| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 14649, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00025904995904995904, |
| "loss": 5.6935, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00021809991809991808, |
| "loss": 5.9538, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00017714987714987715, |
| "loss": 5.9526, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0001361998361998362, |
| "loss": 5.9532, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 9.524979524979524e-05, |
| "loss": 5.9517, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 5.429975429975429e-05, |
| "loss": 5.9514, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 1.3349713349713349e-05, |
| "loss": 5.9512, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.0, |
| "loss": 5.9513, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.0, |
| "loss": 5.9513, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.0, |
| "loss": 5.9516, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.0, |
| "loss": 5.9515, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0, |
| "loss": 5.9514, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.0, |
| "loss": 5.9518, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.0, |
| "loss": 5.9514, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.0, |
| "loss": 5.9513, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.0, |
| "loss": 5.9514, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0, |
| "loss": 5.9516, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.0, |
| "loss": 5.9515, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.0, |
| "loss": 5.9512, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 0.0, |
| "loss": 5.9512, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 0.0, |
| "loss": 5.9517, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 0.0, |
| "loss": 5.9515, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 0.0, |
| "loss": 5.9518, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 0.0, |
| "loss": 5.9516, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 0.0, |
| "loss": 5.9517, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 0.0, |
| "loss": 5.9511, |
| "step": 13000 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 0.0, |
| "loss": 5.9508, |
| "step": 13500 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 0.0, |
| "loss": 5.9514, |
| "step": 14000 |
| }, |
| { |
| "epoch": 2.97, |
| "learning_rate": 0.0, |
| "loss": 5.9511, |
| "step": 14500 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 14649, |
| "total_flos": 9.185626186297344e+16, |
| "train_loss": 5.942797746566532, |
| "train_runtime": 17726.9284, |
| "train_samples_per_second": 26.441, |
| "train_steps_per_second": 0.826 |
| } |
| ], |
| "max_steps": 14649, |
| "num_train_epochs": 3, |
| "total_flos": 9.185626186297344e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
