| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04953560371517028, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009907120743034056, | |
| "grad_norm": 0.44889354705810547, | |
| "learning_rate": 1e-05, | |
| "loss": 1.286, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009907120743034056, | |
| "eval_loss": 1.456308364868164, | |
| "eval_runtime": 60.7248, | |
| "eval_samples_per_second": 2.8, | |
| "eval_steps_per_second": 1.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019814241486068113, | |
| "grad_norm": 0.5221043825149536, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019814241486068113, | |
| "eval_loss": 1.4471094608306885, | |
| "eval_runtime": 8.7154, | |
| "eval_samples_per_second": 19.506, | |
| "eval_steps_per_second": 9.753, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029721362229102165, | |
| "grad_norm": 0.5328262448310852, | |
| "learning_rate": 3e-05, | |
| "loss": 1.652, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.039628482972136225, | |
| "grad_norm": 0.575575590133667, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3986, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.039628482972136225, | |
| "eval_loss": 1.435658574104309, | |
| "eval_runtime": 8.6849, | |
| "eval_samples_per_second": 19.574, | |
| "eval_steps_per_second": 9.787, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "grad_norm": 0.5304684042930603, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3195, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |