| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5871272353646305, |
| "eval_steps": 500, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19570907845487684, |
| "grad_norm": 2.284667730331421, |
| "learning_rate": 3.7525e-05, |
| "loss": 1.4897, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3914181569097537, |
| "grad_norm": 2.1923739910125732, |
| "learning_rate": 2.5025e-05, |
| "loss": 1.3973, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5871272353646305, |
| "grad_norm": 2.258883237838745, |
| "learning_rate": 1.2525000000000001e-05, |
| "loss": 1.3604, |
| "step": 1500 |
| } |
| ], |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.05353240576e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
