| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 11250, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04, |
| "learning_rate": 4.7777777777777784e-05, |
| "loss": 0.7338, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 4.555555555555556e-05, |
| "loss": 0.1426, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 4.3333333333333334e-05, |
| "loss": 0.0418, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 4.111111111111111e-05, |
| "loss": 0.0146, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.0263, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 3.6666666666666666e-05, |
| "loss": 0.0448, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 3.444444444444445e-05, |
| "loss": 0.0153, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 3.222222222222223e-05, |
| "loss": 0.0115, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 3e-05, |
| "loss": 0.0194, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.0112, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 2.5555555555555554e-05, |
| "loss": 0.0423, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.0059, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 2.111111111111111e-05, |
| "loss": 0.0053, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 1.888888888888889e-05, |
| "loss": 0.0029, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0145, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 1.4444444444444444e-05, |
| "loss": 0.0017, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 1.2222222222222222e-05, |
| "loss": 0.0021, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 1e-05, |
| "loss": 0.0042, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 7.777777777777777e-06, |
| "loss": 0.0049, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 5.555555555555556e-06, |
| "loss": 0.002, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.0058, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 1.1111111111111112e-06, |
| "loss": 0.0035, |
| "step": 11000 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 11250, |
| "total_flos": 5.753298461184e+16, |
| "train_runtime": 4566.3645, |
| "train_samples_per_second": 2.464 |
| } |
| ], |
| "max_steps": 11250, |
| "num_train_epochs": 1, |
| "total_flos": 5.753298461184e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
