| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10714285714285714, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017857142857142856, | |
| "grad_norm": 1.7371450662612915, | |
| "learning_rate": 0.00011904761904761905, | |
| "loss": 5.7811, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 10.240315437316895, | |
| "learning_rate": 0.0001988217967599411, | |
| "loss": 4.4962, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05357142857142857, | |
| "grad_norm": 2.346067190170288, | |
| "learning_rate": 0.000195139911634757, | |
| "loss": 4.1036, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 2.3059897422790527, | |
| "learning_rate": 0.00019145802650957292, | |
| "loss": 3.8267, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 2.589801549911499, | |
| "learning_rate": 0.00018777614138438883, | |
| "loss": 3.9222, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 2.9276719093322754, | |
| "learning_rate": 0.0001840942562592047, | |
| "loss": 3.7279, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 909414236160000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |