| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 6.8, |
| "eval_steps": 500, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.8, |
| "grad_norm": 61.58274553680544, |
| "learning_rate": 8.888888888888888e-06, |
| "loss": -0.2273, |
| "step": 5 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 812.4095102588005, |
| "learning_rate": 6.111111111111112e-06, |
| "loss": -6.9936, |
| "step": 10 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 864.254957491134, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": -22.3869, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 997.907736708941, |
| "learning_rate": 5.555555555555555e-07, |
| "loss": -43.6457, |
| "step": 20 |
| }, |
| { |
| "epoch": 6.8, |
| "step": 20, |
| "total_flos": 0.0, |
| "train_loss": -18.313378661870956, |
| "train_runtime": 33.0286, |
| "train_samples_per_second": 12.111, |
| "train_steps_per_second": 0.606 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 20, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 4, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
