| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "global_step": 102, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00010909090909090909, |
| "loss": 0.2103, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.0001978021978021978, |
| "loss": 0.1736, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00018461538461538463, |
| "loss": 0.1319, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00017142857142857143, |
| "loss": 0.1167, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.00015824175824175824, |
| "loss": 0.1057, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00014505494505494506, |
| "loss": 0.0955, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00013186813186813188, |
| "loss": 0.0915, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00011868131868131869, |
| "loss": 0.0833, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.0001054945054945055, |
| "loss": 0.0807, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.0751, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 7.912087912087912e-05, |
| "loss": 0.0723, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 6.593406593406594e-05, |
| "loss": 0.0655, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 5.274725274725275e-05, |
| "loss": 0.0635, |
| "step": 78 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 3.956043956043956e-05, |
| "loss": 0.0605, |
| "step": 84 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 2.6373626373626374e-05, |
| "loss": 0.0592, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 1.3186813186813187e-05, |
| "loss": 0.0564, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 0.0, |
| "loss": 0.0547, |
| "step": 102 |
| } |
| ], |
| "max_steps": 102, |
| "num_train_epochs": 3, |
| "total_flos": 191627834425344.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
