| { | |
| "best_metric": 0.8518154428697561, | |
| "best_model_checkpoint": "model/checkpoint-1252", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 1565, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.763400077819824, | |
| "learning_rate": 1.7092150170648464e-05, | |
| "loss": 0.9929, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8242811501597445, | |
| "eval_f1": 0.8190724938847023, | |
| "eval_loss": 0.8321825861930847, | |
| "eval_precision": 0.8210601694276454, | |
| "eval_recall": 0.8242811501597445, | |
| "eval_runtime": 3.3376, | |
| "eval_samples_per_second": 93.779, | |
| "eval_steps_per_second": 11.985, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.7372869253158569, | |
| "learning_rate": 1.281911262798635e-05, | |
| "loss": 0.7181, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8498402555910544, | |
| "eval_f1": 0.8053276047082008, | |
| "eval_loss": 1.3033751249313354, | |
| "eval_precision": 0.857962395302651, | |
| "eval_recall": 0.8498402555910544, | |
| "eval_runtime": 3.3428, | |
| "eval_samples_per_second": 93.635, | |
| "eval_steps_per_second": 11.966, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 86.433349609375, | |
| "learning_rate": 8.546075085324232e-06, | |
| "loss": 0.3916, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8306709265175719, | |
| "eval_f1": 0.8409538025804452, | |
| "eval_loss": 1.007387399673462, | |
| "eval_precision": 0.8585334191289256, | |
| "eval_recall": 0.8306709265175719, | |
| "eval_runtime": 3.3378, | |
| "eval_samples_per_second": 93.773, | |
| "eval_steps_per_second": 11.984, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.03480984643101692, | |
| "learning_rate": 4.273037542662116e-06, | |
| "loss": 0.1311, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8594249201277955, | |
| "eval_f1": 0.8518154428697561, | |
| "eval_loss": 1.7190024852752686, | |
| "eval_precision": 0.8474117456400535, | |
| "eval_recall": 0.8594249201277955, | |
| "eval_runtime": 3.3488, | |
| "eval_samples_per_second": 93.465, | |
| "eval_steps_per_second": 11.944, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.17574211955070496, | |
| "learning_rate": 0.0, | |
| "loss": 0.0597, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.853035143769968, | |
| "eval_f1": 0.842110528584532, | |
| "eval_loss": 1.8323806524276733, | |
| "eval_precision": 0.8375123279276634, | |
| "eval_recall": 0.853035143769968, | |
| "eval_runtime": 3.3685, | |
| "eval_samples_per_second": 92.92, | |
| "eval_steps_per_second": 11.875, | |
| "step": 1565 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1565, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3288917721600000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |