| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 953, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.496503496503497e-06, | |
| "loss": 5.6988, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.993006993006994e-06, | |
| "loss": 5.6631, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.048951048951049e-05, | |
| "loss": 5.7268, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.3986013986013988e-05, | |
| "loss": 5.2938, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.7482517482517483e-05, | |
| "loss": 5.0975, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.097902097902098e-05, | |
| "loss": 4.8578, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.4475524475524478e-05, | |
| "loss": 4.3282, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.7972027972027976e-05, | |
| "loss": 4.0068, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.146853146853147e-05, | |
| "loss": 3.7421, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.4965034965034965e-05, | |
| "loss": 3.2654, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 3.0331, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.195804195804196e-05, | |
| "loss": 2.8466, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.545454545454546e-05, | |
| "loss": 2.6892, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.8951048951048956e-05, | |
| "loss": 2.7062, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.972762645914397e-05, | |
| "loss": 2.6551, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.933852140077821e-05, | |
| "loss": 2.6632, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.894941634241245e-05, | |
| "loss": 2.7111, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.856031128404669e-05, | |
| "loss": 2.6711, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.817120622568094e-05, | |
| "loss": 2.562, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.778210116731518e-05, | |
| "loss": 2.543, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.739299610894942e-05, | |
| "loss": 2.5899, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.700389105058366e-05, | |
| "loss": 2.5576, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.66147859922179e-05, | |
| "loss": 2.5863, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.622568093385214e-05, | |
| "loss": 2.4993, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.583657587548638e-05, | |
| "loss": 2.5329, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.544747081712062e-05, | |
| "loss": 2.5328, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.505836575875487e-05, | |
| "loss": 2.5523, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.466926070038911e-05, | |
| "loss": 2.6414, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.428015564202335e-05, | |
| "loss": 2.5356, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.389105058365759e-05, | |
| "loss": 2.5604, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3501945525291833e-05, | |
| "loss": 2.5026, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.311284046692607e-05, | |
| "loss": 2.5861, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.272373540856031e-05, | |
| "loss": 2.6518, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.233463035019455e-05, | |
| "loss": 2.4669, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.19455252918288e-05, | |
| "loss": 2.4614, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.155642023346304e-05, | |
| "loss": 2.5185, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.116731517509728e-05, | |
| "loss": 2.5792, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.077821011673152e-05, | |
| "loss": 2.4151, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.0389105058365764e-05, | |
| "loss": 2.5522, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5522, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 3.961089494163424e-05, | |
| "loss": 2.4389, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.922178988326848e-05, | |
| "loss": 2.3915, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.883268482490273e-05, | |
| "loss": 2.4208, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.844357976653697e-05, | |
| "loss": 2.4861, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.805447470817121e-05, | |
| "loss": 2.4987, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.766536964980545e-05, | |
| "loss": 2.5472, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.7276264591439694e-05, | |
| "loss": 2.5182, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5792096979068868, | |
| "eval_loss": 2.443359375, | |
| "eval_runtime": 25.0491, | |
| "eval_samples_per_second": 76.09, | |
| "eval_steps_per_second": 9.541, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.6887159533073934e-05, | |
| "loss": 2.3115, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.649805447470817e-05, | |
| "loss": 2.3429, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.610894941634241e-05, | |
| "loss": 2.4361, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.571984435797666e-05, | |
| "loss": 2.4135, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.53307392996109e-05, | |
| "loss": 2.3602, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.494163424124514e-05, | |
| "loss": 2.4515, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.455252918287938e-05, | |
| "loss": 2.4394, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.4163424124513624e-05, | |
| "loss": 2.4532, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.3774319066147864e-05, | |
| "loss": 2.4665, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.3385214007782103e-05, | |
| "loss": 2.3228, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.299610894941634e-05, | |
| "loss": 2.3944, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.260700389105058e-05, | |
| "loss": 2.4102, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.221789883268483e-05, | |
| "loss": 2.4339, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.182879377431907e-05, | |
| "loss": 2.3893, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.143968871595331e-05, | |
| "loss": 2.3751, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.105058365758755e-05, | |
| "loss": 2.3861, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.0661478599221794e-05, | |
| "loss": 2.4282, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.027237354085603e-05, | |
| "loss": 2.3462, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9883268482490273e-05, | |
| "loss": 2.3599, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9494163424124516e-05, | |
| "loss": 2.4088, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.910505836575876e-05, | |
| "loss": 2.3874, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.8715953307392995e-05, | |
| "loss": 2.484, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.832684824902724e-05, | |
| "loss": 2.3859, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.793774319066148e-05, | |
| "loss": 2.3496, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7548638132295724e-05, | |
| "loss": 2.5695, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.715953307392996e-05, | |
| "loss": 2.3911, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.6770428015564204e-05, | |
| "loss": 2.4357, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6381322957198447e-05, | |
| "loss": 2.4545, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.599221789883269e-05, | |
| "loss": 2.3346, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5603112840466926e-05, | |
| "loss": 2.3698, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 2.521400778210117e-05, | |
| "loss": 2.4074, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.4824902723735412e-05, | |
| "loss": 2.5796, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 2.443579766536965e-05, | |
| "loss": 2.4123, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4046692607003894e-05, | |
| "loss": 2.3395, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3657587548638134e-05, | |
| "loss": 2.3278, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.3268482490272377e-05, | |
| "loss": 2.4002, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.2879377431906616e-05, | |
| "loss": 2.3189, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.2490272373540856e-05, | |
| "loss": 2.4051, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.21011673151751e-05, | |
| "loss": 2.3595, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.171206225680934e-05, | |
| "loss": 2.3412, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.132295719844358e-05, | |
| "loss": 2.3462, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.093385214007782e-05, | |
| "loss": 2.3828, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 2.054474708171206e-05, | |
| "loss": 2.3796, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0155642023346304e-05, | |
| "loss": 2.2987, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.9766536964980543e-05, | |
| "loss": 2.3002, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9377431906614786e-05, | |
| "loss": 2.4586, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.8988326848249026e-05, | |
| "loss": 2.4058, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.859922178988327e-05, | |
| "loss": 2.3934, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5807643452808307, | |
| "eval_loss": 2.384765625, | |
| "eval_runtime": 25.0512, | |
| "eval_samples_per_second": 76.084, | |
| "eval_steps_per_second": 9.54, | |
| "step": 953 | |
| } | |
| ], | |
| "max_steps": 1428, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.11391603907625e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |