lilt_mt_re_all / trainer_state.json
arvisioncode's picture
Upload trainer_state.json with huggingface_hub
6350c45 verified
raw
history blame
10.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 191.38755980861245,
"global_step": 40000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 2.39,
"learning_rate": 3.125e-06,
"loss": 0.4016,
"step": 500
},
{
"epoch": 4.78,
"learning_rate": 6.25e-06,
"loss": 0.202,
"step": 1000
},
{
"epoch": 7.18,
"learning_rate": 9.375000000000001e-06,
"loss": 0.1987,
"step": 1500
},
{
"epoch": 9.57,
"learning_rate": 1.25e-05,
"loss": 0.1964,
"step": 2000
},
{
"epoch": 11.96,
"learning_rate": 1.5625e-05,
"loss": 0.1579,
"step": 2500
},
{
"epoch": 14.35,
"learning_rate": 1.8750000000000002e-05,
"loss": 0.1305,
"step": 3000
},
{
"epoch": 16.75,
"learning_rate": 2.1875e-05,
"loss": 0.1194,
"step": 3500
},
{
"epoch": 19.14,
"learning_rate": 2.5e-05,
"loss": 0.1094,
"step": 4000
},
{
"epoch": 21.53,
"learning_rate": 2.465277777777778e-05,
"loss": 0.0994,
"step": 4500
},
{
"epoch": 23.92,
"learning_rate": 2.4305555555555558e-05,
"loss": 0.0881,
"step": 5000
},
{
"epoch": 26.32,
"learning_rate": 2.3958333333333334e-05,
"loss": 0.0795,
"step": 5500
},
{
"epoch": 28.71,
"learning_rate": 2.361111111111111e-05,
"loss": 0.0738,
"step": 6000
},
{
"epoch": 31.1,
"learning_rate": 2.326388888888889e-05,
"loss": 0.0673,
"step": 6500
},
{
"epoch": 33.49,
"learning_rate": 2.2916666666666667e-05,
"loss": 0.0621,
"step": 7000
},
{
"epoch": 35.89,
"learning_rate": 2.2569444444444447e-05,
"loss": 0.058,
"step": 7500
},
{
"epoch": 38.28,
"learning_rate": 2.2222222222222223e-05,
"loss": 0.0539,
"step": 8000
},
{
"epoch": 40.67,
"learning_rate": 2.1875e-05,
"loss": 0.0489,
"step": 8500
},
{
"epoch": 43.06,
"learning_rate": 2.152777777777778e-05,
"loss": 0.0463,
"step": 9000
},
{
"epoch": 45.45,
"learning_rate": 2.1180555555555556e-05,
"loss": 0.0424,
"step": 9500
},
{
"epoch": 47.85,
"learning_rate": 2.0833333333333336e-05,
"loss": 0.0402,
"step": 10000
},
{
"epoch": 50.24,
"learning_rate": 2.0486111111111113e-05,
"loss": 0.0375,
"step": 10500
},
{
"epoch": 52.63,
"learning_rate": 2.013888888888889e-05,
"loss": 0.0348,
"step": 11000
},
{
"epoch": 55.02,
"learning_rate": 1.9791666666666665e-05,
"loss": 0.0328,
"step": 11500
},
{
"epoch": 57.42,
"learning_rate": 1.9444444444444445e-05,
"loss": 0.0306,
"step": 12000
},
{
"epoch": 59.81,
"learning_rate": 1.9097222222222222e-05,
"loss": 0.0291,
"step": 12500
},
{
"epoch": 62.2,
"learning_rate": 1.8750000000000002e-05,
"loss": 0.0271,
"step": 13000
},
{
"epoch": 64.59,
"learning_rate": 1.8402777777777778e-05,
"loss": 0.0261,
"step": 13500
},
{
"epoch": 66.99,
"learning_rate": 1.8055555555555555e-05,
"loss": 0.0244,
"step": 14000
},
{
"epoch": 69.38,
"learning_rate": 1.7708333333333335e-05,
"loss": 0.0227,
"step": 14500
},
{
"epoch": 71.77,
"learning_rate": 1.736111111111111e-05,
"loss": 0.0217,
"step": 15000
},
{
"epoch": 74.16,
"learning_rate": 1.701388888888889e-05,
"loss": 0.0212,
"step": 15500
},
{
"epoch": 76.56,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.0199,
"step": 16000
},
{
"epoch": 78.95,
"learning_rate": 1.6319444444444444e-05,
"loss": 0.019,
"step": 16500
},
{
"epoch": 81.34,
"learning_rate": 1.597222222222222e-05,
"loss": 0.0183,
"step": 17000
},
{
"epoch": 83.73,
"learning_rate": 1.5625e-05,
"loss": 0.0169,
"step": 17500
},
{
"epoch": 86.12,
"learning_rate": 1.527777777777778e-05,
"loss": 0.0166,
"step": 18000
},
{
"epoch": 88.52,
"learning_rate": 1.4930555555555557e-05,
"loss": 0.016,
"step": 18500
},
{
"epoch": 90.91,
"learning_rate": 1.4583333333333335e-05,
"loss": 0.015,
"step": 19000
},
{
"epoch": 93.3,
"learning_rate": 1.4236111111111111e-05,
"loss": 0.0148,
"step": 19500
},
{
"epoch": 95.69,
"learning_rate": 1.388888888888889e-05,
"loss": 0.0139,
"step": 20000
},
{
"epoch": 98.09,
"learning_rate": 1.3541666666666666e-05,
"loss": 0.0138,
"step": 20500
},
{
"epoch": 100.48,
"learning_rate": 1.3194444444444446e-05,
"loss": 0.0137,
"step": 21000
},
{
"epoch": 102.87,
"learning_rate": 1.2847222222222222e-05,
"loss": 0.0123,
"step": 21500
},
{
"epoch": 105.26,
"learning_rate": 1.25e-05,
"loss": 0.0122,
"step": 22000
},
{
"epoch": 107.66,
"learning_rate": 1.2152777777777779e-05,
"loss": 0.0115,
"step": 22500
},
{
"epoch": 110.05,
"learning_rate": 1.1805555555555555e-05,
"loss": 0.0116,
"step": 23000
},
{
"epoch": 112.44,
"learning_rate": 1.1458333333333333e-05,
"loss": 0.0109,
"step": 23500
},
{
"epoch": 114.83,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.0105,
"step": 24000
},
{
"epoch": 117.22,
"learning_rate": 1.076388888888889e-05,
"loss": 0.0105,
"step": 24500
},
{
"epoch": 119.62,
"learning_rate": 1.0416666666666668e-05,
"loss": 0.01,
"step": 25000
},
{
"epoch": 122.01,
"learning_rate": 1.0069444444444445e-05,
"loss": 0.0095,
"step": 25500
},
{
"epoch": 124.4,
"learning_rate": 9.722222222222223e-06,
"loss": 0.0097,
"step": 26000
},
{
"epoch": 126.79,
"learning_rate": 9.375000000000001e-06,
"loss": 0.0092,
"step": 26500
},
{
"epoch": 129.19,
"learning_rate": 9.027777777777777e-06,
"loss": 0.0088,
"step": 27000
},
{
"epoch": 131.58,
"learning_rate": 8.680555555555556e-06,
"loss": 0.0087,
"step": 27500
},
{
"epoch": 133.97,
"learning_rate": 8.333333333333334e-06,
"loss": 0.0086,
"step": 28000
},
{
"epoch": 136.36,
"learning_rate": 7.98611111111111e-06,
"loss": 0.0085,
"step": 28500
},
{
"epoch": 138.76,
"learning_rate": 7.63888888888889e-06,
"loss": 0.0081,
"step": 29000
},
{
"epoch": 141.15,
"learning_rate": 7.2916666666666674e-06,
"loss": 0.0081,
"step": 29500
},
{
"epoch": 143.54,
"learning_rate": 6.944444444444445e-06,
"loss": 0.0077,
"step": 30000
},
{
"epoch": 145.93,
"learning_rate": 6.597222222222223e-06,
"loss": 0.0075,
"step": 30500
},
{
"epoch": 148.33,
"learning_rate": 6.25e-06,
"loss": 0.0077,
"step": 31000
},
{
"epoch": 150.72,
"learning_rate": 5.902777777777778e-06,
"loss": 0.0078,
"step": 31500
},
{
"epoch": 153.11,
"learning_rate": 5.555555555555556e-06,
"loss": 0.0071,
"step": 32000
},
{
"epoch": 155.5,
"learning_rate": 5.208333333333334e-06,
"loss": 0.0073,
"step": 32500
},
{
"epoch": 157.89,
"learning_rate": 4.861111111111111e-06,
"loss": 0.007,
"step": 33000
},
{
"epoch": 160.29,
"learning_rate": 4.513888888888889e-06,
"loss": 0.0068,
"step": 33500
},
{
"epoch": 162.68,
"learning_rate": 4.166666666666667e-06,
"loss": 0.0071,
"step": 34000
},
{
"epoch": 165.07,
"learning_rate": 3.819444444444445e-06,
"loss": 0.0068,
"step": 34500
},
{
"epoch": 167.46,
"learning_rate": 3.4722222222222224e-06,
"loss": 0.0068,
"step": 35000
},
{
"epoch": 169.86,
"learning_rate": 3.125e-06,
"loss": 0.0066,
"step": 35500
},
{
"epoch": 172.25,
"learning_rate": 2.777777777777778e-06,
"loss": 0.0065,
"step": 36000
},
{
"epoch": 174.64,
"learning_rate": 2.4305555555555557e-06,
"loss": 0.0064,
"step": 36500
},
{
"epoch": 177.03,
"learning_rate": 2.0833333333333334e-06,
"loss": 0.0066,
"step": 37000
},
{
"epoch": 179.43,
"learning_rate": 1.7361111111111112e-06,
"loss": 0.0064,
"step": 37500
},
{
"epoch": 181.82,
"learning_rate": 1.388888888888889e-06,
"loss": 0.0062,
"step": 38000
},
{
"epoch": 184.21,
"learning_rate": 1.0416666666666667e-06,
"loss": 0.0061,
"step": 38500
},
{
"epoch": 186.6,
"learning_rate": 6.944444444444445e-07,
"loss": 0.0061,
"step": 39000
},
{
"epoch": 189.0,
"learning_rate": 3.4722222222222224e-07,
"loss": 0.006,
"step": 39500
},
{
"epoch": 191.39,
"learning_rate": 0.0,
"loss": 0.0063,
"step": 40000
},
{
"epoch": 191.39,
"step": 40000,
"total_flos": 2.8134821491393536e+17,
"train_runtime": 19555.7785,
"train_samples_per_second": 2.045
}
],
"max_steps": 40000,
"num_train_epochs": 192,
"total_flos": 2.8134821491393536e+17,
"trial_name": null,
"trial_params": null
}