| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0017359498727114757, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00034718997454229514, |
| "grad_norm": 0.8856930732727051, |
| "learning_rate": 0.00019999994169931, |
| "loss": 2.4069, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0006943799490845903, |
| "grad_norm": 0.8890424966812134, |
| "learning_rate": 0.0001999997644357777, |
| "loss": 2.3882, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0010415699236268853, |
| "grad_norm": 0.8619076013565063, |
| "learning_rate": 0.00019999946820366553, |
| "loss": 2.4208, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.0013887598981691806, |
| "grad_norm": 0.8981874585151672, |
| "learning_rate": 0.00019999905300332595, |
| "loss": 2.3859, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.0017359498727114757, |
| "grad_norm": 1.1088451147079468, |
| "learning_rate": 0.0001999985188352529, |
| "loss": 2.4031, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 288027, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3740660968730624e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
