loss": 3.4068, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7979880932648394e-05, + "loss": 3.4179, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971494985137874e-05, + "loss": 3.411, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7963109037627354e-05, + "loss": 3.4137, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7954739468920563e-05, + "loss": 3.4003, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.7946353521410046e-05, + "loss": 3.409, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793798395270326e-05, + "loss": 3.4087, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792959800519274e-05, + "loss": 3.4124, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921212057682215e-05, + "loss": 3.4049, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912826110171695e-05, + "loss": 3.4073, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904440162661175e-05, + "loss": 3.4071, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896054215150655e-05, + "loss": 3.4102, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788766826764014e-05, + "loss": 3.3956, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787928232012962e-05, + "loss": 3.4099, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870912751422827e-05, + "loss": 3.3938, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862526803912307e-05, + "loss": 3.4136, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854157235205517e-05, + "loss": 3.4011, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845771287695e-05, + "loss": 3.4024, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783738534018448e-05, + "loss": 3.3978, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782899939267396e-05, + "loss": 3.4168, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.782061344516344e-05, + "loss": 3.4069, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.781222749765292e-05, + "loss": 3.4043, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803841550142396e-05, + "loss": 3.4119, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779547198143561e-05, + "loss": 3.4186, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787086033925092e-05, + "loss": 3.4135, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.777870008641457e-05, + "loss": 3.4016, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.777033051770778e-05, + "loss": 3.3997, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776194457019726e-05, + "loss": 3.4084, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775355862268674e-05, + "loss": 3.407, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745172675176218e-05, + "loss": 3.3955, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.77367867276657e-05, + "loss": 3.3968, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.772840078015518e-05, + "loss": 3.4126, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.772001483264466e-05, + "loss": 3.4073, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.771162888513414e-05, + "loss": 3.4074, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.770325931642735e-05, + "loss": 3.4067, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.769487336891683e-05, + "loss": 3.4044, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768648742140631e-05, + "loss": 3.4029, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678101473895793e-05, + "loss": 3.4165, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7669731905189002e-05, + "loss": 3.4029, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661345957678482e-05, + "loss": 3.4118, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765297638897169e-05, + "loss": 3.3972, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764459044146117e-05, + "loss": 3.4202, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636204493950655e-05, + "loss": 3.4028, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627818546440135e-05, + "loss": 3.4168, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619432598929615e-05, + "loss": 3.4068, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7611046651419094e-05, + "loss": 3.4118, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760266070390857e-05, + "loss": 3.402, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759427475639805e-05, + "loss": 3.4255, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7585905187691264e-05, + "loss": 3.3998, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7577519240180747e-05, + "loss": 3.4149, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569133292670223e-05, + "loss": 3.4119, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560747345159703e-05, + "loss": 3.4027, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552377776452916e-05, + "loss": 3.4077, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7543991828942396e-05, + "loss": 3.4089, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7535605881431876e-05, + "loss": 3.4117, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527219933921356e-05, + "loss": 3.409, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518850365214568e-05, + "loss": 3.4097, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.861348867416382, + "eval_runtime": 302.2511, + "eval_samples_per_second": 1262.496, + "eval_steps_per_second": 39.454, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510464417704045e-05, + "loss": 3.3951, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502078470193525e-05, + "loss": 3.4, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493692522683005e-05, + "loss": 3.4011, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485322953976217e-05, + "loss": 3.4087, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.747695338526943e-05, + "loss": 3.4185, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.746856743775891e-05, + "loss": 3.404, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.746018149024839e-05, + "loss": 3.4026, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.745179554273787e-05, + "loss": 3.4053, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443409595227346e-05, + "loss": 3.4084, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435023647716826e-05, + "loss": 3.4121, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426654079010042e-05, + "loss": 3.3982, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741826813149952e-05, + "loss": 3.4027, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7409882183989e-05, + "loss": 3.4134, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.740149623647848e-05, + "loss": 3.3937, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.739311028896796e-05, + "loss": 3.4046, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384724341457438e-05, + "loss": 3.3898, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376338393946918e-05, + "loss": 3.3959, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.736796882524013e-05, + "loss": 3.3979, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.735958287772961e-05, + "loss": 3.3916, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735119693021909e-05, + "loss": 3.4089, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734281098270857e-05, + "loss": 3.4091, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733444141400178e-05, + "loss": 3.4067, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326055466491263e-05, + "loss": 3.4009, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317669518980743e-05, + "loss": 3.4015, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309283571470223e-05, + "loss": 3.4078, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7300914002763432e-05, + "loss": 3.3995, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292528055252912e-05, + "loss": 3.3933, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284142107742392e-05, + "loss": 3.4133, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275756160231872e-05, + "loss": 3.3956, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267386591525084e-05, + "loss": 3.3962, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259000644014564e-05, + "loss": 3.3979, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250614696504044e-05, + "loss": 3.4108, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242228748993524e-05, + "loss": 3.4002, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7233859180286733e-05, + "loss": 3.4191, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225473232776217e-05, + "loss": 3.3943, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217087285265697e-05, + "loss": 3.398, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208701337755173e-05, + "loss": 3.4151, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200331769048386e-05, + "loss": 3.3861, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7191945821537866e-05, + "loss": 3.3998, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183559874027346e-05, + "loss": 3.399, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7175173926516826e-05, + "loss": 3.3965, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7166804357810038e-05, + "loss": 3.4024, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158418410299518e-05, + "loss": 3.4035, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150032462788998e-05, + "loss": 3.4067, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141646515278475e-05, + "loss": 3.3948, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133276946571687e-05, + "loss": 3.4057, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.712489099906117e-05, + "loss": 3.3938, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116505051550647e-05, + "loss": 3.4017, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108119104040127e-05, + "loss": 3.3697, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.709974953533334e-05, + "loss": 3.4097, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.709136358782282e-05, + "loss": 3.3982, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.70829776403123e-05, + "loss": 3.4054, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.707459169280178e-05, + "loss": 3.396, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066222124094992e-05, + "loss": 3.4, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705783617658447e-05, + "loss": 3.3844, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049450229073948e-05, + "loss": 3.3912, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041064281563428e-05, + "loss": 3.4109, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703269471285664e-05, + "loss": 3.3885, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702430876534612e-05, + "loss": 3.4057, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.70159228178356e-05, + "loss": 3.4034, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7007553249128813e-05, + "loss": 3.3822, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999167301618293e-05, + "loss": 3.4084, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.699078135410777e-05, + "loss": 3.3876, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698239540659725e-05, + "loss": 3.3885, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974009459086733e-05, + "loss": 3.4025, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965623511576213e-05, + "loss": 3.3974, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957237564065693e-05, + "loss": 3.3897, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.6948851616555173e-05, + "loss": 3.3988, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.6940482047848382e-05, + "loss": 3.3858, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932096100337862e-05, + "loss": 3.4004, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923710152827342e-05, + "loss": 3.4031, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915324205316825e-05, + "loss": 3.4017, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6906954636610034e-05, + "loss": 3.4065, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898568689099514e-05, + "loss": 3.4046, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6890182741588994e-05, + "loss": 3.4143, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6881796794078474e-05, + "loss": 3.3929, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873427225371687e-05, + "loss": 3.4047, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865041277861167e-05, + "loss": 3.4011, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856655330350647e-05, + "loss": 3.3827, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848269382840123e-05, + "loss": 3.4061, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839916192937065e-05, + "loss": 3.4047, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6831530245426548e-05, + "loss": 3.3998, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823144297916028e-05, + "loss": 3.4134, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6814758350405508e-05, + "loss": 3.3837, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806372402894988e-05, + "loss": 3.3885, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6797986455384468e-05, + "loss": 3.4, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789600507873948e-05, + "loss": 3.4035, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781214560363424e-05, + "loss": 3.4004, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.677284499165664e-05, + "loss": 3.3939, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.676445904414612e-05, + "loss": 3.3896, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756073096635597e-05, + "loss": 3.3967, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747687149125077e-05, + "loss": 3.3993, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.673931758041829e-05, + "loss": 3.3972, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.673093163290777e-05, + "loss": 3.407, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.672254568539725e-05, + "loss": 3.4072, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.671415973788673e-05, + "loss": 3.3983, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.670579016917994e-05, + "loss": 3.3932, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.669740422166942e-05, + "loss": 3.3983, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689018274158898e-05, + "loss": 3.3979, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680632326648378e-05, + "loss": 3.4038, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672262757941594e-05, + "loss": 3.3951, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666387681043107e-05, + "loss": 3.3959, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.665549086292055e-05, + "loss": 3.3986, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664710491541003e-05, + "loss": 3.392, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6638735346703243e-05, + "loss": 3.3947, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630349399192723e-05, + "loss": 3.3959, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6621963451682203e-05, + "loss": 3.3843, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613577504171683e-05, + "loss": 3.4066, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6605207935464895e-05, + "loss": 3.3932, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.6596821987954372e-05, + "loss": 3.3872, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588436040443852e-05, + "loss": 3.387, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580066471737064e-05, + "loss": 3.4042, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6571680524226544e-05, + "loss": 3.3985, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.6563294576716024e-05, + "loss": 3.3913, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.6554908629205504e-05, + "loss": 3.4023, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.6546539060498717e-05, + "loss": 3.4103, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.6538153112988193e-05, + "loss": 3.3998, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6529767165477673e-05, + "loss": 3.3938, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521381217967156e-05, + "loss": 3.3926, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651301164926037e-05, + "loss": 3.3954, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504625701749846e-05, + "loss": 3.3991, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496239754239325e-05, + "loss": 3.3859, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487853806728805e-05, + "loss": 3.3884, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479484238022018e-05, + "loss": 3.4017, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471098290511498e-05, + "loss": 3.3939, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6462712343000978e-05, + "loss": 3.3954, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454326395490458e-05, + "loss": 3.4006, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6445956826783667e-05, + "loss": 3.3908, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437570879273147e-05, + "loss": 3.3925, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429184931762627e-05, + "loss": 3.4047, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.642079898425211e-05, + "loss": 3.3935, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641242941554532e-05, + "loss": 3.403, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404059846838532e-05, + "loss": 3.3861, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639567389932801e-05, + "loss": 3.4056, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387287951817488e-05, + "loss": 3.3977, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.637890200430697e-05, + "loss": 3.4042, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.637051605679645e-05, + "loss": 3.3969, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.636213010928593e-05, + "loss": 3.3968, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.635376054057914e-05, + "loss": 3.3971, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.634537459306862e-05, + "loss": 3.4098, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.63369886455581e-05, + "loss": 3.3922, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632860269804758e-05, + "loss": 3.3998, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320216750537064e-05, + "loss": 3.4031, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6311830803026544e-05, + "loss": 3.393, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630344485551602e-05, + "loss": 3.3965, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.62950589080055e-05, + "loss": 3.404, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6286689339298713e-05, + "loss": 3.3996, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278303391788193e-05, + "loss": 3.3989, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6269917444277673e-05, + "loss": 3.3975, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8634541034698486, + "eval_runtime": 302.2877, + "eval_samples_per_second": 1262.344, + "eval_steps_per_second": 39.449, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261531496767153e-05, + "loss": 3.3852, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6253145549256633e-05, + "loss": 3.3905, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244759601746113e-05, + "loss": 3.3938, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236373654235593e-05, + "loss": 3.3992, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.62280040855288e-05, + "loss": 3.4042, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621961813801828e-05, + "loss": 3.3947, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.6211232190507765e-05, + "loss": 3.3932, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202846242997245e-05, + "loss": 3.3963, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194460295486725e-05, + "loss": 3.3989, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.61860743479762e-05, + "loss": 3.4006, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6177704779269414e-05, + "loss": 3.3928, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169318831758894e-05, + "loss": 3.3915, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6160932884248374e-05, + "loss": 3.4015, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152546936737854e-05, + "loss": 3.383, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144160989227334e-05, + "loss": 3.3928, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135775041716814e-05, + "loss": 3.3778, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127405473010026e-05, + "loss": 3.389, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119019525499503e-05, + "loss": 3.391, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110633577988986e-05, + "loss": 3.3812, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102247630478466e-05, + "loss": 3.4001, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6093861682967946e-05, + "loss": 3.3982, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085475735457426e-05, + "loss": 3.3934, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077089787946906e-05, + "loss": 3.3926, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068703840436382e-05, + "loss": 3.3911, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060334271729595e-05, + "loss": 3.3993, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6051948324219078e-05, + "loss": 3.3919, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043562376708558e-05, + "loss": 3.3799, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035176429198035e-05, + "loss": 3.403, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026806860491247e-05, + "loss": 3.3855, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018420912980727e-05, + "loss": 3.3863, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010034965470207e-05, + "loss": 3.3918, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001649017959687e-05, + "loss": 3.3959, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.59932794492529e-05, + "loss": 3.3905, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598489350174238e-05, + "loss": 3.4088, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.5976507554231856e-05, + "loss": 3.387, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5968121606721336e-05, + "loss": 3.3898, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595975203801455e-05, + "loss": 3.405, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595136609050403e-05, + "loss": 3.3755, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594298014299351e-05, + "loss": 3.3879, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593459419548299e-05, + "loss": 3.3904, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.59262246267762e-05, + "loss": 3.3855, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591783867926568e-05, + "loss": 3.3935, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909452731755157e-05, + "loss": 3.3943, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590106678424464e-05, + "loss": 3.3947, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892697215537853e-05, + "loss": 3.3875, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.588431126802733e-05, + "loss": 3.3946, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587592532051681e-05, + "loss": 3.3854, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586753937300629e-05, + "loss": 3.3952, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859169804299502e-05, + "loss": 3.3606, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850783856788982e-05, + "loss": 3.3943, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842397909278462e-05, + "loss": 3.3891, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834028340571675e-05, + "loss": 3.3984, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.582564239306115e-05, + "loss": 3.3831, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.581725644555063e-05, + "loss": 3.3906, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.580887049804011e-05, + "loss": 3.3764, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800500929333327e-05, + "loss": 3.3794, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792114981822804e-05, + "loss": 3.4039, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783729034312284e-05, + "loss": 3.3773, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775343086801763e-05, + "loss": 3.3967, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5766973518094976e-05, + "loss": 3.3948, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.575860394938819e-05, + "loss": 3.3701, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.575021800187767e-05, + "loss": 3.4008, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.574183205436715e-05, + "loss": 3.3789, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733446106856625e-05, + "loss": 3.3779, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725060159346105e-05, + "loss": 3.3901, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716674211835585e-05, + "loss": 3.3916, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708288264325065e-05, + "loss": 3.3785, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5699902316814548e-05, + "loss": 3.3895, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691532748107757e-05, + "loss": 3.3754, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683146800597237e-05, + "loss": 3.3905, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674760853086717e-05, + "loss": 3.3944, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666374905576197e-05, + "loss": 3.3915, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565800533686941e-05, + "loss": 3.3945, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.564961938935889e-05, + "loss": 3.391, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564123344184837e-05, + "loss": 3.406, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.563284749433785e-05, + "loss": 3.3838, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562447792563106e-05, + "loss": 3.3983, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561609197812054e-05, + "loss": 3.3836, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560770603061002e-05, + "loss": 3.3777, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599320083099502e-05, + "loss": 3.3936, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5590966893196443e-05, + "loss": 3.3932, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582580945685923e-05, + "loss": 3.3902, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.55741949981754e-05, + "loss": 3.4017, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556580905066488e-05, + "loss": 3.3751, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557423103154363e-05, + "loss": 3.3808, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549037155643843e-05, + "loss": 3.3901, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540651208133323e-05, + "loss": 3.3912, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532265260622803e-05, + "loss": 3.3884, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5523895691916012e-05, + "loss": 3.3816, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515509744405492e-05, + "loss": 3.3848, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507123796894972e-05, + "loss": 3.3871, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498737849384452e-05, + "loss": 3.389, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490368280677665e-05, + "loss": 3.3835, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5481982333167145e-05, + "loss": 3.3954, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473596385656624e-05, + "loss": 3.3957, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465210438146104e-05, + "loss": 3.3881, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5456840869439314e-05, + "loss": 3.3828, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448454921928797e-05, + "loss": 3.3886, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440068974418277e-05, + "loss": 3.3888, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431683026907753e-05, + "loss": 3.3921, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423313458200966e-05, + "loss": 3.3864, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5414927510690446e-05, + "loss": 3.3847, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406541563179926e-05, + "loss": 3.3877, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398155615669406e-05, + "loss": 3.3866, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389786046962618e-05, + "loss": 3.3857, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381400099452098e-05, + "loss": 3.3833, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373014151941578e-05, + "loss": 3.3764, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364628204431055e-05, + "loss": 3.3938, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356258635724267e-05, + "loss": 3.3868, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.534787268821375e-05, + "loss": 3.3775, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339486740703227e-05, + "loss": 3.3795, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331100793192707e-05, + "loss": 3.3926, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.532273122448592e-05, + "loss": 3.3887, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.53143452769754e-05, + "loss": 3.3789, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.530595932946488e-05, + "loss": 3.3923, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297589760758092e-05, + "loss": 3.4007, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289203813247572e-05, + "loss": 3.3892, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5280817865737052e-05, + "loss": 3.3835, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527244829703026e-05, + "loss": 3.3823, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526406234951974e-05, + "loss": 3.386, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255676402009223e-05, + "loss": 3.3914, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.52472904544987e-05, + "loss": 3.3768, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.523890450698818e-05, + "loss": 3.376, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.523051855947766e-05, + "loss": 3.3898, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.522213261196714e-05, + "loss": 3.3843, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.521374666445662e-05, + "loss": 3.3874, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205377095749831e-05, + "loss": 3.391, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196991148239311e-05, + "loss": 3.3795, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188605200728791e-05, + "loss": 3.383, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180219253218273e-05, + "loss": 3.3952, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171849684511482e-05, + "loss": 3.3832, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163463737000964e-05, + "loss": 3.3939, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155094168294173e-05, + "loss": 3.3792, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146708220783653e-05, + "loss": 3.3901, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138322273273134e-05, + "loss": 3.392, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5129936325762614e-05, + "loss": 3.3909, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121550378252094e-05, + "loss": 3.3922, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113164430741574e-05, + "loss": 3.3865, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104794862034785e-05, + "loss": 3.3893, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096408914524265e-05, + "loss": 3.4011, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088022967013745e-05, + "loss": 3.3846, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079637019503227e-05, + "loss": 3.3883, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071251071992703e-05, + "loss": 3.3942, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062865124482183e-05, + "loss": 3.3834, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054479176971665e-05, + "loss": 3.3852, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046093229461145e-05, + "loss": 3.3972, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037723660754356e-05, + "loss": 3.3849, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029337713243836e-05, + "loss": 3.3898, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020951765733315e-05, + "loss": 3.3868, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.864868640899658, + "eval_runtime": 303.1472, + "eval_samples_per_second": 1258.765, + "eval_steps_per_second": 39.337, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012565818222795e-05, + "loss": 3.3786, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004196249516006e-05, + "loss": 3.3793, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995810302005486e-05, + "loss": 3.3826, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987424354494966e-05, + "loss": 3.3916, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979054785788177e-05, + "loss": 3.3911, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970668838277657e-05, + "loss": 3.3872, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962282890767137e-05, + "loss": 3.387, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4953896943256618e-05, + "loss": 3.3861, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945510995746098e-05, + "loss": 3.3858, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937125048235578e-05, + "loss": 3.3913, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.492875547952879e-05, + "loss": 3.3863, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4920369532018269e-05, + "loss": 3.3786, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4911983584507749e-05, + "loss": 3.3923, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903597636997229e-05, + "loss": 3.375, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.489521168948671e-05, + "loss": 3.3821, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886825741976187e-05, + "loss": 3.3702, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878439794465667e-05, + "loss": 3.3769, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870053846955149e-05, + "loss": 3.3781, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861684278248358e-05, + "loss": 3.3747, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853298330737838e-05, + "loss": 3.3845, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.484491238322732e-05, + "loss": 3.3914, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836542814520532e-05, + "loss": 3.3839, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.482815686701001e-05, + "loss": 3.3792, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.481977091949949e-05, + "loss": 3.3861, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.481138497198897e-05, + "loss": 3.3878, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803015403282183e-05, + "loss": 3.3782, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794629455771661e-05, + "loss": 3.3717, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786243508261141e-05, + "loss": 3.3936, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4777857560750621e-05, + "loss": 3.3779, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769487992043832e-05, + "loss": 3.374, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761102044533312e-05, + "loss": 3.379, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752716097022792e-05, + "loss": 3.3832, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744330149512273e-05, + "loss": 3.3844, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735960580805482e-05, + "loss": 3.3993, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727574633294964e-05, + "loss": 3.3709, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719188685784444e-05, + "loss": 3.3866, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710802738273924e-05, + "loss": 3.3927, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702433169567135e-05, + "loss": 3.3637, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694047222056615e-05, + "loss": 3.3798, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685661274546095e-05, + "loss": 3.3819, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677275327035575e-05, + "loss": 3.3713, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668905758328785e-05, + "loss": 3.3889, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660519810818265e-05, + "loss": 3.3795, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652133863307745e-05, + "loss": 3.3867, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643747915797227e-05, + "loss": 3.3753, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635378347090436e-05, + "loss": 3.3814, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4626992399579918e-05, + "loss": 3.3729, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618606452069398e-05, + "loss": 3.3875, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610220504558878e-05, + "loss": 3.3529, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.4601850935852088e-05, + "loss": 3.3832, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593464988341568e-05, + "loss": 3.3792, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585079040831048e-05, + "loss": 3.3901, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.4576693093320528e-05, + "loss": 3.3693, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4568323524613739e-05, + "loss": 3.378, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559937577103219e-05, + "loss": 3.3709, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551551629592699e-05, + "loss": 3.3716, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.454316568208218e-05, + "loss": 3.3956, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.453477973457166e-05, + "loss": 3.3657, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526393787061137e-05, + "loss": 3.3881, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518007839550619e-05, + "loss": 3.3856, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509638270843831e-05, + "loss": 3.3629, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501252323333308e-05, + "loss": 3.3891, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.449286637582279e-05, + "loss": 3.3658, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.448448042831227e-05, + "loss": 3.3689, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.447609448080175e-05, + "loss": 3.3797, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.446770853329123e-05, + "loss": 3.3813, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459322585780711e-05, + "loss": 3.3676, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450936638270191e-05, + "loss": 3.3821, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.44425670695634e-05, + "loss": 3.3649, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434181122052882e-05, + "loss": 3.3784, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425795174542362e-05, + "loss": 3.3867, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417409227031842e-05, + "loss": 3.3784, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409039658325052e-05, + "loss": 3.387, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400653710814532e-05, + "loss": 3.3814, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392267763304012e-05, + "loss": 3.3956, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.438388181579349e-05, + "loss": 3.3755, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375512247086703e-05, + "loss": 3.3882, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367126299576183e-05, + "loss": 3.375, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358740352065665e-05, + "loss": 3.3652, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350354404555141e-05, + "loss": 3.3835, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341984835848354e-05, + "loss": 3.3852, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333598888337835e-05, + "loss": 3.3843, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325212940827315e-05, + "loss": 3.3936, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316826993316792e-05, + "loss": 3.3683, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308457424610006e-05, + "loss": 3.3672, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300071477099486e-05, + "loss": 3.3783, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291685529588964e-05, + "loss": 3.3885, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4283299582078444e-05, + "loss": 3.3768, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274930013371657e-05, + "loss": 3.3696, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266544065861137e-05, + "loss": 3.3763, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258158118350615e-05, + "loss": 3.3737, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249772170840095e-05, + "loss": 3.3785, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241402602133307e-05, + "loss": 3.3744, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233016654622789e-05, + "loss": 3.3868, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224630707112266e-05, + "loss": 3.3879, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216244759601746e-05, + "loss": 3.3802, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.420787519089496e-05, + "loss": 3.372, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199489243384436e-05, + "loss": 3.3766, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191103295873916e-05, + "loss": 3.3767, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.418273372716713e-05, + "loss": 3.3883, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417434777965661e-05, + "loss": 3.3721, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4165961832146089e-05, + "loss": 3.3746, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157575884635569e-05, + "loss": 3.3799, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149206315928781e-05, + "loss": 3.3721, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140820368418261e-05, + "loss": 3.3795, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.413243442090774e-05, + "loss": 3.3747, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.412404847339722e-05, + "loss": 3.3629, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115678904690432e-05, + "loss": 3.385, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.410729295717991e-05, + "loss": 3.3728, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.409890700966939e-05, + "loss": 3.3706, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.409052106215887e-05, + "loss": 3.3657, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082151493452084e-05, + "loss": 3.381, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.407376554594156e-05, + "loss": 3.3831, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065379598431042e-05, + "loss": 3.3665, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056993650920522e-05, + "loss": 3.3834, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048624082213735e-05, + "loss": 3.3865, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040238134703213e-05, + "loss": 3.3855, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031852187192693e-05, + "loss": 3.3743, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023466239682173e-05, + "loss": 3.3722, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015096670975384e-05, + "loss": 3.3764, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006710723464864e-05, + "loss": 3.3822, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998324775954344e-05, + "loss": 3.3644, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3989938828443824e-05, + "loss": 3.3718, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981552880933305e-05, + "loss": 3.3708, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973166933422785e-05, + "loss": 3.3763, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964780985912265e-05, + "loss": 3.3765, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956411417205476e-05, + "loss": 3.3808, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948025469694956e-05, + "loss": 3.368, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939655900988167e-05, + "loss": 3.3728, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931269953477647e-05, + "loss": 3.3886, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3922884005967127e-05, + "loss": 3.3737, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914498058456607e-05, + "loss": 3.3867, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906128489749817e-05, + "loss": 3.3639, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897742542239297e-05, + "loss": 3.3838, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889356594728777e-05, + "loss": 3.3804, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880970647218259e-05, + "loss": 3.3813, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872584699707739e-05, + "loss": 3.3809, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864198752197215e-05, + "loss": 3.3716, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855812804686697e-05, + "loss": 3.3832, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847426857176177e-05, + "loss": 3.39, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839057288469388e-05, + "loss": 3.3765, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830671340958868e-05, + "loss": 3.3781, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822285393448348e-05, + "loss": 3.3835, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813899445937828e-05, + "loss": 3.3715, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805529877231038e-05, + "loss": 3.3748, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797143929720518e-05, + "loss": 3.3872, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788757982209998e-05, + "loss": 3.3761, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780372034699478e-05, + "loss": 3.3823, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772002465992689e-05, + "loss": 3.3748, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.865447521209717, + "eval_runtime": 303.3797, + "eval_samples_per_second": 1257.8, + "eval_steps_per_second": 39.307, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763616518482169e-05, + "loss": 3.3795, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.375523057097165e-05, + "loss": 3.3682, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.374684462346113e-05, + "loss": 3.3744, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.373845867595061e-05, + "loss": 3.3819, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730089107243821e-05, + "loss": 3.3809, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721703159733301e-05, + "loss": 3.3798, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713333591026512e-05, + "loss": 3.3732, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704947643515992e-05, + "loss": 3.375, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696561696005472e-05, + "loss": 3.3758, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688175748494952e-05, + "loss": 3.3868, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679789800984432e-05, + "loss": 3.371, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671403853473914e-05, + "loss": 3.3712, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.3663034284767123e-05, + "loss": 3.3817, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654648337256604e-05, + "loss": 3.3612, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646262389746084e-05, + "loss": 3.3723, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3637876442235564e-05, + "loss": 3.3607, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3629506873528775e-05, + "loss": 3.3715, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621120926018255e-05, + "loss": 3.3674, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612734978507735e-05, + "loss": 3.3666, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604349030997215e-05, + "loss": 3.3681, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3595963083486693e-05, + "loss": 3.3839, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587577135976173e-05, + "loss": 3.3745, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579191188465653e-05, + "loss": 3.3701, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3570805240955135e-05, + "loss": 3.3729, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3562435672248344e-05, + "loss": 3.3836, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554049724737824e-05, + "loss": 3.3657, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545663777227305e-05, + "loss": 3.3614, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537277829716785e-05, + "loss": 3.3831, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528908261009996e-05, + "loss": 3.365, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520522313499476e-05, + "loss": 3.3647, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512136365988956e-05, + "loss": 3.3727, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503750418478436e-05, + "loss": 3.3698, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495380849771647e-05, + "loss": 3.3791, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3486994902261127e-05, + "loss": 3.3836, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478608954750607e-05, + "loss": 3.366, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470223007240087e-05, + "loss": 3.3698, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461853438533298e-05, + "loss": 3.3821, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453467491022778e-05, + "loss": 3.3565, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.344508154351226e-05, + "loss": 3.3774, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436695596001739e-05, + "loss": 3.3664, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428326027294948e-05, + "loss": 3.3615, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.341994007978443e-05, + "loss": 3.3768, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.341155413227391e-05, + "loss": 3.3763, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.340316818476339e-05, + "loss": 3.3702, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.33947986160566e-05, + "loss": 3.3657, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.338641266854608e-05, + "loss": 3.3696, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.337802672103556e-05, + "loss": 3.37, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.336964077352504e-05, + "loss": 3.3736, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361271204818251e-05, + "loss": 3.3463, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3352885257307731e-05, + "loss": 3.3712, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344499309797213e-05, + "loss": 3.373, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336129741090422e-05, + "loss": 3.3788, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327743793579902e-05, + "loss": 3.3629, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3319357846069384e-05, + "loss": 3.3676, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310971898558863e-05, + "loss": 3.3593, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302602329852074e-05, + "loss": 3.3611, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3294216382341554e-05, + "loss": 3.3814, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285830434831034e-05, + "loss": 3.3536, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3277444487320514e-05, + "loss": 3.3801, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269074918613725e-05, + "loss": 3.374, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260705349906936e-05, + "loss": 3.3578, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252319402396416e-05, + "loss": 3.3798, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243933454885896e-05, + "loss": 3.3523, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235547507375376e-05, + "loss": 3.3571, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227161559864856e-05, + "loss": 3.3703, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218775612354337e-05, + "loss": 3.373, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210389664843817e-05, + "loss": 3.354, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202003717333294e-05, + "loss": 3.3786, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193634148626508e-05, + "loss": 3.3531, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185248201115988e-05, + "loss": 3.366, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176862253605466e-05, + "loss": 3.3782, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168476306094946e-05, + "loss": 3.3709, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160106737388159e-05, + "loss": 3.3752, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151720789877639e-05, + "loss": 3.3724, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143334842367117e-05, + "loss": 3.3868, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134948894856597e-05, + "loss": 3.3657, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.312657932614981e-05, + "loss": 3.378, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118193378639291e-05, + "loss": 3.3614, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109807431128767e-05, + "loss": 3.3579, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101421483618247e-05, + "loss": 3.3721, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.309306829371519e-05, + "loss": 3.3717, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.308468234620467e-05, + "loss": 3.3726, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076296398694152e-05, + "loss": 3.3824, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3067910451183632e-05, + "loss": 3.3643, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059524503673112e-05, + "loss": 3.357, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.305113855616259e-05, + "loss": 3.3658, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.304275260865207e-05, + "loss": 3.379, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.303436666114155e-05, + "loss": 3.3666, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025997092434763e-05, + "loss": 3.3581, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017611144924241e-05, + "loss": 3.3668, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009225197413721e-05, + "loss": 3.3636, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3000839249903201e-05, + "loss": 3.3704, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992469681196412e-05, + "loss": 3.365, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984083733685892e-05, + "loss": 3.3742, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975697786175372e-05, + "loss": 3.38, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967311838664853e-05, + "loss": 3.3677, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958942269958062e-05, + "loss": 3.3624, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2950572701251277e-05, + "loss": 3.3681, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942186753740757e-05, + "loss": 3.3688, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933800806230237e-05, + "loss": 3.3751, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2925414858719715e-05, + "loss": 3.3653, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917028911209195e-05, + "loss": 3.363, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908642963698675e-05, + "loss": 3.3719, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900257016188155e-05, + "loss": 3.3643, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891871068677636e-05, + "loss": 3.3646, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883501499970845e-05, + "loss": 3.3663, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875115552460325e-05, + "loss": 3.3567, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866729604949807e-05, + "loss": 3.3733, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858360036243016e-05, + "loss": 3.3659, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849974088732498e-05, + "loss": 3.3592, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841588141221978e-05, + "loss": 3.356, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833202193711458e-05, + "loss": 3.3679, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824816246200938e-05, + "loss": 3.374, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816430298690418e-05, + "loss": 3.3594, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808044351179896e-05, + "loss": 3.3716, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799658403669376e-05, + "loss": 3.3725, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.279128883496259e-05, + "loss": 3.378, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782902887452067e-05, + "loss": 3.3665, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774516939941547e-05, + "loss": 3.361, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.276614737123476e-05, + "loss": 3.3656, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.275776142372424e-05, + "loss": 3.3716, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749375476213717e-05, + "loss": 3.354, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2740989528703199e-05, + "loss": 3.3629, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732603581192679e-05, + "loss": 3.3629, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724217633682159e-05, + "loss": 3.3657, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715831686171639e-05, + "loss": 3.3646, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.270746211746485e-05, + "loss": 3.3752, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.269907616995433e-05, + "loss": 3.3554, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.269069022244381e-05, + "loss": 3.3638, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682304274933291e-05, + "loss": 3.3775, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.26739347062265e-05, + "loss": 3.3669, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.266554875871598e-05, + "loss": 3.3753, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657179190009191e-05, + "loss": 3.3552, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648793242498671e-05, + "loss": 3.3728, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640407294988153e-05, + "loss": 3.3725, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632021347477633e-05, + "loss": 3.3691, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623635399967112e-05, + "loss": 3.368, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615249452456592e-05, + "loss": 3.3654, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.260686350494607e-05, + "loss": 3.3793, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.259847755743555e-05, + "loss": 3.3719, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590107988728763e-05, + "loss": 3.3728, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581722041218245e-05, + "loss": 3.3642, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2573336093707721e-05, + "loss": 3.3766, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564950146197201e-05, + "loss": 3.3656, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556580577490415e-05, + "loss": 3.3607, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548194629979895e-05, + "loss": 3.3805, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539808682469372e-05, + "loss": 3.3622, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531422734958854e-05, + "loss": 3.3759, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523053166252066e-05, + "loss": 3.3606, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.866931438446045, + "eval_runtime": 304.0939, + "eval_samples_per_second": 1254.846, + "eval_steps_per_second": 39.215, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514667218741544e-05, + "loss": 3.3584, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506281271231024e-05, + "loss": 3.3608, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497911702524235e-05, + "loss": 3.3634, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489525755013717e-05, + "loss": 3.3687, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481139807503197e-05, + "loss": 3.3723, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472753859992677e-05, + "loss": 3.3706, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464400670089618e-05, + "loss": 3.3609, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456014722579098e-05, + "loss": 3.3639, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447628775068578e-05, + "loss": 3.367, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.243924282755806e-05, + "loss": 3.376, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430856880047538e-05, + "loss": 3.3632, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422470932537018e-05, + "loss": 3.362, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.241410136383023e-05, + "loss": 3.3735, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2405715416319709e-05, + "loss": 3.353, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397329468809189e-05, + "loss": 3.3601, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388943521298669e-05, + "loss": 3.3543, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.238055757378815e-05, + "loss": 3.362, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372171626277629e-05, + "loss": 3.3537, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363785678767109e-05, + "loss": 3.3571, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355399731256589e-05, + "loss": 3.3621, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.23470301625498e-05, + "loss": 3.3701, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.233864421503928e-05, + "loss": 3.3661, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330258267528761e-05, + "loss": 3.3572, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321872320018241e-05, + "loss": 3.3664, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2313502751311452e-05, + "loss": 3.3735, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305116803800932e-05, + "loss": 3.3563, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296730856290412e-05, + "loss": 3.3523, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.228834490877989e-05, + "loss": 3.3722, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2279975340073102e-05, + "loss": 3.3536, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2271589392562582e-05, + "loss": 3.3599, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263203445052062e-05, + "loss": 3.3581, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254817497541542e-05, + "loss": 3.362, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246447928834753e-05, + "loss": 3.3662, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238061981324233e-05, + "loss": 3.3739, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229676033813715e-05, + "loss": 3.36, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221306465106924e-05, + "loss": 3.3616, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2212920517596404e-05, + "loss": 3.3726, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204534570085885e-05, + "loss": 3.3487, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196148622575364e-05, + "loss": 3.3656, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187779053868576e-05, + "loss": 3.3549, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179393106358056e-05, + "loss": 3.3563, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171007158847536e-05, + "loss": 3.3636, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162621211337014e-05, + "loss": 3.3709, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154251642630227e-05, + "loss": 3.3611, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145865695119707e-05, + "loss": 3.3594, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137479747609187e-05, + "loss": 3.3604, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129093800098667e-05, + "loss": 3.3582, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2120724231391877e-05, + "loss": 3.3618, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112338283881357e-05, + "loss": 3.3379, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103952336370837e-05, + "loss": 3.3622, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095566388860317e-05, + "loss": 3.3629, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.208719682015353e-05, + "loss": 3.3712, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.207881087264301e-05, + "loss": 3.352, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070441303936219e-05, + "loss": 3.352, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.20620553564257e-05, + "loss": 3.3498, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.205366940891518e-05, + "loss": 3.3491, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.204528346140466e-05, + "loss": 3.3753, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036897513894139e-05, + "loss": 3.3479, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.202851156638362e-05, + "loss": 3.3673, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.20201256188731e-05, + "loss": 3.3616, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011756050166311e-05, + "loss": 3.3507, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003370102655791e-05, + "loss": 3.3678, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994984155145271e-05, + "loss": 3.3459, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.198659820763475e-05, + "loss": 3.3486, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978212260124231e-05, + "loss": 3.3581, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.196982631261371e-05, + "loss": 3.3647, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.196144036510319e-05, + "loss": 3.3462, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1953054417592669e-05, + "loss": 3.3677, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944684848885882e-05, + "loss": 3.3407, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936298901375361e-05, + "loss": 3.3575, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927912953864841e-05, + "loss": 3.3676, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919527006354321e-05, + "loss": 3.3619, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911157437647532e-05, + "loss": 3.3626, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902771490137012e-05, + "loss": 3.365, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1894385542626492e-05, + "loss": 3.375, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885999595115972e-05, + "loss": 3.3582, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1877630026409185e-05, + "loss": 3.3721, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869244078898664e-05, + "loss": 3.3506, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860858131388143e-05, + "loss": 3.3467, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852472183877623e-05, + "loss": 3.3608, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844118993974566e-05, + "loss": 3.365, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835733046464046e-05, + "loss": 3.3623, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827347098953526e-05, + "loss": 3.3753, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818961151443006e-05, + "loss": 3.3552, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810575203932486e-05, + "loss": 3.3436, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802189256421966e-05, + "loss": 3.3594, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793803308911446e-05, + "loss": 3.3662, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785417361400926e-05, + "loss": 3.3577, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777047792694138e-05, + "loss": 3.3524, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768661845183616e-05, + "loss": 3.3587, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760275897673096e-05, + "loss": 3.3523, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751889950162576e-05, + "loss": 3.3625, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743520381455787e-05, + "loss": 3.3526, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735134433945267e-05, + "loss": 3.3649, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1726748486434749e-05, + "loss": 3.3719, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718362538924229e-05, + "loss": 3.3612, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1709992970217438e-05, + "loss": 3.3515, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170162340151065e-05, + "loss": 3.359, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.169323745400013e-05, + "loss": 3.3582, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168485150648961e-05, + "loss": 3.3633, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.167646555897909e-05, + "loss": 3.357, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.166807961146857e-05, + "loss": 3.3541, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.165969366395805e-05, + "loss": 3.3586, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.165130771644753e-05, + "loss": 3.356, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.164292176893701e-05, + "loss": 3.3583, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.163455220023022e-05, + "loss": 3.3556, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.16261662527197e-05, + "loss": 3.3496, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.161778030520918e-05, + "loss": 3.3629, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.160939435769866e-05, + "loss": 3.3586, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601024788991873e-05, + "loss": 3.3451, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592638841481351e-05, + "loss": 3.3487, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584252893970831e-05, + "loss": 3.3527, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1575866946460311e-05, + "loss": 3.3702, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1567497377753524e-05, + "loss": 3.3513, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559111430243002e-05, + "loss": 3.3599, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1550725482732484e-05, + "loss": 3.3576, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1542339535221964e-05, + "loss": 3.3738, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533969966515174e-05, + "loss": 3.3565, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525584019004654e-05, + "loss": 3.3515, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517198071494134e-05, + "loss": 3.3589, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508812123983614e-05, + "loss": 3.3573, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500442555276825e-05, + "loss": 3.3456, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492056607766305e-05, + "loss": 3.3537, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483670660255785e-05, + "loss": 3.3544, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475284712745265e-05, + "loss": 3.3552, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466915144038476e-05, + "loss": 3.3509, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458529196527956e-05, + "loss": 3.3649, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450143249017436e-05, + "loss": 3.3524, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441757301506916e-05, + "loss": 3.3556, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433387732800126e-05, + "loss": 3.3654, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425001785289608e-05, + "loss": 3.3579, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416615837779088e-05, + "loss": 3.3634, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408229890268566e-05, + "loss": 3.349, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399860321561779e-05, + "loss": 3.362, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391474374051259e-05, + "loss": 3.3661, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383088426540739e-05, + "loss": 3.357, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.137471885783395e-05, + "loss": 3.3611, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.136633291032343e-05, + "loss": 3.3545, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.135794696281291e-05, + "loss": 3.3695, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.134956101530239e-05, + "loss": 3.3621, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.13411914465956e-05, + "loss": 3.3621, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.133280549908508e-05, + "loss": 3.3561, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324419551574562e-05, + "loss": 3.3648, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.131603360406404e-05, + "loss": 3.3533, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130766403535725e-05, + "loss": 3.3514, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299278087846732e-05, + "loss": 3.3723, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129089214033621e-05, + "loss": 3.3532, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128250619282569e-05, + "loss": 3.3657, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274136624118903e-05, + "loss": 3.3532, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.8672256469726562, + "eval_runtime": 305.0941, + "eval_samples_per_second": 1250.732, + "eval_steps_per_second": 39.086, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1265750676608383e-05, + "loss": 3.3365, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257364729097861e-05, + "loss": 3.3519, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1248978781587343e-05, + "loss": 3.3524, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1240592834076823e-05, + "loss": 3.3596, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232223265370034e-05, + "loss": 3.3597, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1223837317859514e-05, + "loss": 3.3645, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1215451370348994e-05, + "loss": 3.3524, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207081801642204e-05, + "loss": 3.3529, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198695854131684e-05, + "loss": 3.3561, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190309906621164e-05, + "loss": 3.3679, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1181923959110644e-05, + "loss": 3.3505, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173538011600124e-05, + "loss": 3.3553, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165168442893335e-05, + "loss": 3.3597, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1156782495382815e-05, + "loss": 3.3489, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148396547872297e-05, + "loss": 3.3495, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140010600361775e-05, + "loss": 3.3463, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131624652851255e-05, + "loss": 3.3466, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123238705340735e-05, + "loss": 3.3471, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114852757830217e-05, + "loss": 3.3489, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106466810319695e-05, + "loss": 3.3505, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098097241612907e-05, + "loss": 3.3636, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089711294102387e-05, + "loss": 3.3533, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081325346591865e-05, + "loss": 3.3515, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1072939399081345e-05, + "loss": 3.356, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064569830374558e-05, + "loss": 3.367, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056183882864038e-05, + "loss": 3.3426, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1047797935353516e-05, + "loss": 3.3474, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039411987842998e-05, + "loss": 3.3589, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031042419136209e-05, + "loss": 3.3478, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022672850429421e-05, + "loss": 3.3493, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.10142869029189e-05, + "loss": 3.3448, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.100590095540838e-05, + "loss": 3.3535, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.099751500789786e-05, + "loss": 3.3575, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.098912906038734e-05, + "loss": 3.3617, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980743112876819e-05, + "loss": 3.354, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0972357165366299e-05, + "loss": 3.35, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963987596659512e-05, + "loss": 3.3612, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.095560164914899e-05, + "loss": 3.3383, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.094721570163847e-05, + "loss": 3.3606, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0938829754127951e-05, + "loss": 3.3432, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930460185421162e-05, + "loss": 3.3487, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922074237910642e-05, + "loss": 3.3511, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0913688290400122e-05, + "loss": 3.36, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905302342889602e-05, + "loss": 3.3528, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0896932774182813e-05, + "loss": 3.3495, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888546826672293e-05, + "loss": 3.3505, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880160879161773e-05, + "loss": 3.3498, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0871774931651253e-05, + "loss": 3.3557, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863405362944464e-05, + "loss": 3.3258, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855019415433944e-05, + "loss": 3.3488, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846633467923423e-05, + "loss": 3.3577, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838247520412903e-05, + "loss": 3.3563, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0829877951706114e-05, + "loss": 3.3416, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0821508382999327e-05, + "loss": 3.3473, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813122435488807e-05, + "loss": 3.3407, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0804736487978285e-05, + "loss": 3.3377, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796350540467767e-05, + "loss": 3.3694, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0787964592957247e-05, + "loss": 3.3375, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779578645446726e-05, + "loss": 3.3577, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771192697936205e-05, + "loss": 3.3489, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0762823129229417e-05, + "loss": 3.345, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754437181718897e-05, + "loss": 3.3525, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746051234208377e-05, + "loss": 3.3383, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737665286697857e-05, + "loss": 3.3419, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729279339187337e-05, + "loss": 3.3427, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720893391676815e-05, + "loss": 3.3605, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712507444166297e-05, + "loss": 3.3349, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704121496655777e-05, + "loss": 3.3556, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695751927948988e-05, + "loss": 3.3319, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687365980438468e-05, + "loss": 3.3461, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0678980032927948e-05, + "loss": 3.3588, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670594085417428e-05, + "loss": 3.3578, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.066222451671064e-05, + "loss": 3.3513, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0653838569200118e-05, + "loss": 3.3552, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645452621689598e-05, + "loss": 3.365, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637066674179078e-05, + "loss": 3.346, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0628697105472289e-05, + "loss": 3.3602, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620311157961769e-05, + "loss": 3.3454, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061192521045125e-05, + "loss": 3.3412, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.060353926294073e-05, + "loss": 3.3493, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595186073037672e-05, + "loss": 3.3544, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0586800125527152e-05, + "loss": 3.3547, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578414178016632e-05, + "loss": 3.3628, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570028230506112e-05, + "loss": 3.3545, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0561642282995592e-05, + "loss": 3.3324, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0553256335485072e-05, + "loss": 3.345, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0544870387974552e-05, + "loss": 3.3554, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0536484440464032e-05, + "loss": 3.3494, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528114871757243e-05, + "loss": 3.3424, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0519728924246723e-05, + "loss": 3.3491, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511342976736203e-05, + "loss": 3.3427, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502957029225683e-05, + "loss": 3.352, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494587460518893e-05, + "loss": 3.3459, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486201513008375e-05, + "loss": 3.3551, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0477815565497853e-05, + "loss": 3.3574, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469429617987333e-05, + "loss": 3.354, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461060049280546e-05, + "loss": 3.3425, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452690480573756e-05, + "loss": 3.3509, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444304533063236e-05, + "loss": 3.3494, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435918585552716e-05, + "loss": 3.3529, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427532638042196e-05, + "loss": 3.3471, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419146690531676e-05, + "loss": 3.3435, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0410760743021156e-05, + "loss": 3.3483, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402374795510636e-05, + "loss": 3.3474, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0393988848000116e-05, + "loss": 3.3484, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0385619279293327e-05, + "loss": 3.3456, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377233331782807e-05, + "loss": 3.3372, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0368847384272287e-05, + "loss": 3.3543, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.03604778155655e-05, + "loss": 3.3504, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352091868054978e-05, + "loss": 3.3364, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0343705920544458e-05, + "loss": 3.3408, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033531997303394e-05, + "loss": 3.3431, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326934025523417e-05, + "loss": 3.3573, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0318548078012897e-05, + "loss": 3.3433, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310162130502377e-05, + "loss": 3.3507, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0301776182991859e-05, + "loss": 3.3519, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0293406614285068e-05, + "loss": 3.3638, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285020666774548e-05, + "loss": 3.346, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.027663471926403e-05, + "loss": 3.3389, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.026826515055724e-05, + "loss": 3.3524, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.025987920304672e-05, + "loss": 3.3439, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.02514932555362e-05, + "loss": 3.3386, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.024310730802568e-05, + "loss": 3.3403, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0234721360515159e-05, + "loss": 3.3466, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.022633541300464e-05, + "loss": 3.3479, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.021794946549412e-05, + "loss": 3.3421, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209563517983599e-05, + "loss": 3.3572, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201193949276811e-05, + "loss": 3.3426, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0192808001766291e-05, + "loss": 3.3468, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184422054255771e-05, + "loss": 3.3484, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176052485548982e-05, + "loss": 3.3556, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0167666538038462e-05, + "loss": 3.3541, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159280590527942e-05, + "loss": 3.3377, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0150894643017422e-05, + "loss": 3.3482, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142525074310632e-05, + "loss": 3.3568, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134139126800112e-05, + "loss": 3.3466, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125753179289594e-05, + "loss": 3.3549, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117367231779072e-05, + "loss": 3.3456, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0108981284268552e-05, + "loss": 3.3606, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100611715561765e-05, + "loss": 3.3506, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092225768051245e-05, + "loss": 3.3528, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0083839820540723e-05, + "loss": 3.3459, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075453873030203e-05, + "loss": 3.3553, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067067925519685e-05, + "loss": 3.346, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0058681978009163e-05, + "loss": 3.339, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050296030498643e-05, + "loss": 3.3615, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0041926461791855e-05, + "loss": 3.348, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033540514281335e-05, + "loss": 3.3552, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025154566770813e-05, + "loss": 3.3456, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0016768619260295e-05, + "loss": 3.3371, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.868391513824463, + "eval_runtime": 305.1215, + "eval_samples_per_second": 1250.62, + "eval_steps_per_second": 39.083, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008399050553506e-05, + "loss": 3.3423, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000013103042986e-05, + "loss": 3.3439, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.991627155532466e-06, + "loss": 3.3505, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.983241208021946e-06, + "loss": 3.3506, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.974871639315157e-06, + "loss": 3.356, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.966485691804636e-06, + "loss": 3.3438, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958116123097847e-06, + "loss": 3.3433, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.949730175587329e-06, + "loss": 3.3449, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.941344228076809e-06, + "loss": 3.3622, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.932958280566287e-06, + "loss": 3.3426, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.924572333055767e-06, + "loss": 3.3446, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91620276434898e-06, + "loss": 3.3488, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.907816816838458e-06, + "loss": 