| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9999686534570014, |
| "global_step": 13458, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.0001, |
| "loss": 1.7771, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.0001, |
| "loss": 1.7423, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.0001, |
| "loss": 1.7222, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0001, |
| "loss": 1.7155, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0001, |
| "loss": 1.7066, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0001, |
| "loss": 1.6995, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.0001, |
| "loss": 1.6894, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.0001, |
| "loss": 1.6856, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0001, |
| "loss": 1.6766, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.0001, |
| "loss": 1.6338, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0001, |
| "loss": 1.6337, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.0001, |
| "loss": 1.628, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.0001, |
| "loss": 1.6274, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.0001, |
| "loss": 1.6266, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.0001, |
| "loss": 1.622, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.0001, |
| "loss": 1.623, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.0001, |
| "loss": 1.6207, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 0.0001, |
| "loss": 1.6101, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 0.0001, |
| "loss": 1.5756, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 0.0001, |
| "loss": 1.579, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 0.0001, |
| "loss": 1.5752, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 0.0001, |
| "loss": 1.5687, |
| "step": 11000 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 0.0001, |
| "loss": 1.5768, |
| "step": 11500 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 0.0001, |
| "loss": 1.5722, |
| "step": 12000 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 0.0001, |
| "loss": 1.5782, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 0.0001, |
| "loss": 1.5727, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 13458, |
| "total_flos": 9.355626883376916e+17, |
| "train_loss": 1.63751159477489, |
| "train_runtime": 129707.2979, |
| "train_samples_per_second": 6.641, |
| "train_steps_per_second": 0.104 |
| } |
| ], |
| "max_steps": 13458, |
| "num_train_epochs": 3, |
| "total_flos": 9.355626883376916e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
