| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.0002, |
| "loss": 1.8802, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 1.8259, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00019458172417006347, |
| "loss": 1.3073, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 1.144, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 0.9936, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00016772815716257412, |
| "loss": 0.9241, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00015469481581224272, |
| "loss": 0.8818, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00014016954246529696, |
| "loss": 0.8515, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.00012454854871407994, |
| "loss": 0.8175, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 0.797, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 9.174206545276677e-05, |
| "loss": 0.7956, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 7.54514512859201e-05, |
| "loss": 0.763, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 5.983045753470308e-05, |
| "loss": 0.799, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 4.530518418775733e-05, |
| "loss": 0.7313, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 3.227184283742591e-05, |
| "loss": 0.8197, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 2.1085949060360654e-05, |
| "loss": 0.7664, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 1.2052624879351104e-05, |
| "loss": 0.6936, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 5.418275829936537e-06, |
| "loss": 0.7089, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 1.3638696597277679e-06, |
| "loss": 0.6891, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.0, |
| "loss": 0.7192, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 20, |
| "total_flos": 498510692352.0, |
| "train_loss": 0.945431512594223, |
| "train_runtime": 176.9883, |
| "train_samples_per_second": 1.74, |
| "train_steps_per_second": 0.113 |
| } |
| ], |
| "max_steps": 20, |
| "num_train_epochs": 1, |
| "total_flos": 498510692352.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
