| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02141648641123937, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005354121602809843, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 11.8252, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.010708243205619685, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666669e-06, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01606236480842953, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.333333333333334e-07, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.02141648641123937, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.02141648641123937, | |
| "step": 2000, | |
| "total_flos": 8.380982415051637e+18, | |
| "train_loss": 2.956299072265625, | |
| "train_runtime": 3006.0711, | |
| "train_samples_per_second": 2.661, | |
| "train_steps_per_second": 0.665 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.380982415051637e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |