| { | |
| "best_metric": 0.6361710372570955, | |
| "best_model_checkpoint": "training_dir/checkpoint-250", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.6677370071411133, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9403, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.47246503496503495, | |
| "eval_f1": 0.37635514577655893, | |
| "eval_loss": 1.0853666067123413, | |
| "eval_precision": 0.4261448543164962, | |
| "eval_recall": 0.47246503496503495, | |
| "eval_runtime": 29.0544, | |
| "eval_samples_per_second": 78.749, | |
| "eval_steps_per_second": 9.844, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.521803855895996, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5748, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6407342657342657, | |
| "eval_f1": 0.6361710372570955, | |
| "eval_loss": 0.8366930484771729, | |
| "eval_precision": 0.6428210794762689, | |
| "eval_recall": 0.6407342657342657, | |
| "eval_runtime": 29.8222, | |
| "eval_samples_per_second": 76.721, | |
| "eval_steps_per_second": 9.59, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 7.845700263977051, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3732, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.603583916083916, | |
| "eval_f1": 0.565369682305176, | |
| "eval_loss": 1.3425886631011963, | |
| "eval_precision": 0.6364003210803549, | |
| "eval_recall": 0.603583916083916, | |
| "eval_runtime": 29.9297, | |
| "eval_samples_per_second": 76.446, | |
| "eval_steps_per_second": 9.556, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 27.72207260131836, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2795, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.611451048951049, | |
| "eval_f1": 0.5839059582567918, | |
| "eval_loss": 1.4940129518508911, | |
| "eval_precision": 0.6264845385709801, | |
| "eval_recall": 0.611451048951049, | |
| "eval_runtime": 29.8938, | |
| "eval_samples_per_second": 76.538, | |
| "eval_steps_per_second": 9.567, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 815516966304000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |