| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 3396, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.4416961130742049, |
| "grad_norm": 7.1157612800598145, |
| "learning_rate": 4.99e-05, |
| "loss": 1.0279, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8833922261484098, |
| "grad_norm": 7.284318923950195, |
| "learning_rate": 4.13846685082873e-05, |
| "loss": 0.8107, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.325088339222615, |
| "grad_norm": 4.767754554748535, |
| "learning_rate": 3.275207182320442e-05, |
| "loss": 0.696, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.76678445229682, |
| "grad_norm": 7.098174571990967, |
| "learning_rate": 2.4119475138121546e-05, |
| "loss": 0.6697, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.208480565371025, |
| "grad_norm": 5.806668758392334, |
| "learning_rate": 1.5486878453038674e-05, |
| "loss": 0.5664, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.65017667844523, |
| "grad_norm": 4.647528171539307, |
| "learning_rate": 6.8542817679558015e-06, |
| "loss": 0.4623, |
| "step": 3000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3396, |
| "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": 3574196847230976.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
