| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.896, |
| "eval_steps": 500, |
| "global_step": 7, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.128, |
| "grad_norm": 8.980382327939969, |
| "learning_rate": 2e-05, |
| "loss": 0.8812, |
| "mean_token_accuracy": 0.7794624902307987, |
| "num_tokens": 199571.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 4.024367259166998, |
| "learning_rate": 1.7142857142857142e-05, |
| "loss": 0.7072, |
| "mean_token_accuracy": 0.8019827287644148, |
| "num_tokens": 400126.0, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.384, |
| "grad_norm": 4.267673370597383, |
| "learning_rate": 1.4285714285714287e-05, |
| "loss": 0.626, |
| "mean_token_accuracy": 0.8145374022424221, |
| "num_tokens": 602165.0, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 2.8984998787251763, |
| "learning_rate": 1.1428571428571429e-05, |
| "loss": 0.5865, |
| "mean_token_accuracy": 0.8273635869845748, |
| "num_tokens": 793346.0, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 2.404083692706254, |
| "learning_rate": 8.571428571428571e-06, |
| "loss": 0.5124, |
| "mean_token_accuracy": 0.8430413184687495, |
| "num_tokens": 985959.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 1.4038257018173572, |
| "learning_rate": 5.7142857142857145e-06, |
| "loss": 0.5255, |
| "mean_token_accuracy": 0.8419803585857153, |
| "num_tokens": 1195075.0, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.896, |
| "grad_norm": 1.0636640599679472, |
| "learning_rate": 2.8571428571428573e-06, |
| "loss": 0.4919, |
| "mean_token_accuracy": 0.8463326394557953, |
| "num_tokens": 1408042.0, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.896, |
| "step": 7, |
| "total_flos": 2812687974400.0, |
| "train_loss": 0.6186651417187282, |
| "train_runtime": 1162.3265, |
| "train_samples_per_second": 0.86, |
| "train_steps_per_second": 0.006 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 7, |
| "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": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2812687974400.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
