| { |
| "best_metric": 2.78603196144104, |
| "best_model_checkpoint": "output/queen/checkpoint-68", |
| "epoch": 1.0, |
| "global_step": 68, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00013537785052914354, |
| "loss": 3.396, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0001300082017869573, |
| "loss": 3.2987, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.0001213763104094255, |
| "loss": 2.8576, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.000109940736055617, |
| "loss": 2.9968, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 9.630898093421199e-05, |
| "loss": 2.9324, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 8.120521692221673e-05, |
| "loss": 2.9931, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 6.543181473690228e-05, |
| "loss": 2.8919, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 4.982671888105512e-05, |
| "loss": 2.7977, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 3.5218932770313667e-05, |
| "loss": 2.9689, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 2.2384478845846175e-05, |
| "loss": 2.756, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.200517324255647e-05, |
| "loss": 2.8716, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 4.6324050628611986e-06, |
| "loss": 2.9236, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 6.578444419609313e-07, |
| "loss": 2.8184, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.78603196144104, |
| "eval_runtime": 4.3884, |
| "eval_samples_per_second": 21.192, |
| "eval_steps_per_second": 2.734, |
| "step": 68 |
| } |
| ], |
| "max_steps": 68, |
| "num_train_epochs": 1, |
| "total_flos": 70679494656000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
