| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 7.461538461538462, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15, |
| "learning_rate": 5.454545454545454e-05, |
| "loss": 0.8622, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00010909090909090908, |
| "loss": 0.8607, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.0001636363636363636, |
| "loss": 0.8091, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.00021818181818181816, |
| "loss": 0.738, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.0002727272727272727, |
| "loss": 0.6651, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.0002967741935483871, |
| "loss": 0.5799, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 0.00029032258064516127, |
| "loss": 0.4795, |
| "step": 14 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 0.00028387096774193545, |
| "loss": 0.4095, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 0.0002774193548387096, |
| "loss": 0.2854, |
| "step": 18 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 0.00027096774193548386, |
| "loss": 0.2146, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 0.00026451612903225804, |
| "loss": 0.176, |
| "step": 22 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 0.0002580645161290322, |
| "loss": 0.1498, |
| "step": 24 |
| }, |
| { |
| "epoch": 4.15, |
| "learning_rate": 0.00025161290322580645, |
| "loss": 0.1382, |
| "step": 26 |
| }, |
| { |
| "epoch": 4.31, |
| "learning_rate": 0.0002451612903225806, |
| "loss": 0.1273, |
| "step": 28 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 0.0002387096774193548, |
| "loss": 0.1222, |
| "step": 30 |
| }, |
| { |
| "epoch": 5.15, |
| "learning_rate": 0.000232258064516129, |
| "loss": 0.1074, |
| "step": 32 |
| }, |
| { |
| "epoch": 5.31, |
| "learning_rate": 0.00022580645161290321, |
| "loss": 0.1078, |
| "step": 34 |
| }, |
| { |
| "epoch": 5.46, |
| "learning_rate": 0.0002193548387096774, |
| "loss": 0.1087, |
| "step": 36 |
| }, |
| { |
| "epoch": 6.15, |
| "learning_rate": 0.0002129032258064516, |
| "loss": 0.0975, |
| "step": 38 |
| }, |
| { |
| "epoch": 6.31, |
| "learning_rate": 0.0002064516129032258, |
| "loss": 0.0958, |
| "step": 40 |
| }, |
| { |
| "epoch": 6.46, |
| "learning_rate": 0.00019999999999999998, |
| "loss": 0.0843, |
| "step": 42 |
| }, |
| { |
| "epoch": 7.15, |
| "learning_rate": 0.00019354838709677416, |
| "loss": 0.0783, |
| "step": 44 |
| }, |
| { |
| "epoch": 7.31, |
| "learning_rate": 0.00018709677419354837, |
| "loss": 0.0781, |
| "step": 46 |
| }, |
| { |
| "epoch": 7.46, |
| "learning_rate": 0.00018064516129032257, |
| "loss": 0.079, |
| "step": 48 |
| } |
| ], |
| "max_steps": 104, |
| "num_train_epochs": 8, |
| "total_flos": 3984531891683328.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
