| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 54, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 2.1338958740234375, |
| "learning_rate": 1.8e-05, |
| "loss": 1.1905, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 1.5124315023422241, |
| "learning_rate": 3.8e-05, |
| "loss": 1.0775, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 1.2144043445587158, |
| "learning_rate": 5.8e-05, |
| "loss": 0.8018, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.2222222222222223, |
| "grad_norm": 0.8732782006263733, |
| "learning_rate": 7.800000000000001e-05, |
| "loss": 0.7853, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.7777777777777777, |
| "grad_norm": 0.9764874577522278, |
| "learning_rate": 9.8e-05, |
| "loss": 0.6885, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 54, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1.914298996831027e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
