| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.08343360002810395, |
| "eval_steps": 1000, |
| "global_step": 9500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 8.782484213484626e-06, |
| "grad_norm": 14.945822715759277, |
| "learning_rate": 3e-06, |
| "loss": 2.5517, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.008782484213484626, |
| "grad_norm": 12.854056358337402, |
| "learning_rate": 2.9736788948121867e-06, |
| "loss": 1.8558, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.017564968426969252, |
| "grad_norm": 25.257680892944336, |
| "learning_rate": 2.9473314421717326e-06, |
| "loss": 1.4921, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.026347452640453878, |
| "grad_norm": 20.81689453125, |
| "learning_rate": 2.920983989531279e-06, |
| "loss": 1.3421, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.035129936853938504, |
| "grad_norm": 15.642374038696289, |
| "learning_rate": 2.8946365368908247e-06, |
| "loss": 1.2323, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.04391242106742313, |
| "grad_norm": 18.790782928466797, |
| "learning_rate": 2.868289084250371e-06, |
| "loss": 1.1605, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.052694905280907756, |
| "grad_norm": 21.282241821289062, |
| "learning_rate": 2.8419416316099173e-06, |
| "loss": 1.1584, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.06147738949439238, |
| "grad_norm": 15.543569564819336, |
| "learning_rate": 2.8155941789694636e-06, |
| "loss": 1.0822, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.07025987370787701, |
| "grad_norm": 18.986188888549805, |
| "learning_rate": 2.7892467263290094e-06, |
| "loss": 1.0594, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.07904235792136163, |
| "grad_norm": 17.61521339416504, |
| "learning_rate": 2.7628992736885557e-06, |
| "loss": 1.0399, |
| "step": 9000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 113863, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "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": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
