| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004929548535513289, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016431828451710963, | |
| "grad_norm": 1.6920582056045532, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016431828451710963, | |
| "eval_loss": 1.8038899898529053, | |
| "eval_runtime": 188.5099, | |
| "eval_samples_per_second": 13.596, | |
| "eval_steps_per_second": 6.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032863656903421926, | |
| "grad_norm": 1.5381139516830444, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004929548535513289, | |
| "grad_norm": 2.7109837532043457, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004929548535513289, | |
| "eval_loss": 1.794869065284729, | |
| "eval_runtime": 193.4515, | |
| "eval_samples_per_second": 13.249, | |
| "eval_steps_per_second": 6.627, | |
| "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": 232501951856640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |