| { | |
| "best_metric": 1.7362614870071411, | |
| "best_model_checkpoint": "qa_finetuning/run-4/checkpoint-200", | |
| "epoch": 5.0, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 7.338883876800537, | |
| "learning_rate": 1.8677116057865877e-05, | |
| "loss": 3.2617, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 1.8736786842346191, | |
| "eval_runtime": 3.6445, | |
| "eval_samples_per_second": 137.192, | |
| "eval_steps_per_second": 4.39, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 30.04753303527832, | |
| "learning_rate": 0.0, | |
| "loss": 1.439, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7362614870071411, | |
| "eval_runtime": 3.6733, | |
| "eval_samples_per_second": 136.118, | |
| "eval_steps_per_second": 4.356, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 2449745625600000.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.7354232115731755e-05, | |
| "num_train_epochs": 5, | |
| "per_device_train_batch_size": 64, | |
| "seed": 9 | |
| } | |
| } | |