| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18127435874195594, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.999549488698767e-05, | |
| "loss": 0.9367, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.998198117163414e-05, | |
| "loss": 0.8539, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.995946372440459e-05, | |
| "loss": 0.8563, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.99279506607906e-05, | |
| "loss": 0.8552, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9887453338385195e-05, | |
| "loss": 0.8377, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.98379863527895e-05, | |
| "loss": 0.8346, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.9779567532352364e-05, | |
| "loss": 0.8338, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.971221793174483e-05, | |
| "loss": 0.8176, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.9635961824371865e-05, | |
| "loss": 0.8297, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.9550826693624e-05, | |
| "loss": 0.8337, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 16548, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "total_flos": 9.021600914767086e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |