| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 8751, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17, |
| "learning_rate": 4.714318363615587e-05, |
| "loss": 3.0752, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 4.428636727231174e-05, |
| "loss": 1.3251, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 4.142955090846761e-05, |
| "loss": 0.9722, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 3.857273454462347e-05, |
| "loss": 0.923, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 3.571591818077934e-05, |
| "loss": 0.8754, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 3.285910181693521e-05, |
| "loss": 0.7869, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 3.0002285453091078e-05, |
| "loss": 0.5717, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 2.7145469089246944e-05, |
| "loss": 0.5819, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 2.4288652725402813e-05, |
| "loss": 0.568, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 2.143183636155868e-05, |
| "loss": 0.5581, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 1.8575019997714548e-05, |
| "loss": 0.5506, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 1.5718203633870414e-05, |
| "loss": 0.4619, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 1.2861387270026285e-05, |
| "loss": 0.3245, |
| "step": 6500 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 1.0004570906182151e-05, |
| "loss": 0.3176, |
| "step": 7000 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 7.147754542338019e-06, |
| "loss": 0.3069, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 4.290938178493887e-06, |
| "loss": 0.3089, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 1.4341218146497544e-06, |
| "loss": 0.2988, |
| "step": 8500 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 8751, |
| "total_flos": 2.1528253275439104e+16, |
| "train_loss": 0.7404402195692145, |
| "train_runtime": 4141.2406, |
| "train_samples_per_second": 16.905, |
| "train_steps_per_second": 2.113 |
| } |
| ], |
| "max_steps": 8751, |
| "num_train_epochs": 3, |
| "total_flos": 2.1528253275439104e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
