| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.027285129604365622, |
| "eval_steps": 500, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0068212824010914054, |
| "grad_norm": 1.9269121253558394, |
| "learning_rate": 4.7288159402146e-05, |
| "loss": 0.8471, |
| "num_tokens": 3759146.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.013642564802182811, |
| "grad_norm": 0.5808226827267438, |
| "learning_rate": 3.3023423460667985e-05, |
| "loss": 0.7116, |
| "num_tokens": 7668808.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.020463847203274217, |
| "grad_norm": 0.37829142833477414, |
| "learning_rate": 1.5193666442245402e-05, |
| "loss": 0.6539, |
| "num_tokens": 11368873.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.027285129604365622, |
| "grad_norm": 0.29058282503596367, |
| "learning_rate": 5.3068706734387484e-06, |
| "loss": 0.6388, |
| "num_tokens": 15118063.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.027285129604365622, |
| "step": 20, |
| "total_flos": 30770262441984.0, |
| "train_loss": 0.712840223312378, |
| "train_runtime": 169.7887, |
| "train_samples_per_second": 15.078, |
| "train_steps_per_second": 0.118 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 20, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 30770262441984.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
