| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 100.0, |
| "eval_steps": 0, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 12.0, |
| "grad_norm": 0.1227988204220739, |
| "learning_rate": 9.558232931726908e-06, |
| "loss": 0.0104, |
| "step": 12 |
| }, |
| { |
| "epoch": 24.0, |
| "grad_norm": 0.16713882339517502, |
| "learning_rate": 9.076305220883535e-06, |
| "loss": 0.0047, |
| "step": 24 |
| }, |
| { |
| "epoch": 36.0, |
| "grad_norm": 0.15359159039550918, |
| "learning_rate": 8.594377510040161e-06, |
| "loss": 0.0034, |
| "step": 36 |
| }, |
| { |
| "epoch": 48.0, |
| "grad_norm": 0.8594042294557663, |
| "learning_rate": 8.112449799196788e-06, |
| "loss": 0.0007, |
| "step": 48 |
| }, |
| { |
| "epoch": 60.0, |
| "grad_norm": 11.89227329162224, |
| "learning_rate": 7.630522088353415e-06, |
| "loss": -0.0763, |
| "step": 60 |
| }, |
| { |
| "epoch": 72.0, |
| "grad_norm": 21.264478034391686, |
| "learning_rate": 7.148594377510041e-06, |
| "loss": -0.5386, |
| "step": 72 |
| }, |
| { |
| "epoch": 84.0, |
| "grad_norm": 28.48895934450598, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": -1.5866, |
| "step": 84 |
| }, |
| { |
| "epoch": 96.0, |
| "grad_norm": 23.81904322908575, |
| "learning_rate": 6.184738955823294e-06, |
| "loss": -2.81, |
| "step": 96 |
| } |
| ], |
| "logging_steps": 12, |
| "max_steps": 250, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 250, |
| "save_steps": 25, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
