bert-large-sst2 / trainer_state.json
Cheng98's picture
Upload folder using huggingface_hub
5957503 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"global_step": 21050,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12,
"learning_rate": 1.952969121140143e-05,
"loss": 0.3269,
"step": 500
},
{
"epoch": 0.24,
"learning_rate": 1.9054631828978623e-05,
"loss": 0.275,
"step": 1000
},
{
"epoch": 0.36,
"learning_rate": 1.857957244655582e-05,
"loss": 0.2457,
"step": 1500
},
{
"epoch": 0.48,
"learning_rate": 1.8104513064133016e-05,
"loss": 0.2285,
"step": 2000
},
{
"epoch": 0.59,
"learning_rate": 1.7629453681710215e-05,
"loss": 0.2181,
"step": 2500
},
{
"epoch": 0.71,
"learning_rate": 1.7154394299287413e-05,
"loss": 0.2131,
"step": 3000
},
{
"epoch": 0.83,
"learning_rate": 1.6679334916864608e-05,
"loss": 0.2115,
"step": 3500
},
{
"epoch": 0.95,
"learning_rate": 1.6204275534441806e-05,
"loss": 0.2013,
"step": 4000
},
{
"epoch": 1.07,
"learning_rate": 1.5730166270783847e-05,
"loss": 0.174,
"step": 4500
},
{
"epoch": 1.19,
"learning_rate": 1.5255106888361047e-05,
"loss": 0.1483,
"step": 5000
},
{
"epoch": 1.31,
"learning_rate": 1.4780997624703088e-05,
"loss": 0.157,
"step": 5500
},
{
"epoch": 1.43,
"learning_rate": 1.4305938242280287e-05,
"loss": 0.1516,
"step": 6000
},
{
"epoch": 1.54,
"learning_rate": 1.3830878859857483e-05,
"loss": 0.1509,
"step": 6500
},
{
"epoch": 1.66,
"learning_rate": 1.335581947743468e-05,
"loss": 0.1455,
"step": 7000
},
{
"epoch": 1.78,
"learning_rate": 1.2880760095011876e-05,
"loss": 0.1481,
"step": 7500
},
{
"epoch": 1.9,
"learning_rate": 1.2405700712589075e-05,
"loss": 0.1469,
"step": 8000
},
{
"epoch": 2.02,
"learning_rate": 1.1930641330166273e-05,
"loss": 0.1406,
"step": 8500
},
{
"epoch": 2.14,
"learning_rate": 1.1455581947743468e-05,
"loss": 0.1038,
"step": 9000
},
{
"epoch": 2.26,
"learning_rate": 1.0980522565320666e-05,
"loss": 0.0981,
"step": 9500
},
{
"epoch": 2.38,
"learning_rate": 1.0505463182897864e-05,
"loss": 0.1033,
"step": 10000
},
{
"epoch": 2.49,
"learning_rate": 1.003040380047506e-05,
"loss": 0.1123,
"step": 10500
},
{
"epoch": 2.61,
"learning_rate": 9.555344418052257e-06,
"loss": 0.1069,
"step": 11000
},
{
"epoch": 2.73,
"learning_rate": 9.0812351543943e-06,
"loss": 0.1074,
"step": 11500
},
{
"epoch": 2.85,
"learning_rate": 8.606175771971497e-06,
"loss": 0.115,
"step": 12000
},
{
"epoch": 2.97,
"learning_rate": 8.13206650831354e-06,
"loss": 0.1136,
"step": 12500
},
{
"epoch": 3.09,
"learning_rate": 7.657007125890738e-06,
"loss": 0.0729,
"step": 13000
},
{
"epoch": 3.21,
"learning_rate": 7.181947743467934e-06,
"loss": 0.0719,
"step": 13500
},
{
"epoch": 3.33,
"learning_rate": 6.7068883610451305e-06,
"loss": 0.0751,
"step": 14000
},
{
"epoch": 3.44,
"learning_rate": 6.231828978622329e-06,
"loss": 0.0675,
"step": 14500
},
{
"epoch": 3.56,
"learning_rate": 5.757719714964372e-06,
"loss": 0.0771,
"step": 15000
},
{
"epoch": 3.68,
"learning_rate": 5.282660332541568e-06,
"loss": 0.0739,
"step": 15500
},
{
"epoch": 3.8,
"learning_rate": 4.807600950118766e-06,
"loss": 0.0699,
"step": 16000
},
{
"epoch": 3.92,
"learning_rate": 4.332541567695962e-06,
"loss": 0.0749,
"step": 16500
},
{
"epoch": 4.04,
"learning_rate": 3.857482185273159e-06,
"loss": 0.0638,
"step": 17000
},
{
"epoch": 4.16,
"learning_rate": 3.383372921615202e-06,
"loss": 0.0382,
"step": 17500
},
{
"epoch": 4.28,
"learning_rate": 2.9083135391923996e-06,
"loss": 0.0474,
"step": 18000
},
{
"epoch": 4.39,
"learning_rate": 2.4332541567695966e-06,
"loss": 0.0527,
"step": 18500
},
{
"epoch": 4.51,
"learning_rate": 1.9581947743467935e-06,
"loss": 0.0457,
"step": 19000
},
{
"epoch": 4.63,
"learning_rate": 1.4831353919239907e-06,
"loss": 0.0448,
"step": 19500
},
{
"epoch": 4.75,
"learning_rate": 1.0080760095011877e-06,
"loss": 0.0417,
"step": 20000
},
{
"epoch": 4.87,
"learning_rate": 5.330166270783848e-07,
"loss": 0.0457,
"step": 20500
},
{
"epoch": 4.99,
"learning_rate": 5.8907363420427555e-08,
"loss": 0.0509,
"step": 21000
},
{
"epoch": 5.0,
"step": 21050,
"total_flos": 7.845580673597184e+16,
"train_loss": 0.1226784371989923,
"train_runtime": 1894.6082,
"train_samples_per_second": 177.739,
"train_steps_per_second": 11.11
}
],
"max_steps": 21050,
"num_train_epochs": 5,
"total_flos": 7.845580673597184e+16,
"trial_name": null,
"trial_params": null
}