| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0037203534335761897, |
| "eval_steps": 3, |
| "global_step": 6, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0006200589055960316, |
| "grad_norm": 0.7607094645500183, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.1893, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0012401178111920632, |
| "grad_norm": 0.3518824279308319, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.9752, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "grad_norm": 0.4024870693683624, |
| "learning_rate": 1.2e-05, |
| "loss": 0.8467, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0018601767167880949, |
| "eval_loss": 1.0757174491882324, |
| "eval_runtime": 26.414, |
| "eval_samples_per_second": 3.786, |
| "eval_steps_per_second": 3.786, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.0024802356223841263, |
| "grad_norm": 0.36653462052345276, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.0056, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.0031002945279801583, |
| "grad_norm": 0.47098514437675476, |
| "learning_rate": 2e-05, |
| "loss": 0.8545, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0037203534335761897, |
| "grad_norm": 0.5030912160873413, |
| "learning_rate": 1.9200000000000003e-05, |
| "loss": 0.9553, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.0037203534335761897, |
| "eval_loss": 1.0662517547607422, |
| "eval_runtime": 26.7124, |
| "eval_samples_per_second": 3.744, |
| "eval_steps_per_second": 3.744, |
| "step": 6 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 30, |
| "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": 7554675219038208.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
