| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.2932428063368897, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.6466214031684449, | |
| "grad_norm": 1.7960103750228882, | |
| "learning_rate": 1.5060539027168317e-05, | |
| "loss": 0.0424, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6466214031684449, | |
| "eval_retrival_loss": 0.0060070110484957695, | |
| "eval_retrival_runtime": 2.5865, | |
| "eval_retrival_samples_per_second": 386.62, | |
| "eval_retrival_steps_per_second": 24.357, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2932428063368897, | |
| "grad_norm": 0.3418584167957306, | |
| "learning_rate": 5.030361696847706e-06, | |
| "loss": 0.0073, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.2932428063368897, | |
| "eval_retrival_loss": 0.004016744904220104, | |
| "eval_retrival_runtime": 2.5619, | |
| "eval_retrival_samples_per_second": 390.338, | |
| "eval_retrival_steps_per_second": 24.591, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |