| { | |
| "best_metric": 2.5200698375701904, | |
| "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/nw_egy/checkpoint-1326", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1326, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.6992121934890747, | |
| "learning_rate": 4.4200000000000004e-05, | |
| "loss": 4.0723, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.22275841970876573, | |
| "eval_loss": 2.958087921142578, | |
| "eval_rouge1": 0.3912678429308313, | |
| "eval_rouge2": 0.16481568948149655, | |
| "eval_rougeL": 0.32008248461173605, | |
| "eval_runtime": 28.7079, | |
| "eval_samples_per_second": 30.793, | |
| "eval_steps_per_second": 3.867, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.676450252532959, | |
| "learning_rate": 2.6755447941888623e-05, | |
| "loss": 2.8055, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.24154624358915514, | |
| "eval_loss": 2.606330633163452, | |
| "eval_rouge1": 0.43470628711649895, | |
| "eval_rouge2": 0.19710102219495218, | |
| "eval_rougeL": 0.3776869994743499, | |
| "eval_runtime": 28.9632, | |
| "eval_samples_per_second": 30.521, | |
| "eval_steps_per_second": 3.832, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.5551148653030396, | |
| "learning_rate": 0.0, | |
| "loss": 2.5505, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.25109238074220425, | |
| "eval_loss": 2.5200698375701904, | |
| "eval_rouge1": 0.4533940426786972, | |
| "eval_rouge2": 0.21369906854716414, | |
| "eval_rougeL": 0.39838507960838365, | |
| "eval_runtime": 29.2852, | |
| "eval_samples_per_second": 30.186, | |
| "eval_steps_per_second": 3.79, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1326, | |
| "total_flos": 4151799742464000.0, | |
| "train_loss": 3.1427729219692684, | |
| "train_runtime": 589.6608, | |
| "train_samples_per_second": 17.965, | |
| "train_steps_per_second": 2.249 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1326, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4151799742464000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |