| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 12.1569, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0485, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002, | |
| "loss": 5.1593, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.116, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2684, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0943, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0002, | |
| "loss": 29.8504, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0173, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6532, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6314, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0475, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9073, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0704, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0002, | |
| "loss": 21.957, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002, | |
| "loss": 1247.1927, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0146, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6174, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1367, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0002, | |
| "loss": 280.2191, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5996, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0002, | |
| "loss": 89.4102, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0508, | |
| "step": 2500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2500, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 2.38468349952e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |