| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9047619047619047, |
| "eval_steps": 500, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 6.44710347055919, |
| "learning_rate": 9.755282581475769e-06, |
| "loss": 0.3366, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 2.9514573674228846, |
| "learning_rate": 9.045084971874738e-06, |
| "loss": 0.248, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 1.2549763142117352, |
| "learning_rate": 7.938926261462366e-06, |
| "loss": 0.1986, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.7365155891765774, |
| "learning_rate": 6.545084971874738e-06, |
| "loss": 0.1832, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 1.7493795536783088, |
| "learning_rate": 5e-06, |
| "loss": 0.2008, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 2.1637528778892285, |
| "learning_rate": 3.4549150281252635e-06, |
| "loss": 0.3273, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 0.8120363238008694, |
| "learning_rate": 2.061073738537635e-06, |
| "loss": 0.1662, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.5238095238095237, |
| "grad_norm": 0.7987161490099776, |
| "learning_rate": 9.549150281252633e-07, |
| "loss": 0.1735, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 0.7476135062723098, |
| "learning_rate": 2.447174185242324e-07, |
| "loss": 0.1679, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 0.731758935440235, |
| "learning_rate": 0.0, |
| "loss": 0.1679, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "step": 10, |
| "total_flos": 1295536619520.0, |
| "train_loss": 0.21700615733861922, |
| "train_runtime": 74.5403, |
| "train_samples_per_second": 10.759, |
| "train_steps_per_second": 0.134 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 5000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1295536619520.0, |
| "train_batch_size": 5, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
