| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 74, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.0259285002946854, |
| "epoch": 0.273972602739726, |
| "grad_norm": 3.722426652908325, |
| "learning_rate": 9e-06, |
| "loss": 1.0839, |
| "mean_token_accuracy": 0.761720848083496, |
| "num_tokens": 584826.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.9608730539679528, |
| "epoch": 0.547945205479452, |
| "grad_norm": 0.8895509839057922, |
| "learning_rate": 9.934881598487478e-06, |
| "loss": 0.9788, |
| "mean_token_accuracy": 0.7810790002346039, |
| "num_tokens": 1174174.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.9163148060441018, |
| "epoch": 0.821917808219178, |
| "grad_norm": 0.802199125289917, |
| "learning_rate": 9.711957702320176e-06, |
| "loss": 0.9307, |
| "mean_token_accuracy": 0.7890266820788383, |
| "num_tokens": 1762094.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.8868917273847681, |
| "epoch": 1.0821917808219177, |
| "grad_norm": 0.7817137837409973, |
| "learning_rate": 9.337587608588588e-06, |
| "loss": 0.8963, |
| "mean_token_accuracy": 0.7947045470538893, |
| "num_tokens": 2322415.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.8300882771611213, |
| "epoch": 1.356164383561644, |
| "grad_norm": 0.6832650899887085, |
| "learning_rate": 8.823803880137993e-06, |
| "loss": 0.8464, |
| "mean_token_accuracy": 0.8045218542218209, |
| "num_tokens": 2910028.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.8211456254124642, |
| "epoch": 1.6301369863013697, |
| "grad_norm": 0.6951064467430115, |
| "learning_rate": 8.18711994874345e-06, |
| "loss": 0.8352, |
| "mean_token_accuracy": 0.8072828114032745, |
| "num_tokens": 3495988.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.8173969030380249, |
| "epoch": 1.904109589041096, |
| "grad_norm": 0.762572705745697, |
| "learning_rate": 7.447999359825263e-06, |
| "loss": 0.8315, |
| "mean_token_accuracy": 0.8067627891898155, |
| "num_tokens": 4083547.0, |
| "step": 70 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 185, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "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": 2.831815282786304e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
