| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010202780257620201, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020405560515240405, | |
| "grad_norm": 14.39073657989502, | |
| "learning_rate": 1e-05, | |
| "loss": 15.5503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020405560515240405, | |
| "eval_loss": 0.9874714612960815, | |
| "eval_runtime": 119.3719, | |
| "eval_samples_per_second": 6.92, | |
| "eval_steps_per_second": 3.46, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004081112103048081, | |
| "grad_norm": 14.59347915649414, | |
| "learning_rate": 2e-05, | |
| "loss": 16.3011, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004081112103048081, | |
| "eval_loss": 0.9826858043670654, | |
| "eval_runtime": 32.5431, | |
| "eval_samples_per_second": 25.382, | |
| "eval_steps_per_second": 12.691, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006121668154572121, | |
| "grad_norm": 14.123443603515625, | |
| "learning_rate": 3e-05, | |
| "loss": 15.6399, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008162224206096162, | |
| "grad_norm": 12.838105201721191, | |
| "learning_rate": 4e-05, | |
| "loss": 15.2732, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008162224206096162, | |
| "eval_loss": 0.9703367948532104, | |
| "eval_runtime": 32.6924, | |
| "eval_samples_per_second": 25.266, | |
| "eval_steps_per_second": 12.633, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010202780257620201, | |
| "grad_norm": 11.981393814086914, | |
| "learning_rate": 5e-05, | |
| "loss": 14.5658, | |
| "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": 6660152837013504.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |