| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6699507389162561, |
| "eval_steps": 500, |
| "global_step": 136, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0, |
| "learning_rate": 1.9998802517966852e-05, |
| "loss": 1.6867, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 1.997007728639956e-05, |
| "loss": 1.6643, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 1.9880488219356086e-05, |
| "loss": 1.6033, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 1.973176894846855e-05, |
| "loss": 1.5009, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 1.9524809490566878e-05, |
| "loss": 1.4372, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 1.926084840336821e-05, |
| "loss": 1.3919, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 1.894146537327533e-05, |
| "loss": 1.3516, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 1.8568571761675893e-05, |
| "loss": 1.3139, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 1.814439916631857e-05, |
| "loss": 1.3003, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 1.7671486066220965e-05, |
| "loss": 1.2773, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 1.7152662630033506e-05, |
| "loss": 1.2509, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 1.659103377877423e-05, |
| "loss": 1.2446, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 1.598996060429634e-05, |
| "loss": 1.2166, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.5353040254690396e-05, |
| "loss": 1.2083, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 1.4684084406997903e-05, |
| "loss": 1.1924, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 1.3987096456067236e-05, |
| "loss": 1.1791, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 1.3266247556066122e-05, |
| "loss": 1.1585, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 1.252585165803135e-05, |
| "loss": 1.1669, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 1.1770339692844484e-05, |
| "loss": 1.1496, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 1.1004233054136726e-05, |
| "loss": 1.1544, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 1.0232116539815558e-05, |
| "loss": 1.1439, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 9.458610914145826e-06, |
| "loss": 1.1387, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 8.688345254588579e-06, |
| "loss": 1.1402, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 7.92592924888925e-06, |
| "loss": 1.1356, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 7.175925608204428e-06, |
| "loss": 1.1331, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 6.442822761362015e-06, |
| "loss": 1.1302, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 5.731007993667155e-06, |
| "loss": 1.1232, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 5.044741191005908e-06, |
| "loss": 1.1212, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.67, |
| "eval_loss": 1.1265710592269897, |
| "eval_runtime": 1525.6654, |
| "eval_samples_per_second": 15.147, |
| "eval_steps_per_second": 0.947, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.67, |
| "step": 136, |
| "total_flos": 5.175783400144896e+16, |
| "train_loss": 1.253584722385687, |
| "train_runtime": 48775.3998, |
| "train_samples_per_second": 4.262, |
| "train_steps_per_second": 0.004 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 203, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "total_flos": 5.175783400144896e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
