whisper-el-sm-farsipal-e8 / trainer_state.json
emilios's picture
End of training
22668c5
{
"best_metric": 16.465453194650816,
"best_model_checkpoint": "./checkpoint-3000",
"epoch": 12.437810945273633,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 5.045361133432068e-10,
"loss": 0.0002,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 6.229195710491768e-10,
"loss": 0.0002,
"step": 50
},
{
"epoch": 0.19,
"learning_rate": 6.903829450223392e-10,
"loss": 0.0002,
"step": 75
},
{
"epoch": 0.25,
"learning_rate": 7.377725845391017e-10,
"loss": 0.0002,
"step": 100
},
{
"epoch": 0.31,
"learning_rate": 7.743343231239583e-10,
"loss": 0.0002,
"step": 125
},
{
"epoch": 0.37,
"learning_rate": 8.041073861170494e-10,
"loss": 0.0002,
"step": 150
},
{
"epoch": 0.44,
"learning_rate": 8.292222957399573e-10,
"loss": 0.0002,
"step": 175
},
{
"epoch": 0.5,
"learning_rate": 8.509413541357753e-10,
"loss": 0.0002,
"step": 200
},
{
"epoch": 0.56,
"learning_rate": 8.700744577655556e-10,
"loss": 0.0002,
"step": 225
},
{
"epoch": 0.62,
"learning_rate": 8.871723942761204e-10,
"loss": 0.0002,
"step": 250
},
{
"epoch": 0.68,
"learning_rate": 9.026267958246848e-10,
"loss": 0.0002,
"step": 275
},
{
"epoch": 0.75,
"learning_rate": 9.16726106663399e-10,
"loss": 0.0002,
"step": 300
},
{
"epoch": 0.81,
"learning_rate": 9.296889251455016e-10,
"loss": 0.0002,
"step": 325
},
{
"epoch": 0.87,
"learning_rate": 9.416848797368693e-10,
"loss": 0.0002,
"step": 350
},
{
"epoch": 0.93,
"learning_rate": 9.528482449516372e-10,
"loss": 0.0002,
"step": 375
},
{
"epoch": 1.0,
"learning_rate": 9.632871309784313e-10,
"loss": 0.0002,
"step": 400
},
{
"epoch": 1.06,
"learning_rate": 9.73089868785391e-10,
"loss": 0.0002,
"step": 425
},
{
"epoch": 1.12,
"learning_rate": 9.823295589572114e-10,
"loss": 0.0002,
"step": 450
},
{
"epoch": 1.18,
"learning_rate": 9.910673836465485e-10,
"loss": 0.0002,
"step": 475
},
{
"epoch": 1.24,
"learning_rate": 9.993550644973806e-10,
"loss": 0.0002,
"step": 500
},
{
"epoch": 1.31,
"learning_rate": 9.95111111111111e-10,
"loss": 0.0002,
"step": 525
},
{
"epoch": 1.37,
"learning_rate": 9.895555555555556e-10,
"loss": 0.0002,
"step": 550
},
{
"epoch": 1.43,
"learning_rate": 9.840000000000001e-10,
"loss": 0.0002,
"step": 575
},
{
"epoch": 1.49,
"learning_rate": 9.784444444444444e-10,
"loss": 0.0002,
"step": 600
},
{
"epoch": 1.55,
"learning_rate": 9.72888888888889e-10,
"loss": 0.0002,
"step": 625
},
{
"epoch": 1.62,
"learning_rate": 9.673333333333335e-10,
"loss": 0.0002,
"step": 650
},
{
"epoch": 1.68,
"learning_rate": 9.617777777777778e-10,
"loss": 0.0002,
"step": 675
},
{
"epoch": 1.74,
"learning_rate": 9.562222222222222e-10,
"loss": 0.0002,
"step": 700
},
{
"epoch": 1.8,
"learning_rate": 9.506666666666667e-10,
"loss": 0.0002,
"step": 725
},
{
"epoch": 1.87,
"learning_rate": 9.451111111111112e-10,
"loss": 0.0002,
"step": 750
},
{
"epoch": 1.93,
"learning_rate": 9.395555555555556e-10,
"loss": 0.0002,
"step": 775
},
{
"epoch": 1.99,
"learning_rate": 9.34e-10,
"loss": 0.0002,
"step": 800
},
{
"epoch": 2.05,
"learning_rate": 9.284444444444445e-10,
"loss": 0.0002,
"step": 825
},
{
"epoch": 2.11,
"learning_rate": 9.228888888888889e-10,
"loss": 0.0002,
"step": 850
},
{
"epoch": 2.18,
"learning_rate": 9.173333333333334e-10,
"loss": 0.0002,
"step": 875
},
{
"epoch": 2.24,
"learning_rate": 9.117777777777779e-10,
"loss": 0.0002,
"step": 900
},
{
"epoch": 2.3,
"learning_rate": 9.062222222222223e-10,
"loss": 0.0002,
"step": 925
},
{
"epoch": 2.36,
"learning_rate": 9.006666666666667e-10,
"loss": 0.0002,
"step": 950
},
{
"epoch": 2.43,
"learning_rate": 8.951111111111111e-10,
"loss": 0.0002,
"step": 975
},
{
"epoch": 2.49,
"learning_rate": 8.895555555555556e-10,
"loss": 0.0002,
"step": 1000
},
{
"epoch": 2.49,
"eval_loss": 0.50146484375,
"eval_runtime": 168.0976,
"eval_samples_per_second": 10.089,
"eval_steps_per_second": 0.631,
"eval_wer": 16.51188707280832,
"step": 1000
},
{
"epoch": 2.55,
"learning_rate": 8.844444444444446e-10,
"loss": 0.0002,
"step": 1025
},
{
"epoch": 2.61,
"learning_rate": 8.78888888888889e-10,
"loss": 0.0002,
"step": 1050
},
{
"epoch": 2.67,
"learning_rate": 8.733333333333333e-10,
"loss": 0.0002,
"step": 1075
},
{
"epoch": 2.74,
"learning_rate": 8.677777777777778e-10,
"loss": 0.0002,
"step": 1100
},
{
"epoch": 2.8,
"learning_rate": 8.622222222222223e-10,
"loss": 0.0002,
"step": 1125
},
{
"epoch": 2.86,
"learning_rate": 8.566666666666667e-10,
"loss": 0.0002,
"step": 1150
},
{
"epoch": 2.92,
"learning_rate": 8.511111111111112e-10,
"loss": 0.0002,
"step": 1175
},
{
"epoch": 2.99,
"learning_rate": 8.455555555555556e-10,
"loss": 0.0002,
"step": 1200
},
{
"epoch": 3.05,
"learning_rate": 8.4e-10,
"loss": 0.0002,
"step": 1225
},
{
"epoch": 3.11,
"learning_rate": 8.344444444444445e-10,
"loss": 0.0002,
"step": 1250
},
{
"epoch": 3.17,
"learning_rate": 8.28888888888889e-10,
"loss": 0.0002,
"step": 1275
},
{
"epoch": 3.23,
"learning_rate": 8.233333333333334e-10,
"loss": 0.0002,
"step": 1300
},
{
"epoch": 3.3,
"learning_rate": 8.177777777777779e-10,
"loss": 0.0002,
"step": 1325
},
{
"epoch": 3.36,
"learning_rate": 8.122222222222222e-10,
"loss": 0.0002,
"step": 1350
},
{
"epoch": 3.42,
"learning_rate": 8.066666666666667e-10,
"loss": 0.0002,
"step": 1375
},
{
"epoch": 3.48,
"learning_rate": 8.011111111111112e-10,
"loss": 0.0002,
"step": 1400
},
{
"epoch": 3.54,
"learning_rate": 7.955555555555556e-10,
"loss": 0.0002,
"step": 1425
},
{
"epoch": 3.61,
"learning_rate": 7.900000000000001e-10,
"loss": 0.0002,
"step": 1450
},
{
"epoch": 3.67,
"learning_rate": 7.844444444444446e-10,
"loss": 0.0002,
"step": 1475
},
{
"epoch": 3.73,
"learning_rate": 7.788888888888889e-10,
"loss": 0.0002,
"step": 1500
},
{
"epoch": 3.79,
"learning_rate": 7.733333333333334e-10,
"loss": 0.0002,
"step": 1525
},
{
"epoch": 3.86,
"learning_rate": 7.677777777777778e-10,
"loss": 0.0002,
"step": 1550
},
{
"epoch": 3.92,
"learning_rate": 7.622222222222223e-10,
"loss": 0.0002,
"step": 1575
},
{
"epoch": 3.98,
"learning_rate": 7.566666666666667e-10,
"loss": 0.0002,
"step": 1600
},
{
"epoch": 4.04,
"learning_rate": 7.511111111111111e-10,
"loss": 0.0002,
"step": 1625
},
{
"epoch": 4.1,
"learning_rate": 7.455555555555556e-10,
"loss": 0.0002,
"step": 1650
},
{
"epoch": 4.17,
"learning_rate": 7.4e-10,
"loss": 0.0002,
"step": 1675
},
{
"epoch": 4.23,
"learning_rate": 7.344444444444445e-10,
"loss": 0.0002,
"step": 1700
},
{
"epoch": 4.29,
"learning_rate": 7.28888888888889e-10,
"loss": 0.0002,
"step": 1725
},
{
"epoch": 4.35,
"learning_rate": 7.233333333333334e-10,
"loss": 0.0002,
"step": 1750
},
{
"epoch": 4.42,
"learning_rate": 7.177777777777777e-10,
"loss": 0.0002,
"step": 1775
},
{
"epoch": 4.48,
"learning_rate": 7.122222222222223e-10,
"loss": 0.0002,
"step": 1800
},
{
"epoch": 4.54,
"learning_rate": 7.066666666666667e-10,
"loss": 0.0002,
"step": 1825
},
{
"epoch": 4.6,
"learning_rate": 7.011111111111111e-10,
"loss": 0.0002,
"step": 1850
},
{
"epoch": 4.66,
"learning_rate": 6.955555555555557e-10,
"loss": 0.0002,
"step": 1875
},
{
"epoch": 4.73,
"learning_rate": 6.9e-10,
"loss": 0.0002,
"step": 1900
},
{
"epoch": 4.79,
"learning_rate": 6.844444444444444e-10,
"loss": 0.0002,
"step": 1925
},
{
"epoch": 4.85,
"learning_rate": 6.78888888888889e-10,
"loss": 0.0002,
"step": 1950
},
{
"epoch": 4.91,
"learning_rate": 6.733333333333334e-10,
"loss": 0.0002,
"step": 1975
},
{
"epoch": 4.98,
"learning_rate": 6.677777777777778e-10,
"loss": 0.0002,
"step": 2000
},
{
"epoch": 4.98,
"eval_loss": 0.50146484375,
"eval_runtime": 168.0899,
"eval_samples_per_second": 10.09,
"eval_steps_per_second": 0.631,
"eval_wer": 16.558320950965825,
"step": 2000
},
{
"epoch": 5.04,
"learning_rate": 6.626666666666667e-10,
"loss": 0.0002,
"step": 2025
},
{
"epoch": 5.1,
"learning_rate": 6.571111111111111e-10,
"loss": 0.0002,
"step": 2050
},
{
"epoch": 5.16,
"learning_rate": 6.515555555555556e-10,
"loss": 0.0002,
"step": 2075
},
{
"epoch": 5.22,
"learning_rate": 6.46e-10,
"loss": 0.0002,
"step": 2100
},
{
"epoch": 5.29,
"learning_rate": 6.404444444444445e-10,
"loss": 0.0002,
"step": 2125
},
{
"epoch": 5.35,
"learning_rate": 6.348888888888889e-10,
"loss": 0.0002,
"step": 2150
},
{
"epoch": 5.41,
"learning_rate": 6.293333333333333e-10,
"loss": 0.0002,
"step": 2175
},
{
"epoch": 5.47,
"learning_rate": 6.237777777777778e-10,
"loss": 0.0002,
"step": 2200
},
{
"epoch": 5.53,
"learning_rate": 6.182222222222223e-10,
"loss": 0.0002,
"step": 2225
},
{
"epoch": 5.6,
"learning_rate": 6.126666666666667e-10,
"loss": 0.0002,
"step": 2250
},
{
"epoch": 5.66,
"learning_rate": 6.071111111111112e-10,
"loss": 0.0002,
"step": 2275
},
{
"epoch": 5.72,
"learning_rate": 6.015555555555556e-10,
"loss": 0.0002,
"step": 2300
},
{
"epoch": 5.78,
"learning_rate": 5.96e-10,
"loss": 0.0002,
"step": 2325
},
{
"epoch": 5.85,
"learning_rate": 5.904444444444444e-10,
"loss": 0.0002,
"step": 2350
},
{
"epoch": 5.91,
"learning_rate": 5.84888888888889e-10,
"loss": 0.0002,
"step": 2375
},
{
"epoch": 5.97,
"learning_rate": 5.793333333333334e-10,
"loss": 0.0002,
"step": 2400
},
{
"epoch": 6.03,
"learning_rate": 5.737777777777778e-10,
"loss": 0.0002,
"step": 2425
},
{
"epoch": 6.09,
"learning_rate": 5.682222222222223e-10,
"loss": 0.0002,
"step": 2450
},
{
"epoch": 6.16,
"learning_rate": 5.626666666666667e-10,
"loss": 0.0002,
"step": 2475
},
{
"epoch": 6.22,
"learning_rate": 5.571111111111111e-10,
"loss": 0.0002,
"step": 2500
},
{
"epoch": 6.28,
"learning_rate": 5.515555555555556e-10,
"loss": 0.0002,
"step": 2525
},
{
"epoch": 6.34,
"learning_rate": 5.460000000000001e-10,
"loss": 0.0002,
"step": 2550
},
{
"epoch": 6.41,
"learning_rate": 5.404444444444444e-10,
"loss": 0.0002,
"step": 2575
},
{
"epoch": 6.47,
"learning_rate": 5.348888888888889e-10,
"loss": 0.0002,
"step": 2600
},
{
"epoch": 6.53,
"learning_rate": 5.293333333333334e-10,
"loss": 0.0002,
"step": 2625
},
{
"epoch": 6.59,
"learning_rate": 5.237777777777778e-10,
"loss": 0.0002,
"step": 2650
},
{
"epoch": 6.65,
"learning_rate": 5.182222222222223e-10,
"loss": 0.0002,
"step": 2675
},
{
"epoch": 6.72,
"learning_rate": 5.126666666666668e-10,
"loss": 0.0002,
"step": 2700
},
{
"epoch": 6.78,
"learning_rate": 5.071111111111111e-10,
"loss": 0.0002,
"step": 2725
},
{
"epoch": 6.84,
"learning_rate": 5.015555555555555e-10,
"loss": 0.0002,
"step": 2750
},
{
"epoch": 6.9,
"learning_rate": 4.96e-10,
"loss": 0.0002,
"step": 2775
},
{
"epoch": 6.97,
"learning_rate": 4.904444444444445e-10,
"loss": 0.0002,
"step": 2800
},
{
"epoch": 7.03,
"learning_rate": 4.848888888888889e-10,
"loss": 0.0002,
"step": 2825
},
{
"epoch": 7.09,
"learning_rate": 4.793333333333333e-10,
"loss": 0.0002,
"step": 2850
},
{
"epoch": 7.15,
"learning_rate": 4.737777777777779e-10,
"loss": 0.0002,
"step": 2875
},
{
"epoch": 7.21,
"learning_rate": 4.682222222222222e-10,
"loss": 0.0002,
"step": 2900
},
{
"epoch": 7.28,
"learning_rate": 4.626666666666667e-10,
"loss": 0.0002,
"step": 2925
},
{
"epoch": 7.34,
"learning_rate": 4.5711111111111115e-10,
"loss": 0.0002,
"step": 2950
},
{
"epoch": 7.4,
"learning_rate": 4.515555555555556e-10,
"loss": 0.0002,
"step": 2975
},
{
"epoch": 7.46,
"learning_rate": 4.46e-10,
"loss": 0.0002,
"step": 3000
},
{
"epoch": 7.46,
"eval_loss": 0.50146484375,
"eval_runtime": 167.3892,
"eval_samples_per_second": 10.132,
"eval_steps_per_second": 0.633,
"eval_wer": 16.465453194650816,
"step": 3000
},
{
"epoch": 7.52,
"learning_rate": 4.408888888888889e-10,
"loss": 0.0002,
"step": 3025
},
{
"epoch": 7.59,
"learning_rate": 4.353333333333334e-10,
"loss": 0.0001,
"step": 3050
},
{
"epoch": 7.65,
"learning_rate": 4.297777777777778e-10,
"loss": 0.0002,
"step": 3075
},
{
"epoch": 7.71,
"learning_rate": 4.2422222222222224e-10,
"loss": 0.0002,
"step": 3100
},
{
"epoch": 7.77,
"learning_rate": 4.186666666666667e-10,
"loss": 0.0002,
"step": 3125
},
{
"epoch": 7.84,
"learning_rate": 4.131111111111111e-10,
"loss": 0.0002,
"step": 3150
},
{
"epoch": 7.9,
"learning_rate": 4.075555555555556e-10,
"loss": 0.0002,
"step": 3175
},
{
"epoch": 7.96,
"learning_rate": 4.0200000000000006e-10,
"loss": 0.0002,
"step": 3200
},
{
"epoch": 8.02,
"learning_rate": 3.9644444444444444e-10,
"loss": 0.0002,
"step": 3225
},
{
"epoch": 8.08,
"learning_rate": 3.908888888888889e-10,
"loss": 0.0002,
"step": 3250
},
{
"epoch": 8.15,
"learning_rate": 3.853333333333334e-10,
"loss": 0.0002,
"step": 3275
},
{
"epoch": 8.21,
"learning_rate": 3.797777777777778e-10,
"loss": 0.0002,
"step": 3300
},
{
"epoch": 8.27,
"learning_rate": 3.7422222222222226e-10,
"loss": 0.0002,
"step": 3325
},
{
"epoch": 8.33,
"learning_rate": 3.686666666666667e-10,
"loss": 0.0002,
"step": 3350
},
{
"epoch": 8.4,
"learning_rate": 3.631111111111111e-10,
"loss": 0.0002,
"step": 3375
},
{
"epoch": 8.46,
"learning_rate": 3.575555555555556e-10,
"loss": 0.0002,
"step": 3400
},
{
"epoch": 8.52,
"learning_rate": 3.52e-10,
"loss": 0.0002,
"step": 3425
},
{
"epoch": 8.58,
"learning_rate": 3.4644444444444445e-10,
"loss": 0.0002,
"step": 3450
},
{
"epoch": 8.64,
"learning_rate": 3.4088888888888894e-10,
"loss": 0.0002,
"step": 3475
},
{
"epoch": 8.71,
"learning_rate": 3.353333333333333e-10,
"loss": 0.0002,
"step": 3500
},
{
"epoch": 8.77,
"learning_rate": 3.297777777777778e-10,
"loss": 0.0002,
"step": 3525
},
{
"epoch": 8.83,
"learning_rate": 3.242222222222223e-10,
"loss": 0.0002,
"step": 3550
},
{
"epoch": 8.89,
"learning_rate": 3.1866666666666665e-10,
"loss": 0.0002,
"step": 3575
},
{
"epoch": 8.96,
"learning_rate": 3.1311111111111113e-10,
"loss": 0.0002,
"step": 3600
},
{
"epoch": 9.02,
"learning_rate": 3.075555555555556e-10,
"loss": 0.0002,
"step": 3625
},
{
"epoch": 9.08,
"learning_rate": 3.02e-10,
"loss": 0.0002,
"step": 3650
},
{
"epoch": 9.14,
"learning_rate": 2.9644444444444447e-10,
"loss": 0.0002,
"step": 3675
},
{
"epoch": 9.2,
"learning_rate": 2.908888888888889e-10,
"loss": 0.0002,
"step": 3700
},
{
"epoch": 9.27,
"learning_rate": 2.8533333333333333e-10,
"loss": 0.0002,
"step": 3725
},
{
"epoch": 9.33,
"learning_rate": 2.797777777777778e-10,
"loss": 0.0002,
"step": 3750
},
{
"epoch": 9.39,
"learning_rate": 2.7422222222222224e-10,
"loss": 0.0002,
"step": 3775
},
{
"epoch": 9.45,
"learning_rate": 2.6866666666666667e-10,
"loss": 0.0002,
"step": 3800
},
{
"epoch": 9.51,
"learning_rate": 2.6311111111111115e-10,
"loss": 0.0002,
"step": 3825
},
{
"epoch": 9.58,
"learning_rate": 2.5755555555555553e-10,
"loss": 0.0002,
"step": 3850
},
{
"epoch": 9.64,
"learning_rate": 2.52e-10,
"loss": 0.0002,
"step": 3875
},
{
"epoch": 9.7,
"learning_rate": 2.4644444444444444e-10,
"loss": 0.0002,
"step": 3900
},
{
"epoch": 9.76,
"learning_rate": 2.408888888888889e-10,
"loss": 0.0002,
"step": 3925
},
{
"epoch": 9.83,
"learning_rate": 2.3533333333333335e-10,
"loss": 0.0002,
"step": 3950
},
{
"epoch": 9.89,
"learning_rate": 2.2977777777777778e-10,
"loss": 0.0002,
"step": 3975
},
{
"epoch": 9.95,
"learning_rate": 2.2422222222222223e-10,
"loss": 0.0002,
"step": 4000
},
{
"epoch": 9.95,
"eval_loss": 0.50146484375,
"eval_runtime": 167.9097,
"eval_samples_per_second": 10.101,
"eval_steps_per_second": 0.631,
"eval_wer": 16.51188707280832,
"step": 4000
},
{
"epoch": 10.01,
"learning_rate": 2.1911111111111112e-10,
"loss": 0.0002,
"step": 4025
},
{
"epoch": 10.07,
"learning_rate": 2.1355555555555558e-10,
"loss": 0.0002,
"step": 4050
},
{
"epoch": 10.14,
"learning_rate": 2.08e-10,
"loss": 0.0002,
"step": 4075
},
{
"epoch": 10.2,
"learning_rate": 2.0244444444444446e-10,
"loss": 0.0002,
"step": 4100
},
{
"epoch": 10.26,
"learning_rate": 1.9688888888888892e-10,
"loss": 0.0002,
"step": 4125
},
{
"epoch": 10.32,
"learning_rate": 1.9133333333333334e-10,
"loss": 0.0002,
"step": 4150
},
{
"epoch": 10.39,
"learning_rate": 1.8577777777777777e-10,
"loss": 0.0002,
"step": 4175
},
{
"epoch": 10.45,
"learning_rate": 1.8022222222222223e-10,
"loss": 0.0002,
"step": 4200
},
{
"epoch": 10.51,
"learning_rate": 1.7466666666666668e-10,
"loss": 0.0002,
"step": 4225
},
{
"epoch": 10.57,
"learning_rate": 1.6911111111111111e-10,
"loss": 0.0002,
"step": 4250
},
{
"epoch": 10.63,
"learning_rate": 1.6355555555555557e-10,
"loss": 0.0002,
"step": 4275
},
{
"epoch": 10.7,
"learning_rate": 1.5800000000000002e-10,
"loss": 0.0002,
"step": 4300
},
{
"epoch": 10.76,
"learning_rate": 1.5244444444444445e-10,
"loss": 0.0002,
"step": 4325
},
{
"epoch": 10.82,
"learning_rate": 1.468888888888889e-10,
"loss": 0.0002,
"step": 4350
},
{
"epoch": 10.88,
"learning_rate": 1.4133333333333334e-10,
"loss": 0.0002,
"step": 4375
},
{
"epoch": 10.95,
"learning_rate": 1.357777777777778e-10,
"loss": 0.0002,
"step": 4400
},
{
"epoch": 11.01,
"learning_rate": 1.3022222222222222e-10,
"loss": 0.0002,
"step": 4425
},
{
"epoch": 11.07,
"learning_rate": 1.2466666666666668e-10,
"loss": 0.0002,
"step": 4450
},
{
"epoch": 11.13,
"learning_rate": 1.1911111111111113e-10,
"loss": 0.0002,
"step": 4475
},
{
"epoch": 11.19,
"learning_rate": 1.1355555555555557e-10,
"loss": 0.0002,
"step": 4500
},
{
"epoch": 11.26,
"learning_rate": 1.08e-10,
"loss": 0.0002,
"step": 4525
},
{
"epoch": 11.32,
"learning_rate": 1.0244444444444446e-10,
"loss": 0.0002,
"step": 4550
},
{
"epoch": 11.38,
"learning_rate": 9.688888888888889e-11,
"loss": 0.0002,
"step": 4575
},
{
"epoch": 11.44,
"learning_rate": 9.133333333333334e-11,
"loss": 0.0002,
"step": 4600
},
{
"epoch": 11.5,
"learning_rate": 8.577777777777778e-11,
"loss": 0.0002,
"step": 4625
},
{
"epoch": 11.57,
"learning_rate": 8.022222222222223e-11,
"loss": 0.0002,
"step": 4650
},
{
"epoch": 11.63,
"learning_rate": 7.466666666666668e-11,
"loss": 0.0002,
"step": 4675
},
{
"epoch": 11.69,
"learning_rate": 6.911111111111111e-11,
"loss": 0.0002,
"step": 4700
},
{
"epoch": 11.75,
"learning_rate": 6.355555555555556e-11,
"loss": 0.0002,
"step": 4725
},
{
"epoch": 11.82,
"learning_rate": 5.8000000000000007e-11,
"loss": 0.0002,
"step": 4750
},
{
"epoch": 11.88,
"learning_rate": 5.244444444444445e-11,
"loss": 0.0002,
"step": 4775
},
{
"epoch": 11.94,
"learning_rate": 4.688888888888889e-11,
"loss": 0.0002,
"step": 4800
},
{
"epoch": 12.0,
"learning_rate": 4.133333333333333e-11,
"loss": 0.0002,
"step": 4825
},
{
"epoch": 12.06,
"learning_rate": 3.577777777777778e-11,
"loss": 0.0002,
"step": 4850
},
{
"epoch": 12.13,
"learning_rate": 3.0222222222222223e-11,
"loss": 0.0002,
"step": 4875
},
{
"epoch": 12.19,
"learning_rate": 2.466666666666667e-11,
"loss": 0.0002,
"step": 4900
},
{
"epoch": 12.25,
"learning_rate": 1.911111111111111e-11,
"loss": 0.0002,
"step": 4925
},
{
"epoch": 12.31,
"learning_rate": 1.3555555555555556e-11,
"loss": 0.0002,
"step": 4950
},
{
"epoch": 12.38,
"learning_rate": 8.000000000000001e-12,
"loss": 0.0002,
"step": 4975
},
{
"epoch": 12.44,
"learning_rate": 2.4444444444444444e-12,
"loss": 0.0002,
"step": 5000
},
{
"epoch": 12.44,
"eval_loss": 0.50146484375,
"eval_runtime": 168.0048,
"eval_samples_per_second": 10.095,
"eval_steps_per_second": 0.631,
"eval_wer": 16.558320950965825,
"step": 5000
},
{
"epoch": 12.44,
"step": 5000,
"total_flos": 4.615288630123325e+19,
"train_loss": 0.00017441691160202026,
"train_runtime": 9920.3408,
"train_samples_per_second": 16.128,
"train_steps_per_second": 0.504
}
],
"max_steps": 5000,
"num_train_epochs": 13,
"total_flos": 4.615288630123325e+19,
"trial_name": null,
"trial_params": null
}