| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 16235, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9076070218663384e-05, | |
| "loss": 2.2393, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.8152140437326767e-05, | |
| "loss": 1.4831, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.7228210655990143e-05, | |
| "loss": 1.3501, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.6304280874653526e-05, | |
| "loss": 1.3197, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.538035109331691e-05, | |
| "loss": 1.2581, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.4456421311980292e-05, | |
| "loss": 1.2174, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.3532491530643672e-05, | |
| "loss": 1.1655, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.2608561749307052e-05, | |
| "loss": 1.1402, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.1684631967970435e-05, | |
| "loss": 1.0944, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.0760702186633818e-05, | |
| "loss": 1.152, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.9836772405297198e-05, | |
| "loss": 1.1138, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.8912842623960577e-05, | |
| "loss": 1.0516, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.798891284262396e-05, | |
| "loss": 1.0912, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.7064983061287344e-05, | |
| "loss": 1.0322, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.6141053279950723e-05, | |
| "loss": 0.9863, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.5217123498614105e-05, | |
| "loss": 0.9888, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.4293193717277488e-05, | |
| "loss": 1.0046, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.3369263935940867e-05, | |
| "loss": 0.9813, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.244533415460425e-05, | |
| "loss": 0.9854, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.1521404373267632e-05, | |
| "loss": 0.9457, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.0597474591931013e-05, | |
| "loss": 0.931, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.673544810594396e-06, | |
| "loss": 0.8925, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.749615029257776e-06, | |
| "loss": 0.9469, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.82568524792116e-06, | |
| "loss": 0.9721, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.90175546658454e-06, | |
| "loss": 0.9377, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5.977825685247921e-06, | |
| "loss": 0.8359, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.0538959039113025e-06, | |
| "loss": 0.9046, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.129966122574684e-06, | |
| "loss": 0.8857, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.206036341238066e-06, | |
| "loss": 0.8674, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.2821065599014475e-06, | |
| "loss": 0.8429, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3581767785648291e-06, | |
| "loss": 0.9049, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.3424699722821066e-07, | |
| "loss": 0.8825, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 16235, | |
| "total_flos": 4.523174534460211e+16, | |
| "train_loss": 1.0714931627842768, | |
| "train_runtime": 16914.7753, | |
| "train_samples_per_second": 5.759, | |
| "train_steps_per_second": 0.96 | |
| } | |
| ], | |
| "max_steps": 16235, | |
| "num_train_epochs": 1, | |
| "total_flos": 4.523174534460211e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |