| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.26907036189963673, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.991071065046783e-05, | |
| "loss": 3.0435, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9643480408906496e-05, | |
| "loss": 0.0382, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.920021814047156e-05, | |
| "loss": 0.0227, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.858409013313266e-05, | |
| "loss": 0.0258, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7799497480410125e-05, | |
| "loss": 0.0256, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.685204464371269e-05, | |
| "loss": 0.0312, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.574849941884044e-05, | |
| "loss": 0.0212, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.449674459261804e-05, | |
| "loss": 0.0271, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.310572163498205e-05, | |
| "loss": 0.0203, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.158536682873821e-05, | |
| "loss": 0.0172, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3716, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 8.230715481076531e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |