| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11555683952043912, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.12320374168921262, |
| "epoch": 0.023111367904087823, |
| "grad_norm": 0.28571996092796326, |
| "learning_rate": 9.484363707663442e-05, |
| "loss": 0.21908848285675048, |
| "mean_token_accuracy": 0.9422738157212734, |
| "num_tokens": 91409.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.16207303220871835, |
| "epoch": 0.046222735808175645, |
| "grad_norm": 0.28375348448753357, |
| "learning_rate": 7.211443451095007e-05, |
| "loss": 0.12006372213363647, |
| "mean_token_accuracy": 0.9627217166125774, |
| "num_tokens": 186627.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.10619779330445453, |
| "epoch": 0.06933410371226346, |
| "grad_norm": 0.20916548371315002, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.09217150807380677, |
| "mean_token_accuracy": 0.9706527393311262, |
| "num_tokens": 276604.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.0921842057723552, |
| "epoch": 0.09244547161635129, |
| "grad_norm": 0.22539521753787994, |
| "learning_rate": 1.2408009626051137e-05, |
| "loss": 0.10293728113174438, |
| "mean_token_accuracy": 0.9714588195085525, |
| "num_tokens": 368108.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.09835841043386609, |
| "epoch": 0.11555683952043912, |
| "grad_norm": 0.21315635740756989, |
| "learning_rate": 1.0705383806982606e-07, |
| "loss": 0.09969227313995362, |
| "mean_token_accuracy": 0.9657726161181927, |
| "num_tokens": 457334.0, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.962335904050995e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
