| { |
| "best_metric": 1.870347023010254, |
| "best_model_checkpoint": "output/v-x-v-prince/checkpoint-43", |
| "epoch": 1.0, |
| "global_step": 43, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0001326735050590528, |
| "loss": 2.371, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.00011969137173622343, |
| "loss": 2.1954, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 9.99668233786982e-05, |
| "loss": 1.9526, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 7.61028648947222e-05, |
| "loss": 2.0134, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 5.1248769967930697e-05, |
| "loss": 1.8518, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 2.8684478392724447e-05, |
| "loss": 1.8567, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 1.1387749692754382e-05, |
| "loss": 1.7488, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 1.6411947996634035e-06, |
| "loss": 1.8109, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.870347023010254, |
| "eval_runtime": 3.043, |
| "eval_samples_per_second": 21.032, |
| "eval_steps_per_second": 2.629, |
| "step": 43 |
| } |
| ], |
| "max_steps": 43, |
| "num_train_epochs": 1, |
| "total_flos": 44288999424000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