3.3431, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.899430869327938e-06, + "loss": 3.3379, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.89104492181742e-06, + "loss": 3.3353, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.8826589743069e-06, + "loss": 3.3367, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.874273026796378e-06, + "loss": 3.337, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.86588707928586e-06, + "loss": 3.3396, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.85750113177534e-06, + "loss": 3.3371, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.849131563068548e-06, + "loss": 3.3576, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.84074561555803e-06, + "loss": 3.3443, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.83235966804751e-06, + "loss": 3.3398, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.82397372053699e-06, + "loss": 3.3453, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.8156041518302e-06, + "loss": 3.358, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.80721820431968e-06, + "loss": 3.3349, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.79883225680916e-06, + "loss": 3.3383, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.79044630929864e-06, + "loss": 3.3442, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782076740591851e-06, + "loss": 3.3455, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.773707171885064e-06, + "loss": 3.3355, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.765321224374544e-06, + "loss": 3.3334, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.756935276864022e-06, + "loss": 3.3492, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748549329353502e-06, + "loss": 3.347, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740163381842984e-06, + "loss": 3.3525, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.731777434332464e-06, + "loss": 3.3472, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723391486821942e-06, + "loss": 3.3418, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715021918115154e-06, + "loss": 3.3474, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.706635970604634e-06, + "loss": 3.3297, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698250023094113e-06, + "loss": 3.3498, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.689864075583594e-06, + "loss": 3.3363, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681494506876805e-06, + "loss": 3.3372, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673108559366285e-06, + "loss": 3.3406, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.664722611855765e-06, + "loss": 3.3531, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656336664345245e-06, + "loss": 3.3413, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.647967095638456e-06, + "loss": 3.3403, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.639581148127937e-06, + "loss": 3.3434, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631195200617416e-06, + "loss": 3.3371, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.622809253106896e-06, + "loss": 3.3478, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614439684400108e-06, + "loss": 3.3197, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606053736889586e-06, + "loss": 3.3339, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.597667789379066e-06, + "loss": 3.3473, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.589281841868546e-06, + "loss": 3.3482, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.580912273161759e-06, + "loss": 3.3343, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.57254270445497e-06, + "loss": 3.3335, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.56415675694445e-06, + "loss": 3.3374, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.55577080943393e-06, + "loss": 3.3254, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.54738486192341e-06, + "loss": 3.3565, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.53899891441289e-06, + "loss": 3.334, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.53061296690237e-06, + "loss": 3.3477, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.52222701939185e-06, + "loss": 3.3407, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.51384107188133e-06, + "loss": 3.3332, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.50547150317454e-06, + "loss": 3.3421, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.49708555566402e-06, + "loss": 3.3316, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.4886996081535e-06, + "loss": 3.3315, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.48031366064298e-06, + "loss": 3.3296, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.47192771313246e-06, + "loss": 3.3535, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.46354176562194e-06, + "loss": 3.3321, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.45515581811142e-06, + "loss": 3.3396, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.44678624940463e-06, + "loss": 3.3243, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.43840030189411e-06, + "loss": 3.3411, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.43001435438359e-06, + "loss": 3.3469, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.42162840687307e-06, + "loss": 3.3471, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413258838166283e-06, + "loss": 3.3429, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.404872890655763e-06, + "loss": 3.3492, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.396486943145241e-06, + "loss": 3.3536, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388100995634721e-06, + "loss": 3.3374, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.379731426927934e-06, + "loss": 3.3499, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371345479417413e-06, + "loss": 3.3384, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.362959531906892e-06, + "loss": 3.3307, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.354573584396373e-06, + "loss": 3.3397, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346204015689584e-06, + "loss": 3.3421, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.337818068179064e-06, + "loss": 3.3451, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329448499472275e-06, + "loss": 3.3543, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.321062551961755e-06, + "loss": 3.3449, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.312676604451235e-06, + "loss": 3.3217, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.304290656940715e-06, + "loss": 3.3378, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.295904709430195e-06, + "loss": 3.3446, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287518761919675e-06, + "loss": 3.342, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279132814409155e-06, + "loss": 3.3345, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.270746866898635e-06, + "loss": 3.3367, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262377298191845e-06, + "loss": 3.3344, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.253991350681327e-06, + "loss": 3.3403, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.245605403170805e-06, + "loss": 3.3391, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.237219455660285e-06, + "loss": 3.3479, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.228849886953498e-06, + "loss": 3.3466, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220463939442978e-06, + "loss": 3.3478, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212077991932456e-06, + "loss": 3.3285, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.203692044421938e-06, + "loss": 3.3406, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.195322475715148e-06, + "loss": 3.3411, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.186936528204627e-06, + "loss": 3.3438, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.178550580694108e-06, + "loss": 3.3431, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170164633183588e-06, + "loss": 3.3339, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.161795064476799e-06, + "loss": 3.3371, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153409116966279e-06, + "loss": 3.3367, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145023169455759e-06, + "loss": 3.3423, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.136637221945239e-06, + "loss": 3.3341, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.128267653238451e-06, + "loss": 3.3304, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.11988170572793e-06, + "loss": 3.3458, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.11149575821741e-06, + "loss": 3.3382, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103109810706891e-06, + "loss": 3.3309, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.0947402420001e-06, + "loss": 3.3315, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.08635429448958e-06, + "loss": 3.3313, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.077968346979062e-06, + "loss": 3.3483, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.069582399468542e-06, + "loss": 3.3349, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061212830761753e-06, + "loss": 3.3396, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.052826883251233e-06, + "loss": 3.3426, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044440935740713e-06, + "loss": 3.3543, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036071367033923e-06, + "loss": 3.3343, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.027685419523403e-06, + "loss": 3.3324, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.019315850816614e-06, + "loss": 3.3387, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.010929903306096e-06, + "loss": 3.339, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002543955795574e-06, + "loss": 3.329, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994158008285054e-06, + "loss": 3.333, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.985772060774534e-06, + "loss": 3.3355, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977386113264016e-06, + "loss": 3.3388, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969000165753494e-06, + "loss": 3.3342, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.960614218242974e-06, + "loss": 3.345, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.952244649536186e-06, + "loss": 3.3356, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.943858702025665e-06, + "loss": 3.3361, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.935472754515145e-06, + "loss": 3.3365, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927086807004626e-06, + "loss": 3.3503, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.918717238297837e-06, + "loss": 3.3408, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.910331290787315e-06, + "loss": 3.3352, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.901961722080528e-06, + "loss": 3.3304, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.893575774570008e-06, + "loss": 3.3487, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885189827059488e-06, + "loss": 3.339, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.876803879548968e-06, + "loss": 3.3469, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868417932038448e-06, + "loss": 3.3372, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860031984527928e-06, + "loss": 3.3508, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.851662415821138e-06, + "loss": 3.3404, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843276468310618e-06, + "loss": 3.342, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.834890520800098e-06, + "loss": 3.3396, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826504573289578e-06, + "loss": 3.3472, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818118625779058e-06, + "loss": 3.3413, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.809732678268538e-06, + "loss": 3.3252, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801346730758018e-06, + "loss": 3.3514, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.792977162051229e-06, + "loss": 3.3418, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.784591214540709e-06, + "loss": 3.3448, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776205267030189e-06, + "loss": 3.3373, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.767819319519669e-06, + "loss": 3.3277, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.86953067779541, + "eval_runtime": 304.0078, + "eval_samples_per_second": 1255.201, + "eval_steps_per_second": 39.226, + "step": 2518560 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7407313876941148e+18, + "trial_name": null, + "trial_params": null +}