| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9955555555555555, |
| "eval_steps": 2500, |
| "global_step": 56, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 27.719364166259766, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 10.5766, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 19.793004989624023, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 8.8999, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 7.705715179443359, |
| "learning_rate": 6e-06, |
| "loss": 7.4242, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 5.494255542755127, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 7.415, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 4.036380290985107, |
| "learning_rate": 1e-05, |
| "loss": 6.6437, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 56, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 2500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 550991422291968.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
