| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9979978438318189, |
| "eval_steps": 500, |
| "global_step": 405, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 9.523809523809524e-05, |
| "loss": 2.2532, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00019047619047619048, |
| "loss": 2.0208, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019972904566786903, |
| "loss": 1.4376, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019879429836063226, |
| "loss": 1.1412, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00019719866448212795, |
| "loss": 1.0641, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019495281805930367, |
| "loss": 1.0379, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.0001920717827298248, |
| "loss": 1.0215, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00018857483124112907, |
| "loss": 1.0256, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00018448535652497073, |
| "loss": 1.016, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00017983071520990315, |
| "loss": 0.9956, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00017464204461852738, |
| "loss": 0.9963, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0001689540544737067, |
| "loss": 1.0188, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00016280479470713344, |
| "loss": 0.9989, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00015623540092349732, |
| "loss": 0.9916, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00014928981922297842, |
| "loss": 0.9849, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00014201451222287025, |
| "loss": 0.9778, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00013445814824490805, |
| "loss": 0.9728, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00012667127574748986, |
| "loss": 0.9669, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.0001187059851806832, |
| "loss": 0.9786, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00011061556052604578, |
| "loss": 0.9766, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00010245412285229124, |
| "loss": 0.9884, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 9.427626827124317e-05, |
| "loss": 0.9762, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 8.613670271597733e-05, |
| "loss": 0.9811, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 7.808987598431303e-05, |
| "loss": 0.9803, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 7.018961749572604e-05, |
| "loss": 0.9752, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 6.248877619829619e-05, |
| "loss": 0.9642, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 5.503886703453933e-05, |
| "loss": 0.9635, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 4.7889726331097686e-05, |
| "loss": 0.9708, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 4.1089178417567164e-05, |
| "loss": 0.9692, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 3.468271570462235e-05, |
| "loss": 0.9752, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 2.8713194361562036e-05, |
| "loss": 0.9734, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 2.3220547629048796e-05, |
| "loss": 0.9758, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.824151868484164e-05, |
| "loss": 0.9668, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 1.3809414849522584e-05, |
| "loss": 0.9736, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 9.953884776463652e-06, |
| "loss": 0.9818, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 6.700720116526116e-06, |
| "loss": 0.9776, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 4.071682984260638e-06, |
| "loss": 0.9626, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 2.0843603797766287e-06, |
| "loss": 0.9745, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 7.520465401290033e-07, |
| "loss": 0.9609, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 8.365400723512328e-08, |
| "loss": 0.9675, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 405, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "total_flos": 2.0624848885598822e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
