| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 387, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8521, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3037, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2252, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1315, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1229, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0858, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0459, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0339, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0291, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9882, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9745, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0002, | |
| "loss": 0.964, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9044, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0002, | |
| "loss": 0.853, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8678, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8541, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002, | |
| "loss": 0.819, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7849, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7699, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7246, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6986, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6825, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6821, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6454, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6072, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5905, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0002, | |
| "loss": 0.581, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0002, | |
| "loss": 0.565, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.555, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5141, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4724, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0002, | |
| "loss": 0.47, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4308, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4407, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4079, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4103, | |
| "step": 380 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 579, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.526439877419991e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |