| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010484927916120577, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020969855832241153, | |
| "grad_norm": 0.015240407548844814, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020969855832241153, | |
| "eval_loss": 11.931079864501953, | |
| "eval_runtime": 17.944, | |
| "eval_samples_per_second": 44.806, | |
| "eval_steps_per_second": 22.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0041939711664482305, | |
| "grad_norm": 0.016336986795067787, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0041939711664482305, | |
| "eval_loss": 11.931077003479004, | |
| "eval_runtime": 1.1612, | |
| "eval_samples_per_second": 692.411, | |
| "eval_steps_per_second": 346.206, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006290956749672346, | |
| "grad_norm": 0.01226983405649662, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9304, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008387942332896461, | |
| "grad_norm": 0.010739377699792385, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008387942332896461, | |
| "eval_loss": 11.931066513061523, | |
| "eval_runtime": 1.1762, | |
| "eval_samples_per_second": 683.538, | |
| "eval_steps_per_second": 341.769, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010484927916120577, | |
| "grad_norm": 0.016481827944517136, | |
| "learning_rate": 5e-05, | |
| "loss": 11.928, | |
| "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": 2363228160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |