| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 500.0, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 100.0, |
| "grad_norm": 1.8578704595565796, |
| "learning_rate": 4.8020000000000004e-05, |
| "loss": 0.4234, |
| "step": 200 |
| }, |
| { |
| "epoch": 200.0, |
| "grad_norm": 0.6928507685661316, |
| "learning_rate": 3.604e-05, |
| "loss": 0.1814, |
| "step": 400 |
| }, |
| { |
| "epoch": 300.0, |
| "grad_norm": 1.1086845397949219, |
| "learning_rate": 2.406e-05, |
| "loss": 0.1281, |
| "step": 600 |
| }, |
| { |
| "epoch": 400.0, |
| "grad_norm": 1.4631288051605225, |
| "learning_rate": 1.2079999999999998e-05, |
| "loss": 0.1144, |
| "step": 800 |
| }, |
| { |
| "epoch": 500.0, |
| "grad_norm": 0.9606817364692688, |
| "learning_rate": 1e-07, |
| "loss": 0.1007, |
| "step": 1000 |
| }, |
| { |
| "epoch": 500.0, |
| "step": 1000, |
| "total_flos": 7.8886713950208e+16, |
| "train_loss": 0.1895984401702881, |
| "train_runtime": 397.1334, |
| "train_samples_per_second": 20.144, |
| "train_steps_per_second": 2.518 |
| } |
| ], |
| "logging_steps": 200, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 500, |
| "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": 7.8886713950208e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
