| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00015851209975694812, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.283736658564937e-05, | |
| "grad_norm": 15.33159351348877, | |
| "learning_rate": 2e-05, | |
| "loss": 7.6823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.283736658564937e-05, | |
| "eval_loss": 7.635408878326416, | |
| "eval_runtime": 151.6456, | |
| "eval_samples_per_second": 52.55, | |
| "eval_steps_per_second": 26.278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010567473317129874, | |
| "grad_norm": 15.896822929382324, | |
| "learning_rate": 4e-05, | |
| "loss": 7.3373, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00015851209975694812, | |
| "grad_norm": 15.872105598449707, | |
| "learning_rate": 6e-05, | |
| "loss": 7.3625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00015851209975694812, | |
| "eval_loss": 7.4907331466674805, | |
| "eval_runtime": 150.6864, | |
| "eval_samples_per_second": 52.885, | |
| "eval_steps_per_second": 26.446, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 26711449141248.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |