| { | |
| "best_metric": 0.01787894032895565, | |
| "best_model_checkpoint": "mulder-scully-2024/checkpoint-44", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.7706, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.6318, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.892, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.36, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.42857142857142855, | |
| "eval_auc": 0.8333333333333334, | |
| "eval_f1": 0.3333333333333333, | |
| "eval_loss": 0.7393712401390076, | |
| "eval_precision": 0.5, | |
| "eval_recall": 0.25, | |
| "eval_runtime": 0.2422, | |
| "eval_samples_per_second": 28.896, | |
| "eval_steps_per_second": 4.128, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.7442, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.6257, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.6755, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.5589, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.75, | |
| "eval_loss": 0.5653250813484192, | |
| "eval_precision": 0.75, | |
| "eval_recall": 0.75, | |
| "eval_runtime": 0.2778, | |
| "eval_samples_per_second": 25.2, | |
| "eval_steps_per_second": 3.6, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5628, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 0.3517, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.5619, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.791666666666667e-05, | |
| "loss": 0.1437, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8571428571428571, | |
| "eval_auc": 1.0, | |
| "eval_f1": 0.888888888888889, | |
| "eval_loss": 0.385323703289032, | |
| "eval_precision": 0.8, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.234, | |
| "eval_samples_per_second": 29.911, | |
| "eval_steps_per_second": 4.273, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.5414, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 4.652777777777778e-05, | |
| "loss": 0.2829, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.3696, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.3601, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.2203500121831894, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2467, | |
| "eval_samples_per_second": 28.369, | |
| "eval_steps_per_second": 4.053, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1114, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.4256, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.2173, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.236111111111111e-05, | |
| "loss": 0.2773, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.117597296833992, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.3084, | |
| "eval_samples_per_second": 22.696, | |
| "eval_steps_per_second": 3.242, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.2782, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 4.0972222222222225e-05, | |
| "loss": 0.162, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.1054, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.958333333333333e-05, | |
| "loss": 0.2455, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0715898796916008, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2402, | |
| "eval_samples_per_second": 29.148, | |
| "eval_steps_per_second": 4.164, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.0537, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.1639, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.6805555555555556e-05, | |
| "loss": 0.0457, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.045065738260746, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2361, | |
| "eval_samples_per_second": 29.646, | |
| "eval_steps_per_second": 4.235, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.0697, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 3.541666666666667e-05, | |
| "loss": 0.0911, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.0988, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.402777777777778e-05, | |
| "loss": 0.1209, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0308271162211895, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.239, | |
| "eval_samples_per_second": 29.289, | |
| "eval_steps_per_second": 4.184, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.027, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 3.263888888888889e-05, | |
| "loss": 0.0827, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.0694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.2395, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.02402932569384575, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2369, | |
| "eval_samples_per_second": 29.554, | |
| "eval_steps_per_second": 4.222, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.0317, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 2.9861111111111113e-05, | |
| "loss": 0.2163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.0338, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 0.0082, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.01993233896791935, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2369, | |
| "eval_samples_per_second": 29.546, | |
| "eval_steps_per_second": 4.221, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1323, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.0175, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.0088, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 0.0176, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.01787894032895565, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2348, | |
| "eval_samples_per_second": 29.813, | |
| "eval_steps_per_second": 4.259, | |
| "step": 44 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 2.3015120915533824e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |