| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 1.043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9941379571543597e-05, | |
| "loss": 1.0156, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.976620555710087e-05, | |
| "loss": 1.0234, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 1.9476531711828027e-05, | |
| "loss": 0.959, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.9075754196709574e-05, | |
| "loss": 0.8301, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8568571761675893e-05, | |
| "loss": 0.9688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.796093065705644e-05, | |
| "loss": 0.9766, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.725995491923131e-05, | |
| "loss": 0.9648, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.647386284781828e-05, | |
| "loss": 0.8242, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.5611870653623826e-05, | |
| "loss": 0.9551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.4684084406997903e-05, | |
| "loss": 0.9336, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.3701381553399147e-05, | |
| "loss": 0.9395, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.2675283385292212e-05, | |
| "loss": 0.9629, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.161781996552765e-05, | |
| "loss": 0.9258, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.0541389085854177e-05, | |
| "loss": 0.9297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.458610914145826e-06, | |
| "loss": 0.9062, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 8.382180034472353e-06, | |
| "loss": 0.9121, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.324716614707794e-06, | |
| "loss": 0.9453, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 6.298618446600856e-06, | |
| "loss": 0.9375, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 5.3159155930021e-06, | |
| "loss": 0.9238, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.388129346376177e-06, | |
| "loss": 0.877, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.5261371521817247e-06, | |
| "loss": 0.8945, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 2.740045080768694e-06, | |
| "loss": 0.9004, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2.0390693429435626e-06, | |
| "loss": 0.9102, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.4314282383241097e-06, | |
| "loss": 0.877, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.242458032904311e-07, | |
| "loss": 0.8867, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.234682881719766e-07, | |
| "loss": 0.8848, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.3379444289913344e-07, | |
| "loss": 0.8828, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.862042845640403e-08, | |
| "loss": 0.9258, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.9492, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 30, | |
| "total_flos": 9782320777134080.0, | |
| "train_loss": 0.9288411458333333, | |
| "train_runtime": 387.3517, | |
| "train_samples_per_second": 2.478, | |
| "train_steps_per_second": 0.077 | |
| } | |
| ], | |
| "max_steps": 30, | |
| "num_train_epochs": 1, | |
| "total_flos": 9782320777134080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |