| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5224215246636771, |
| "eval_steps": 500, |
| "global_step": 233, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11210762331838565, |
| "grad_norm": 1.2583035230636597, |
| "learning_rate": 0.00015793991416309012, |
| "loss": 0.5625, |
| "mean_token_accuracy": 0.8795297014713287, |
| "num_tokens": 52890.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2242152466367713, |
| "grad_norm": 1.6966702938079834, |
| "learning_rate": 0.00011502145922746782, |
| "loss": 0.2627, |
| "mean_token_accuracy": 0.9433401429653168, |
| "num_tokens": 106911.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.336322869955157, |
| "grad_norm": 0.9325768947601318, |
| "learning_rate": 7.21030042918455e-05, |
| "loss": 0.2004, |
| "mean_token_accuracy": 0.9534589314460754, |
| "num_tokens": 160877.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.4484304932735426, |
| "grad_norm": 0.9472081065177917, |
| "learning_rate": 2.9184549356223178e-05, |
| "loss": 0.1618, |
| "mean_token_accuracy": 0.9602310359477997, |
| "num_tokens": 213294.0, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 233, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.3668023634886656e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
