| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 32.25, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 18.015, | |
| "mean_token_accuracy": 0.05287854002090171, | |
| "num_tokens": 368640.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.296875, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 8.2945, | |
| "mean_token_accuracy": 0.10326525047421456, | |
| "num_tokens": 737280.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 0.00011800505538843798, | |
| "loss": 7.1982, | |
| "mean_token_accuracy": 0.13623093739151954, | |
| "num_tokens": 1105920.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.0390625, | |
| "learning_rate": 3.473983337147118e-05, | |
| "loss": 6.893, | |
| "mean_token_accuracy": 0.15668845251202584, | |
| "num_tokens": 1474560.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 8.201139886109264e-08, | |
| "loss": 6.8184, | |
| "mean_token_accuracy": 0.16309368163347243, | |
| "num_tokens": 1843200.0, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 100, | |
| "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": 606641533747200.0, | |
| "train_batch_size": 72, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |