| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 21, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "entropy": 0.5876428335905075, | |
| "epoch": 0.8, | |
| "grad_norm": 26.097728729248047, | |
| "learning_rate": 0.0001, | |
| "loss": 6.2434, | |
| "mean_token_accuracy": 0.48119242638349535, | |
| "num_tokens": 15116.0, | |
| "step": 5 | |
| }, | |
| { | |
| "entropy": 1.4853135066873886, | |
| "epoch": 1.48, | |
| "grad_norm": 5.605739593505859, | |
| "learning_rate": 9.371733080722911e-05, | |
| "loss": 2.4627, | |
| "mean_token_accuracy": 0.6227525683010325, | |
| "num_tokens": 27973.0, | |
| "step": 10 | |
| }, | |
| { | |
| "entropy": 1.726570823613335, | |
| "epoch": 2.16, | |
| "grad_norm": 3.4330334663391113, | |
| "learning_rate": 7.644820051634812e-05, | |
| "loss": 1.4966, | |
| "mean_token_accuracy": 0.7552376985549927, | |
| "num_tokens": 40761.0, | |
| "step": 15 | |
| }, | |
| { | |
| "entropy": 1.1423663020133972, | |
| "epoch": 2.96, | |
| "grad_norm": 2.336728811264038, | |
| "learning_rate": 5.2532458441935636e-05, | |
| "loss": 0.9415, | |
| "mean_token_accuracy": 0.8482233583927155, | |
| "num_tokens": 55844.0, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 35, | |
| "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": 35657548827648.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |