| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.4065102195306585, | |
| "eval_steps": 500, | |
| "global_step": 9000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.8950710741021115e-05, | |
| "loss": 2.4415, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.78993186979561e-05, | |
| "loss": 1.7099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.684792665489108e-05, | |
| "loss": 1.4997, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.579653461182606e-05, | |
| "loss": 1.3625, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.4745142568761036e-05, | |
| "loss": 1.2689, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.3693750525696025e-05, | |
| "loss": 1.0546, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 4.264235848263101e-05, | |
| "loss": 0.9711, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 4.159096643956599e-05, | |
| "loss": 0.9487, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.05416771805871e-05, | |
| "loss": 0.9202, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.949238792160821e-05, | |
| "loss": 0.8953, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.844309866262932e-05, | |
| "loss": 0.6436, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3.73917066195643e-05, | |
| "loss": 0.6361, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 3.6340314576499284e-05, | |
| "loss": 0.6473, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 3.52910253175204e-05, | |
| "loss": 0.6383, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.423963327445538e-05, | |
| "loss": 0.6312, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.318824123139036e-05, | |
| "loss": 0.5965, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.213684918832535e-05, | |
| "loss": 0.4106, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 3.1085457145260324e-05, | |
| "loss": 0.4265, | |
| "step": 9000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 23778, | |
| "num_train_epochs": 9, | |
| "save_steps": 1000, | |
| "total_flos": 4.841971331668378e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |