diff --git "a/checkpoint-1755360/trainer_state.json" "b/checkpoint-1755360/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1755360/trainer_state.json" @@ -0,0 +1,20777 @@ +{ + "best_metric": 3.864252805709839, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/transformer/1/checkpoints/checkpoint-915840", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1755360, + "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": 11.0276, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8021, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1657, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9659, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8071, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7018, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5962, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5359, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4402, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3993, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.338, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3128, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2656, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2117, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1781, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1281, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1052, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0833, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.054, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0234, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0129, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9818, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9619, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9277, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9254, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.8956, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 4.8836, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8629, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8362, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8213, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.804, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7957, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7803, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7726, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7597, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7466, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7344, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6997, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.6981, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6868, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6695, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6729, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6665, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6459, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6451, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6382, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.63, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.627, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6066, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5942, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5962, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5816, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5817, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5545, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5682, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5432, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5632, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5377, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5358, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5275, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5215, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5078, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5121, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4892, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4831, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4971, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4867, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4762, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.46, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4617, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4688, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4631, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 4.4559, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4538, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4554, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4489, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4262, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4268, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4253, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4178, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.418, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.41, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4266, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4016, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3882, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3984, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.3951, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.3988, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 4.3806, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3827, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 4.3806, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 4.3755, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 4.3623, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 4.3662, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 4.3675, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.3758, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 4.3542, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.3475, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3471, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.3435, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.3529, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.3364, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914491179359039e-05, + "loss": 4.3334, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.326, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.3348, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.3036, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111384382352036e-05, + "loss": 4.323, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.3156, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.3238, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.3105, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.3161, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.3038, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906108507609265e-05, + "loss": 4.3052, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.3091, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.2915, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.3073, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.90275576648543e-05, + "loss": 4.3058, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2974, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2871, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2855, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2885, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2847, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2868, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2754, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.2814, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952116894867085e-05, + "loss": 4.2659, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943730947356565e-05, + "loss": 4.2692, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.893534499984604e-05, + "loss": 4.2571, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.2602, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.2501, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.2717, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.277, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889343164109717e-05, + "loss": 4.262, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888504569358665e-05, + "loss": 4.241, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.8876659746076134e-05, + "loss": 4.2613, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.8868273798565614e-05, + "loss": 4.254, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885990422985882e-05, + "loss": 4.252, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2432, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2515, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.2453, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.2394, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.2385, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.2408, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880121897608891e-05, + "loss": 4.2284, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879284940738212e-05, + "loss": 4.2302, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.87844634598716e-05, + "loss": 4.242, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877607751236109e-05, + "loss": 4.2287, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876769156485057e-05, + "loss": 4.2271, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875930561734005e-05, + "loss": 4.2376, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875091966982953e-05, + "loss": 4.2191, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.213301658630371, + "eval_runtime": 302.9256, + "eval_samples_per_second": 1259.686, + "eval_steps_per_second": 39.366, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874253372231901e-05, + "loss": 4.2016, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873414777480849e-05, + "loss": 4.2101, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.87257782061017e-05, + "loss": 4.2246, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.871739225859118e-05, + "loss": 4.2134, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2197, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.1985, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.2098, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.1902, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2064, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.191, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2063, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.2009, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1943, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.1819, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1752, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1746, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.1841, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.1819, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.1756, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.1951, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.1855, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.1781, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855810839230249e-05, + "loss": 4.1701, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.1876, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1607, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1742, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1702, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.1639, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850782546484683e-05, + "loss": 4.1553, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849943951733631e-05, + "loss": 4.156, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.16, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.1598, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.1607, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.1572, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.158, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.1525, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844077064237013e-05, + "loss": 4.1348, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.1438, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.1361, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.1326, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1418, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1454, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.1332, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1331, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.1352, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.1371, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.1388, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.1281, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.1244, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833178608234084e-05, + "loss": 4.1276, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832340013483032e-05, + "loss": 4.1209, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.83150141873198e-05, + "loss": 4.1246, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830662823980928e-05, + "loss": 4.113, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298258671102486e-05, + "loss": 4.1272, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289872723591966e-05, + "loss": 4.1018, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281486776081446e-05, + "loss": 4.1269, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273100828570926e-05, + "loss": 4.1136, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.1104, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.1199, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8247959364843095e-05, + "loss": 4.1072, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823957341733258e-05, + "loss": 4.1012, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823118746982206e-05, + "loss": 4.1162, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.0891, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.0907, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.1058, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.1042, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.0976, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.0871, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.0881, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.0958, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.1038, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.0949, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.0997, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.0988, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.0986, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.0787, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105463772379184e-05, + "loss": 4.0823, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809707782486866e-05, + "loss": 4.091, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808869187735814e-05, + "loss": 4.0796, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808030592984762e-05, + "loss": 4.0852, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.80719199823371e-05, + "loss": 4.0764, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806353403482658e-05, + "loss": 4.0978, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055164466119786e-05, + "loss": 4.0785, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804677851860927e-05, + "loss": 4.0674, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803839257109875e-05, + "loss": 4.077, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803000662358823e-05, + "loss": 4.0801, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802162067607771e-05, + "loss": 4.086, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801325110737092e-05, + "loss": 4.0693, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.80048651598604e-05, + "loss": 4.071, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799647921234988e-05, + "loss": 4.0798, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798809326483936e-05, + "loss": 4.0675, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797972369613257e-05, + "loss": 4.0626, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797133774862205e-05, + "loss": 4.0671, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796295180111153e-05, + "loss": 4.0738, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795458223240474e-05, + "loss": 4.0757, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794619628489423e-05, + "loss": 4.0707, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793781033738371e-05, + "loss": 4.0542, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792942438987319e-05, + "loss": 4.0593, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792103844236267e-05, + "loss": 4.0612, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791265249485215e-05, + "loss": 4.0646, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790426654734163e-05, + "loss": 4.0621, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895880599831107e-05, + "loss": 4.0569, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887511031124316e-05, + "loss": 4.0485, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879125083613796e-05, + "loss": 4.0647, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870739136103276e-05, + "loss": 4.0309, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862353188592756e-05, + "loss": 4.0551, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853983619885965e-05, + "loss": 4.0468, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845597672375445e-05, + "loss": 4.0594, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837211724864925e-05, + "loss": 4.0448, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782882577735441e-05, + "loss": 4.0547, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782043982984389e-05, + "loss": 4.0435, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781205388233337e-05, + "loss": 4.0453, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803667934822844e-05, + "loss": 4.0537, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.7795281987312324e-05, + "loss": 4.0405, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778691241860554e-05, + "loss": 4.0521, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777852647109502e-05, + "loss": 4.0577, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.0484, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.0387, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.0424, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774499905985666e-05, + "loss": 4.0466, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773661311234615e-05, + "loss": 4.0323, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772822716483563e-05, + "loss": 4.0498, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771984121732511e-05, + "loss": 4.0325, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771145526981459e-05, + "loss": 4.0428, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.77030857011078e-05, + "loss": 4.0346, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769469975359728e-05, + "loss": 4.0329, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768631380608676e-05, + "loss": 4.0214, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767792785857624e-05, + "loss": 4.0261, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766955828986945e-05, + "loss": 4.0211, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766117234235893e-05, + "loss": 4.0412, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765278639484841e-05, + "loss": 4.05, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764440044733789e-05, + "loss": 4.0343, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636030878631096e-05, + "loss": 4.0163, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762764493112058e-05, + "loss": 4.0375, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761925898361006e-05, + "loss": 4.0276, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761087303609954e-05, + "loss": 4.0291, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760250346739275e-05, + "loss": 4.0258, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759411751988223e-05, + "loss": 4.0283, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758573157237171e-05, + "loss": 4.0232, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757734562486119e-05, + "loss": 4.0278, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.75689760561544e-05, + "loss": 4.0229, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756059010864388e-05, + "loss": 4.0267, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755220416113336e-05, + "loss": 4.0216, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754383459242657e-05, + "loss": 4.0131, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753544864491605e-05, + "loss": 4.0323, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527062697405536e-05, + "loss": 4.0237, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518676749895016e-05, + "loss": 4.0147, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510290802384496e-05, + "loss": 4.0302, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501904854873976e-05, + "loss": 4.0124, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.044633388519287, + "eval_runtime": 303.5157, + "eval_samples_per_second": 1257.236, + "eval_steps_per_second": 39.29, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493518907363456e-05, + "loss": 3.9987, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485132959852936e-05, + "loss": 4.0053, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476747012342416e-05, + "loss": 4.0223, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468361064831896e-05, + "loss": 4.015, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7459975117321376e-05, + "loss": 4.0205, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745158916981085e-05, + "loss": 4.0009, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744320322230033e-05, + "loss": 4.0141, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743481727478981e-05, + "loss": 3.9902, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742643132727929e-05, + "loss": 4.0163, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741804537976877e-05, + "loss": 3.9977, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740965943225825e-05, + "loss": 4.0133, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401289863551465e-05, + "loss": 4.0083, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739292029484468e-05, + "loss": 4.0045, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384534347334154e-05, + "loss": 3.9928, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376148399823634e-05, + "loss": 3.9908, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367762452313114e-05, + "loss": 3.9899, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359376504802594e-05, + "loss": 3.9968, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350990557292074e-05, + "loss": 3.9979, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342604609781554e-05, + "loss": 3.9954, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334218662271034e-05, + "loss": 4.0103, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732584909356424e-05, + "loss": 4.0039, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731746314605372e-05, + "loss": 4.002, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73090771985432e-05, + "loss": 3.9945, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730069125103269e-05, + "loss": 4.0042, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.72923216823259e-05, + "loss": 3.9859, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728393573481538e-05, + "loss": 3.9976, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727554978730486e-05, + "loss": 3.9951, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726716383979434e-05, + "loss": 3.991, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725879427108755e-05, + "loss": 3.9811, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725040832357703e-05, + "loss": 3.9831, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724202237606651e-05, + "loss": 3.9863, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233652807359716e-05, + "loss": 3.993, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225266859849196e-05, + "loss": 3.9949, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216880912338676e-05, + "loss": 3.9861, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208494964828156e-05, + "loss": 3.9864, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720010901731764e-05, + "loss": 3.9841, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719172306980712e-05, + "loss": 3.9707, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833371222966e-05, + "loss": 3.9815, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717496755358981e-05, + "loss": 3.9721, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716658160607929e-05, + "loss": 3.9721, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715819565856877e-05, + "loss": 3.9747, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.714980971105825e-05, + "loss": 3.985, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714144014235146e-05, + "loss": 3.9736, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713305419484094e-05, + "loss": 3.9707, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712466824733042e-05, + "loss": 3.9831, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.71162822998199e-05, + "loss": 3.976, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710791273111311e-05, + "loss": 3.9837, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709952678360259e-05, + "loss": 3.9686, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709114083609208e-05, + "loss": 3.9639, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708275488858156e-05, + "loss": 3.9759, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074385319874766e-05, + "loss": 3.9663, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065999372364246e-05, + "loss": 3.971, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.7057613424853726e-05, + "loss": 3.9608, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.7049227477343206e-05, + "loss": 3.9683, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040857908636415e-05, + "loss": 3.9546, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032471961125895e-05, + "loss": 3.97, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024086013615375e-05, + "loss": 3.9619, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015700066104855e-05, + "loss": 3.9615, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007314118594335e-05, + "loss": 3.9718, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998928171083814e-05, + "loss": 3.9549, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990542223573294e-05, + "loss": 3.9521, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698217265486651e-05, + "loss": 3.9728, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973786707355983e-05, + "loss": 3.9432, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965400759845463e-05, + "loss": 3.9417, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6957014812334943e-05, + "loss": 3.9574, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694864524362816e-05, + "loss": 3.9643, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694025929611763e-05, + "loss": 3.954, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693187334860711e-05, + "loss": 3.9437, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692348740109659e-05, + "loss": 3.9486, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691511783238981e-05, + "loss": 3.9495, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690673188487928e-05, + "loss": 3.9618, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689834593736877e-05, + "loss": 3.9534, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688995998985825e-05, + "loss": 3.9569, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688159042115146e-05, + "loss": 3.957, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687320447364094e-05, + "loss": 3.9616, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686481852613042e-05, + "loss": 3.9404, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.68564325786199e-05, + "loss": 3.9445, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848063009913106e-05, + "loss": 3.9534, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839677062402586e-05, + "loss": 3.9407, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831291114892066e-05, + "loss": 3.9487, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822905167381546e-05, + "loss": 3.9405, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814535598674755e-05, + "loss": 3.9593, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806149651164235e-05, + "loss": 3.9446, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679776370365372e-05, + "loss": 3.9344, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.67893777561432e-05, + "loss": 3.9389, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678100818743641e-05, + "loss": 3.9453, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677262223992589e-05, + "loss": 3.956, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676423629241537e-05, + "loss": 3.9362, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675585034490485e-05, + "loss": 3.9409, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674748077619806e-05, + "loss": 3.9386, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673909482868754e-05, + "loss": 3.9461, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673070888117702e-05, + "loss": 3.9331, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.67223229336665e-05, + "loss": 3.9328, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671395336495971e-05, + "loss": 3.9463, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705583796252925e-05, + "loss": 3.9448, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697197848742405e-05, + "loss": 3.9434, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688811901231885e-05, + "loss": 3.9267, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680425953721365e-05, + "loss": 3.9319, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672040006210844e-05, + "loss": 3.9332, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663654058700324e-05, + "loss": 3.9371, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655268111189804e-05, + "loss": 3.9376, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.6646882163679284e-05, + "loss": 3.9295, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.6638512594972493e-05, + "loss": 3.9247, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.6630126647461973e-05, + "loss": 3.9379, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662174069995145e-05, + "loss": 3.9098, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661335475244093e-05, + "loss": 3.9277, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660498518373414e-05, + "loss": 3.922, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659659923622363e-05, + "loss": 3.9368, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658821328871311e-05, + "loss": 3.9245, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657982734120259e-05, + "loss": 3.9274, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657144139369207e-05, + "loss": 3.921, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656305544618155e-05, + "loss": 3.9244, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655466949867103e-05, + "loss": 3.9325, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654628355116051e-05, + "loss": 3.9241, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653791398245372e-05, + "loss": 3.9321, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.65295280349432e-05, + "loss": 3.9348, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652115846623641e-05, + "loss": 3.9321, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651277251872589e-05, + "loss": 3.9209, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650438657121537e-05, + "loss": 3.9183, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649600062370485e-05, + "loss": 3.9301, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648761467619433e-05, + "loss": 3.9128, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647922872868381e-05, + "loss": 3.9303, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470842781173294e-05, + "loss": 3.9159, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646245683366277e-05, + "loss": 3.9243, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645408726495598e-05, + "loss": 3.92, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644570131744546e-05, + "loss": 3.9193, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643731536993494e-05, + "loss": 3.9029, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428929422424416e-05, + "loss": 3.9149, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642055985371763e-05, + "loss": 3.9097, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641217390620711e-05, + "loss": 3.921, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640378795869659e-05, + "loss": 3.9331, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395402011186065e-05, + "loss": 3.9279, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638703244247928e-05, + "loss": 3.896, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637864649496876e-05, + "loss": 3.927, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637026054745824e-05, + "loss": 3.9157, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636187459994772e-05, + "loss": 3.9172, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353505031240936e-05, + "loss": 3.9062, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345119083730416e-05, + "loss": 3.9186, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633673313621989e-05, + "loss": 3.9113, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632834718870937e-05, + "loss": 3.9166, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.631996124119885e-05, + "loss": 3.9147, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631157529368833e-05, + "loss": 3.9161, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630318934617781e-05, + "loss": 3.9137, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629481977747102e-05, + "loss": 3.9069, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864338299605e-05, + "loss": 3.9184, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278047882449985e-05, + "loss": 3.915, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269661934939465e-05, + "loss": 3.9069, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.6261275987428945e-05, + "loss": 3.9205, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252890039918425e-05, + "loss": 3.9042, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.968932628631592, + "eval_runtime": 308.6955, + "eval_samples_per_second": 1236.14, + "eval_steps_per_second": 38.63, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244504092407905e-05, + "loss": 3.8974, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236118144897385e-05, + "loss": 3.8996, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.6227748576190594e-05, + "loss": 3.9148, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219362628680074e-05, + "loss": 3.9061, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.6210976681169554e-05, + "loss": 3.9191, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.6202590733659034e-05, + "loss": 3.8935, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619422116495224e-05, + "loss": 3.9098, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618583521744172e-05, + "loss": 3.8843, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.61774492699312e-05, + "loss": 3.9134, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616906332242068e-05, + "loss": 3.8961, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.61606937537139e-05, + "loss": 3.9082, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615230780620338e-05, + "loss": 3.9051, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614395461630032e-05, + "loss": 3.8952, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.61355686687898e-05, + "loss": 3.896, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612718272127928e-05, + "loss": 3.8898, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611879677376876e-05, + "loss": 3.886, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110410826258237e-05, + "loss": 3.8978, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102024878747717e-05, + "loss": 3.8942, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093638931237196e-05, + "loss": 3.8935, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085252983726676e-05, + "loss": 3.9069, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076867036216156e-05, + "loss": 3.9063, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068481088705636e-05, + "loss": 3.8993, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606009514119512e-05, + "loss": 3.8955, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605172557248833e-05, + "loss": 3.903, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604335600378154e-05, + "loss": 3.8861, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603497005627102e-05, + "loss": 3.9032, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.60265841087605e-05, + "loss": 3.8948, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601819816124998e-05, + "loss": 3.8891, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600981221373946e-05, + "loss": 3.8828, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600142626622894e-05, + "loss": 3.8874, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599304031871842e-05, + "loss": 3.888, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598467075001163e-05, + "loss": 3.8973, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597628480250111e-05, + "loss": 3.8971, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596789885499059e-05, + "loss": 3.8914, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.595951290748008e-05, + "loss": 3.8909, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595112695996955e-05, + "loss": 3.8898, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594274101245903e-05, + "loss": 3.8754, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593435506494851e-05, + "loss": 3.8834, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5925985496241726e-05, + "loss": 3.8749, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.59175995487312e-05, + "loss": 3.8795, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590921360122068e-05, + "loss": 3.8816, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590082765371016e-05, + "loss": 3.8881, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589244170619964e-05, + "loss": 3.8853, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588405575868912e-05, + "loss": 3.8737, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.58756698111786e-05, + "loss": 3.8876, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586728386366808e-05, + "loss": 3.8885, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858914294961295e-05, + "loss": 3.8857, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850528347450774e-05, + "loss": 3.8802, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842142399940254e-05, + "loss": 3.8679, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.5833756452429734e-05, + "loss": 3.8855, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.5825386883722943e-05, + "loss": 3.8724, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817000936212423e-05, + "loss": 3.8796, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.58086149887019e-05, + "loss": 3.8717, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580024541999511e-05, + "loss": 3.8731, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579185947248459e-05, + "loss": 3.866, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578347352497407e-05, + "loss": 3.8769, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577508757746355e-05, + "loss": 3.8759, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576671800875677e-05, + "loss": 3.8743, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575833206124625e-05, + "loss": 3.8781, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574994611373573e-05, + "loss": 3.8665, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574156016622521e-05, + "loss": 3.8668, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573317421871469e-05, + "loss": 3.8868, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.57248046500079e-05, + "loss": 3.8561, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571641870249738e-05, + "loss": 3.8532, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570803275498686e-05, + "loss": 3.8652, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569964680747634e-05, + "loss": 3.876, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569126085996582e-05, + "loss": 3.8652, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.56828749124553e-05, + "loss": 3.8603, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567448896494478e-05, + "loss": 3.8577, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566610301743426e-05, + "loss": 3.8616, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657733448727466e-05, + "loss": 3.8759, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649347501216946e-05, + "loss": 3.8661, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564096155370643e-05, + "loss": 3.8677, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563257560619591e-05, + "loss": 3.8747, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562420603748912e-05, + "loss": 3.8744, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.56158200899786e-05, + "loss": 3.857, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560745052127181e-05, + "loss": 3.861, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559906457376129e-05, + "loss": 3.871, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559067862625077e-05, + "loss": 3.85, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558229267874025e-05, + "loss": 3.8657, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557390673122973e-05, + "loss": 3.8545, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565520783719204e-05, + "loss": 3.8768, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557134836208684e-05, + "loss": 3.8582, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.55487652675019e-05, + "loss": 3.8518, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540379319991386e-05, + "loss": 3.8518, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553199337248086e-05, + "loss": 3.8631, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552360742497034e-05, + "loss": 3.8736, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551522147745982e-05, + "loss": 3.8568, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550685190875303e-05, + "loss": 3.8549, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549846596124251e-05, + "loss": 3.856, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549008001373199e-05, + "loss": 3.8646, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548169406622147e-05, + "loss": 3.8512, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547330811871095e-05, + "loss": 3.853, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546492217120043e-05, + "loss": 3.863, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545655260249364e-05, + "loss": 3.8653, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448166654983124e-05, + "loss": 3.8608, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439780707472604e-05, + "loss": 3.8425, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431394759962084e-05, + "loss": 3.8539, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542302519125529e-05, + "loss": 3.8492, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541463924374477e-05, + "loss": 3.8581, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540625329623425e-05, + "loss": 3.8582, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539786734872373e-05, + "loss": 3.8484, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538948140121321e-05, + "loss": 3.8483, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538109545370269e-05, + "loss": 3.8559, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537270950619217e-05, + "loss": 3.8326, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536432355868165e-05, + "loss": 3.85, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535595398997486e-05, + "loss": 3.8409, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534756804246434e-05, + "loss": 3.8577, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533918209495382e-05, + "loss": 3.8463, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533079614744331e-05, + "loss": 3.8473, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532241019993279e-05, + "loss": 3.8424, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314040631226e-05, + "loss": 3.8501, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530565468371548e-05, + "loss": 3.8549, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529726873620496e-05, + "loss": 3.8418, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528888278869444e-05, + "loss": 3.8537, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528049684118392e-05, + "loss": 3.8571, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272127272477126e-05, + "loss": 3.851, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263741324966606e-05, + "loss": 3.8509, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255355377456086e-05, + "loss": 3.837, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5246969429945566e-05, + "loss": 3.8542, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238583482435046e-05, + "loss": 3.8421, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230197534924526e-05, + "loss": 3.8504, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221811587414006e-05, + "loss": 3.8391, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213425639903486e-05, + "loss": 3.8471, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205056071196695e-05, + "loss": 3.8439, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196670123686175e-05, + "loss": 3.84, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188284176175655e-05, + "loss": 3.8317, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179898228665135e-05, + "loss": 3.8369, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171512281154615e-05, + "loss": 3.8391, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163142712447824e-05, + "loss": 3.8439, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154756764937304e-05, + "loss": 3.8555, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146370817426784e-05, + "loss": 3.8532, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5137984869916264e-05, + "loss": 3.8241, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129598922405744e-05, + "loss": 3.8537, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512122935369896e-05, + "loss": 3.84, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511284340618844e-05, + "loss": 3.8425, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510445745867792e-05, + "loss": 3.8335, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.50960715111674e-05, + "loss": 3.8435, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508770194246061e-05, + "loss": 3.8347, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507931599495009e-05, + "loss": 3.8486, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507093004743957e-05, + "loss": 3.8376, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506254409992905e-05, + "loss": 3.8401, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505417453122226e-05, + "loss": 3.8426, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504578858371174e-05, + "loss": 3.8328, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503741901500495e-05, + "loss": 3.8414, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029033067494434e-05, + "loss": 3.8478, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020647119983914e-05, + "loss": 3.8324, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012261172473394e-05, + "loss": 3.8429, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5003875224962873e-05, + "loss": 3.8378, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.928152322769165, + "eval_runtime": 305.6895, + "eval_samples_per_second": 1248.296, + "eval_steps_per_second": 39.01, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995489277452353e-05, + "loss": 3.8214, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498710332994183e-05, + "loss": 3.8266, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497871738243131e-05, + "loss": 3.8379, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497033143492079e-05, + "loss": 3.8385, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496194548741027e-05, + "loss": 3.8494, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495355953989975e-05, + "loss": 3.8224, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945173592389226e-05, + "loss": 3.833, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936787644878706e-05, + "loss": 3.8184, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928401697368186e-05, + "loss": 3.8377, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.49200321286614e-05, + "loss": 3.8278, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491164618115088e-05, + "loss": 3.8324, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490326023364036e-05, + "loss": 3.8375, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489489066493358e-05, + "loss": 3.8233, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488650471742305e-05, + "loss": 3.8279, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487811876991253e-05, + "loss": 3.8187, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486973282240201e-05, + "loss": 3.8157, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486134687489149e-05, + "loss": 3.8257, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485296092738097e-05, + "loss": 3.8267, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484457497987045e-05, + "loss": 3.8238, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483618903235993e-05, + "loss": 3.8373, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482781946365314e-05, + "loss": 3.8389, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481943351614262e-05, + "loss": 3.8303, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.48110475686321e-05, + "loss": 3.8297, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802661621121587e-05, + "loss": 3.8355, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794275673611067e-05, + "loss": 3.8164, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.4785889726100547e-05, + "loss": 3.8343, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.4777503778590026e-05, + "loss": 3.8297, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.4769134209883236e-05, + "loss": 3.819, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.4760748262372716e-05, + "loss": 3.8175, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.4752362314862195e-05, + "loss": 3.8171, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.4743976367351675e-05, + "loss": 3.8217, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735606798644885e-05, + "loss": 3.8278, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727220851134364e-05, + "loss": 3.8316, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718834903623844e-05, + "loss": 3.826, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710448956113324e-05, + "loss": 3.8252, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4702063008602804e-05, + "loss": 3.8246, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469369343989602e-05, + "loss": 3.8072, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.46853074923855e-05, + "loss": 3.8206, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467692154487498e-05, + "loss": 3.8091, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466853559736446e-05, + "loss": 3.8129, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466014964985394e-05, + "loss": 3.8137, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465178008114715e-05, + "loss": 3.8277, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464339413363663e-05, + "loss": 3.819, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463500818612611e-05, + "loss": 3.8073, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462662223861559e-05, + "loss": 3.8265, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.46182526699088e-05, + "loss": 3.8202, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460986672239828e-05, + "loss": 3.8194, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460148077488776e-05, + "loss": 3.8165, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459309482737724e-05, + "loss": 3.8027, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584725258670454e-05, + "loss": 3.8221, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576339311159934e-05, + "loss": 3.8082, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4567953363649414e-05, + "loss": 3.8164, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455956741613889e-05, + "loss": 3.8078, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.45511978474321e-05, + "loss": 3.8081, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454281189992158e-05, + "loss": 3.8046, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453442595241106e-05, + "loss": 3.8124, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526040004900536e-05, + "loss": 3.8102, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451767043619375e-05, + "loss": 3.8098, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450928448868323e-05, + "loss": 3.818, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450089854117271e-05, + "loss": 3.8023, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449251259366219e-05, + "loss": 3.7997, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448414302495541e-05, + "loss": 3.8257, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447575707744489e-05, + "loss": 3.7907, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446737112993436e-05, + "loss": 3.7914, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445898518242384e-05, + "loss": 3.8032, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445059923491332e-05, + "loss": 3.8185, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.44422132874028e-05, + "loss": 3.798, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443384371869601e-05, + "loss": 3.8018, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442545777118549e-05, + "loss": 3.7948, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441707182367497e-05, + "loss": 3.8006, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440868587616445e-05, + "loss": 3.8109, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400316307457665e-05, + "loss": 3.8068, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4391930359947145e-05, + "loss": 3.8052, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.4383544412436625e-05, + "loss": 3.8105, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.4375158464926105e-05, + "loss": 3.812, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.4366772517415585e-05, + "loss": 3.7987, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.4358402948708794e-05, + "loss": 3.7995, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350017001198274e-05, + "loss": 3.8096, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341631053687754e-05, + "loss": 3.7887, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333245106177234e-05, + "loss": 3.8037, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324859158666714e-05, + "loss": 3.7941, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431648958995992e-05, + "loss": 3.815, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.43081036424494e-05, + "loss": 3.7982, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429971769493888e-05, + "loss": 3.7935, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429133174742836e-05, + "loss": 3.785, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428296217872158e-05, + "loss": 3.8061, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427457623121106e-05, + "loss": 3.8085, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426619028370054e-05, + "loss": 3.8017, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425780433619002e-05, + "loss": 3.7932, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.42494183886795e-05, + "loss": 3.7976, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424104881997271e-05, + "loss": 3.8033, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423266287246219e-05, + "loss": 3.7914, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422427692495167e-05, + "loss": 3.7925, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421589097744115e-05, + "loss": 3.8042, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420752140873436e-05, + "loss": 3.8041, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419913546122384e-05, + "loss": 3.803, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419074951371332e-05, + "loss": 3.7873, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182363566202803e-05, + "loss": 3.795, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417399399749601e-05, + "loss": 3.788, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416560804998549e-05, + "loss": 3.7986, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415722210247497e-05, + "loss": 3.7978, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414883615496445e-05, + "loss": 3.7943, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414046658625766e-05, + "loss": 3.7895, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413208063874714e-05, + "loss": 3.7918, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412369469123662e-05, + "loss": 3.7855, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.41153087437261e-05, + "loss": 3.7875, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410693917501931e-05, + "loss": 3.7826, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409855322750879e-05, + "loss": 3.799, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409016727999827e-05, + "loss": 3.7903, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408178133248776e-05, + "loss": 3.7874, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.4073411763780966e-05, + "loss": 3.7819, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.4065025816270446e-05, + "loss": 3.7965, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.4056639868759926e-05, + "loss": 3.7949, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.4048253921249406e-05, + "loss": 3.7834, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039867973738886e-05, + "loss": 3.7956, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031498405032095e-05, + "loss": 3.8007, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023128836325304e-05, + "loss": 3.7931, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.4014742888814784e-05, + "loss": 3.7952, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.4006356941304264e-05, + "loss": 3.7817, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.3997970993793744e-05, + "loss": 3.7939, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989585046283224e-05, + "loss": 3.7894, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981199098772704e-05, + "loss": 3.7947, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397281315126219e-05, + "loss": 3.776, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396442720375167e-05, + "loss": 3.7917, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395605763504488e-05, + "loss": 3.7883, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394767168753436e-05, + "loss": 3.7827, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393928574002384e-05, + "loss": 3.7784, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393089979251331e-05, + "loss": 3.7798, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392251384500279e-05, + "loss": 3.782, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391414427629601e-05, + "loss": 3.791, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390575832878549e-05, + "loss": 3.7939, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389737238127496e-05, + "loss": 3.7992, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388898643376445e-05, + "loss": 3.768, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388061686505766e-05, + "loss": 3.797, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872230917547144e-05, + "loss": 3.7878, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386384497003662e-05, + "loss": 3.7828, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.38554590225261e-05, + "loss": 3.7766, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847089453819313e-05, + "loss": 3.7924, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838703506308787e-05, + "loss": 3.7811, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830317558798267e-05, + "loss": 3.7885, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821931611287746e-05, + "loss": 3.7801, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381356204258096e-05, + "loss": 3.7855, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805176095070436e-05, + "loss": 3.7869, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796790147559916e-05, + "loss": 3.7798, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378842057885313e-05, + "loss": 3.7863, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378003463134261e-05, + "loss": 3.7926, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377164868383209e-05, + "loss": 3.7791, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376326273632157e-05, + "loss": 3.7853, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375487678881105e-05, + "loss": 3.7862, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.903557777404785, + "eval_runtime": 301.953, + "eval_samples_per_second": 1263.743, + "eval_steps_per_second": 39.493, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374649084130053e-05, + "loss": 3.7761, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373810489379001e-05, + "loss": 3.7704, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372973532508322e-05, + "loss": 3.7843, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.37213493775727e-05, + "loss": 3.7864, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371296343006218e-05, + "loss": 3.7925, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370457748255166e-05, + "loss": 3.7741, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369619153504114e-05, + "loss": 3.7785, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368782196633435e-05, + "loss": 3.7669, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679436018823836e-05, + "loss": 3.7804, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.3671050071313316e-05, + "loss": 3.7759, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.3662664123802796e-05, + "loss": 3.7774, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.3654294555096005e-05, + "loss": 3.7827, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3645924986389214e-05, + "loss": 3.7737, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637539038878694e-05, + "loss": 3.7744, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629153091368174e-05, + "loss": 3.7678, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620767143857654e-05, + "loss": 3.7629, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612381196347134e-05, + "loss": 3.7684, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3603995248836614e-05, + "loss": 3.7747, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595609301326094e-05, + "loss": 3.7709, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587223353815574e-05, + "loss": 3.7868, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357885378510879e-05, + "loss": 3.7848, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357046783759827e-05, + "loss": 3.7802, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356208189008775e-05, + "loss": 3.779, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355369594257723e-05, + "loss": 3.782, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354532637387044e-05, + "loss": 3.7679, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353694042635992e-05, + "loss": 3.7802, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.35285544788494e-05, + "loss": 3.7773, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352016853133888e-05, + "loss": 3.7666, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351179896263209e-05, + "loss": 3.7648, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350341301512157e-05, + "loss": 3.7695, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349502706761105e-05, + "loss": 3.7714, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486657498904256e-05, + "loss": 3.774, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347827155139374e-05, + "loss": 3.7829, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.346988560388322e-05, + "loss": 3.7727, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.34614996563727e-05, + "loss": 3.773, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345311370886218e-05, + "loss": 3.7742, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344472776135166e-05, + "loss": 3.762, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343634181384114e-05, + "loss": 3.7636, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342795586633062e-05, + "loss": 3.7583, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341958629762383e-05, + "loss": 3.7608, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341120035011331e-05, + "loss": 3.7617, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340281440260279e-05, + "loss": 3.7774, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339442845509227e-05, + "loss": 3.7693, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338605888638548e-05, + "loss": 3.7567, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337767293887496e-05, + "loss": 3.7772, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336928699136444e-05, + "loss": 3.7662, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336090104385393e-05, + "loss": 3.7737, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335253147514714e-05, + "loss": 3.764, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334414552763662e-05, + "loss": 3.7533, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33357595801261e-05, + "loss": 3.7689, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332737363261557e-05, + "loss": 3.7611, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.3319004063908786e-05, + "loss": 3.7687, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.3310618116398266e-05, + "loss": 3.7548, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302232168887746e-05, + "loss": 3.7605, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329384622137722e-05, + "loss": 3.7521, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285476652670435e-05, + "loss": 3.7631, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277090705159915e-05, + "loss": 3.7633, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268704757649395e-05, + "loss": 3.7574, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260318810138875e-05, + "loss": 3.7706, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325194924143209e-05, + "loss": 3.7559, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324356329392157e-05, + "loss": 3.7496, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3235177346411044e-05, + "loss": 3.7787, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3226791398900523e-05, + "loss": 3.7425, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321842183019374e-05, + "loss": 3.7383, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321003588268322e-05, + "loss": 3.7571, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320164993517269e-05, + "loss": 3.7708, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319326398766217e-05, + "loss": 3.7453, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318489441895539e-05, + "loss": 3.7571, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317650847144487e-05, + "loss": 3.7468, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316812252393435e-05, + "loss": 3.7513, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315973657642383e-05, + "loss": 3.7626, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151367007717044e-05, + "loss": 3.7589, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314298106020652e-05, + "loss": 3.7596, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134595112696e-05, + "loss": 3.758, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312620916518548e-05, + "loss": 3.7665, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311783959647869e-05, + "loss": 3.7472, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109453648968166e-05, + "loss": 3.7551, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101067701457646e-05, + "loss": 3.7589, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092681753947126e-05, + "loss": 3.7434, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308431218524034e-05, + "loss": 3.7548, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307592623772982e-05, + "loss": 3.7515, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.30675402902193e-05, + "loss": 3.7645, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305915434270878e-05, + "loss": 3.7561, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305078477400199e-05, + "loss": 3.7461, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304239882649147e-05, + "loss": 3.7403, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303401287898095e-05, + "loss": 3.757, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302562693147043e-05, + "loss": 3.7612, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301725736276364e-05, + "loss": 3.7506, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300887141525312e-05, + "loss": 3.751, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.30004854677426e-05, + "loss": 3.751, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299209952023208e-05, + "loss": 3.7549, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298372995152529e-05, + "loss": 3.7475, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975344004014776e-05, + "loss": 3.7433, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2966958056504256e-05, + "loss": 3.7597, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958572108993736e-05, + "loss": 3.7571, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950202540286945e-05, + "loss": 3.7538, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2941816592776425e-05, + "loss": 3.7393, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933430645265905e-05, + "loss": 3.7516, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925044697755384e-05, + "loss": 3.74, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916675129048594e-05, + "loss": 3.7549, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908289181538074e-05, + "loss": 3.7507, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2899903234027553e-05, + "loss": 3.7487, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891517286517033e-05, + "loss": 3.7449, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288314771781024e-05, + "loss": 3.7402, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287476177029973e-05, + "loss": 3.744, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286637582278921e-05, + "loss": 3.7384, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285798987527869e-05, + "loss": 3.7404, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.28496203065719e-05, + "loss": 3.7518, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284123435906138e-05, + "loss": 3.7471, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283284841155086e-05, + "loss": 3.7414, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282446246404034e-05, + "loss": 3.7364, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281609289533355e-05, + "loss": 3.7483, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.280770694782303e-05, + "loss": 3.7511, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279932100031251e-05, + "loss": 3.7403, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279093505280199e-05, + "loss": 3.7515, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782565484095196e-05, + "loss": 3.7528, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.277417953658468e-05, + "loss": 3.7513, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.276579358907416e-05, + "loss": 3.7456, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275740764156364e-05, + "loss": 3.7404, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274903807285685e-05, + "loss": 3.7438, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274065212534633e-05, + "loss": 3.7445, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273226617783581e-05, + "loss": 3.7507, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272388023032529e-05, + "loss": 3.7344, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.27155106616185e-05, + "loss": 3.7449, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270712471410798e-05, + "loss": 3.7453, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269873876659746e-05, + "loss": 3.7411, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269035281908694e-05, + "loss": 3.7306, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268198325038015e-05, + "loss": 3.7385, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267359730286964e-05, + "loss": 3.7372, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.2665211355359117e-05, + "loss": 3.7479, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.2656825407848597e-05, + "loss": 3.7483, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648455839141806e-05, + "loss": 3.7552, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640069891631286e-05, + "loss": 3.7256, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631683944120766e-05, + "loss": 3.7519, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623297996610245e-05, + "loss": 3.7424, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614928427903455e-05, + "loss": 3.7391, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606542480392935e-05, + "loss": 3.7327, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598156532882414e-05, + "loss": 3.7493, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2589770585371894e-05, + "loss": 3.734, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581401016665104e-05, + "loss": 3.7487, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257301506915459e-05, + "loss": 3.7346, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256462912164407e-05, + "loss": 3.744, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255624317413355e-05, + "loss": 3.7425, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254787360542676e-05, + "loss": 3.7379, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253950403671997e-05, + "loss": 3.7482, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253111808920945e-05, + "loss": 3.7418, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252273214169893e-05, + "loss": 3.7432, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251434619418841e-05, + "loss": 3.7336, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250596024667789e-05, + "loss": 3.7465, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8875081539154053, + "eval_runtime": 301.9304, + "eval_samples_per_second": 1263.838, + "eval_steps_per_second": 39.496, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249757429916737e-05, + "loss": 3.7338, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248918835165685e-05, + "loss": 3.7254, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248080240414633e-05, + "loss": 3.7383, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247241645663581e-05, + "loss": 3.7446, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246403050912529e-05, + "loss": 3.7487, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455644561614775e-05, + "loss": 3.73, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244725861410425e-05, + "loss": 3.7336, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243887266659373e-05, + "loss": 3.7246, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430503097886944e-05, + "loss": 3.7417, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242211715037642e-05, + "loss": 3.7326, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.24137312028659e-05, + "loss": 3.7391, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240534525535538e-05, + "loss": 3.7377, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239699206545232e-05, + "loss": 3.7302, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.23886061179418e-05, + "loss": 3.7354, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238022017043128e-05, + "loss": 3.7212, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237183422292076e-05, + "loss": 3.7204, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236344827541024e-05, + "loss": 3.7271, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235506232789972e-05, + "loss": 3.7385, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.23466763803892e-05, + "loss": 3.7274, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233829043287868e-05, + "loss": 3.7476, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232992086417189e-05, + "loss": 3.7392, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232153491666137e-05, + "loss": 3.7408, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231314896915085e-05, + "loss": 3.7358, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230476302164033e-05, + "loss": 3.7389, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229639345293354e-05, + "loss": 3.7247, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228800750542302e-05, + "loss": 3.7431, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.22796215579125e-05, + "loss": 3.7316, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227123561040198e-05, + "loss": 3.7251, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262866041695195e-05, + "loss": 3.7264, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254480094184675e-05, + "loss": 3.728, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246094146674155e-05, + "loss": 3.7304, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237708199163635e-05, + "loss": 3.7362, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229338630456844e-05, + "loss": 3.7351, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2220952682946324e-05, + "loss": 3.7386, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212566735435804e-05, + "loss": 3.7242, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204180787925284e-05, + "loss": 3.7327, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219581121921849e-05, + "loss": 3.7271, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218742527170797e-05, + "loss": 3.7182, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217903932419745e-05, + "loss": 3.7161, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217066975549067e-05, + "loss": 3.7217, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216228380798015e-05, + "loss": 3.7208, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215389786046963e-05, + "loss": 3.7363, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214551191295911e-05, + "loss": 3.7294, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213714234425232e-05, + "loss": 3.7184, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.21287563967418e-05, + "loss": 3.7367, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212037044923128e-05, + "loss": 3.7237, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211198450172076e-05, + "loss": 3.7335, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210361493301397e-05, + "loss": 3.7224, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209522898550345e-05, + "loss": 3.7083, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208684303799293e-05, + "loss": 3.736, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207845709048241e-05, + "loss": 3.7173, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207008752177562e-05, + "loss": 3.7285, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.20617015742651e-05, + "loss": 3.7195, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205331562675458e-05, + "loss": 3.7224, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204492967924406e-05, + "loss": 3.708, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203656011053727e-05, + "loss": 3.7202, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202817416302675e-05, + "loss": 3.7287, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201978821551623e-05, + "loss": 3.7145, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201140226800571e-05, + "loss": 3.7309, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200303269929892e-05, + "loss": 3.7196, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.19946467517884e-05, + "loss": 3.7104, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198626080427788e-05, + "loss": 3.7355, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197787485676736e-05, + "loss": 3.7058, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969505288060576e-05, + "loss": 3.7007, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961119340550056e-05, + "loss": 3.7201, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952733393039536e-05, + "loss": 3.7266, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944347445529016e-05, + "loss": 3.7052, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1935977876822225e-05, + "loss": 3.7207, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927591929311705e-05, + "loss": 3.7036, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919205981801185e-05, + "loss": 3.716, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910820034290665e-05, + "loss": 3.7222, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902450465583874e-05, + "loss": 3.7169, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894064518073354e-05, + "loss": 3.7215, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885678570562834e-05, + "loss": 3.7188, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877292623052314e-05, + "loss": 3.7285, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186892305434553e-05, + "loss": 3.7083, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186053710683501e-05, + "loss": 3.7175, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185215115932449e-05, + "loss": 3.7165, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184376521181397e-05, + "loss": 3.7058, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183539564310718e-05, + "loss": 3.7168, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182700969559666e-05, + "loss": 3.7162, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181862374808614e-05, + "loss": 3.7262, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181023780057562e-05, + "loss": 3.7199, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180186823186883e-05, + "loss": 3.7002, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179348228435831e-05, + "loss": 3.7029, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178509633684779e-05, + "loss": 3.7185, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177671038933727e-05, + "loss": 3.7255, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768340820630484e-05, + "loss": 3.7141, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759954873119964e-05, + "loss": 3.7077, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751568925609444e-05, + "loss": 3.7163, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743182978098924e-05, + "loss": 3.7135, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173481340939213e-05, + "loss": 3.7131, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172642746188161e-05, + "loss": 3.7038, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171804151437109e-05, + "loss": 3.7207, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170965556686057e-05, + "loss": 3.7185, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170128599815378e-05, + "loss": 3.718, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169290005064326e-05, + "loss": 3.702, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168451410313274e-05, + "loss": 3.7093, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167612815562222e-05, + "loss": 3.7062, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166775858691544e-05, + "loss": 3.7161, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165937263940492e-05, + "loss": 3.7106, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16509866918944e-05, + "loss": 3.708, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164260074438388e-05, + "loss": 3.7115, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634231175677086e-05, + "loss": 3.702, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625845228166566e-05, + "loss": 3.7056, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617459280656046e-05, + "loss": 3.7006, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609073333145526e-05, + "loss": 3.7078, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.1600703764438735e-05, + "loss": 3.7087, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592317816928215e-05, + "loss": 3.7157, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583931869417695e-05, + "loss": 3.6986, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575562300710904e-05, + "loss": 3.7028, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156717635320039e-05, + "loss": 3.7059, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155879040568987e-05, + "loss": 3.714, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155040445817935e-05, + "loss": 3.703, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154203488947256e-05, + "loss": 3.7167, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153364894196204e-05, + "loss": 3.7132, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152526299445152e-05, + "loss": 3.7145, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1516877046941e-05, + "loss": 3.7082, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150850747823421e-05, + "loss": 3.7066, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150012153072369e-05, + "loss": 3.706, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149173558321317e-05, + "loss": 3.7108, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148334963570265e-05, + "loss": 3.7081, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147498006699586e-05, + "loss": 3.701, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466594119485345e-05, + "loss": 3.7119, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458208171974825e-05, + "loss": 3.7084, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449822224464305e-05, + "loss": 3.7035, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441452655757514e-05, + "loss": 3.6933, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.1433066708246994e-05, + "loss": 3.7006, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424680760736474e-05, + "loss": 3.6995, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.1416294813225954e-05, + "loss": 3.7106, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140792524451916e-05, + "loss": 3.7133, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139953929700864e-05, + "loss": 3.7176, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139115334949812e-05, + "loss": 3.692, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.13827674019876e-05, + "loss": 3.7134, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137439783328081e-05, + "loss": 3.7059, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136601188577029e-05, + "loss": 3.7074, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135762593825978e-05, + "loss": 3.6966, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134923999074926e-05, + "loss": 3.711, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134087042204247e-05, + "loss": 3.6973, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133248447453195e-05, + "loss": 3.7158, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132409852702143e-05, + "loss": 3.6957, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131571257951091e-05, + "loss": 3.7073, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307343010804116e-05, + "loss": 3.7066, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298957063293596e-05, + "loss": 3.704, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290587494586805e-05, + "loss": 3.708, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282201547076285e-05, + "loss": 3.7047, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273815599565765e-05, + "loss": 3.7075, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265429652055245e-05, + "loss": 3.6976, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125704370454473e-05, + "loss": 3.7125, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.878002405166626, + "eval_runtime": 302.5539, + "eval_samples_per_second": 1261.233, + "eval_steps_per_second": 39.414, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124865775703421e-05, + "loss": 3.6983, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240271809523685e-05, + "loss": 3.6881, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1231885862013165e-05, + "loss": 3.7056, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122351629330638e-05, + "loss": 3.7097, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121513034579586e-05, + "loss": 3.7115, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206744398285334e-05, + "loss": 3.6957, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119837482957855e-05, + "loss": 3.7002, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118998888206803e-05, + "loss": 3.6899, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118160293455751e-05, + "loss": 3.7033, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117321698704698e-05, + "loss": 3.6993, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.11648474183402e-05, + "loss": 3.7012, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156461470829686e-05, + "loss": 3.7023, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148108280926624e-05, + "loss": 3.6989, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139722333416104e-05, + "loss": 3.695, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131336385905584e-05, + "loss": 3.6885, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1122950438395064e-05, + "loss": 3.6839, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114564490884544e-05, + "loss": 3.693, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106178543374024e-05, + "loss": 3.7028, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097792595863504e-05, + "loss": 3.6935, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089406648352984e-05, + "loss": 3.7064, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108102070084246e-05, + "loss": 3.7083, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107263475333194e-05, + "loss": 3.7088, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064248805821423e-05, + "loss": 3.6988, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1055862858310903e-05, + "loss": 3.7012, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104749328960411e-05, + "loss": 3.6974, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103910734209359e-05, + "loss": 3.7057, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103072139458307e-05, + "loss": 3.6951, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102233544707255e-05, + "loss": 3.6956, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101396587836576e-05, + "loss": 3.6936, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100557993085524e-05, + "loss": 3.693, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099719398334472e-05, + "loss": 3.6902, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.09888080358342e-05, + "loss": 3.6998, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098043846712741e-05, + "loss": 3.7051, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097205251961689e-05, + "loss": 3.7021, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096366657210638e-05, + "loss": 3.6864, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095528062459586e-05, + "loss": 3.7038, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946911055889066e-05, + "loss": 3.6948, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938525108378546e-05, + "loss": 3.6811, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930139160868026e-05, + "loss": 3.683, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921753213357506e-05, + "loss": 3.6868, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913383644650715e-05, + "loss": 3.6908, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904997697140195e-05, + "loss": 3.697, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896611749629675e-05, + "loss": 3.6957, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888242180922884e-05, + "loss": 3.6833, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.0879856233412364e-05, + "loss": 3.7023, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.0871470285901844e-05, + "loss": 3.6897, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086308433839133e-05, + "loss": 3.7004, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085471476968454e-05, + "loss": 3.6926, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084632882217402e-05, + "loss": 3.6676, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.08379428746635e-05, + "loss": 3.7061, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082955692715298e-05, + "loss": 3.6816, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082118735844619e-05, + "loss": 3.6938, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081280141093567e-05, + "loss": 3.6901, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080441546342515e-05, + "loss": 3.6854, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079602951591463e-05, + "loss": 3.6793, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078765994720784e-05, + "loss": 3.683, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077927399969732e-05, + "loss": 3.6995, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.07708880521868e-05, + "loss": 3.6777, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762502104676284e-05, + "loss": 3.6951, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754132535969494e-05, + "loss": 3.6912, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745746588458974e-05, + "loss": 3.6742, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737360640948453e-05, + "loss": 3.698, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.0728974693437933e-05, + "loss": 3.679, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072060512473114e-05, + "loss": 3.6695, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071221917722062e-05, + "loss": 3.6838, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.07038332297101e-05, + "loss": 3.6904, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069544728219958e-05, + "loss": 3.6735, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068707771349279e-05, + "loss": 3.6892, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067869176598227e-05, + "loss": 3.6725, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067030581847175e-05, + "loss": 3.6814, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066191987096124e-05, + "loss": 3.6897, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065355030225445e-05, + "loss": 3.6821, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064516435474393e-05, + "loss": 3.6936, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063677840723341e-05, + "loss": 3.683, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062839245972289e-05, + "loss": 3.6952, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620022891016096e-05, + "loss": 3.6796, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611636943505576e-05, + "loss": 3.6883, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603250995995056e-05, + "loss": 3.6764, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0594865048484536e-05, + "loss": 3.6763, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586495479777745e-05, + "loss": 3.6829, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578109532267225e-05, + "loss": 3.6837, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.0569723584756705e-05, + "loss": 3.6904, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056133763724619e-05, + "loss": 3.6922, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.05529680685394e-05, + "loss": 3.6632, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054458212102888e-05, + "loss": 3.6703, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053619617351836e-05, + "loss": 3.6855, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052781022600784e-05, + "loss": 3.6916, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051944065730105e-05, + "loss": 3.6844, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051105470979053e-05, + "loss": 3.676, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050266876228001e-05, + "loss": 3.6879, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049428281476949e-05, + "loss": 3.6801, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.04859132460627e-05, + "loss": 3.6813, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047752729855218e-05, + "loss": 3.6714, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046914135104166e-05, + "loss": 3.6858, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046075540353114e-05, + "loss": 3.6894, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.0452385834824355e-05, + "loss": 3.6882, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.0443999887313835e-05, + "loss": 3.6737, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.0435613939803314e-05, + "loss": 3.6738, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427244371096524e-05, + "loss": 3.6719, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418858423586004e-05, + "loss": 3.6865, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410472476075483e-05, + "loss": 3.6809, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.0402086528564963e-05, + "loss": 3.6751, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039371695985817e-05, + "loss": 3.6774, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038533101234765e-05, + "loss": 3.6718, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037694506483713e-05, + "loss": 3.6735, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036855911732661e-05, + "loss": 3.6677, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036018954861983e-05, + "loss": 3.6761, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035180360110931e-05, + "loss": 3.676, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034341765359879e-05, + "loss": 3.6812, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335048084892e-05, + "loss": 3.6716, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032666213738148e-05, + "loss": 3.6653, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031827618987096e-05, + "loss": 3.6791, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030989024236044e-05, + "loss": 3.6804, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030150429484992e-05, + "loss": 3.6735, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.02931183473394e-05, + "loss": 3.6832, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028473239982888e-05, + "loss": 3.6802, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027634645231836e-05, + "loss": 3.6859, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267976883611566e-05, + "loss": 3.677, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259590936101046e-05, + "loss": 3.6757, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025120498859053e-05, + "loss": 3.6724, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024283541988374e-05, + "loss": 3.6849, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023444947237322e-05, + "loss": 3.6755, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.02260635248627e-05, + "loss": 3.6676, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021767757735218e-05, + "loss": 3.6786, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020930800864539e-05, + "loss": 3.6831, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020092206113487e-05, + "loss": 3.6687, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019253611362435e-05, + "loss": 3.6666, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018415016611383e-05, + "loss": 3.6685, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017578059740704e-05, + "loss": 3.6674, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016739464989652e-05, + "loss": 3.6802, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159008702386e-05, + "loss": 3.6833, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.0150622754875486e-05, + "loss": 3.6854, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.0142253186168696e-05, + "loss": 3.6594, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.0133867238658175e-05, + "loss": 3.6848, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125481291147655e-05, + "loss": 3.6745, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011709534363713e-05, + "loss": 3.6741, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108725774930344e-05, + "loss": 3.6651, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100339827419824e-05, + "loss": 3.6783, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0091953879909304e-05, + "loss": 3.67, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008356793239878e-05, + "loss": 3.6871, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.0075198363691993e-05, + "loss": 3.6658, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006681241618147e-05, + "loss": 3.6747, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005842646867095e-05, + "loss": 3.6742, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005004052116043e-05, + "loss": 3.6754, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004167095245365e-05, + "loss": 3.6752, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003328500494313e-05, + "loss": 3.6726, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.00248990574326e-05, + "loss": 3.6805, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001651310992208e-05, + "loss": 3.6684, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000812716241156e-05, + "loss": 3.6811, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8711984157562256, + "eval_runtime": 302.465, + "eval_samples_per_second": 1261.604, + "eval_steps_per_second": 39.426, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.999974121490104e-05, + "loss": 3.6651, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999135526739052e-05, + "loss": 3.6595, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998296931988e-05, + "loss": 3.6693, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997458337236948e-05, + "loss": 3.6792, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996619742485896e-05, + "loss": 3.684, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995781147734844e-05, + "loss": 3.6643, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994942552983792e-05, + "loss": 3.6731, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994103958232741e-05, + "loss": 3.6627, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993267001362062e-05, + "loss": 3.6684, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.99242840661101e-05, + "loss": 3.6682, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991589811859958e-05, + "loss": 3.6711, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990751217108906e-05, + "loss": 3.6702, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899175359989725e-05, + "loss": 3.6715, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890789412479205e-05, + "loss": 3.662, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882403464968685e-05, + "loss": 3.6628, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874017517458165e-05, + "loss": 3.653, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865631569947645e-05, + "loss": 3.6619, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985724562243713e-05, + "loss": 3.6754, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984885967492661e-05, + "loss": 3.6606, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984047372741609e-05, + "loss": 3.6765, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983208777990557e-05, + "loss": 3.6787, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982370183239505e-05, + "loss": 3.6761, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981531588488453e-05, + "loss": 3.6746, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980692993737401e-05, + "loss": 3.6668, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.6655, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979019079996043e-05, + "loss": 3.6722, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978180485244991e-05, + "loss": 3.673, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977341890493939e-05, + "loss": 3.6658, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976503295742887e-05, + "loss": 3.6657, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975664700991835e-05, + "loss": 3.6634, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974826106240783e-05, + "loss": 3.6583, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973987511489731e-05, + "loss": 3.6721, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.9731505546190525e-05, + "loss": 3.6717, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9723119598680005e-05, + "loss": 3.6719, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714733651169485e-05, + "loss": 3.6606, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706347703658965e-05, + "loss": 3.6714, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9697978134952174e-05, + "loss": 3.6664, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689592187441654e-05, + "loss": 3.6513, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.9681206239931134e-05, + "loss": 3.6591, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672820292420614e-05, + "loss": 3.6548, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966445072371382e-05, + "loss": 3.6587, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96560647762033e-05, + "loss": 3.6701, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964767882869278e-05, + "loss": 3.6665, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963929288118226e-05, + "loss": 3.6569, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963092331247548e-05, + "loss": 3.6685, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962253736496496e-05, + "loss": 3.6611, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961415141745444e-05, + "loss": 3.6714, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960578184874765e-05, + "loss": 3.6634, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959739590123713e-05, + "loss": 3.6379, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958900995372661e-05, + "loss": 3.6756, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958062400621609e-05, + "loss": 3.6543, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95722544375093e-05, + "loss": 3.6654, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956386848999878e-05, + "loss": 3.6608, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955548254248826e-05, + "loss": 3.6565, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954711297378147e-05, + "loss": 3.6495, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953872702627095e-05, + "loss": 3.6543, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953034107876043e-05, + "loss": 3.6733, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952195513124991e-05, + "loss": 3.6461, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513569183739386e-05, + "loss": 3.6704, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505183236228865e-05, + "loss": 3.6616, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496797288718345e-05, + "loss": 3.6446, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488411341207825e-05, + "loss": 3.6706, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480041772501035e-05, + "loss": 3.652, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471655824990514e-05, + "loss": 3.6397, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9463269877479994e-05, + "loss": 3.6545, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454883929969474e-05, + "loss": 3.6627, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944651436126269e-05, + "loss": 3.6465, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943812841375217e-05, + "loss": 3.6584, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942974246624165e-05, + "loss": 3.6459, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942135651873113e-05, + "loss": 3.6492, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941298695002434e-05, + "loss": 3.6613, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940460100251382e-05, + "loss": 3.6564, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.93962150550033e-05, + "loss": 3.6623, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938782910749278e-05, + "loss": 3.6563, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937945953878599e-05, + "loss": 3.6683, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937107359127547e-05, + "loss": 3.6509, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936268764376495e-05, + "loss": 3.6579, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354318075058164e-05, + "loss": 3.6465, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345932127547644e-05, + "loss": 3.648, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.9337546180037124e-05, + "loss": 3.6572, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.9329160232526604e-05, + "loss": 3.6526, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.9320774285016084e-05, + "loss": 3.6645, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312388337505564e-05, + "loss": 3.6648, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304002389995044e-05, + "loss": 3.6355, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295616442484524e-05, + "loss": 3.6426, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928724687377773e-05, + "loss": 3.6583, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927886092626721e-05, + "loss": 3.6587, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927047497875669e-05, + "loss": 3.6578, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.65, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.6561, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.6523, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923696394632208e-05, + "loss": 3.6512, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922857799881156e-05, + "loss": 3.6474, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922019205130104e-05, + "loss": 3.6563, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921180610379052e-05, + "loss": 3.6638, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.6614, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919503420876948e-05, + "loss": 3.6418, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918664826125896e-05, + "loss": 3.6487, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917826231374844e-05, + "loss": 3.6449, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169892745041646e-05, + "loss": 3.6572, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161506797531126e-05, + "loss": 3.6554, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153120850020606e-05, + "loss": 3.6464, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144734902510086e-05, + "loss": 3.6524, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91363653338033e-05, + "loss": 3.6401, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.6459, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911959343878226e-05, + "loss": 3.6414, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911122387007547e-05, + "loss": 3.6512, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910283792256495e-05, + "loss": 3.6495, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909445197505443e-05, + "loss": 3.6525, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908608240634764e-05, + "loss": 3.6429, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907769645883712e-05, + "loss": 3.6436, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.90693105113266e-05, + "loss": 3.6475, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906092456381608e-05, + "loss": 3.6566, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905253861630556e-05, + "loss": 3.6454, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904415266879504e-05, + "loss": 3.6495, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903576672128452e-05, + "loss": 3.6523, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027380773774e-05, + "loss": 3.6628, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019011205067216e-05, + "loss": 3.6493, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010625257556696e-05, + "loss": 3.6486, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900223931004617e-05, + "loss": 3.6487, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899385336253565e-05, + "loss": 3.6544, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985483793828865e-05, + "loss": 3.6486, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897709784631834e-05, + "loss": 3.6424, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896871189880782e-05, + "loss": 3.6501, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960342330101034e-05, + "loss": 3.6555, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951956382590514e-05, + "loss": 3.6444, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943570435079994e-05, + "loss": 3.6375, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935184487569473e-05, + "loss": 3.6413, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892681491886269e-05, + "loss": 3.6405, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891842897135217e-05, + "loss": 3.6547, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891004302384164e-05, + "loss": 3.653, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890167345513486e-05, + "loss": 3.6569, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889328750762434e-05, + "loss": 3.6352, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888490156011381e-05, + "loss": 3.6566, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887651561260329e-05, + "loss": 3.6479, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886812966509277e-05, + "loss": 3.6463, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885974371758225e-05, + "loss": 3.6401, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885135777007173e-05, + "loss": 3.6448, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884297182256121e-05, + "loss": 3.6438, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883460225385443e-05, + "loss": 3.6597, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882621630634391e-05, + "loss": 3.6384, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881783035883339e-05, + "loss": 3.6478, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880944441132287e-05, + "loss": 3.6504, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801074842616076e-05, + "loss": 3.6504, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792705273909285e-05, + "loss": 3.644, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784319326398765e-05, + "loss": 3.6495, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775933378888245e-05, + "loss": 3.6518, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767547431377725e-05, + "loss": 3.6414, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759161483867205e-05, + "loss": 3.6533, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8683042526245117, + "eval_runtime": 304.601, + "eval_samples_per_second": 1252.757, + "eval_steps_per_second": 39.15, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6441, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6291, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873402002013938e-05, + "loss": 3.6439, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872563407262886e-05, + "loss": 3.6534, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871724812511834e-05, + "loss": 3.6573, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6395, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.6471, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.6347, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868372071387999e-05, + "loss": 3.6425, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867533476636947e-05, + "loss": 3.6438, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866694881885895e-05, + "loss": 3.6434, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865856287134843e-05, + "loss": 3.6448, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6524, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6328, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6343, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6219, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6412, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608279943892774e-05, + "loss": 3.6491, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599893996382254e-05, + "loss": 3.6333, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591508048871734e-05, + "loss": 3.6466, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.8583122101361214e-05, + "loss": 3.6552, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574736153850694e-05, + "loss": 3.649, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566350206340174e-05, + "loss": 3.6464, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855798063763338e-05, + "loss": 3.6432, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854959469012286e-05, + "loss": 3.6452, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854120874261234e-05, + "loss": 3.6428, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853282279510182e-05, + "loss": 3.6457, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.85244368475913e-05, + "loss": 3.6471, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851605090008078e-05, + "loss": 3.6345, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850766495257026e-05, + "loss": 3.6325, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849929538386347e-05, + "loss": 3.6337, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849090943635295e-05, + "loss": 3.6462, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848252348884243e-05, + "loss": 3.6491, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847413754133191e-05, + "loss": 3.6452, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846576797262512e-05, + "loss": 3.6351, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.84573820251146e-05, + "loss": 3.6392, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844899607760408e-05, + "loss": 3.6434, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844061013009356e-05, + "loss": 3.627, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843224056138677e-05, + "loss": 3.6302, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423870992679986e-05, + "loss": 3.6315, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841548504516947e-05, + "loss": 3.6321, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407099097658946e-05, + "loss": 3.6439, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398713150148426e-05, + "loss": 3.6429, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.6321, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8381941255127386e-05, + "loss": 3.6446, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373555307616866e-05, + "loss": 3.6342, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6432, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6441, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348413843889035e-05, + "loss": 3.6134, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340027896378515e-05, + "loss": 3.6447, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331641948867994e-05, + "loss": 3.6311, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832327238016121e-05, + "loss": 3.6386, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831488643265069e-05, + "loss": 3.6365, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830650048514017e-05, + "loss": 3.6301, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829811453762965e-05, + "loss": 3.6275, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828974496892286e-05, + "loss": 3.6291, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828135902141234e-05, + "loss": 3.6493, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827297307390182e-05, + "loss": 3.6222, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.82645871263913e-05, + "loss": 3.6447, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825621755768451e-05, + "loss": 3.6362, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824783161017399e-05, + "loss": 3.6197, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823944566266347e-05, + "loss": 3.6461, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823105971515295e-05, + "loss": 3.6236, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822267376764243e-05, + "loss": 3.6155, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821428782013191e-05, + "loss": 3.6251, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205918251425124e-05, + "loss": 3.6417, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197532303914604e-05, + "loss": 3.6187, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189146356404084e-05, + "loss": 3.637, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180760408893564e-05, + "loss": 3.6217, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172374461383044e-05, + "loss": 3.6228, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8163988513872524e-05, + "loss": 3.6341, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155602566362004e-05, + "loss": 3.6322, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814723299765521e-05, + "loss": 3.6367, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813886342894842e-05, + "loss": 3.6324, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81304774814379e-05, + "loss": 3.6399, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812209153392738e-05, + "loss": 3.6286, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811370558641686e-05, + "loss": 3.6327, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810533601771008e-05, + "loss": 3.6183, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809695007019956e-05, + "loss": 3.6243, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808856412268904e-05, + "loss": 3.6324, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6233, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071792227668e-05, + "loss": 3.6391, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063422658961207e-05, + "loss": 3.6382, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055036711450686e-05, + "loss": 3.6181, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046650763940166e-05, + "loss": 3.6164, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038264816429646e-05, + "loss": 3.6334, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029878868919126e-05, + "loss": 3.6333, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.80214929214086e-05, + "loss": 3.6326, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801310697389808e-05, + "loss": 3.6233, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004737405191295e-05, + "loss": 3.6348, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6275, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987965510170255e-05, + "loss": 3.6263, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979579562659735e-05, + "loss": 3.6251, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971193615149215e-05, + "loss": 3.6302, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962807667638695e-05, + "loss": 3.6351, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954438098931904e-05, + "loss": 3.637, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946052151421384e-05, + "loss": 3.6167, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937666203910864e-05, + "loss": 3.6265, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929280256400344e-05, + "loss": 3.6158, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920894308889824e-05, + "loss": 3.6322, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.6298, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790413879267252e-05, + "loss": 3.6261, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895752845162e-05, + "loss": 3.6248, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788736689765148e-05, + "loss": 3.616, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787898095014096e-05, + "loss": 3.6214, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787059500263044e-05, + "loss": 3.6152, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786220905511992e-05, + "loss": 3.625, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.78538231076094e-05, + "loss": 3.6267, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784545353890261e-05, + "loss": 3.6272, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783708397019582e-05, + "loss": 3.618, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.618, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.6235, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.6323, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.6228, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779515423264322e-05, + "loss": 3.6245, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786768285132704e-05, + "loss": 3.629, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778382337622184e-05, + "loss": 3.6364, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777002914771912e-05, + "loss": 3.6267, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.77616432002086e-05, + "loss": 3.6237, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775325725269808e-05, + "loss": 3.6241, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774487130518756e-05, + "loss": 3.6281, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773648535767704e-05, + "loss": 3.6275, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.6198, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6208, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771132751514548e-05, + "loss": 3.6316, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770295794643869e-05, + "loss": 3.619, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769457199892817e-05, + "loss": 3.6144, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6156, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767780010390714e-05, + "loss": 3.6138, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766943053520035e-05, + "loss": 3.6349, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6245, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6383, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764427269266879e-05, + "loss": 3.615, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635903123961996e-05, + "loss": 3.6295, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627517176451476e-05, + "loss": 3.6228, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619131228940956e-05, + "loss": 3.6244, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610745281430436e-05, + "loss": 3.618, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760235933391991e-05, + "loss": 3.6172, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759397338640939e-05, + "loss": 3.6208, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585587438898876e-05, + "loss": 3.6412, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577201491388356e-05, + "loss": 3.6124, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.6241, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.7560445975171045e-05, + "loss": 3.6288, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755207640646426e-05, + "loss": 3.6237, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543690458953734e-05, + "loss": 3.6202, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535304511443214e-05, + "loss": 3.6245, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6296, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518532616422174e-05, + "loss": 3.622, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510146668911654e-05, + "loss": 3.6278, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.866147041320801, + "eval_runtime": 305.1833, + "eval_samples_per_second": 1250.367, + "eval_steps_per_second": 39.075, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750177710020486e-05, + "loss": 3.6151, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749339115269434e-05, + "loss": 3.6087, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748500520518383e-05, + "loss": 3.622, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747661925767331e-05, + "loss": 3.6286, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746824968896652e-05, + "loss": 3.6342, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459863741456e-05, + "loss": 3.6164, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745147779394548e-05, + "loss": 3.623, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744309184643496e-05, + "loss": 3.6147, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743470589892444e-05, + "loss": 3.618, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742633633021765e-05, + "loss": 3.6201, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741795038270713e-05, + "loss": 3.6164, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740956443519661e-05, + "loss": 3.6236, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401194866489816e-05, + "loss": 3.6279, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392808918979296e-05, + "loss": 3.6099, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738442297146878e-05, + "loss": 3.6115, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737603702395826e-05, + "loss": 3.6009, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736765107644774e-05, + "loss": 3.6197, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735926512893722e-05, + "loss": 3.6237, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.73508791814267e-05, + "loss": 3.6093, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734249323391618e-05, + "loss": 3.6202, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733410728640566e-05, + "loss": 3.6375, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732573771769887e-05, + "loss": 3.6267, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731735177018835e-05, + "loss": 3.6216, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730896582267783e-05, + "loss": 3.6182, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730057987516731e-05, + "loss": 3.6256, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729219392765679e-05, + "loss": 3.6184, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728382435895e-05, + "loss": 3.618, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727543841143948e-05, + "loss": 3.624, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726705246392897e-05, + "loss": 3.6136, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6129, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725028056890793e-05, + "loss": 3.6128, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.72418946213974e-05, + "loss": 3.6209, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723350867388688e-05, + "loss": 3.6216, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225139105180096e-05, + "loss": 3.6237, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721675315766957e-05, + "loss": 3.6144, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720836721015905e-05, + "loss": 3.6162, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719998126264853e-05, + "loss": 3.6201, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719159531513801e-05, + "loss": 3.6071, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.6074, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.6086, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166453851410185e-05, + "loss": 3.6061, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158067903899665e-05, + "loss": 3.6187, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149698335192874e-05, + "loss": 3.6191, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6148, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7132926440171834e-05, + "loss": 3.6151, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124540492661314e-05, + "loss": 3.6133, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116154545150794e-05, + "loss": 3.6229, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107784976444e-05, + "loss": 3.6223, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709939902893348e-05, + "loss": 3.5894, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709101308142296e-05, + "loss": 3.6231, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708262713391244e-05, + "loss": 3.6072, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707425756520566e-05, + "loss": 3.6184, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.6151, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705748567018462e-05, + "loss": 3.6048, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.70490997226741e-05, + "loss": 3.6083, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704073015396731e-05, + "loss": 3.6034, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703234420645679e-05, + "loss": 3.6227, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702395825894627e-05, + "loss": 3.6026, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701557231143575e-05, + "loss": 3.6204, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700720274272896e-05, + "loss": 3.6154, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699881679521844e-05, + "loss": 3.6016, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699043084770792e-05, + "loss": 3.6204, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.69820449001974e-05, + "loss": 3.6014, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697365895268688e-05, + "loss": 3.5968, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696527300517636e-05, + "loss": 3.6015, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695690343646957e-05, + "loss": 3.6179, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694851748895905e-05, + "loss": 3.5967, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694013154144853e-05, + "loss": 3.6173, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693174559393801e-05, + "loss": 3.5955, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692335964642749e-05, + "loss": 3.6042, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691497369891697e-05, + "loss": 3.6103, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690658775140645e-05, + "loss": 3.6084, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689820180389593e-05, + "loss": 3.6165, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688984861399287e-05, + "loss": 3.6138, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688146266648235e-05, + "loss": 3.6185, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687307671897183e-05, + "loss": 3.6026, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686469077146131e-05, + "loss": 3.611, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856321202754526e-05, + "loss": 3.5972, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847935255244006e-05, + "loss": 3.6032, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839549307733486e-05, + "loss": 3.6085, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831163360222966e-05, + "loss": 3.6003, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822777412712446e-05, + "loss": 3.6169, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814391465201926e-05, + "loss": 3.6159, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806005517691406e-05, + "loss": 3.6013, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679761957018088e-05, + "loss": 3.589, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789250001474095e-05, + "loss": 3.6118, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780880432767304e-05, + "loss": 3.6088, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772494485256784e-05, + "loss": 3.6174, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764108537746264e-05, + "loss": 3.5952, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755722590235744e-05, + "loss": 3.6141, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674733664272523e-05, + "loss": 3.606, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673896707401844e-05, + "loss": 3.6039, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673058112650792e-05, + "loss": 3.5996, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.67221951789974e-05, + "loss": 3.6088, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671380923148688e-05, + "loss": 3.6127, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670543966278009e-05, + "loss": 3.6153, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669705371526957e-05, + "loss": 3.595, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668866776775905e-05, + "loss": 3.6025, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668028182024853e-05, + "loss": 3.5985, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671895872738e-05, + "loss": 3.6091, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666352630403122e-05, + "loss": 3.6068, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.66551403565207e-05, + "loss": 3.6051, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664675440901018e-05, + "loss": 3.6018, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663836846149966e-05, + "loss": 3.5955, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.662998251398914e-05, + "loss": 3.6024, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662159656647862e-05, + "loss": 3.5924, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613226997771827e-05, + "loss": 3.6027, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604841050261307e-05, + "loss": 3.6011, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596455102750786e-05, + "loss": 3.6097, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588069155240266e-05, + "loss": 3.5936, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579699586533476e-05, + "loss": 3.5979, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.6001, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562927691512435e-05, + "loss": 3.6099, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655454174400192e-05, + "loss": 3.6028, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.65461557964914e-05, + "loss": 3.6042, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653776984898088e-05, + "loss": 3.6075, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652938390147036e-05, + "loss": 3.6141, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652101433276357e-05, + "loss": 3.6035, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651262838525305e-05, + "loss": 3.6032, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650424243774253e-05, + "loss": 3.6018, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649585649023201e-05, + "loss": 3.6062, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648748692152522e-05, + "loss": 3.6031, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64791009740147e-05, + "loss": 3.5987, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647071502650418e-05, + "loss": 3.6008, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646232907899366e-05, + "loss": 3.609, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645394313148314e-05, + "loss": 3.5949, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445573562776356e-05, + "loss": 3.5971, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437187615265836e-05, + "loss": 3.5891, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428801667755316e-05, + "loss": 3.5955, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420415720244796e-05, + "loss": 3.6081, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412029772734276e-05, + "loss": 3.6069, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403660204027485e-05, + "loss": 3.6162, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395274256516965e-05, + "loss": 3.5891, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386888309006445e-05, + "loss": 3.6076, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378502361495925e-05, + "loss": 3.6004, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370116413985405e-05, + "loss": 3.6029, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.6361730466474884e-05, + "loss": 3.5954, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635334451896436e-05, + "loss": 3.5948, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634495857145384e-05, + "loss": 3.6026, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.6336589002747053e-05, + "loss": 3.6157, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632820305523654e-05, + "loss": 3.589, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319817107726013e-05, + "loss": 3.6058, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631144753901923e-05, + "loss": 3.6062, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630306159150871e-05, + "loss": 3.6022, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629467564399819e-05, + "loss": 3.6013, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628628969648766e-05, + "loss": 3.6057, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627790374897714e-05, + "loss": 3.6033, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626953418027036e-05, + "loss": 3.6043, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626114823275983e-05, + "loss": 3.604, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.865309238433838, + "eval_runtime": 306.2695, + "eval_samples_per_second": 1245.932, + "eval_steps_per_second": 38.936, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625276228524931e-05, + "loss": 3.5942, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624437633773879e-05, + "loss": 3.5874, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623599039022828e-05, + "loss": 3.6006, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622762082152149e-05, + "loss": 3.6066, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621923487401097e-05, + "loss": 3.613, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621084892650045e-05, + "loss": 3.5964, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620246297898993e-05, + "loss": 3.6036, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619407703147941e-05, + "loss": 3.5953, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185707462772616e-05, + "loss": 3.5947, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177321515262096e-05, + "loss": 3.5955, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6168935567751576e-05, + "loss": 3.6019, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160549620241056e-05, + "loss": 3.598, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152196430338e-05, + "loss": 3.6091, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614381048282748e-05, + "loss": 3.5892, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613542453531696e-05, + "loss": 3.5908, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612703858780644e-05, + "loss": 3.5793, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611865264029592e-05, + "loss": 3.5987, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.61102666927854e-05, + "loss": 3.6006, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610188074527488e-05, + "loss": 3.5891, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609349479776436e-05, + "loss": 3.6009, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608510885025384e-05, + "loss": 3.6161, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607673928154705e-05, + "loss": 3.6036, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606835333403653e-05, + "loss": 3.5997, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605996738652601e-05, + "loss": 3.5989, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605158143901549e-05, + "loss": 3.605, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604319549150497e-05, + "loss": 3.599, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034825922798185e-05, + "loss": 3.5962, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026439975287665e-05, + "loss": 3.6007, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018054027777145e-05, + "loss": 3.5937, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009668080266625e-05, + "loss": 3.5911, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001282132756105e-05, + "loss": 3.5969, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992896185245585e-05, + "loss": 3.5957, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5984510237735065e-05, + "loss": 3.6015, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976140669028274e-05, + "loss": 3.6052, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.5967754721517754e-05, + "loss": 3.5944, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.5959368774007234e-05, + "loss": 3.5935, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5950982826496714e-05, + "loss": 3.6015, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942596878986194e-05, + "loss": 3.5852, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.59342273102794e-05, + "loss": 3.5902, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592584136276888e-05, + "loss": 3.5849, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591745541525837e-05, + "loss": 3.5878, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590906946774785e-05, + "loss": 3.5936, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590069989904106e-05, + "loss": 3.5986, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589231395153054e-05, + "loss": 3.5968, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588392800402002e-05, + "loss": 3.5905, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.58755420565095e-05, + "loss": 3.5982, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586717248780271e-05, + "loss": 3.5979, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585878654029219e-05, + "loss": 3.6019, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585040059278167e-05, + "loss": 3.572, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584201464527114e-05, + "loss": 3.6039, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583362869776062e-05, + "loss": 3.584, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582524275025011e-05, + "loss": 3.5972, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581687318154332e-05, + "loss": 3.5928, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.58084872340328e-05, + "loss": 3.5876, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800101286522277e-05, + "loss": 3.5827, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791715339011757e-05, + "loss": 3.5814, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578334577030497e-05, + "loss": 3.6075, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5774959822794446e-05, + "loss": 3.5805, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766573875283926e-05, + "loss": 3.6003, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758187927773405e-05, + "loss": 3.5915, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5749818359066615e-05, + "loss": 3.5821, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741432411556095e-05, + "loss": 3.5992, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733046464045575e-05, + "loss": 3.5835, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572466051653506e-05, + "loss": 3.574, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571627456902454e-05, + "loss": 3.5818, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570788862151402e-05, + "loss": 3.5979, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569951905280723e-05, + "loss": 3.577, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569113310529671e-05, + "loss": 3.5968, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568274715778619e-05, + "loss": 3.5718, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567436121027567e-05, + "loss": 3.585, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566599164156888e-05, + "loss": 3.5897, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565760569405836e-05, + "loss": 3.5917, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564921974654784e-05, + "loss": 3.5904, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564083379903732e-05, + "loss": 3.5938, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.56324478515268e-05, + "loss": 3.5976, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562407828282001e-05, + "loss": 3.5839, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615692335309495e-05, + "loss": 3.5877, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607306387798975e-05, + "loss": 3.58, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598920440288455e-05, + "loss": 3.5849, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590534492777935e-05, + "loss": 3.5848, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582164924071144e-05, + "loss": 3.5823, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5573778976560624e-05, + "loss": 3.5949, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565393029050104e-05, + "loss": 3.5941, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557007081539584e-05, + "loss": 3.5825, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554863751283279e-05, + "loss": 3.5667, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554025156532227e-05, + "loss": 3.5916, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553186561781175e-05, + "loss": 3.5907, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552347967030123e-05, + "loss": 3.5965, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551509372279071e-05, + "loss": 3.5772, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550672415408393e-05, + "loss": 3.5905, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549833820657341e-05, + "loss": 3.5928, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548995225906289e-05, + "loss": 3.5805, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548156631155237e-05, + "loss": 3.5779, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547318036404185e-05, + "loss": 3.5899, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546481079533506e-05, + "loss": 3.5901, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545642484782454e-05, + "loss": 3.5966, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544803890031402e-05, + "loss": 3.5784, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.54396529528035e-05, + "loss": 3.5802, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431283384096706e-05, + "loss": 3.5766, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422897436586186e-05, + "loss": 3.5899, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414511489075666e-05, + "loss": 3.5889, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406125541565146e-05, + "loss": 3.5835, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539775597285836e-05, + "loss": 3.5828, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538937002534784e-05, + "loss": 3.5771, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538098407783732e-05, + "loss": 3.5812, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.53725981303268e-05, + "loss": 3.5703, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536422856162001e-05, + "loss": 3.5811, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535584261410949e-05, + "loss": 3.5815, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534745666659897e-05, + "loss": 3.5869, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533907071908845e-05, + "loss": 3.576, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330684771577924e-05, + "loss": 3.5832, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532231520287114e-05, + "loss": 3.5755, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531392925536062e-05, + "loss": 3.5923, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.53055433078501e-05, + "loss": 3.5809, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529715736033958e-05, + "loss": 3.5849, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528877141282906e-05, + "loss": 3.5848, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528038546531854e-05, + "loss": 3.5996, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527201589661175e-05, + "loss": 3.5812, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526362994910123e-05, + "loss": 3.5833, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525524400159071e-05, + "loss": 3.5844, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524685805408019e-05, + "loss": 3.5859, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.52384884853734e-05, + "loss": 3.5808, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523010253786288e-05, + "loss": 3.5838, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522171659035236e-05, + "loss": 3.5776, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521333064284184e-05, + "loss": 3.5871, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5204961074135054e-05, + "loss": 3.5729, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196575126624534e-05, + "loss": 3.5783, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5188189179114013e-05, + "loss": 3.5698, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5179803231603493e-05, + "loss": 3.5818, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.51714336628967e-05, + "loss": 3.5876, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516304771538618e-05, + "loss": 3.5864, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515466176787566e-05, + "loss": 3.5955, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514627582036514e-05, + "loss": 3.5735, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513790625165835e-05, + "loss": 3.5833, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512952030414783e-05, + "loss": 3.5855, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512113435663731e-05, + "loss": 3.5837, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511274840912679e-05, + "loss": 3.5751, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510437884042001e-05, + "loss": 3.5729, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509599289290949e-05, + "loss": 3.5836, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508760694539897e-05, + "loss": 3.5914, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507922099788845e-05, + "loss": 3.5762, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070851429181656e-05, + "loss": 3.5838, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062465481671136e-05, + "loss": 3.5863, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5054079534160616e-05, + "loss": 3.5832, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.5045693586650096e-05, + "loss": 3.5796, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037324017943305e-05, + "loss": 3.5842, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5028938070432785e-05, + "loss": 3.5831, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020552122922265e-05, + "loss": 3.5823, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012166175411745e-05, + "loss": 3.5878, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.864252805709839, + "eval_runtime": 305.9627, + "eval_samples_per_second": 1247.182, + "eval_steps_per_second": 38.975, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500379660670496e-05, + "loss": 3.5795, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499541065919444e-05, + "loss": 3.5628, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498702471168392e-05, + "loss": 3.5801, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.49786387641734e-05, + "loss": 3.5866, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497026919546661e-05, + "loss": 3.5892, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496188324795609e-05, + "loss": 3.5812, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495349730044557e-05, + "loss": 3.5822, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494511135293505e-05, + "loss": 3.5779, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493674178422826e-05, + "loss": 3.5751, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492835583671774e-05, + "loss": 3.5779, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491996988920722e-05, + "loss": 3.5831, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49115839416967e-05, + "loss": 3.5778, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903214372989915e-05, + "loss": 3.5892, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4894828425479395e-05, + "loss": 3.5686, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886442477968874e-05, + "loss": 3.57, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878056530458354e-05, + "loss": 3.5629, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869670582947834e-05, + "loss": 3.5827, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861284635437314e-05, + "loss": 3.5794, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4852898687926794e-05, + "loss": 3.576, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844512740416274e-05, + "loss": 3.5775, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836126792905754e-05, + "loss": 3.595, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482775722419896e-05, + "loss": 3.5853, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481937127668844e-05, + "loss": 3.5815, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481098532917792e-05, + "loss": 3.5777, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48025993816674e-05, + "loss": 3.5905, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479421343415688e-05, + "loss": 3.5788, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.47858438654501e-05, + "loss": 3.5742, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477745791793958e-05, + "loss": 3.5883, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476907197042906e-05, + "loss": 3.5678, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476068602291853e-05, + "loss": 3.5745, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475231645421175e-05, + "loss": 3.5789, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474393050670123e-05, + "loss": 3.5729, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473554455919071e-05, + "loss": 3.5839, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472715861168018e-05, + "loss": 3.5877, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471877266416966e-05, + "loss": 3.5739, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471040309546288e-05, + "loss": 3.5766, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470201714795236e-05, + "loss": 3.5835, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469363120044184e-05, + "loss": 3.5655, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468524525293132e-05, + "loss": 3.5697, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467687568422453e-05, + "loss": 3.5734, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.4668489736714006e-05, + "loss": 3.567, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.4660103789203486e-05, + "loss": 3.5701, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.4651717841692966e-05, + "loss": 3.5818, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643331894182446e-05, + "loss": 3.5773, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4634962325475655e-05, + "loss": 3.5712, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626576377965135e-05, + "loss": 3.5751, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618190430454615e-05, + "loss": 3.5812, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609804482944095e-05, + "loss": 3.5807, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460143491423731e-05, + "loss": 3.5579, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459304896672679e-05, + "loss": 3.5814, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458466301921627e-05, + "loss": 3.5662, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457627707170575e-05, + "loss": 3.5761, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456789112419523e-05, + "loss": 3.5762, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455952155548844e-05, + "loss": 3.5675, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455113560797792e-05, + "loss": 3.5671, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.45427496604674e-05, + "loss": 3.5604, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453436371295688e-05, + "loss": 3.5917, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452599414425009e-05, + "loss": 3.5639, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451760819673957e-05, + "loss": 3.5767, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450922224922905e-05, + "loss": 3.574, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450083630171853e-05, + "loss": 3.5641, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492466733011744e-05, + "loss": 3.5754, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484080785501224e-05, + "loss": 3.5668, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475694837990704e-05, + "loss": 3.5593, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467308890480184e-05, + "loss": 3.5565, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4458922942969664e-05, + "loss": 3.5835, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445055337426287e-05, + "loss": 3.5618, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444216742675235e-05, + "loss": 3.5701, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443378147924183e-05, + "loss": 3.5544, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442539553173131e-05, + "loss": 3.5696, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441702596302452e-05, + "loss": 3.5657, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408640015514e-05, + "loss": 3.5752, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440025406800348e-05, + "loss": 3.5721, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439186812049296e-05, + "loss": 3.5746, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438349855178618e-05, + "loss": 3.5779, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437511260427566e-05, + "loss": 3.5666, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436672665676514e-05, + "loss": 3.5692, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435834070925462e-05, + "loss": 3.5608, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.43499547617441e-05, + "loss": 3.5676, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434158519303731e-05, + "loss": 3.5699, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433319924552679e-05, + "loss": 3.5609, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324813298016267e-05, + "loss": 3.581, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316427350505747e-05, + "loss": 3.5765, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308057781798956e-05, + "loss": 3.5662, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4299671834288436e-05, + "loss": 3.547, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291285886777916e-05, + "loss": 3.5678, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282899939267396e-05, + "loss": 3.5721, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427451399175688e-05, + "loss": 3.5792, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426612804424636e-05, + "loss": 3.5637, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425775847553957e-05, + "loss": 3.5697, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424937252802905e-05, + "loss": 3.5744, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424098658051853e-05, + "loss": 3.5623, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423260063300801e-05, + "loss": 3.5597, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224214685497484e-05, + "loss": 3.5715, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.42158451167907e-05, + "loss": 3.5685, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420745916928018e-05, + "loss": 3.5774, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419907322176966e-05, + "loss": 3.5662, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419068727425913e-05, + "loss": 3.5618, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418231770555235e-05, + "loss": 3.5597, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173931758041836e-05, + "loss": 3.5711, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165545810531316e-05, + "loss": 3.5714, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415715986302079e-05, + "loss": 3.5645, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148790294314005e-05, + "loss": 3.563, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140404346803485e-05, + "loss": 3.5564, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413201839929296e-05, + "loss": 3.5679, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412363245178244e-05, + "loss": 3.549, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411524650427192e-05, + "loss": 3.5592, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106876935565134e-05, + "loss": 3.5683, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409849098805461e-05, + "loss": 3.5693, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409010504054409e-05, + "loss": 3.553, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081719093033574e-05, + "loss": 3.5674, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407334952432679e-05, + "loss": 3.5596, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406496357681626e-05, + "loss": 3.5703, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405657762930574e-05, + "loss": 3.5638, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404819168179522e-05, + "loss": 3.5652, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403982211308843e-05, + "loss": 3.5658, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403143616557791e-05, + "loss": 3.5813, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402305021806739e-05, + "loss": 3.5633, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401466427055687e-05, + "loss": 3.5649, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400629470185008e-05, + "loss": 3.5684, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790875433956e-05, + "loss": 3.5639, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398952280682904e-05, + "loss": 3.5633, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398113685931853e-05, + "loss": 3.5653, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397275091180801e-05, + "loss": 3.5604, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3964381343101216e-05, + "loss": 3.5702, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955995395590696e-05, + "loss": 3.5535, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947609448080176e-05, + "loss": 3.5649, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939223500569656e-05, + "loss": 3.5555, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930837553059136e-05, + "loss": 3.5623, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922467984352345e-05, + "loss": 3.5634, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914082036841825e-05, + "loss": 3.5697, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905696089331305e-05, + "loss": 3.5779, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897310141820785e-05, + "loss": 3.5579, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888940573113994e-05, + "loss": 3.5668, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388055462560348e-05, + "loss": 3.5653, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387216867809296e-05, + "loss": 3.564, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386378273058244e-05, + "loss": 3.5615, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385541316187565e-05, + "loss": 3.5527, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384702721436513e-05, + "loss": 3.569, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383864126685461e-05, + "loss": 3.5745, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383025531934409e-05, + "loss": 3.5568, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.38218857506373e-05, + "loss": 3.5661, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381349980312678e-05, + "loss": 3.5702, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380511385561626e-05, + "loss": 3.5621, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379672790810574e-05, + "loss": 3.5621, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378835833939895e-05, + "loss": 3.5701, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779972391888435e-05, + "loss": 3.562, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771586444377915e-05, + "loss": 3.5658, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763200496867395e-05, + "loss": 3.5705, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8659350872039795, + "eval_runtime": 303.2187, + "eval_samples_per_second": 1258.468, + "eval_steps_per_second": 39.328, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754830928160604e-05, + "loss": 3.5716, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746444980650084e-05, + "loss": 3.5448, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3738059033139564e-05, + "loss": 3.5615, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729673085629044e-05, + "loss": 3.5723, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372130351692225e-05, + "loss": 3.5688, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371291756941173e-05, + "loss": 3.5666, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370453162190121e-05, + "loss": 3.5627, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369614567439069e-05, + "loss": 3.5586, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.36877761056839e-05, + "loss": 3.5571, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367939015817339e-05, + "loss": 3.5624, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367100421066287e-05, + "loss": 3.5618, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366261826315235e-05, + "loss": 3.5609, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365424869444556e-05, + "loss": 3.5726, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364586274693504e-05, + "loss": 3.5499, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363747679942452e-05, + "loss": 3.5527, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629090851914e-05, + "loss": 3.5426, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362070490440348e-05, + "loss": 3.5668, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.361231895689296e-05, + "loss": 3.5597, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360393300938244e-05, + "loss": 3.5598, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359554706187192e-05, + "loss": 3.5584, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358716111436139e-05, + "loss": 3.5779, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578791545654606e-05, + "loss": 3.5646, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570405598144086e-05, + "loss": 3.5632, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3562019650633566e-05, + "loss": 3.5607, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553633703123046e-05, + "loss": 3.5762, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545247755612526e-05, + "loss": 3.5547, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353687818690574e-05, + "loss": 3.56, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528492239395215e-05, + "loss": 3.5701, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3520106291884695e-05, + "loss": 3.5502, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351173672317791e-05, + "loss": 3.556, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350335077566739e-05, + "loss": 3.5584, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.3494964828156864e-05, + "loss": 3.5558, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.3486578880646344e-05, + "loss": 3.5687, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.3478192933135824e-05, + "loss": 3.5695, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.3469806985625304e-05, + "loss": 3.5566, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346143741691852e-05, + "loss": 3.5593, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453051469408e-05, + "loss": 3.5679, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344466552189748e-05, + "loss": 3.5432, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343627957438696e-05, + "loss": 3.5551, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.342789362687644e-05, + "loss": 3.5565, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341952405816965e-05, + "loss": 3.5465, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341113811065913e-05, + "loss": 3.5549, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340275216314861e-05, + "loss": 3.5658, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339436621563809e-05, + "loss": 3.5607, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.338598026812757e-05, + "loss": 3.553, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.337761069942078e-05, + "loss": 3.5568, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.336922475191026e-05, + "loss": 3.5594, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3360838804399744e-05, + "loss": 3.5633, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.3352452856889224e-05, + "loss": 3.5436, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334408328818243e-05, + "loss": 3.5641, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333569734067191e-05, + "loss": 3.5521, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332731139316139e-05, + "loss": 3.557, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.331892544565087e-05, + "loss": 3.559, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331055587694408e-05, + "loss": 3.545, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330216992943356e-05, + "loss": 3.5533, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329378398192304e-05, + "loss": 3.5428, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328539803441252e-05, + "loss": 3.5751, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327702846570573e-05, + "loss": 3.5474, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326864251819521e-05, + "loss": 3.5636, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.32602565706847e-05, + "loss": 3.5496, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325187062317418e-05, + "loss": 3.5468, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324348467566366e-05, + "loss": 3.5576, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.323511510695687e-05, + "loss": 3.5527, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.322672915944635e-05, + "loss": 3.5456, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.321834321193583e-05, + "loss": 3.5355, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.320995726442531e-05, + "loss": 3.5605, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201587695718516e-05, + "loss": 3.5493, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193201748207996e-05, + "loss": 3.5527, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184815800697476e-05, + "loss": 3.54, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176429853186956e-05, + "loss": 3.5482, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3168060284480165e-05, + "loss": 3.5525, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315967433696965e-05, + "loss": 3.5584, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315128838945913e-05, + "loss": 3.5548, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314290244194861e-05, + "loss": 3.5594, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313451649443809e-05, + "loss": 3.5602, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.31261469257313e-05, + "loss": 3.5486, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311776097822078e-05, + "loss": 3.5517, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310937503071026e-05, + "loss": 3.5452, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310098908319974e-05, + "loss": 3.5487, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309261951449295e-05, + "loss": 3.5525, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308423356698243e-05, + "loss": 3.5436, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307584761947191e-05, + "loss": 3.5609, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306746167196139e-05, + "loss": 3.5577, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059092103254605e-05, + "loss": 3.5443, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050706155744085e-05, + "loss": 3.535, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042320208233565e-05, + "loss": 3.5517, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.3033934260723045e-05, + "loss": 3.556, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.3025548313212525e-05, + "loss": 3.559, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.3017162365702e-05, + "loss": 3.5465, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.3008792796995214e-05, + "loss": 3.5515, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000406849484694e-05, + "loss": 3.5569, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299202090197417e-05, + "loss": 3.5426, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298363495446365e-05, + "loss": 3.5449, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297524900695313e-05, + "loss": 3.5503, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296687943824634e-05, + "loss": 3.5525, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295849349073582e-05, + "loss": 3.5612, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.29501075432253e-05, + "loss": 3.552, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294172159571478e-05, + "loss": 3.5406, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.2933352027008e-05, + "loss": 3.5446, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292496607949747e-05, + "loss": 3.5527, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291658013198695e-05, + "loss": 3.5559, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290819418447643e-05, + "loss": 3.549, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289982461576964e-05, + "loss": 3.5449, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289143866825912e-05, + "loss": 3.5395, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.28830527207486e-05, + "loss": 3.555, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287466677323808e-05, + "loss": 3.531, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.28662972045313e-05, + "loss": 3.5424, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285791125702078e-05, + "loss": 3.5518, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849525309510257e-05, + "loss": 3.5524, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2841139361999737e-05, + "loss": 3.5361, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2832769793292946e-05, + "loss": 3.5508, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824383845782426e-05, + "loss": 3.5439, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2815997898271906e-05, + "loss": 3.5529, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2807611950761386e-05, + "loss": 3.5502, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2799226003250865e-05, + "loss": 3.5458, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.2790856434544075e-05, + "loss": 3.5497, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2782470487033555e-05, + "loss": 3.5649, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2774084539523034e-05, + "loss": 3.546, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2765698592012514e-05, + "loss": 3.5504, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275732902330573e-05, + "loss": 3.552, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.274894307579521e-05, + "loss": 3.5459, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274055712828469e-05, + "loss": 3.5476, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.273217118077417e-05, + "loss": 3.5484, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272380161206738e-05, + "loss": 3.544, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271541566455686e-05, + "loss": 3.5504, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270702971704634e-05, + "loss": 3.5426, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269864376953582e-05, + "loss": 3.5446, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.26902578220253e-05, + "loss": 3.5398, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268188825331851e-05, + "loss": 3.5466, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267350230580799e-05, + "loss": 3.5416, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266511635829747e-05, + "loss": 3.5582, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265673041078695e-05, + "loss": 3.5613, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.2648360842080164e-05, + "loss": 3.5394, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.2639974894569644e-05, + "loss": 3.5487, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631588947059124e-05, + "loss": 3.5508, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.2623202999548604e-05, + "loss": 3.5497, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261483343084181e-05, + "loss": 3.5375, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260644748333129e-05, + "loss": 3.5387, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259806153582077e-05, + "loss": 3.5545, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258967558831025e-05, + "loss": 3.5562, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258128964079973e-05, + "loss": 3.5404, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257292007209294e-05, + "loss": 3.5505, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256453412458242e-05, + "loss": 3.5548, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.25561481770719e-05, + "loss": 3.548, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254776222956138e-05, + "loss": 3.5436, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.25393926608546e-05, + "loss": 3.5539, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253100671334408e-05, + "loss": 3.543, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252262076583356e-05, + "loss": 3.5509, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251423481832304e-05, + "loss": 3.5519, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.867368221282959, + "eval_runtime": 309.1287, + "eval_samples_per_second": 1234.408, + "eval_steps_per_second": 38.576, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505865249616247e-05, + "loss": 3.5607, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497479302105726e-05, + "loss": 3.5298, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.2489093354595206e-05, + "loss": 3.5433, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.2480707407084686e-05, + "loss": 3.5583, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472321459574166e-05, + "loss": 3.5533, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463951890867375e-05, + "loss": 3.5501, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455565943356855e-05, + "loss": 3.5432, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447179995846335e-05, + "loss": 3.5421, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243879404833582e-05, + "loss": 3.5403, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243042447962903e-05, + "loss": 3.5475, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242203853211851e-05, + "loss": 3.5427, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241365258460799e-05, + "loss": 3.5493, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.24052830159012e-05, + "loss": 3.5532, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239689706839068e-05, + "loss": 3.5348, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238851112088016e-05, + "loss": 3.5358, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238012517336964e-05, + "loss": 3.5253, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237173922585912e-05, + "loss": 3.5483, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.23633532783486e-05, + "loss": 3.5456, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235496733083807e-05, + "loss": 3.5441, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234658138332756e-05, + "loss": 3.539, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233819543581704e-05, + "loss": 3.5647, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232982586711025e-05, + "loss": 3.5498, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232143991959973e-05, + "loss": 3.5458, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231305397208921e-05, + "loss": 3.5446, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230466802457869e-05, + "loss": 3.562, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229628207706817e-05, + "loss": 3.5397, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228791250836138e-05, + "loss": 3.5398, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227952656085086e-05, + "loss": 3.5566, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227114061334034e-05, + "loss": 3.5338, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226275466582982e-05, + "loss": 3.5379, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225438509712303e-05, + "loss": 3.5412, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2245999149612514e-05, + "loss": 3.5392, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237613202101993e-05, + "loss": 3.5516, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229227254591473e-05, + "loss": 3.5529, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222085768588468e-05, + "loss": 3.5378, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221247173837416e-05, + "loss": 3.5495, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220408579086364e-05, + "loss": 3.5477, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219569984335312e-05, + "loss": 3.5284, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218733027464633e-05, + "loss": 3.5386, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217894432713581e-05, + "loss": 3.5422, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217055837962529e-05, + "loss": 3.5285, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216217243211477e-05, + "loss": 3.5416, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215380286340798e-05, + "loss": 3.5492, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214541691589747e-05, + "loss": 3.5428, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213703096838695e-05, + "loss": 3.5386, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212864502087643e-05, + "loss": 3.5438, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120275452169636e-05, + "loss": 3.5398, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2111889504659116e-05, + "loss": 3.5484, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103503557148596e-05, + "loss": 3.525, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095117609638076e-05, + "loss": 3.5464, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2086748040931285e-05, + "loss": 3.5418, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078362093420765e-05, + "loss": 3.5392, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2069976145910245e-05, + "loss": 3.5429, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061590198399725e-05, + "loss": 3.5292, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053220629692934e-05, + "loss": 3.5411, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044834682182414e-05, + "loss": 3.5244, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.20364487346719e-05, + "loss": 3.558, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202806278716138e-05, + "loss": 3.5317, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201969321845459e-05, + "loss": 3.5454, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201130727094407e-05, + "loss": 3.5383, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200292132343355e-05, + "loss": 3.5301, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199453537592303e-05, + "loss": 3.5402, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198616580721624e-05, + "loss": 3.5406, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197777985970572e-05, + "loss": 3.5252, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.19693939121952e-05, + "loss": 3.5207, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196100796468468e-05, + "loss": 3.545, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195263839597789e-05, + "loss": 3.5372, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194425244846737e-05, + "loss": 3.5324, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1935866500956854e-05, + "loss": 3.5225, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927480553446334e-05, + "loss": 3.5355, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919094605935814e-05, + "loss": 3.5356, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910725037229023e-05, + "loss": 3.5409, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902339089718503e-05, + "loss": 3.5417, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1893953142207983e-05, + "loss": 3.5434, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188556719469746e-05, + "loss": 3.5441, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187719762599067e-05, + "loss": 3.5348, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186881167848015e-05, + "loss": 3.5338, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186042573096963e-05, + "loss": 3.5294, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185203978345911e-05, + "loss": 3.5361, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184367021475232e-05, + "loss": 3.5371, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183528426724181e-05, + "loss": 3.5304, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182689831973129e-05, + "loss": 3.5421, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181851237222077e-05, + "loss": 3.5435, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181014280351398e-05, + "loss": 3.5314, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180175685600346e-05, + "loss": 3.524, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179337090849294e-05, + "loss": 3.5309, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178498496098242e-05, + "loss": 3.537, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17765990134719e-05, + "loss": 3.5487, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768229444765106e-05, + "loss": 3.5321, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759843497254586e-05, + "loss": 3.5347, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751457549744066e-05, + "loss": 3.5397, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743071602233546e-05, + "loss": 3.5297, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173470203352676e-05, + "loss": 3.5277, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172631608601624e-05, + "loss": 3.5319, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171793013850572e-05, + "loss": 3.5372, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.17095441909952e-05, + "loss": 3.5427, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170117462228841e-05, + "loss": 3.5395, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169278867477789e-05, + "loss": 3.5236, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168440272726737e-05, + "loss": 3.5314, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167601677975685e-05, + "loss": 3.5327, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166764721105006e-05, + "loss": 3.5419, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165926126353954e-05, + "loss": 3.5331, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165087531602902e-05, + "loss": 3.5294, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.16424893685185e-05, + "loss": 3.524, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634119799811715e-05, + "loss": 3.5376, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625733852301195e-05, + "loss": 3.5165, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617347904790675e-05, + "loss": 3.5297, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.1608961957280155e-05, + "loss": 3.5377, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1600592388573364e-05, + "loss": 3.5319, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592206441062844e-05, + "loss": 3.5239, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1583820493552324e-05, + "loss": 3.5347, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.15754345460418e-05, + "loss": 3.5268, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567064977335013e-05, + "loss": 3.5338, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155867902982449e-05, + "loss": 3.5378, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155029308231397e-05, + "loss": 3.5278, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154190713480345e-05, + "loss": 3.5382, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153352118729293e-05, + "loss": 3.5444, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152515161858615e-05, + "loss": 3.5353, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151676567107563e-05, + "loss": 3.5281, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.15083797235651e-05, + "loss": 3.5404, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149999377605458e-05, + "loss": 3.5317, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.14916242073478e-05, + "loss": 3.5268, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148323825983727e-05, + "loss": 3.536, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147485231232675e-05, + "loss": 3.5301, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146646636481623e-05, + "loss": 3.534, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145809679610945e-05, + "loss": 3.5269, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144971084859892e-05, + "loss": 3.5282, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144132490108841e-05, + "loss": 3.5237, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143293895357789e-05, + "loss": 3.5287, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.14245693848711e-05, + "loss": 3.5237, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416183437360576e-05, + "loss": 3.5424, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407797489850056e-05, + "loss": 3.5453, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399411542339536e-05, + "loss": 3.5286, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391041973632745e-05, + "loss": 3.5292, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1382656026122225e-05, + "loss": 3.5391, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374270078611705e-05, + "loss": 3.5324, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1365884131101185e-05, + "loss": 3.5242, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357514562394394e-05, + "loss": 3.5246, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349128614883874e-05, + "loss": 3.5383, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134074266737336e-05, + "loss": 3.538, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133235671986284e-05, + "loss": 3.5265, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132398715115605e-05, + "loss": 3.5317, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131560120364553e-05, + "loss": 3.5409, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130721525613501e-05, + "loss": 3.529, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129882930862449e-05, + "loss": 3.5288, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.12904597399177e-05, + "loss": 3.5399, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128207379240718e-05, + "loss": 3.5284, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127368784489666e-05, + "loss": 3.5365, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126530189738614e-05, + "loss": 3.5332, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8692779541015625, + "eval_runtime": 302.5965, + "eval_samples_per_second": 1261.056, + "eval_steps_per_second": 39.409, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125693232867935e-05, + "loss": 3.5289, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124854638116883e-05, + "loss": 3.5177, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240160433658314e-05, + "loss": 3.526, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231774486147794e-05, + "loss": 3.5404, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.1223404917441e-05, + "loss": 3.5345, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121501896993048e-05, + "loss": 3.5397, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120663302241996e-05, + "loss": 3.5236, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119824707490944e-05, + "loss": 3.5321, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118986112739892e-05, + "loss": 3.5217, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118149155869213e-05, + "loss": 3.5324, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117310561118161e-05, + "loss": 3.5233, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116471966367109e-05, + "loss": 3.5363, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.11563500949643e-05, + "loss": 3.5376, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114796414745378e-05, + "loss": 3.5195, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113957819994326e-05, + "loss": 3.5196, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113119225243275e-05, + "loss": 3.5135, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112280630492223e-05, + "loss": 3.5248, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111442035741171e-05, + "loss": 3.5319, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110603440990119e-05, + "loss": 3.5312, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109764846239067e-05, + "loss": 3.5209, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108926251488015e-05, + "loss": 3.5515, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108089294617336e-05, + "loss": 3.5334, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107250699866284e-05, + "loss": 3.5325, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106412105115232e-05, + "loss": 3.528, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.10557351036418e-05, + "loss": 3.5468, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047349156131277e-05, + "loss": 3.5248, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1038979587424486e-05, + "loss": 3.5287, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1030593639913966e-05, + "loss": 3.5365, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022207692403446e-05, + "loss": 3.5178, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101382174489293e-05, + "loss": 3.5259, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100545217618614e-05, + "loss": 3.522, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099706622867562e-05, + "loss": 3.5286, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.09886802811651e-05, + "loss": 3.5322, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098029433365458e-05, + "loss": 3.5386, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097192476494779e-05, + "loss": 3.5262, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096353881743727e-05, + "loss": 3.5349, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095515286992675e-05, + "loss": 3.532, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094676692241623e-05, + "loss": 3.5117, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093839735370944e-05, + "loss": 3.5252, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093001140619892e-05, + "loss": 3.5243, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.09216254586884e-05, + "loss": 3.5095, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091323951117788e-05, + "loss": 3.527, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0904869942471095e-05, + "loss": 3.5353, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896483994960575e-05, + "loss": 3.5304, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.0888098047450055e-05, + "loss": 3.5163, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879728478743264e-05, + "loss": 3.533, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871342531232744e-05, + "loss": 3.5276, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0862956583722224e-05, + "loss": 3.5344, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854570636211704e-05, + "loss": 3.5098, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084618468870118e-05, + "loss": 3.5276, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083781511999439e-05, + "loss": 3.5299, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082942917248387e-05, + "loss": 3.5225, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082104322497335e-05, + "loss": 3.5296, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081265727746283e-05, + "loss": 3.5124, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080428770875605e-05, + "loss": 3.5285, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079590176124553e-05, + "loss": 3.5085, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787515813735e-05, + "loss": 3.54, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077912986622448e-05, + "loss": 3.5191, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.07707602975177e-05, + "loss": 3.5292, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076237435000718e-05, + "loss": 3.5258, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075398840249665e-05, + "loss": 3.5175, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074560245498613e-05, + "loss": 3.5231, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073723288627935e-05, + "loss": 3.5266, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072884693876883e-05, + "loss": 3.5097, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720460991258307e-05, + "loss": 3.5058, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0712075043747787e-05, + "loss": 3.5282, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0703705475041e-05, + "loss": 3.5216, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695319527530476e-05, + "loss": 3.5221, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0686933580019956e-05, + "loss": 3.5088, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678547632509436e-05, + "loss": 3.5175, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670178063802645e-05, + "loss": 3.5217, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0661792116292125e-05, + "loss": 3.5236, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653406168781605e-05, + "loss": 3.526, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645020221271084e-05, + "loss": 3.5277, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06366506525643e-05, + "loss": 3.5287, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062826470505378e-05, + "loss": 3.521, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061987875754326e-05, + "loss": 3.518, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061149281003274e-05, + "loss": 3.517, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060312324132595e-05, + "loss": 3.5172, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059473729381543e-05, + "loss": 3.523, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058635134630491e-05, + "loss": 3.5189, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057796539879439e-05, + "loss": 3.5207, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.05695958300876e-05, + "loss": 3.5348, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056120988257708e-05, + "loss": 3.515, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055282393506656e-05, + "loss": 3.5092, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054443798755604e-05, + "loss": 3.5158, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536068418849254e-05, + "loss": 3.5242, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527682471338734e-05, + "loss": 3.5286, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0519296523828214e-05, + "loss": 3.5187, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051091057631769e-05, + "loss": 3.5186, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502541007610903e-05, + "loss": 3.5263, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494155060100383e-05, + "loss": 3.5175, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485769112589863e-05, + "loss": 3.5115, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477383165079343e-05, + "loss": 3.5155, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468997217568823e-05, + "loss": 3.5231, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460627648862032e-05, + "loss": 3.5275, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452241701351515e-05, + "loss": 3.5254, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443855753840995e-05, + "loss": 3.5106, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435469806330475e-05, + "loss": 3.5135, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427100237623684e-05, + "loss": 3.5157, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418714290113164e-05, + "loss": 3.5303, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410328342602644e-05, + "loss": 3.5153, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401942395092124e-05, + "loss": 3.5136, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393572826385337e-05, + "loss": 3.5108, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385186878874817e-05, + "loss": 3.519, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376800931364297e-05, + "loss": 3.5038, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368414983853776e-05, + "loss": 3.5179, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360045415146986e-05, + "loss": 3.5184, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035165946763647e-05, + "loss": 3.5181, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034327352012595e-05, + "loss": 3.5106, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033488757261543e-05, + "loss": 3.5203, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326518003908638e-05, + "loss": 3.5097, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318132056398118e-05, + "loss": 3.5215, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309746108887598e-05, + "loss": 3.5221, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301360161377078e-05, + "loss": 3.5123, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029299059267029e-05, + "loss": 3.523, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028460464515977e-05, + "loss": 3.5293, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027621869764925e-05, + "loss": 3.5215, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026783275013873e-05, + "loss": 3.5161, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.025946318143194e-05, + "loss": 3.5188, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251077233921423e-05, + "loss": 3.5202, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242691286410903e-05, + "loss": 3.5121, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234305338900383e-05, + "loss": 3.5214, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022593577019359e-05, + "loss": 3.5136, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021754982268307e-05, + "loss": 3.5205, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020916387517255e-05, + "loss": 3.5103, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020077792766203e-05, + "loss": 3.5162, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192391980151515e-05, + "loss": 3.5099, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184022411444724e-05, + "loss": 3.5128, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175636463934204e-05, + "loss": 3.5099, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167250516423684e-05, + "loss": 3.5258, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158864568913164e-05, + "loss": 3.5336, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150495000206376e-05, + "loss": 3.5166, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142109052695856e-05, + "loss": 3.5082, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133723105185336e-05, + "loss": 3.5233, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125337157674816e-05, + "loss": 3.5197, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0116967588968025e-05, + "loss": 3.5137, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108581641457505e-05, + "loss": 3.5063, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100195693946985e-05, + "loss": 3.5257, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091809746436465e-05, + "loss": 3.5201, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008342379892595e-05, + "loss": 3.5155, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075054230219158e-05, + "loss": 3.5147, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066668282708637e-05, + "loss": 3.5231, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058282335198117e-05, + "loss": 3.515, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.004991276649133e-05, + "loss": 3.5128, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004152681898081e-05, + "loss": 3.5249, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003314087147029e-05, + "loss": 3.5144, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002475492395977e-05, + "loss": 3.52, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.001636897644925e-05, + "loss": 3.5219, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.000799940774246e-05, + "loss": 3.516, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8696019649505615, + "eval_runtime": 302.8779, + "eval_samples_per_second": 1259.884, + "eval_steps_per_second": 39.372, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999961346023194e-05, + "loss": 3.502, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999122751272142e-05, + "loss": 3.5104, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982841565210902e-05, + "loss": 3.5251, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997447199650411e-05, + "loss": 3.5225, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996608604899359e-05, + "loss": 3.5242, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995770010148307e-05, + "loss": 3.5081, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994931415397255e-05, + "loss": 3.5182, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940944585265764e-05, + "loss": 3.504, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932558637755244e-05, + "loss": 3.5239, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924172690244723e-05, + "loss": 3.5058, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915786742734197e-05, + "loss": 3.5246, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907400795223677e-05, + "loss": 3.5227, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899047605320625e-05, + "loss": 3.5097, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890661657810105e-05, + "loss": 3.5048, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882275710299585e-05, + "loss": 3.5036, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873889762789065e-05, + "loss": 3.5037, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865503815278545e-05, + "loss": 3.5166, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857117867768025e-05, + "loss": 3.514, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.98487319202575e-05, + "loss": 3.512, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984034597274698e-05, + "loss": 3.535, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831976404040197e-05, + "loss": 3.519, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982359045652967e-05, + "loss": 3.5218, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981520450901915e-05, + "loss": 3.5142, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980681856150863e-05, + "loss": 3.5305, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979843261399811e-05, + "loss": 3.5079, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790063045291323e-05, + "loss": 3.5183, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781677097780803e-05, + "loss": 3.5199, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773291150270283e-05, + "loss": 3.5064, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9764905202759763e-05, + "loss": 3.5081, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975653563405297e-05, + "loss": 3.5081, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748149686542455e-05, + "loss": 3.5155, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739763739031935e-05, + "loss": 3.5167, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731377791521415e-05, + "loss": 3.5208, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723008222814624e-05, + "loss": 3.5144, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714622275304104e-05, + "loss": 3.5184, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706236327793584e-05, + "loss": 3.5181, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697850380283064e-05, + "loss": 3.5024, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689480811576276e-05, + "loss": 3.5114, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681094864065756e-05, + "loss": 3.5081, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672708916555236e-05, + "loss": 3.4999, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664322969044716e-05, + "loss": 3.5112, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655953400337925e-05, + "loss": 3.5219, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964756745282741e-05, + "loss": 3.5105, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963918150531689e-05, + "loss": 3.507, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963079555780637e-05, + "loss": 3.5169, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622425989099578e-05, + "loss": 3.5188, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614040041589058e-05, + "loss": 3.5129, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605654094078538e-05, + "loss": 3.4991, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597268146568018e-05, + "loss": 3.5083, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958889857786123e-05, + "loss": 3.5158, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958051263035071e-05, + "loss": 3.5088, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957212668284019e-05, + "loss": 3.5133, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956374073532967e-05, + "loss": 3.499, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955537116662288e-05, + "loss": 3.5137, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546985219112362e-05, + "loss": 3.4953, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538599271601842e-05, + "loss": 3.5226, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530213324091322e-05, + "loss": 3.5083, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952184375538453e-05, + "loss": 3.5134, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951345780787401e-05, + "loss": 3.5097, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950507186036349e-05, + "loss": 3.5075, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949668591285297e-05, + "loss": 3.5052, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488316344146184e-05, + "loss": 3.5121, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479930396635664e-05, + "loss": 3.4987, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471544449125144e-05, + "loss": 3.4919, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463158501614624e-05, + "loss": 3.5104, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454788932907833e-05, + "loss": 3.5107, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446402985397316e-05, + "loss": 3.5067, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438017037886796e-05, + "loss": 3.4926, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429631090376276e-05, + "loss": 3.5026, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421261521669485e-05, + "loss": 3.5088, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412875574158965e-05, + "loss": 3.5116, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404489626648445e-05, + "loss": 3.507, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396103679137925e-05, + "loss": 3.5122, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387734110431137e-05, + "loss": 3.5168, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379348162920617e-05, + "loss": 3.5132, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9370962215410097e-05, + "loss": 3.4988, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362576267899577e-05, + "loss": 3.5017, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354206699192786e-05, + "loss": 3.5088, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934582075168227e-05, + "loss": 3.504, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933743480417175e-05, + "loss": 3.5053, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932904885666123e-05, + "loss": 3.506, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932067928795444e-05, + "loss": 3.5235, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931229334044392e-05, + "loss": 3.4987, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.93039073929334e-05, + "loss": 3.4926, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929552144542288e-05, + "loss": 3.504, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928715187671609e-05, + "loss": 3.5101, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927876592920557e-05, + "loss": 3.5168, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927037998169505e-05, + "loss": 3.5022, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926199403418453e-05, + "loss": 3.5064, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925362446547774e-05, + "loss": 3.5105, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245238517967223e-05, + "loss": 3.5064, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236852570456703e-05, + "loss": 3.4959, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228466622946183e-05, + "loss": 3.5028, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220097054239392e-05, + "loss": 3.5107, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211711106728872e-05, + "loss": 3.5189, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203325159218352e-05, + "loss": 3.5042, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194939211707832e-05, + "loss": 3.4956, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186569643001045e-05, + "loss": 3.5034, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178183695490525e-05, + "loss": 3.5012, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169797747980005e-05, + "loss": 3.5136, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161411800469485e-05, + "loss": 3.5018, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153025852958965e-05, + "loss": 3.5015, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144656284252174e-05, + "loss": 3.4979, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136270336741657e-05, + "loss": 3.5069, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127884389231137e-05, + "loss": 3.4846, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119498441720617e-05, + "loss": 3.5033, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111128873013826e-05, + "loss": 3.5008, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102742925503306e-05, + "loss": 3.5087, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094356977992786e-05, + "loss": 3.496, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085971030482266e-05, + "loss": 3.508, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907760146177548e-05, + "loss": 3.4988, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069215514264958e-05, + "loss": 3.5033, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060829566754438e-05, + "loss": 3.5046, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052443619243918e-05, + "loss": 3.4993, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044074050537127e-05, + "loss": 3.513, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903568810302661e-05, + "loss": 3.5179, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902730215551609e-05, + "loss": 3.5043, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901891620800557e-05, + "loss": 3.5028, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901054663929878e-05, + "loss": 3.5059, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.900216069178826e-05, + "loss": 3.5032, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899377474427774e-05, + "loss": 3.4977, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898538879676722e-05, + "loss": 3.5076, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977019228060432e-05, + "loss": 3.5019, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968633280549912e-05, + "loss": 3.5038, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960247333039392e-05, + "loss": 3.4969, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951861385528872e-05, + "loss": 3.5018, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894347543801835e-05, + "loss": 3.495, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935105869311564e-05, + "loss": 3.497, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926719921801044e-05, + "loss": 3.4942, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918333974290524e-05, + "loss": 3.5127, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909948026779997e-05, + "loss": 3.517, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901578458073213e-05, + "loss": 3.5099, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893192510562693e-05, + "loss": 3.4885, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888480656305217e-05, + "loss": 3.5116, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887642061554165e-05, + "loss": 3.5033, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868051046834866e-05, + "loss": 3.4989, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859665099324346e-05, + "loss": 3.4945, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885127915181382e-05, + "loss": 3.5103, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842893204303302e-05, + "loss": 3.5045, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834523635596518e-05, + "loss": 3.5018, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826137688085998e-05, + "loss": 3.5041, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881775174057547e-05, + "loss": 3.5074, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.880936579306495e-05, + "loss": 3.5006, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800996224358167e-05, + "loss": 3.5013, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792610276847643e-05, + "loss": 3.5144, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784224329337123e-05, + "loss": 3.5029, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775838381826603e-05, + "loss": 3.5055, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876746881311982e-05, + "loss": 3.5098, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759082865609292e-05, + "loss": 3.498, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.870663642883301, + "eval_runtime": 303.1778, + "eval_samples_per_second": 1258.638, + "eval_steps_per_second": 39.333, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750696918098772e-05, + "loss": 3.4903, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742310970588256e-05, + "loss": 3.5006, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733941401881465e-05, + "loss": 3.5108, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725555454370945e-05, + "loss": 3.5074, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717169506860425e-05, + "loss": 3.5139, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708783559349905e-05, + "loss": 3.4935, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700413990643117e-05, + "loss": 3.5039, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692028043132597e-05, + "loss": 3.4911, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683642095622077e-05, + "loss": 3.5083, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675256148111557e-05, + "loss": 3.4958, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666886579404766e-05, + "loss": 3.508, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658500631894246e-05, + "loss": 3.5035, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650131063187462e-05, + "loss": 3.5004, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864174511567694e-05, + "loss": 3.4913, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863335916816642e-05, + "loss": 3.4891, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.86249732206559e-05, + "loss": 3.4917, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861658727314538e-05, + "loss": 3.5016, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860820132563486e-05, + "loss": 3.5029, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859981537812434e-05, + "loss": 3.4972, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591429430613818e-05, + "loss": 3.5194, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858305986190703e-05, + "loss": 3.5073, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857467391439651e-05, + "loss": 3.5054, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856628796688599e-05, + "loss": 3.4984, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855790201937547e-05, + "loss": 3.5183, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854953245066868e-05, + "loss": 3.4925, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541146503158163e-05, + "loss": 3.5041, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532760555647643e-05, + "loss": 3.5062, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524374608137123e-05, + "loss": 3.4996, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516005039430332e-05, + "loss": 3.4913, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507619091919812e-05, + "loss": 3.492, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499233144409292e-05, + "loss": 3.5028, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490847196898772e-05, + "loss": 3.5025, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482477628191984e-05, + "loss": 3.5051, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474091680681464e-05, + "loss": 3.5038, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465705733170944e-05, + "loss": 3.5043, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457319785660424e-05, + "loss": 3.502, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448950216953633e-05, + "loss": 3.4881, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440564269443117e-05, + "loss": 3.5019, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432178321932597e-05, + "loss": 3.4933, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423792374422077e-05, + "loss": 3.4862, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415422805715286e-05, + "loss": 3.4958, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407036858204766e-05, + "loss": 3.5078, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398650910694246e-05, + "loss": 3.497, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390264963183726e-05, + "loss": 3.4923, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381895394476938e-05, + "loss": 3.499, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373509446966418e-05, + "loss": 3.5056, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365123499455898e-05, + "loss": 3.5008, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356737551945378e-05, + "loss": 3.4922, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348367983238587e-05, + "loss": 3.4947, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.833998203572807e-05, + "loss": 3.4996, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833159608821755e-05, + "loss": 3.4952, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.832321014070703e-05, + "loss": 3.498, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831484057200024e-05, + "loss": 3.4912, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830645462448972e-05, + "loss": 3.5021, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.82980686769792e-05, + "loss": 3.4798, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.828968272946868e-05, + "loss": 3.5031, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281313160761892e-05, + "loss": 3.494, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272927213251372e-05, + "loss": 3.4943, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264541265740852e-05, + "loss": 3.5022, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825615531823033e-05, + "loss": 3.493, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824778574952354e-05, + "loss": 3.4916, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823939980201302e-05, + "loss": 3.5036, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231013854502504e-05, + "loss": 3.4814, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222627906991984e-05, + "loss": 3.4795, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214258338285193e-05, + "loss": 3.496, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8205872390774673e-05, + "loss": 3.4964, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197486443264153e-05, + "loss": 3.4941, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189100495753633e-05, + "loss": 3.4808, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180730927046845e-05, + "loss": 3.4867, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172344979536325e-05, + "loss": 3.491, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163959032025805e-05, + "loss": 3.5009, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155573084515285e-05, + "loss": 3.4924, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147203515808494e-05, + "loss": 3.5007, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138817568297974e-05, + "loss": 3.4991, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130431620787458e-05, + "loss": 3.5026, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122045673276938e-05, + "loss": 3.4832, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113676104570147e-05, + "loss": 3.4894, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105290157059627e-05, + "loss": 3.4987, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096904209549107e-05, + "loss": 3.4885, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088518262038587e-05, + "loss": 3.4945, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.80801486933318e-05, + "loss": 3.4892, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807176274582128e-05, + "loss": 3.51, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806337679831076e-05, + "loss": 3.4856, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805499085080024e-05, + "loss": 3.479, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046621282093448e-05, + "loss": 3.4893, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038235334582928e-05, + "loss": 3.4963, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802984938707241e-05, + "loss": 3.5019, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802146343956189e-05, + "loss": 3.4889, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.80130938708551e-05, + "loss": 3.4886, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800470792334458e-05, + "loss": 3.4984, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799632197583406e-05, + "loss": 3.4909, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798793602832354e-05, + "loss": 3.4854, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979550080813017e-05, + "loss": 3.4873, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971180512106233e-05, + "loss": 3.5001, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7962794564595713e-05, + "loss": 3.4999, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954408617085193e-05, + "loss": 3.4976, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946022669574666e-05, + "loss": 3.4798, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937653100867882e-05, + "loss": 3.4898, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929267153357365e-05, + "loss": 3.4901, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920881205846845e-05, + "loss": 3.4954, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912495258336318e-05, + "loss": 3.4912, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904125689629534e-05, + "loss": 3.4892, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895739742119014e-05, + "loss": 3.4835, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788735379460849e-05, + "loss": 3.4946, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787896784709797e-05, + "loss": 3.4696, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870598278391186e-05, + "loss": 3.4912, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862212330880666e-05, + "loss": 3.4864, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785382638337014e-05, + "loss": 3.4956, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784544043585962e-05, + "loss": 3.48, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7837070867152835e-05, + "loss": 3.4926, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782868491964232e-05, + "loss": 3.4849, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820298972131792e-05, + "loss": 3.492, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811913024621272e-05, + "loss": 3.4943, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803543455914488e-05, + "loss": 3.4863, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795157508403964e-05, + "loss": 3.4972, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786771560893444e-05, + "loss": 3.5053, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778385613382924e-05, + "loss": 3.49, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777001604467614e-05, + "loss": 3.4867, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761630097165613e-05, + "loss": 3.4943, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753244149655093e-05, + "loss": 3.4932, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744858202144573e-05, + "loss": 3.4779, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773648863343779e-05, + "loss": 3.4981, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728102685927266e-05, + "loss": 3.485, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719716738416746e-05, + "loss": 3.4909, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711330790906226e-05, + "loss": 3.4877, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7702961222199435e-05, + "loss": 3.4873, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694575274688918e-05, + "loss": 3.4794, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686189327178398e-05, + "loss": 3.4831, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677803379667878e-05, + "loss": 3.4826, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669433810961087e-05, + "loss": 3.4993, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661047863450567e-05, + "loss": 3.5072, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652661915940047e-05, + "loss": 3.4955, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644275968429527e-05, + "loss": 3.4773, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.763590639972274e-05, + "loss": 3.4976, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762752045221222e-05, + "loss": 3.4877, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.76191345047017e-05, + "loss": 3.4856, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761074855719118e-05, + "loss": 3.4855, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602378988484388e-05, + "loss": 3.4928, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759399304097387e-05, + "loss": 3.4874, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758560709346335e-05, + "loss": 3.4906, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757722114595283e-05, + "loss": 3.4906, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756885157724604e-05, + "loss": 3.493, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.756046562973552e-05, + "loss": 3.4914, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552079682225e-05, + "loss": 3.4831, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754369373471448e-05, + "loss": 3.4985, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535324166007693e-05, + "loss": 3.4939, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526938218497173e-05, + "loss": 3.4873, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518552270986653e-05, + "loss": 3.4987, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510166323476133e-05, + "loss": 3.4839, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8720216751098633, + "eval_runtime": 304.5775, + "eval_samples_per_second": 1252.854, + "eval_steps_per_second": 39.153, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501780375965613e-05, + "loss": 3.4782, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493394428455093e-05, + "loss": 3.4847, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485008480944573e-05, + "loss": 3.4977, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476622533434053e-05, + "loss": 3.4942, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468252964727265e-05, + "loss": 3.4987, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459867017216745e-05, + "loss": 3.4806, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451481069706225e-05, + "loss": 3.491, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443095122195705e-05, + "loss": 3.4743, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434725553488918e-05, + "loss": 3.4971, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426339605978397e-05, + "loss": 3.4808, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417953658467877e-05, + "loss": 3.4957, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409567710957357e-05, + "loss": 3.488, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401214521054296e-05, + "loss": 3.4877, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.739282857354378e-05, + "loss": 3.4766, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.738444262603326e-05, + "loss": 3.4805, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737605667852274e-05, + "loss": 3.4793, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736767073101222e-05, + "loss": 3.4875, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.73592847835017e-05, + "loss": 3.4874, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735089883599118e-05, + "loss": 3.4883, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734251288848066e-05, + "loss": 3.5017, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334143319773868e-05, + "loss": 3.4958, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732575737226335e-05, + "loss": 3.4944, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731737142475283e-05, + "loss": 3.4872, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730900185604604e-05, + "loss": 3.4985, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730061590853552e-05, + "loss": 3.483, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292229961025e-05, + "loss": 3.4921, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728384401351448e-05, + "loss": 3.4927, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7275474444807693e-05, + "loss": 3.4865, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7267088497297172e-05, + "loss": 3.4761, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258702549786652e-05, + "loss": 3.4812, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250316602276132e-05, + "loss": 3.4901, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724194703356934e-05, + "loss": 3.4912, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723356108605882e-05, + "loss": 3.495, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225175138548305e-05, + "loss": 3.4888, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216789191037785e-05, + "loss": 3.4869, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208419622330994e-05, + "loss": 3.4879, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200033674820474e-05, + "loss": 3.4763, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191647727309954e-05, + "loss": 3.4899, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183261779799434e-05, + "loss": 3.4784, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174892211092646e-05, + "loss": 3.4775, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166506263582126e-05, + "loss": 3.481, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158120316071606e-05, + "loss": 3.4975, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149734368561086e-05, + "loss": 3.4836, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141348421050566e-05, + "loss": 3.4779, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132978852343775e-05, + "loss": 3.4919, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712459290483326e-05, + "loss": 3.4886, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711620695732274e-05, + "loss": 3.492, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.710782100981222e-05, + "loss": 3.4761, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099451441105427e-05, + "loss": 3.4789, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091065493594907e-05, + "loss": 3.49, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082679546084387e-05, + "loss": 3.4814, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.70743099773776e-05, + "loss": 3.4864, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706592402986708e-05, + "loss": 3.4791, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705753808235656e-05, + "loss": 3.484, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704915213484604e-05, + "loss": 3.4719, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704078256613925e-05, + "loss": 3.4864, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703239661862873e-05, + "loss": 3.4832, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024010671118212e-05, + "loss": 3.4835, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015624723607692e-05, + "loss": 3.4908, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.70072551549009e-05, + "loss": 3.4765, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699886920739038e-05, + "loss": 3.4757, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.699048325987986e-05, + "loss": 3.4951, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.698209731236934e-05, + "loss": 3.4694, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973711364858818e-05, + "loss": 3.466, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965341796152033e-05, + "loss": 3.4801, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956955848641513e-05, + "loss": 3.4877, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948569901130987e-05, + "loss": 3.4802, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940183953620467e-05, + "loss": 3.4694, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931814384913682e-05, + "loss": 3.4748, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923428437403166e-05, + "loss": 3.4749, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691504248989264e-05, + "loss": 3.4872, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690665654238212e-05, + "loss": 3.4795, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898286973675335e-05, + "loss": 3.4881, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889901026164815e-05, + "loss": 3.4851, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688151507865429e-05, + "loss": 3.4913, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687312913114377e-05, + "loss": 3.4719, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864759562436987e-05, + "loss": 3.4756, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685637361492646e-05, + "loss": 3.4861, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684798766741594e-05, + "loss": 3.4724, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683960171990542e-05, + "loss": 3.4833, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831232151198636e-05, + "loss": 3.4759, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822846203688113e-05, + "loss": 3.4947, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814460256177593e-05, + "loss": 3.4744, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806074308667073e-05, + "loss": 3.4678, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797704739960282e-05, + "loss": 3.4762, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789318792449765e-05, + "loss": 3.4812, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780932844939245e-05, + "loss": 3.4926, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772546897428725e-05, + "loss": 3.4756, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764177328721934e-05, + "loss": 3.4788, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755791381211414e-05, + "loss": 3.4768, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747405433700894e-05, + "loss": 3.4866, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739019486190374e-05, + "loss": 3.4711, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730633538679857e-05, + "loss": 3.4722, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722263969973066e-05, + "loss": 3.4874, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713878022462546e-05, + "loss": 3.4862, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705492074952026e-05, + "loss": 3.4868, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697106127441506e-05, + "loss": 3.4694, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668873655873472e-05, + "loss": 3.4773, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.66803506112242e-05, + "loss": 3.4765, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667196466371368e-05, + "loss": 3.4829, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663595095006888e-05, + "loss": 3.4798, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655209147496368e-05, + "loss": 3.4753, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646823199985848e-05, + "loss": 3.4711, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638437252475328e-05, + "loss": 3.4821, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.663006768376854e-05, + "loss": 3.4585, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662168173625802e-05, + "loss": 3.475, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.66132957887475e-05, + "loss": 3.4714, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660490984123698e-05, + "loss": 3.4844, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659654027253019e-05, + "loss": 3.4732, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588154325019672e-05, + "loss": 3.4785, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579768377509152e-05, + "loss": 3.4736, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571382429998632e-05, + "loss": 3.4797, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656301286129184e-05, + "loss": 3.4807, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655462691378132e-05, + "loss": 3.4754, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.65462409662708e-05, + "loss": 3.4845, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653785501876028e-05, + "loss": 3.4872, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529485450053494e-05, + "loss": 3.4806, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521099502542974e-05, + "loss": 3.4761, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512713555032454e-05, + "loss": 3.4745, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504327607521934e-05, + "loss": 3.4841, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495958038815143e-05, + "loss": 3.4675, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487572091304626e-05, + "loss": 3.4826, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479186143794106e-05, + "loss": 3.4726, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470800196283586e-05, + "loss": 3.478, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462430627576795e-05, + "loss": 3.4781, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454044680066275e-05, + "loss": 3.4769, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445658732555755e-05, + "loss": 3.4636, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437272785045235e-05, + "loss": 3.4725, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428903216338447e-05, + "loss": 3.4742, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420517268827927e-05, + "loss": 3.478, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412131321317407e-05, + "loss": 3.4912, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403745373806887e-05, + "loss": 3.4879, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395375805100096e-05, + "loss": 3.4595, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6386989857589576e-05, + "loss": 3.4866, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637860391007906e-05, + "loss": 3.4756, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.637021796256854e-05, + "loss": 3.4746, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636184839386175e-05, + "loss": 3.465, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.635346244635123e-05, + "loss": 3.4838, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.634507649884071e-05, + "loss": 3.4745, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633669055133019e-05, + "loss": 3.4773, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632830460381967e-05, + "loss": 3.4797, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.631993503511288e-05, + "loss": 3.4802, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.631154908760236e-05, + "loss": 3.4793, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630316314009184e-05, + "loss": 3.474, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629477719258132e-05, + "loss": 3.4827, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628640762387453e-05, + "loss": 3.4824, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278021676364013e-05, + "loss": 3.4746, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269635728853493e-05, + "loss": 3.4873, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261249781342973e-05, + "loss": 3.4693, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8749518394470215, + "eval_runtime": 304.6786, + "eval_samples_per_second": 1252.438, + "eval_steps_per_second": 39.14, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252880212636182e-05, + "loss": 3.4685, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244494265125662e-05, + "loss": 3.4726, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236108317615142e-05, + "loss": 3.4852, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227722370104622e-05, + "loss": 3.4778, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219352801397835e-05, + "loss": 3.4936, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6210966853887315e-05, + "loss": 3.4666, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202580906376795e-05, + "loss": 3.4781, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194194958866275e-05, + "loss": 3.4592, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185825390159484e-05, + "loss": 3.4868, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177439442648967e-05, + "loss": 3.4705, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169053495138447e-05, + "loss": 3.4812, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160667547627927e-05, + "loss": 3.4768, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152297978921136e-05, + "loss": 3.4701, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143912031410616e-05, + "loss": 3.4685, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135526083900096e-05, + "loss": 3.4672, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127140136389576e-05, + "loss": 3.4661, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611875418887906e-05, + "loss": 3.4781, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.611036824136854e-05, + "loss": 3.4728, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101982293858012e-05, + "loss": 3.4759, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093596346347492e-05, + "loss": 3.4886, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085226777640708e-05, + "loss": 3.4858, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076840830130188e-05, + "loss": 3.4791, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068454882619665e-05, + "loss": 3.4793, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060068935109145e-05, + "loss": 3.4854, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605169936640236e-05, + "loss": 3.4711, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043313418891834e-05, + "loss": 3.4844, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6034927471381314e-05, + "loss": 3.4772, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026541523870797e-05, + "loss": 3.4732, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018171955164013e-05, + "loss": 3.4644, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009786007653486e-05, + "loss": 3.47, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001400060142966e-05, + "loss": 3.4747, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993014112632446e-05, + "loss": 3.4801, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984644543925662e-05, + "loss": 3.482, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597625859641514e-05, + "loss": 3.4769, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596787264890462e-05, + "loss": 3.4773, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.59594867013941e-05, + "loss": 3.4767, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951117132687307e-05, + "loss": 3.4628, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5942731185176787e-05, + "loss": 3.4734, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934345237666267e-05, + "loss": 3.4647, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592595929015575e-05, + "loss": 3.4685, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591758972144896e-05, + "loss": 3.469, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590920377393844e-05, + "loss": 3.4799, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590081782642792e-05, + "loss": 3.477, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.58924318789174e-05, + "loss": 3.462, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884062310210612e-05, + "loss": 3.4798, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875676362700092e-05, + "loss": 3.4816, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867290415189572e-05, + "loss": 3.4763, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858904467679052e-05, + "loss": 3.4695, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.585053489897226e-05, + "loss": 3.4598, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.584214895146174e-05, + "loss": 3.48, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583376300395122e-05, + "loss": 3.468, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825377056440704e-05, + "loss": 3.4722, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817007487733913e-05, + "loss": 3.4679, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808621540223393e-05, + "loss": 3.4694, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800235592712873e-05, + "loss": 3.4626, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791849645202353e-05, + "loss": 3.4716, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783480076495566e-05, + "loss": 3.473, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775094128985046e-05, + "loss": 3.472, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766708181474526e-05, + "loss": 3.4735, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758322233964006e-05, + "loss": 3.4624, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5749952665257215e-05, + "loss": 3.4659, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741566717746695e-05, + "loss": 3.4852, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733180770236175e-05, + "loss": 3.4583, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724794822725658e-05, + "loss": 3.4525, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716425254018867e-05, + "loss": 3.4669, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708039306508347e-05, + "loss": 3.4753, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5699653358997827e-05, + "loss": 3.4663, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5691267411487307e-05, + "loss": 3.4604, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568289784278052e-05, + "loss": 3.4607, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567451189527e-05, + "loss": 3.4612, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566612594775948e-05, + "loss": 3.4778, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565774000024896e-05, + "loss": 3.4681, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564937043154217e-05, + "loss": 3.4721, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564098448403165e-05, + "loss": 3.477, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563259853652113e-05, + "loss": 3.4794, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624212589010608e-05, + "loss": 3.4605, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561584302030382e-05, + "loss": 3.4652, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.56074570727933e-05, + "loss": 3.4737, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.559907112528278e-05, + "loss": 3.4563, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559068517777226e-05, + "loss": 3.4732, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558231560906547e-05, + "loss": 3.462, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573929661554953e-05, + "loss": 3.4832, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565543714044433e-05, + "loss": 3.4627, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557157766533913e-05, + "loss": 3.4564, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548788197827122e-05, + "loss": 3.4597, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540402250316602e-05, + "loss": 3.4694, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532016302806082e-05, + "loss": 3.4818, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523630355295562e-05, + "loss": 3.4671, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515260786588774e-05, + "loss": 3.4653, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5506874839078254e-05, + "loss": 3.462, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498488891567734e-05, + "loss": 3.4746, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490102944057214e-05, + "loss": 3.4609, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481716996546694e-05, + "loss": 3.4623, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473347427839907e-05, + "loss": 3.4735, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464961480329387e-05, + "loss": 3.476, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456575532818867e-05, + "loss": 3.4747, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448189585308347e-05, + "loss": 3.4544, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439820016601556e-05, + "loss": 3.4665, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431434069091036e-05, + "loss": 3.4639, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423048121580516e-05, + "loss": 3.4711, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541466217407e-05, + "loss": 3.4686, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406292605363208e-05, + "loss": 3.4638, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397906657852688e-05, + "loss": 3.4606, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389520710342168e-05, + "loss": 3.4697, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381151141635377e-05, + "loss": 3.4502, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537276519412486e-05, + "loss": 3.4643, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536437924661434e-05, + "loss": 3.4576, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.535599329910382e-05, + "loss": 3.4738, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534762373039703e-05, + "loss": 3.4605, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.533923778288651e-05, + "loss": 3.4654, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533085183537599e-05, + "loss": 3.4596, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532246588786547e-05, + "loss": 3.4703, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314096319158682e-05, + "loss": 3.4705, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305710371648162e-05, + "loss": 3.4612, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297324424137642e-05, + "loss": 3.47, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528893847662712e-05, + "loss": 3.4762, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.52805525291166e-05, + "loss": 3.4673, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272182960409814e-05, + "loss": 3.4704, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.5263797012899294e-05, + "loss": 3.458, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255411065388774e-05, + "loss": 3.473, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247025117878254e-05, + "loss": 3.4616, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238655549171463e-05, + "loss": 3.4672, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230269601660943e-05, + "loss": 3.4613, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221883654150423e-05, + "loss": 3.4665, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213514085443635e-05, + "loss": 3.4648, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205128137933115e-05, + "loss": 3.4621, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196742190422595e-05, + "loss": 3.4528, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188356242912075e-05, + "loss": 3.4592, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179986674205284e-05, + "loss": 3.4635, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171600726694768e-05, + "loss": 3.4645, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163214779184248e-05, + "loss": 3.4778, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154828831673728e-05, + "loss": 3.4773, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146459262966937e-05, + "loss": 3.4492, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138073315456417e-05, + "loss": 3.4759, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129687367945897e-05, + "loss": 3.4612, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121301420435377e-05, + "loss": 3.4634, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.511291547292486e-05, + "loss": 3.4561, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.510454590421807e-05, + "loss": 3.4692, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509615995670755e-05, + "loss": 3.4601, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508777400919703e-05, + "loss": 3.4697, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507938806168651e-05, + "loss": 3.4643, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507101849297972e-05, + "loss": 3.4648, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.50626325454692e-05, + "loss": 3.4693, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505424659795868e-05, + "loss": 3.459, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504586065044816e-05, + "loss": 3.4682, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503749108174137e-05, + "loss": 3.4739, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502910513423085e-05, + "loss": 3.462, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502071918672033e-05, + "loss": 3.4685, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012333239209807e-05, + "loss": 3.4632, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8760595321655273, + "eval_runtime": 302.6752, + "eval_samples_per_second": 1260.728, + "eval_steps_per_second": 39.399, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003947291699287e-05, + "loss": 3.452, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499556134418877e-05, + "loss": 3.4597, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498717539667825e-05, + "loss": 3.468, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978789449167727e-05, + "loss": 3.4697, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497041988046094e-05, + "loss": 3.4819, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962033932950423e-05, + "loss": 3.4539, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.49536479854399e-05, + "loss": 3.4642, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494526203792938e-05, + "loss": 3.4517, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493689246922259e-05, + "loss": 3.4711, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492850652171207e-05, + "loss": 3.46, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492012057420155e-05, + "loss": 3.4655, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491173462669103e-05, + "loss": 3.4707, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903381436787973e-05, + "loss": 3.4533, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894995489277453e-05, + "loss": 3.4632, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886609541766933e-05, + "loss": 3.4556, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878223594256413e-05, + "loss": 3.4535, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869837646745893e-05, + "loss": 3.4603, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861451699235373e-05, + "loss": 3.4645, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853065751724853e-05, + "loss": 3.4615, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844679804214333e-05, + "loss": 3.4764, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836310235507545e-05, + "loss": 3.473, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4827924287997022e-05, + "loss": 3.4689, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819538340486502e-05, + "loss": 3.4685, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811152392975985e-05, + "loss": 3.4724, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802782824269194e-05, + "loss": 3.4558, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794396876758674e-05, + "loss": 3.4709, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786010929248154e-05, + "loss": 3.4683, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777624981737634e-05, + "loss": 3.4586, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769255413030847e-05, + "loss": 3.4544, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760869465520326e-05, + "loss": 3.4577, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752483518009806e-05, + "loss": 3.4633, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744097570499286e-05, + "loss": 3.4666, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735728001792495e-05, + "loss": 3.4714, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727342054281975e-05, + "loss": 3.4649, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4718956106771455e-05, + "loss": 3.4679, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710586538064668e-05, + "loss": 3.466, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702200590554148e-05, + "loss": 3.4477, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693814643043628e-05, + "loss": 3.4658, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685428695533108e-05, + "loss": 3.4517, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677042748022588e-05, + "loss": 3.4543, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.46686731793158e-05, + "loss": 3.4559, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466028723180528e-05, + "loss": 3.4726, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465190128429476e-05, + "loss": 3.4629, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464351533678424e-05, + "loss": 3.4502, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463514576807745e-05, + "loss": 3.4702, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462675982056693e-05, + "loss": 3.4663, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461837387305641e-05, + "loss": 3.4625, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609987925545892e-05, + "loss": 3.4584, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.46016183568391e-05, + "loss": 3.4479, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459323240932858e-05, + "loss": 3.4691, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458484646181806e-05, + "loss": 3.4551, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457646051430754e-05, + "loss": 3.4625, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568090945600754e-05, + "loss": 3.4573, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559704998090234e-05, + "loss": 3.4517, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551319050579714e-05, + "loss": 3.4526, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542933103069194e-05, + "loss": 3.459, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534563534362403e-05, + "loss": 3.4608, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526177586851883e-05, + "loss": 3.4576, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517791639341363e-05, + "loss": 3.4647, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509405691830846e-05, + "loss": 3.4509, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501036123124055e-05, + "loss": 3.4517, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492650175613535e-05, + "loss": 3.475, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484264228103015e-05, + "loss": 3.4441, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475894659396224e-05, + "loss": 3.4405, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467508711885708e-05, + "loss": 3.4537, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459122764375187e-05, + "loss": 3.4653, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450736816864667e-05, + "loss": 3.4487, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442367248157877e-05, + "loss": 3.4542, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4433981300647356e-05, + "loss": 3.4474, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425595353136836e-05, + "loss": 3.449, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417209405626316e-05, + "loss": 3.4614, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440883983691953e-05, + "loss": 3.4577, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440045388940901e-05, + "loss": 3.457, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439206794189849e-05, + "loss": 3.4637, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438368199438797e-05, + "loss": 3.466, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375312425681178e-05, + "loss": 3.4539, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436692647817066e-05, + "loss": 3.4536, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435854053066014e-05, + "loss": 3.4635, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435015458314962e-05, + "loss": 3.441, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434178501444283e-05, + "loss": 3.4601, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433339906693231e-05, + "loss": 3.4509, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432501311942179e-05, + "loss": 3.4716, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.431662717191127e-05, + "loss": 3.4539, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308257603204483e-05, + "loss": 3.4465, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299871655693962e-05, + "loss": 3.4409, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291485708183442e-05, + "loss": 3.4613, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428309976067292e-05, + "loss": 3.4648, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.427473019196613e-05, + "loss": 3.4592, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266344244455615e-05, + "loss": 3.4502, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257958296945095e-05, + "loss": 3.4531, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424957234943457e-05, + "loss": 3.4621, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241202780727784e-05, + "loss": 3.4477, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232816833217264e-05, + "loss": 3.4492, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422443088570674e-05, + "loss": 3.4631, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216044938196224e-05, + "loss": 3.4605, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207675369489436e-05, + "loss": 3.4636, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199289421978916e-05, + "loss": 3.4452, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190903474468393e-05, + "loss": 3.4555, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182517526957873e-05, + "loss": 3.448, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174147958251085e-05, + "loss": 3.4586, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165762010740565e-05, + "loss": 3.4542, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157376063230045e-05, + "loss": 3.4557, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148990115719525e-05, + "loss": 3.4492, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140620547012738e-05, + "loss": 3.4518, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132234599502214e-05, + "loss": 3.4466, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4123848651991694e-05, + "loss": 3.4489, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115462704481177e-05, + "loss": 3.4441, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410709313577439e-05, + "loss": 3.4619, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098707188263866e-05, + "loss": 3.4504, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090321240753346e-05, + "loss": 3.4493, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4081935293242826e-05, + "loss": 3.4482, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407356572453604e-05, + "loss": 3.4611, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406517977702552e-05, + "loss": 3.4546, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056793829515e-05, + "loss": 3.4497, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404840788200448e-05, + "loss": 3.4584, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040038313297688e-05, + "loss": 3.4642, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031652365787168e-05, + "loss": 3.4552, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023266418276648e-05, + "loss": 3.4586, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401488047076613e-05, + "loss": 3.447, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400651090205934e-05, + "loss": 3.4576, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399812495454882e-05, + "loss": 3.4521, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.39897390070383e-05, + "loss": 3.4595, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398135305952778e-05, + "loss": 3.4447, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972983490820993e-05, + "loss": 3.4558, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964597543310472e-05, + "loss": 3.4543, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956211595799952e-05, + "loss": 3.4515, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947825648289432e-05, + "loss": 3.4449, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393945607958264e-05, + "loss": 3.4478, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.393107013207212e-05, + "loss": 3.45, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.39226841845616e-05, + "loss": 3.4582, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914298237051085e-05, + "loss": 3.4604, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905928668344294e-05, + "loss": 3.4668, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897542720833774e-05, + "loss": 3.4374, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889156773323254e-05, + "loss": 3.4625, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880770825812734e-05, + "loss": 3.454, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872401257105946e-05, + "loss": 3.4472, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864015309595426e-05, + "loss": 3.446, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855629362084906e-05, + "loss": 3.4609, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847243414574386e-05, + "loss": 3.451, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838873845867595e-05, + "loss": 3.4578, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830487898357075e-05, + "loss": 3.45, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822101950846555e-05, + "loss": 3.4549, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381371600333604e-05, + "loss": 3.4587, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.3805346434629247e-05, + "loss": 3.4502, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796976865922457e-05, + "loss": 3.4546, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788590918411937e-05, + "loss": 3.4648, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780204970901416e-05, + "loss": 3.4512, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.37718190233909e-05, + "loss": 3.4542, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376343307588038e-05, + "loss": 3.4533, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.878366708755493, + "eval_runtime": 304.6595, + "eval_samples_per_second": 1252.516, + "eval_steps_per_second": 39.142, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375504712836986e-05, + "loss": 3.4455, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374666118085934e-05, + "loss": 3.446, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738275233348816e-05, + "loss": 3.4545, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.372990566464203e-05, + "loss": 3.4594, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372151971713151e-05, + "loss": 3.4652, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713133769620992e-05, + "loss": 3.447, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370474782211047e-05, + "loss": 3.4509, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.369637825340368e-05, + "loss": 3.4412, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368799230589316e-05, + "loss": 3.455, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679606358382638e-05, + "loss": 3.4486, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671220410872118e-05, + "loss": 3.452, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662850842165333e-05, + "loss": 3.4546, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654481273458543e-05, + "loss": 3.4465, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646095325948023e-05, + "loss": 3.4485, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637709378437502e-05, + "loss": 3.4448, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629323430926982e-05, + "loss": 3.441, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620937483416462e-05, + "loss": 3.4459, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612551535905942e-05, + "loss": 3.4531, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604165588395422e-05, + "loss": 3.4491, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595779640884902e-05, + "loss": 3.4643, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358741007217811e-05, + "loss": 3.4613, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357902412466759e-05, + "loss": 3.4581, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.357063817715707e-05, + "loss": 3.4559, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562252229646555e-05, + "loss": 3.4601, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553882660939764e-05, + "loss": 3.4477, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545496713429244e-05, + "loss": 3.46, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537110765918724e-05, + "loss": 3.4534, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528724818408204e-05, + "loss": 3.4448, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520355249701416e-05, + "loss": 3.4422, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511969302190896e-05, + "loss": 3.449, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503583354680376e-05, + "loss": 3.4528, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495197407169856e-05, + "loss": 3.4521, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486827838463065e-05, + "loss": 3.4607, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478441890952545e-05, + "loss": 3.454, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470055943442025e-05, + "loss": 3.4531, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461669995931508e-05, + "loss": 3.4535, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453300427224717e-05, + "loss": 3.4417, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444914479714197e-05, + "loss": 3.4486, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436528532203677e-05, + "loss": 3.4401, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428142584693157e-05, + "loss": 3.443, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341977301598637e-05, + "loss": 3.4433, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341138706847585e-05, + "loss": 3.4614, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340300112096533e-05, + "loss": 3.4531, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339461517345481e-05, + "loss": 3.4399, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338624560474802e-05, + "loss": 3.4619, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.33778596572375e-05, + "loss": 3.4502, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336947370972698e-05, + "loss": 3.4558, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361087762216462e-05, + "loss": 3.4453, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.335271819350967e-05, + "loss": 3.4349, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.334433224599915e-05, + "loss": 3.4575, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333594629848863e-05, + "loss": 3.4458, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332756035097811e-05, + "loss": 3.4536, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319190782271323e-05, + "loss": 3.4418, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310804834760803e-05, + "loss": 3.4447, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302435266054012e-05, + "loss": 3.4399, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294049318543492e-05, + "loss": 3.4464, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285663371032972e-05, + "loss": 3.4518, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277277423522452e-05, + "loss": 3.4424, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268891476011932e-05, + "loss": 3.4549, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260505528501416e-05, + "loss": 3.4404, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252119580990892e-05, + "loss": 3.4373, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243733633480372e-05, + "loss": 3.4651, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235364064773585e-05, + "loss": 3.4328, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322697811726306e-05, + "loss": 3.4245, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321859216975254e-05, + "loss": 3.4431, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210206222242024e-05, + "loss": 3.4556, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201836653535237e-05, + "loss": 3.4342, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193450706024714e-05, + "loss": 3.4446, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185064758514193e-05, + "loss": 3.4338, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176678811003673e-05, + "loss": 3.4374, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168309242296886e-05, + "loss": 3.4514, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159923294786366e-05, + "loss": 3.4474, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3151537347275846e-05, + "loss": 3.4496, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143151399765326e-05, + "loss": 3.4461, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134781831058535e-05, + "loss": 3.4565, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126395883548015e-05, + "loss": 3.4382, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.3118009936037495e-05, + "loss": 3.4456, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109623988526978e-05, + "loss": 3.4474, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101254419820187e-05, + "loss": 3.4321, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092868472309667e-05, + "loss": 3.4478, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084482524799147e-05, + "loss": 3.4444, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076096577288627e-05, + "loss": 3.455, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.306772700858184e-05, + "loss": 3.4454, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305934106107132e-05, + "loss": 3.4348, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.30509551135608e-05, + "loss": 3.4301, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304256916605028e-05, + "loss": 3.4471, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303419959734349e-05, + "loss": 3.4525, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.302581364983297e-05, + "loss": 3.4442, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301742770232245e-05, + "loss": 3.4452, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009041754811932e-05, + "loss": 3.4407, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.300067218610514e-05, + "loss": 3.4459, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299228623859462e-05, + "loss": 3.4408, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.29839002910841e-05, + "loss": 3.4343, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297551434357358e-05, + "loss": 3.4513, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967144774866793e-05, + "loss": 3.4491, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958758827356273e-05, + "loss": 3.4489, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950372879845753e-05, + "loss": 3.4336, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942003311138962e-05, + "loss": 3.4458, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933617363628442e-05, + "loss": 3.4338, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925231416117922e-05, + "loss": 3.4484, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916845468607402e-05, + "loss": 3.4423, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908475899900615e-05, + "loss": 3.4436, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900089952390095e-05, + "loss": 3.4376, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891704004879575e-05, + "loss": 3.4359, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883318057369054e-05, + "loss": 3.4399, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874948488662264e-05, + "loss": 3.4349, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866562541151747e-05, + "loss": 3.4349, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858176593641227e-05, + "loss": 3.4481, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849790646130707e-05, + "loss": 3.4421, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841421077423916e-05, + "loss": 3.4382, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833035129913396e-05, + "loss": 3.4347, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824649182402876e-05, + "loss": 3.4459, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816263234892356e-05, + "loss": 3.446, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.2807893666185568e-05, + "loss": 3.4393, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2799507718675048e-05, + "loss": 3.447, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791121771164528e-05, + "loss": 3.4531, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782735823654008e-05, + "loss": 3.4464, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774366254947217e-05, + "loss": 3.4425, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.27659803074367e-05, + "loss": 3.4374, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275759435992618e-05, + "loss": 3.4452, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274920841241566e-05, + "loss": 3.4415, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274083884370887e-05, + "loss": 3.4468, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.273245289619835e-05, + "loss": 3.4342, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272406694868783e-05, + "loss": 3.443, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271568100117731e-05, + "loss": 3.4437, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707311432470522e-05, + "loss": 3.4408, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698925484960002e-05, + "loss": 3.4297, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690539537449482e-05, + "loss": 3.4395, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.268215358993896e-05, + "loss": 3.4377, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.267378402123217e-05, + "loss": 3.4445, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665398073721654e-05, + "loss": 3.4473, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657012126211134e-05, + "loss": 3.4566, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264862617870061e-05, + "loss": 3.4277, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640256609993823e-05, + "loss": 3.4521, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631870662483303e-05, + "loss": 3.4425, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623484714972783e-05, + "loss": 3.4382, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615098767462263e-05, + "loss": 3.4315, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606729198755476e-05, + "loss": 3.4488, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598343251244956e-05, + "loss": 3.4355, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589957303734432e-05, + "loss": 3.4489, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2581571356223912e-05, + "loss": 3.4374, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573201787517125e-05, + "loss": 3.4451, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564815840006605e-05, + "loss": 3.4434, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556429892496084e-05, + "loss": 3.4398, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548060323789297e-05, + "loss": 3.4475, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539674376278777e-05, + "loss": 3.4437, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531288428768257e-05, + "loss": 3.4465, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522902481257733e-05, + "loss": 3.4363, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514516533747217e-05, + "loss": 3.4476, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.879415988922119, + "eval_runtime": 305.2683, + "eval_samples_per_second": 1250.018, + "eval_steps_per_second": 39.064, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506130586236697e-05, + "loss": 3.4387, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497744638726177e-05, + "loss": 3.4328, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489358691215657e-05, + "loss": 3.4393, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2480972743705137e-05, + "loss": 3.4509, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472603174998346e-05, + "loss": 3.455, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464217227487826e-05, + "loss": 3.4352, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245583127997731e-05, + "loss": 3.4395, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244744533246679e-05, + "loss": 3.4299, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439075763759998e-05, + "loss": 3.4465, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430689816249478e-05, + "loss": 3.4367, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422303868738958e-05, + "loss": 3.446, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413917921228438e-05, + "loss": 3.4413, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240556473132538e-05, + "loss": 3.4349, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239717878381486e-05, + "loss": 3.4418, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238879283630434e-05, + "loss": 3.4278, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238040688879382e-05, + "loss": 3.4292, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.23720209412833e-05, + "loss": 3.4342, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236363499377278e-05, + "loss": 3.4466, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355249046262263e-05, + "loss": 3.4378, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234686309875174e-05, + "loss": 3.4559, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338493530044952e-05, + "loss": 3.4478, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233010758253443e-05, + "loss": 3.4487, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232172163502391e-05, + "loss": 3.446, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313335687513388e-05, + "loss": 3.4465, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304966118806604e-05, + "loss": 3.4344, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296580171296084e-05, + "loss": 3.4526, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228819422378556e-05, + "loss": 3.4396, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227980827627504e-05, + "loss": 3.4332, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271438707568253e-05, + "loss": 3.4341, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263052760057733e-05, + "loss": 3.4369, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254666812547213e-05, + "loss": 3.4386, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246280865036693e-05, + "loss": 3.4444, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237911296329905e-05, + "loss": 3.4457, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229525348819382e-05, + "loss": 3.4468, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221139401308862e-05, + "loss": 3.4345, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212753453798342e-05, + "loss": 3.4429, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204383885091558e-05, + "loss": 3.4347, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2195997937581034e-05, + "loss": 3.4324, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187611990070514e-05, + "loss": 3.4282, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179226042559994e-05, + "loss": 3.4321, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170856473853207e-05, + "loss": 3.4323, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216248690514642e-05, + "loss": 3.4507, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.21541009576359e-05, + "loss": 3.4421, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214571501012538e-05, + "loss": 3.4279, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137329062614856e-05, + "loss": 3.4485, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128943115104336e-05, + "loss": 3.4381, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120557167593816e-05, + "loss": 3.4443, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112171220083296e-05, + "loss": 3.4337, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103801651376508e-05, + "loss": 3.4194, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095415703865988e-05, + "loss": 3.451, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087029756355468e-05, + "loss": 3.4298, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078643808844948e-05, + "loss": 3.4436, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070257861334428e-05, + "loss": 3.433, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061871913823908e-05, + "loss": 3.4352, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.205350234511712e-05, + "loss": 3.4233, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.20451163976066e-05, + "loss": 3.4347, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203673045009608e-05, + "loss": 3.4457, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202834450258556e-05, + "loss": 3.4301, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019958555075037e-05, + "loss": 3.4431, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011572607564517e-05, + "loss": 3.434, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003186660053997e-05, + "loss": 3.4265, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199480071254348e-05, + "loss": 3.4494, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198643114383669e-05, + "loss": 3.4235, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197804519632617e-05, + "loss": 3.4156, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196965924881565e-05, + "loss": 3.4363, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196127330130513e-05, + "loss": 3.4422, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.195290373259834e-05, + "loss": 3.4213, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.194451778508782e-05, + "loss": 3.4364, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.19361318375773e-05, + "loss": 3.4206, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192774589006678e-05, + "loss": 3.4315, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.191937632135999e-05, + "loss": 3.4392, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191099037384947e-05, + "loss": 3.4337, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190260442633895e-05, + "loss": 3.4383, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894218478828434e-05, + "loss": 3.4334, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885848910121643e-05, + "loss": 3.4462, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877462962611123e-05, + "loss": 3.4258, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869077015100603e-05, + "loss": 3.4386, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860691067590083e-05, + "loss": 3.4306, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852321498883295e-05, + "loss": 3.4229, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843935551372775e-05, + "loss": 3.4359, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835565982665984e-05, + "loss": 3.4335, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827180035155464e-05, + "loss": 3.4438, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818794087644944e-05, + "loss": 3.4383, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810408140134424e-05, + "loss": 3.4191, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802022192623904e-05, + "loss": 3.419, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793636245113387e-05, + "loss": 3.4389, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785250297602867e-05, + "loss": 3.4436, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776864350092344e-05, + "loss": 3.4363, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768494781385556e-05, + "loss": 3.4256, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760108833875036e-05, + "loss": 3.4344, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751722886364516e-05, + "loss": 3.4334, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743336938853996e-05, + "loss": 3.4311, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173496737014721e-05, + "loss": 3.4231, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172658142263669e-05, + "loss": 3.4387, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718195475126165e-05, + "loss": 3.4373, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709809527615645e-05, + "loss": 3.4381, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701439958908858e-05, + "loss": 3.4242, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169305401139834e-05, + "loss": 3.4301, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684668063887818e-05, + "loss": 3.4284, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676282116377298e-05, + "loss": 3.4357, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166791254767051e-05, + "loss": 3.4282, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165952660015999e-05, + "loss": 3.4328, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651140652649467e-05, + "loss": 3.4293, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164275470513895e-05, + "loss": 3.4226, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634385136432162e-05, + "loss": 3.4248, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162599918892164e-05, + "loss": 3.4215, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161761324141112e-05, + "loss": 3.4266, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.16092272939006e-05, + "loss": 3.4302, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.160085772519381e-05, + "loss": 3.4369, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.159247177768329e-05, + "loss": 3.4223, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.158408583017277e-05, + "loss": 3.4288, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575716261465984e-05, + "loss": 3.4297, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156733031395546e-05, + "loss": 3.4366, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155894436644494e-05, + "loss": 3.4273, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155055841893442e-05, + "loss": 3.4381, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542188850227636e-05, + "loss": 3.439, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533802902717113e-05, + "loss": 3.437, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525416955206593e-05, + "loss": 3.4322, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517031007696073e-05, + "loss": 3.4309, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508661438989285e-05, + "loss": 3.4307, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500275491478765e-05, + "loss": 3.4323, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491889543968245e-05, + "loss": 3.4283, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483503596457725e-05, + "loss": 3.4276, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475134027750934e-05, + "loss": 3.4346, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466748080240414e-05, + "loss": 3.4333, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458362132729894e-05, + "loss": 3.429, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1449976185219374e-05, + "loss": 3.4193, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441606616512586e-05, + "loss": 3.4255, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433220669002066e-05, + "loss": 3.4257, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424834721491546e-05, + "loss": 3.4348, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416448773981026e-05, + "loss": 3.439, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408079205274235e-05, + "loss": 3.4443, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139969325776372e-05, + "loss": 3.4166, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.13913073102532e-05, + "loss": 3.4385, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138292136274268e-05, + "loss": 3.4298, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374551794035888e-05, + "loss": 3.4304, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366165846525368e-05, + "loss": 3.4204, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357779899014848e-05, + "loss": 3.4355, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349393951504328e-05, + "loss": 3.4219, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134102438279754e-05, + "loss": 3.4421, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133263843528702e-05, + "loss": 3.4221, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.13242524877765e-05, + "loss": 3.4327, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131586654026598e-05, + "loss": 3.4338, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130749697155919e-05, + "loss": 3.4327, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299127402852405e-05, + "loss": 3.4354, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.129074145534188e-05, + "loss": 3.4329, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.128235550783136e-05, + "loss": 3.4341, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127396956032084e-05, + "loss": 3.4242, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126558361281032e-05, + "loss": 3.4382, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8806588649749756, + "eval_runtime": 301.1921, + "eval_samples_per_second": 1266.936, + "eval_steps_per_second": 39.593, + "step": 1755360 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.1840456754393846e+18, + "trial_name": null, + "trial_params": null +}