| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007623888182973317, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025412960609911056, | |
| "grad_norm": 0.2694489061832428, | |
| "learning_rate": 2e-05, | |
| "loss": 5.4593, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025412960609911056, | |
| "eval_loss": 5.5072832107543945, | |
| "eval_runtime": 5.1676, | |
| "eval_samples_per_second": 32.123, | |
| "eval_steps_per_second": 16.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005082592121982211, | |
| "grad_norm": 0.37336480617523193, | |
| "learning_rate": 4e-05, | |
| "loss": 5.4793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007623888182973317, | |
| "grad_norm": 0.29353266954421997, | |
| "learning_rate": 6e-05, | |
| "loss": 5.4156, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007623888182973317, | |
| "eval_loss": 5.5053815841674805, | |
| "eval_runtime": 4.0708, | |
| "eval_samples_per_second": 40.778, | |
| "eval_steps_per_second": 20.389, | |
| "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": 205681990828032.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |