| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9998833002684094, | |
| "eval_steps": 250, | |
| "global_step": 1071, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2333994631812347, | |
| "grad_norm": 5.517484664916992, | |
| "learning_rate": 8.978253703087328e-05, | |
| "loss": 0.2774, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2333994631812347, | |
| "eval_loss": 0.15229368209838867, | |
| "eval_runtime": 38.4575, | |
| "eval_samples_per_second": 2.262, | |
| "eval_steps_per_second": 2.262, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "grad_norm": 4.271782875061035, | |
| "learning_rate": 5.813544178200335e-05, | |
| "loss": 0.113, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4667989263624694, | |
| "eval_loss": 0.11989569664001465, | |
| "eval_runtime": 38.4799, | |
| "eval_samples_per_second": 2.261, | |
| "eval_steps_per_second": 2.261, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "grad_norm": 2.8904411792755127, | |
| "learning_rate": 2.2048719230965166e-05, | |
| "loss": 0.0976, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7001983895437041, | |
| "eval_loss": 0.10857120901346207, | |
| "eval_runtime": 38.4504, | |
| "eval_samples_per_second": 2.263, | |
| "eval_steps_per_second": 2.263, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "grad_norm": 2.5422346591949463, | |
| "learning_rate": 1.2154116213611399e-06, | |
| "loss": 0.0888, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9335978527249388, | |
| "eval_loss": 0.10513731092214584, | |
| "eval_runtime": 38.3816, | |
| "eval_samples_per_second": 2.267, | |
| "eval_steps_per_second": 2.267, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 1071, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.6276556433152e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |