| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 348, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.43360433604336046, |
| "grad_norm": 1.351936936378479, |
| "learning_rate": 1.9600000000000002e-05, |
| "loss": 8.5745, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8672086720867209, |
| "grad_norm": 0.49343356490135193, |
| "learning_rate": 3.960000000000001e-05, |
| "loss": 7.2834, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.294850948509485, |
| "grad_norm": 0.35413601994514465, |
| "learning_rate": 5.96e-05, |
| "loss": 6.7556, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.7284552845528456, |
| "grad_norm": 0.7609367966651917, |
| "learning_rate": 7.960000000000001e-05, |
| "loss": 6.7161, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.15609756097561, |
| "grad_norm": 0.5119837522506714, |
| "learning_rate": 9.960000000000001e-05, |
| "loss": 6.6669, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.58970189701897, |
| "grad_norm": 0.4061020314693451, |
| "learning_rate": 0.00011960000000000001, |
| "loss": 6.6361, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 348, |
| "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": 6840447945891840.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
