| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 1.8390942811965942, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5065, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.7160496115684509, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.2128, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.446665495634079, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.1702, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 30, | |
| "total_flos": 0.0, | |
| "train_loss": 0.29649561246236167, | |
| "train_runtime": 65.8291, | |
| "train_samples_per_second": 47.547, | |
| "train_steps_per_second": 0.456 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 107, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |