| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 11148, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9551489056332974e-05, | |
| "loss": 2.3375, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.910297811266595e-05, | |
| "loss": 1.5119, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.8654467168998925e-05, | |
| "loss": 1.3999, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.82059562253319e-05, | |
| "loss": 1.2924, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.7757445281664872e-05, | |
| "loss": 1.2685, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.7308934337997848e-05, | |
| "loss": 1.2121, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.6860423394330823e-05, | |
| "loss": 1.2076, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.64119124506638e-05, | |
| "loss": 1.1561, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.596340150699677e-05, | |
| "loss": 1.1587, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.5514890563329747e-05, | |
| "loss": 1.0862, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.506637961966272e-05, | |
| "loss": 1.1046, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 77.8713339640492, | |
| "eval_f1": 86.11994528825018, | |
| "step": 5574 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.4617868675995694e-05, | |
| "loss": 0.8899, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.416935773232867e-05, | |
| "loss": 0.8613, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.3720846788661644e-05, | |
| "loss": 0.849, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 1.3272335844994619e-05, | |
| "loss": 0.8372, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 1.2823824901327593e-05, | |
| "loss": 0.8675, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.2375313957660568e-05, | |
| "loss": 0.8772, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.1926803013993542e-05, | |
| "loss": 0.8653, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.1478292070326518e-05, | |
| "loss": 0.8589, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.1029781126659492e-05, | |
| "loss": 0.8644, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 1.0581270182992467e-05, | |
| "loss": 0.8288, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.0132759239325441e-05, | |
| "loss": 0.8487, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 79.52696310312204, | |
| "eval_f1": 87.21705377119197, | |
| "step": 11148 | |
| } | |
| ], | |
| "max_steps": 22296, | |
| "num_train_epochs": 4, | |
| "total_flos": 3.4955234174304256e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |