sharp_50 / trainer_state.json
eqhylxx's picture
first commit
120fa11
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.984,
"eval_steps": 500,
"global_step": 62,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 3.244,
"step": 1
},
{
"epoch": 0.06,
"learning_rate": 2e-05,
"loss": 2.8814,
"step": 2
},
{
"epoch": 0.1,
"learning_rate": 1.9986295347545738e-05,
"loss": 3.0403,
"step": 3
},
{
"epoch": 0.13,
"learning_rate": 1.9945218953682736e-05,
"loss": 2.6799,
"step": 4
},
{
"epoch": 0.16,
"learning_rate": 1.9876883405951378e-05,
"loss": 2.6526,
"step": 5
},
{
"epoch": 0.19,
"learning_rate": 1.9781476007338058e-05,
"loss": 2.5161,
"step": 6
},
{
"epoch": 0.22,
"learning_rate": 1.9659258262890683e-05,
"loss": 2.4145,
"step": 7
},
{
"epoch": 0.26,
"learning_rate": 1.9510565162951538e-05,
"loss": 2.3619,
"step": 8
},
{
"epoch": 0.29,
"learning_rate": 1.9335804264972018e-05,
"loss": 2.4374,
"step": 9
},
{
"epoch": 0.32,
"learning_rate": 1.913545457642601e-05,
"loss": 2.2143,
"step": 10
},
{
"epoch": 0.35,
"learning_rate": 1.891006524188368e-05,
"loss": 2.2496,
"step": 11
},
{
"epoch": 0.38,
"learning_rate": 1.866025403784439e-05,
"loss": 2.1492,
"step": 12
},
{
"epoch": 0.42,
"learning_rate": 1.8386705679454243e-05,
"loss": 2.0843,
"step": 13
},
{
"epoch": 0.45,
"learning_rate": 1.8090169943749477e-05,
"loss": 2.0363,
"step": 14
},
{
"epoch": 0.48,
"learning_rate": 1.777145961456971e-05,
"loss": 2.1496,
"step": 15
},
{
"epoch": 0.51,
"learning_rate": 1.7431448254773943e-05,
"loss": 2.0326,
"step": 16
},
{
"epoch": 0.54,
"learning_rate": 1.7071067811865477e-05,
"loss": 2.0164,
"step": 17
},
{
"epoch": 0.58,
"learning_rate": 1.6691306063588583e-05,
"loss": 2.0463,
"step": 18
},
{
"epoch": 0.61,
"learning_rate": 1.6293203910498375e-05,
"loss": 1.992,
"step": 19
},
{
"epoch": 0.64,
"learning_rate": 1.5877852522924733e-05,
"loss": 1.957,
"step": 20
},
{
"epoch": 0.67,
"learning_rate": 1.5446390350150272e-05,
"loss": 1.8724,
"step": 21
},
{
"epoch": 0.7,
"learning_rate": 1.5000000000000002e-05,
"loss": 2.0305,
"step": 22
},
{
"epoch": 0.74,
"learning_rate": 1.4539904997395468e-05,
"loss": 1.8814,
"step": 23
},
{
"epoch": 0.77,
"learning_rate": 1.4067366430758004e-05,
"loss": 1.9395,
"step": 24
},
{
"epoch": 0.8,
"learning_rate": 1.3583679495453e-05,
"loss": 1.8587,
"step": 25
},
{
"epoch": 0.83,
"learning_rate": 1.3090169943749475e-05,
"loss": 1.8729,
"step": 26
},
{
"epoch": 0.86,
"learning_rate": 1.2588190451025209e-05,
"loss": 1.8447,
"step": 27
},
{
"epoch": 0.9,
"learning_rate": 1.2079116908177592e-05,
"loss": 1.8578,
"step": 28
},
{
"epoch": 0.93,
"learning_rate": 1.156434465040231e-05,
"loss": 1.7816,
"step": 29
},
{
"epoch": 0.96,
"learning_rate": 1.1045284632676535e-05,
"loss": 1.9164,
"step": 30
},
{
"epoch": 0.99,
"learning_rate": 1.0523359562429441e-05,
"loss": 1.9039,
"step": 31
},
{
"epoch": 1.02,
"learning_rate": 1e-05,
"loss": 1.6931,
"step": 32
},
{
"epoch": 1.06,
"learning_rate": 9.476640437570562e-06,
"loss": 1.7482,
"step": 33
},
{
"epoch": 1.09,
"learning_rate": 8.954715367323468e-06,
"loss": 1.7157,
"step": 34
},
{
"epoch": 1.12,
"learning_rate": 8.43565534959769e-06,
"loss": 1.7507,
"step": 35
},
{
"epoch": 1.15,
"learning_rate": 7.92088309182241e-06,
"loss": 1.7258,
"step": 36
},
{
"epoch": 1.18,
"learning_rate": 7.411809548974792e-06,
"loss": 1.6307,
"step": 37
},
{
"epoch": 1.22,
"learning_rate": 6.909830056250527e-06,
"loss": 1.6894,
"step": 38
},
{
"epoch": 1.25,
"learning_rate": 6.4163205045469975e-06,
"loss": 1.714,
"step": 39
},
{
"epoch": 1.28,
"learning_rate": 5.932633569242e-06,
"loss": 1.6402,
"step": 40
},
{
"epoch": 1.31,
"learning_rate": 5.460095002604533e-06,
"loss": 1.6554,
"step": 41
},
{
"epoch": 1.34,
"learning_rate": 5.000000000000003e-06,
"loss": 1.6722,
"step": 42
},
{
"epoch": 1.38,
"learning_rate": 4.5536096498497295e-06,
"loss": 1.6376,
"step": 43
},
{
"epoch": 1.41,
"learning_rate": 4.12214747707527e-06,
"loss": 1.6696,
"step": 44
},
{
"epoch": 1.44,
"learning_rate": 3.7067960895016277e-06,
"loss": 1.6975,
"step": 45
},
{
"epoch": 1.47,
"learning_rate": 3.308693936411421e-06,
"loss": 1.6124,
"step": 46
},
{
"epoch": 1.5,
"learning_rate": 2.9289321881345257e-06,
"loss": 1.6798,
"step": 47
},
{
"epoch": 1.54,
"learning_rate": 2.5685517452260566e-06,
"loss": 1.5698,
"step": 48
},
{
"epoch": 1.57,
"learning_rate": 2.2285403854302912e-06,
"loss": 1.6288,
"step": 49
},
{
"epoch": 1.6,
"learning_rate": 1.9098300562505266e-06,
"loss": 1.606,
"step": 50
},
{
"epoch": 1.63,
"learning_rate": 1.6132943205457607e-06,
"loss": 1.5923,
"step": 51
},
{
"epoch": 1.66,
"learning_rate": 1.339745962155613e-06,
"loss": 1.6299,
"step": 52
},
{
"epoch": 1.7,
"learning_rate": 1.0899347581163222e-06,
"loss": 1.6253,
"step": 53
},
{
"epoch": 1.73,
"learning_rate": 8.645454235739903e-07,
"loss": 1.715,
"step": 54
},
{
"epoch": 1.76,
"learning_rate": 6.641957350279838e-07,
"loss": 1.6588,
"step": 55
},
{
"epoch": 1.79,
"learning_rate": 4.894348370484648e-07,
"loss": 1.5589,
"step": 56
},
{
"epoch": 1.82,
"learning_rate": 3.4074173710931804e-07,
"loss": 1.6707,
"step": 57
},
{
"epoch": 1.86,
"learning_rate": 2.1852399266194312e-07,
"loss": 1.638,
"step": 58
},
{
"epoch": 1.89,
"learning_rate": 1.231165940486234e-07,
"loss": 1.7396,
"step": 59
},
{
"epoch": 1.92,
"learning_rate": 5.4781046317267103e-08,
"loss": 1.6457,
"step": 60
},
{
"epoch": 1.95,
"learning_rate": 1.370465245426167e-08,
"loss": 1.5623,
"step": 61
},
{
"epoch": 1.98,
"learning_rate": 0.0,
"loss": 1.7258,
"step": 62
},
{
"epoch": 1.98,
"step": 62,
"total_flos": 1.3441958877855744e+16,
"train_loss": 1.9260368904759806,
"train_runtime": 626.5721,
"train_samples_per_second": 12.768,
"train_steps_per_second": 0.099
}
],
"logging_steps": 1.0,
"max_steps": 62,
"num_train_epochs": 2,
"save_steps": 1000,
"total_flos": 1.3441958877855744e+16,
"trial_name": null,
"trial_params": null
}