|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.9216, |
|
"global_step": 75, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2e-05, |
|
"loss": 9.4747, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4e-05, |
|
"loss": 8.5089, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.9315068493150684e-05, |
|
"loss": 7.7975, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.794520547945205e-05, |
|
"loss": 7.2748, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.657534246575342e-05, |
|
"loss": 6.738, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 4.520547945205479e-05, |
|
"loss": 6.4144, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 4.383561643835617e-05, |
|
"loss": 5.924, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.2465753424657536e-05, |
|
"loss": 5.4519, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.1095890410958905e-05, |
|
"loss": 4.9919, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 3.9726027397260274e-05, |
|
"loss": 4.614, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 3.8356164383561644e-05, |
|
"loss": 4.3804, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 3.698630136986301e-05, |
|
"loss": 4.1981, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 3.561643835616438e-05, |
|
"loss": 4.0104, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 3.424657534246575e-05, |
|
"loss": 3.8835, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 3.287671232876712e-05, |
|
"loss": 3.7094, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 3.1506849315068496e-05, |
|
"loss": 3.617, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 3.0136986301369862e-05, |
|
"loss": 3.5407, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 2.8767123287671234e-05, |
|
"loss": 3.4392, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 2.7397260273972603e-05, |
|
"loss": 3.321, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 2.6027397260273973e-05, |
|
"loss": 3.3597, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 2.4657534246575342e-05, |
|
"loss": 3.1786, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 2.328767123287671e-05, |
|
"loss": 3.1039, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 2.1917808219178083e-05, |
|
"loss": 3.0302, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 2.0547945205479453e-05, |
|
"loss": 3.0034, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 1.9178082191780822e-05, |
|
"loss": 2.9383, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 1.780821917808219e-05, |
|
"loss": 2.9056, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 1.643835616438356e-05, |
|
"loss": 2.8352, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 1.5068493150684931e-05, |
|
"loss": 2.802, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 1.3698630136986302e-05, |
|
"loss": 2.7235, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 1.2328767123287671e-05, |
|
"loss": 2.7205, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 1.0958904109589042e-05, |
|
"loss": 2.6843, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 9.589041095890411e-06, |
|
"loss": 2.6673, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 8.21917808219178e-06, |
|
"loss": 2.6858, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 6.849315068493151e-06, |
|
"loss": 2.6202, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 5.479452054794521e-06, |
|
"loss": 2.6411, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 4.10958904109589e-06, |
|
"loss": 2.6201, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 2.7397260273972604e-06, |
|
"loss": 2.6119, |
|
"step": 74 |
|
} |
|
], |
|
"max_steps": 78, |
|
"num_train_epochs": 2, |
|
"total_flos": 1.171669578153984e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|