| { | |
| "best_metric": 0.02599843218922615, | |
| "best_model_checkpoint": "./results4/checkpoint-2400", | |
| "epoch": 4.4036697247706424, | |
| "eval_steps": 200, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 6.81126594543457, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 1.8154, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "eval_accuracy": 0.12834224598930483, | |
| "eval_f1": 0.053512789620671505, | |
| "eval_loss": 1.8153961896896362, | |
| "eval_precision": 0.03873999770058728, | |
| "eval_recall": 0.12834224598930483, | |
| "eval_runtime": 8.8051, | |
| "eval_samples_per_second": 106.189, | |
| "eval_steps_per_second": 26.576, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 9.484223365783691, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 1.7996, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "eval_accuracy": 0.20962566844919786, | |
| "eval_f1": 0.1699240887979582, | |
| "eval_loss": 1.776768684387207, | |
| "eval_precision": 0.2712506960219069, | |
| "eval_recall": 0.20962566844919786, | |
| "eval_runtime": 8.617, | |
| "eval_samples_per_second": 108.506, | |
| "eval_steps_per_second": 27.155, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.1009174311926606, | |
| "grad_norm": 8.83604621887207, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.7653, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.1009174311926606, | |
| "eval_accuracy": 0.35508021390374334, | |
| "eval_f1": 0.34776363638784535, | |
| "eval_loss": 1.7193909883499146, | |
| "eval_precision": 0.5237977574987844, | |
| "eval_recall": 0.35508021390374334, | |
| "eval_runtime": 8.8621, | |
| "eval_samples_per_second": 105.506, | |
| "eval_steps_per_second": 26.405, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "grad_norm": 12.071432113647461, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 1.7051, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.4678899082568808, | |
| "eval_accuracy": 0.5401069518716578, | |
| "eval_f1": 0.5429174295461449, | |
| "eval_loss": 1.6069858074188232, | |
| "eval_precision": 0.6148066517946612, | |
| "eval_recall": 0.5401069518716578, | |
| "eval_runtime": 8.6363, | |
| "eval_samples_per_second": 108.263, | |
| "eval_steps_per_second": 27.095, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "grad_norm": 8.39781379699707, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.561, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.834862385321101, | |
| "eval_accuracy": 0.6181818181818182, | |
| "eval_f1": 0.599751774424811, | |
| "eval_loss": 1.3523486852645874, | |
| "eval_precision": 0.6869881919032953, | |
| "eval_recall": 0.6181818181818182, | |
| "eval_runtime": 8.7123, | |
| "eval_samples_per_second": 107.32, | |
| "eval_steps_per_second": 26.859, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "grad_norm": 7.149374008178711, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.2159, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "eval_accuracy": 0.7561497326203208, | |
| "eval_f1": 0.7396853774240922, | |
| "eval_loss": 0.8623968958854675, | |
| "eval_precision": 0.7976461918397214, | |
| "eval_recall": 0.7561497326203208, | |
| "eval_runtime": 8.4876, | |
| "eval_samples_per_second": 110.161, | |
| "eval_steps_per_second": 27.57, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.5688073394495414, | |
| "grad_norm": 12.584464073181152, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.7501, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.5688073394495414, | |
| "eval_accuracy": 0.8909090909090909, | |
| "eval_f1": 0.8893217599642673, | |
| "eval_loss": 0.43212181329727173, | |
| "eval_precision": 0.8944228004598542, | |
| "eval_recall": 0.8909090909090909, | |
| "eval_runtime": 8.5383, | |
| "eval_samples_per_second": 109.507, | |
| "eval_steps_per_second": 27.406, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "grad_norm": 6.3582305908203125, | |
| "learning_rate": 4.99209709753674e-06, | |
| "loss": 0.4346, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "eval_accuracy": 0.9401069518716577, | |
| "eval_f1": 0.939586410891439, | |
| "eval_loss": 0.20562343299388885, | |
| "eval_precision": 0.942115798236324, | |
| "eval_recall": 0.9401069518716577, | |
| "eval_runtime": 8.5478, | |
| "eval_samples_per_second": 109.384, | |
| "eval_steps_per_second": 27.375, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.302752293577982, | |
| "grad_norm": 1.9859445095062256, | |
| "learning_rate": 4.929173350101025e-06, | |
| "loss": 0.1985, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.302752293577982, | |
| "eval_accuracy": 0.9796791443850268, | |
| "eval_f1": 0.9795557753030716, | |
| "eval_loss": 0.07811883836984634, | |
| "eval_precision": 0.9796698126299838, | |
| "eval_recall": 0.9796791443850268, | |
| "eval_runtime": 8.5151, | |
| "eval_samples_per_second": 109.804, | |
| "eval_steps_per_second": 27.48, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "grad_norm": 3.169071912765503, | |
| "learning_rate": 4.804914636820517e-06, | |
| "loss": 0.1066, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.669724770642202, | |
| "eval_accuracy": 0.9828877005347594, | |
| "eval_f1": 0.9828341396664676, | |
| "eval_loss": 0.05222497880458832, | |
| "eval_precision": 0.9829524348459922, | |
| "eval_recall": 0.9828877005347594, | |
| "eval_runtime": 8.3944, | |
| "eval_samples_per_second": 111.384, | |
| "eval_steps_per_second": 27.876, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.036697247706422, | |
| "grad_norm": 0.22888700664043427, | |
| "learning_rate": 4.622458405228411e-06, | |
| "loss": 0.096, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.036697247706422, | |
| "eval_accuracy": 0.986096256684492, | |
| "eval_f1": 0.9860397886588865, | |
| "eval_loss": 0.037959374487400055, | |
| "eval_precision": 0.9862011528885352, | |
| "eval_recall": 0.986096256684492, | |
| "eval_runtime": 8.8571, | |
| "eval_samples_per_second": 105.565, | |
| "eval_steps_per_second": 26.42, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 4.4036697247706424, | |
| "grad_norm": 0.051910221576690674, | |
| "learning_rate": 4.386411550395576e-06, | |
| "loss": 0.0686, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 4.4036697247706424, | |
| "eval_accuracy": 0.9925133689839573, | |
| "eval_f1": 0.9925048378298892, | |
| "eval_loss": 0.02599843218922615, | |
| "eval_precision": 0.9925302733753678, | |
| "eval_recall": 0.9925133689839573, | |
| "eval_runtime": 8.5262, | |
| "eval_samples_per_second": 109.661, | |
| "eval_steps_per_second": 27.445, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 5450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 396630381488796.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |