| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 2072, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7460424385314921 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.6468745856581467 | |
| }, | |
| "eval_loss": 0.7669360637664795, | |
| "eval_precision": { | |
| "precision": 0.7498298692486852 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.626548030580631 | |
| }, | |
| "eval_runtime": 25.654, | |
| "eval_samples_per_second": 347.197, | |
| "eval_steps_per_second": 21.712, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.9305019305019306, | |
| "grad_norm": 1.1135650873184204, | |
| "learning_rate": 2.2760617760617762e-05, | |
| "loss": 0.5355, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7547995958235096 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7693345628019765 | |
| }, | |
| "eval_loss": 1.091949224472046, | |
| "eval_precision": { | |
| "precision": 0.7745827666215183 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.775266047858661 | |
| }, | |
| "eval_runtime": 25.7836, | |
| "eval_samples_per_second": 345.452, | |
| "eval_steps_per_second": 21.603, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7595149882115191 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7726494361094581 | |
| }, | |
| "eval_loss": 1.3202872276306152, | |
| "eval_precision": { | |
| "precision": 0.7741992798858378 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.7862141909666348 | |
| }, | |
| "eval_runtime": 25.6795, | |
| "eval_samples_per_second": 346.852, | |
| "eval_steps_per_second": 21.69, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 3.861003861003861, | |
| "grad_norm": 0.5814288854598999, | |
| "learning_rate": 1.552123552123552e-05, | |
| "loss": 0.1121, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7726507241495453 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7837280343276152 | |
| }, | |
| "eval_loss": 1.3736612796783447, | |
| "eval_precision": { | |
| "precision": 0.7837340802618142 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.7843424989171847 | |
| }, | |
| "eval_runtime": 25.6794, | |
| "eval_samples_per_second": 346.854, | |
| "eval_steps_per_second": 21.691, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7656899068148647 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.792071365170026 | |
| }, | |
| "eval_loss": 1.5462839603424072, | |
| "eval_precision": { | |
| "precision": 0.818913170460716 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.7749402535371823 | |
| }, | |
| "eval_runtime": 25.7253, | |
| "eval_samples_per_second": 346.235, | |
| "eval_steps_per_second": 21.652, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 5.7915057915057915, | |
| "grad_norm": 0.7229886651039124, | |
| "learning_rate": 8.281853281853282e-06, | |
| "loss": 0.0489, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7669248905355338 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7860035799974232 | |
| }, | |
| "eval_loss": 1.5993564128875732, | |
| "eval_precision": { | |
| "precision": 0.7762488236121527 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.8041145184160382 | |
| }, | |
| "eval_runtime": 25.6577, | |
| "eval_samples_per_second": 347.148, | |
| "eval_steps_per_second": 21.709, | |
| "step": 1554 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7629953968788593 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7931621649235138 | |
| }, | |
| "eval_loss": 1.670336365699768, | |
| "eval_precision": { | |
| "precision": 0.7944488176619807 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.7984954459796072 | |
| }, | |
| "eval_runtime": 25.6877, | |
| "eval_samples_per_second": 346.742, | |
| "eval_steps_per_second": 21.684, | |
| "step": 1813 | |
| }, | |
| { | |
| "epoch": 7.722007722007722, | |
| "grad_norm": 0.011735806241631508, | |
| "learning_rate": 1.0424710424710424e-06, | |
| "loss": 0.0123, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": { | |
| "accuracy": 0.7683844167508701 | |
| }, | |
| "eval_f1": { | |
| "f1": 0.7959143631565831 | |
| }, | |
| "eval_loss": 1.6564217805862427, | |
| "eval_precision": { | |
| "precision": 0.7925798438872362 | |
| }, | |
| "eval_recall": { | |
| "recall": 0.8046718233013863 | |
| }, | |
| "eval_runtime": 25.8167, | |
| "eval_samples_per_second": 345.009, | |
| "eval_steps_per_second": 21.575, | |
| "step": 2072 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2072, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4773365380707600.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |