| { | |
| "best_metric": 0.11768843978643417, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-393", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 393, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.8e-06, | |
| "loss": 0.6931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.56e-05, | |
| "loss": 0.6929, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.34e-05, | |
| "loss": 0.6921, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.12e-05, | |
| "loss": 0.6908, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.9e-05, | |
| "loss": 0.6896, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.68e-05, | |
| "loss": 0.6873, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.170538243626062e-05, | |
| "loss": 0.6809, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 5.082152974504249e-05, | |
| "loss": 0.6779, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.9937677053824355e-05, | |
| "loss": 0.6679, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.9053824362606226e-05, | |
| "loss": 0.6602, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.81699716713881e-05, | |
| "loss": 0.6476, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.728611898016997e-05, | |
| "loss": 0.64, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.640226628895184e-05, | |
| "loss": 0.6289, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.551841359773371e-05, | |
| "loss": 0.613, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.4634560906515584e-05, | |
| "loss": 0.6233, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.375070821529745e-05, | |
| "loss": 0.6072, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.286685552407932e-05, | |
| "loss": 0.5765, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.198300283286119e-05, | |
| "loss": 0.5677, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.1099150141643056e-05, | |
| "loss": 0.5538, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.021529745042493e-05, | |
| "loss": 0.5368, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.93314447592068e-05, | |
| "loss": 0.5341, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.4369600713253021, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 33.4023, | |
| "eval_samples_per_second": 7.844, | |
| "eval_steps_per_second": 0.509, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 3.8447592067988664e-05, | |
| "loss": 0.4985, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.7563739376770535e-05, | |
| "loss": 0.4917, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.667988668555241e-05, | |
| "loss": 0.4849, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 3.579603399433428e-05, | |
| "loss": 0.49, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.491218130311614e-05, | |
| "loss": 0.4381, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 3.4028328611898015e-05, | |
| "loss": 0.479, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.3144475920679886e-05, | |
| "loss": 0.4316, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.226062322946175e-05, | |
| "loss": 0.4146, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.137677053824362e-05, | |
| "loss": 0.4161, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 3.0492917847025494e-05, | |
| "loss": 0.3932, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.9609065155807362e-05, | |
| "loss": 0.3577, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.8725212464589234e-05, | |
| "loss": 0.3574, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.7841359773371105e-05, | |
| "loss": 0.3468, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6957507082152977e-05, | |
| "loss": 0.3356, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.607365439093484e-05, | |
| "loss": 0.2927, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 2.5189801699716713e-05, | |
| "loss": 0.2838, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.430594900849858e-05, | |
| "loss": 0.3153, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 2.3422096317280452e-05, | |
| "loss": 0.2586, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.253824362606232e-05, | |
| "loss": 0.2912, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.1654390934844192e-05, | |
| "loss": 0.3014, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.077053824362606e-05, | |
| "loss": 0.2679, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.988668555240793e-05, | |
| "loss": 0.331, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.17224115133285522, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 32.4437, | |
| "eval_samples_per_second": 8.076, | |
| "eval_steps_per_second": 0.524, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.90028328611898e-05, | |
| "loss": 0.2564, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.811898016997167e-05, | |
| "loss": 0.2979, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.7235127478753543e-05, | |
| "loss": 0.2363, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.635127478753541e-05, | |
| "loss": 0.1956, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.546742209631728e-05, | |
| "loss": 0.217, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.458356940509915e-05, | |
| "loss": 0.2207, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3699716713881019e-05, | |
| "loss": 0.2602, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2815864022662889e-05, | |
| "loss": 0.2192, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 1.1932011331444758e-05, | |
| "loss": 0.2306, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.1048158640226628e-05, | |
| "loss": 0.1996, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.0164305949008498e-05, | |
| "loss": 0.2363, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 9.280453257790368e-06, | |
| "loss": 0.2426, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.396600566572238e-06, | |
| "loss": 0.2642, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.512747875354107e-06, | |
| "loss": 0.2303, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 6.628895184135977e-06, | |
| "loss": 0.26, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.745042492917846e-06, | |
| "loss": 0.2661, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.861189801699716e-06, | |
| "loss": 0.2323, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.977337110481587e-06, | |
| "loss": 0.2782, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.093484419263456e-06, | |
| "loss": 0.2154, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.209631728045326e-06, | |
| "loss": 0.1829, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 1.3257790368271953e-06, | |
| "loss": 0.2378, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 4.419263456090652e-07, | |
| "loss": 0.2288, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.11768843978643417, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 32.1685, | |
| "eval_samples_per_second": 8.145, | |
| "eval_steps_per_second": 0.528, | |
| "step": 393 | |
| } | |
| ], | |
| "logging_steps": 6, | |
| "max_steps": 393, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 6.650928353599488e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |