whisper-small-hr-vox / trainer_state.json
mikr's picture
End of training
bb31423
raw
history blame
25.9 kB
{
"best_metric": 25.37305060024683,
"best_model_checkpoint": "./checkpoint-4000",
"epoch": 124.008,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 4.800000000000001e-07,
"loss": 1.4901,
"step": 25
},
{
"epoch": 1.0,
"learning_rate": 9.800000000000001e-07,
"loss": 1.2499,
"step": 50
},
{
"epoch": 1.01,
"learning_rate": 1.48e-06,
"loss": 1.0153,
"step": 75
},
{
"epoch": 2.0,
"learning_rate": 1.98e-06,
"loss": 0.8027,
"step": 100
},
{
"epoch": 3.0,
"learning_rate": 2.4800000000000004e-06,
"loss": 0.6815,
"step": 125
},
{
"epoch": 3.01,
"learning_rate": 2.9800000000000003e-06,
"loss": 0.5597,
"step": 150
},
{
"epoch": 4.0,
"learning_rate": 3.48e-06,
"loss": 0.4858,
"step": 175
},
{
"epoch": 4.01,
"learning_rate": 3.980000000000001e-06,
"loss": 0.4395,
"step": 200
},
{
"epoch": 5.0,
"learning_rate": 4.48e-06,
"loss": 0.37,
"step": 225
},
{
"epoch": 6.0,
"learning_rate": 4.980000000000001e-06,
"loss": 0.3308,
"step": 250
},
{
"epoch": 6.01,
"learning_rate": 5.480000000000001e-06,
"loss": 0.2814,
"step": 275
},
{
"epoch": 7.0,
"learning_rate": 5.98e-06,
"loss": 0.2378,
"step": 300
},
{
"epoch": 8.0,
"learning_rate": 6.480000000000001e-06,
"loss": 0.2064,
"step": 325
},
{
"epoch": 8.01,
"learning_rate": 6.98e-06,
"loss": 0.1689,
"step": 350
},
{
"epoch": 9.0,
"learning_rate": 7.48e-06,
"loss": 0.1391,
"step": 375
},
{
"epoch": 9.01,
"learning_rate": 7.980000000000002e-06,
"loss": 0.1139,
"step": 400
},
{
"epoch": 10.01,
"learning_rate": 8.48e-06,
"loss": 0.0882,
"step": 425
},
{
"epoch": 11.0,
"learning_rate": 8.98e-06,
"loss": 0.0764,
"step": 450
},
{
"epoch": 11.01,
"learning_rate": 9.48e-06,
"loss": 0.0609,
"step": 475
},
{
"epoch": 12.0,
"learning_rate": 9.980000000000001e-06,
"loss": 0.0437,
"step": 500
},
{
"epoch": 13.0,
"learning_rate": 9.946666666666667e-06,
"loss": 0.0433,
"step": 525
},
{
"epoch": 13.01,
"learning_rate": 9.891111111111113e-06,
"loss": 0.0334,
"step": 550
},
{
"epoch": 14.0,
"learning_rate": 9.835555555555556e-06,
"loss": 0.0249,
"step": 575
},
{
"epoch": 14.01,
"learning_rate": 9.780000000000001e-06,
"loss": 0.0228,
"step": 600
},
{
"epoch": 15.01,
"learning_rate": 9.724444444444445e-06,
"loss": 0.0153,
"step": 625
},
{
"epoch": 16.0,
"learning_rate": 9.66888888888889e-06,
"loss": 0.0147,
"step": 650
},
{
"epoch": 16.01,
"learning_rate": 9.613333333333335e-06,
"loss": 0.013,
"step": 675
},
{
"epoch": 17.0,
"learning_rate": 9.557777777777777e-06,
"loss": 0.0109,
"step": 700
},
{
"epoch": 18.0,
"learning_rate": 9.502222222222223e-06,
"loss": 0.0081,
"step": 725
},
{
"epoch": 18.01,
"learning_rate": 9.446666666666667e-06,
"loss": 0.0082,
"step": 750
},
{
"epoch": 19.0,
"learning_rate": 9.391111111111111e-06,
"loss": 0.006,
"step": 775
},
{
"epoch": 19.01,
"learning_rate": 9.335555555555557e-06,
"loss": 0.0056,
"step": 800
},
{
"epoch": 20.0,
"learning_rate": 9.280000000000001e-06,
"loss": 0.0049,
"step": 825
},
{
"epoch": 21.0,
"learning_rate": 9.224444444444445e-06,
"loss": 0.0043,
"step": 850
},
{
"epoch": 21.01,
"learning_rate": 9.168888888888889e-06,
"loss": 0.0038,
"step": 875
},
{
"epoch": 22.0,
"learning_rate": 9.113333333333335e-06,
"loss": 0.004,
"step": 900
},
{
"epoch": 23.0,
"learning_rate": 9.057777777777779e-06,
"loss": 0.0041,
"step": 925
},
{
"epoch": 23.01,
"learning_rate": 9.002222222222223e-06,
"loss": 0.004,
"step": 950
},
{
"epoch": 24.0,
"learning_rate": 8.946666666666669e-06,
"loss": 0.003,
"step": 975
},
{
"epoch": 24.01,
"learning_rate": 8.891111111111111e-06,
"loss": 0.0028,
"step": 1000
},
{
"epoch": 24.01,
"eval_loss": 0.5302625894546509,
"eval_runtime": 722.0594,
"eval_samples_per_second": 0.922,
"eval_steps_per_second": 0.029,
"eval_wer": 26.17524963536407,
"step": 1000
},
{
"epoch": 25.0,
"learning_rate": 8.835555555555557e-06,
"loss": 0.0025,
"step": 1025
},
{
"epoch": 26.0,
"learning_rate": 8.78e-06,
"loss": 0.0022,
"step": 1050
},
{
"epoch": 26.01,
"learning_rate": 8.724444444444445e-06,
"loss": 0.002,
"step": 1075
},
{
"epoch": 27.0,
"learning_rate": 8.66888888888889e-06,
"loss": 0.0021,
"step": 1100
},
{
"epoch": 28.0,
"learning_rate": 8.613333333333333e-06,
"loss": 0.0018,
"step": 1125
},
{
"epoch": 28.01,
"learning_rate": 8.557777777777778e-06,
"loss": 0.0017,
"step": 1150
},
{
"epoch": 29.0,
"learning_rate": 8.502222222222223e-06,
"loss": 0.0016,
"step": 1175
},
{
"epoch": 29.01,
"learning_rate": 8.446666666666668e-06,
"loss": 0.0015,
"step": 1200
},
{
"epoch": 30.0,
"learning_rate": 8.391111111111112e-06,
"loss": 0.0014,
"step": 1225
},
{
"epoch": 31.0,
"learning_rate": 8.335555555555556e-06,
"loss": 0.0014,
"step": 1250
},
{
"epoch": 31.01,
"learning_rate": 8.28e-06,
"loss": 0.0013,
"step": 1275
},
{
"epoch": 32.0,
"learning_rate": 8.224444444444444e-06,
"loss": 0.0013,
"step": 1300
},
{
"epoch": 33.0,
"learning_rate": 8.16888888888889e-06,
"loss": 0.0012,
"step": 1325
},
{
"epoch": 33.01,
"learning_rate": 8.113333333333334e-06,
"loss": 0.0012,
"step": 1350
},
{
"epoch": 34.0,
"learning_rate": 8.057777777777778e-06,
"loss": 0.0011,
"step": 1375
},
{
"epoch": 34.01,
"learning_rate": 8.002222222222222e-06,
"loss": 0.0011,
"step": 1400
},
{
"epoch": 35.01,
"learning_rate": 7.946666666666666e-06,
"loss": 0.0011,
"step": 1425
},
{
"epoch": 36.0,
"learning_rate": 7.891111111111112e-06,
"loss": 0.001,
"step": 1450
},
{
"epoch": 36.01,
"learning_rate": 7.835555555555556e-06,
"loss": 0.001,
"step": 1475
},
{
"epoch": 37.0,
"learning_rate": 7.78e-06,
"loss": 0.001,
"step": 1500
},
{
"epoch": 38.0,
"learning_rate": 7.724444444444446e-06,
"loss": 0.0009,
"step": 1525
},
{
"epoch": 38.01,
"learning_rate": 7.66888888888889e-06,
"loss": 0.0009,
"step": 1550
},
{
"epoch": 39.0,
"learning_rate": 7.613333333333334e-06,
"loss": 0.0009,
"step": 1575
},
{
"epoch": 39.01,
"learning_rate": 7.557777777777779e-06,
"loss": 0.0009,
"step": 1600
},
{
"epoch": 40.01,
"learning_rate": 7.502222222222223e-06,
"loss": 0.0008,
"step": 1625
},
{
"epoch": 41.0,
"learning_rate": 7.446666666666668e-06,
"loss": 0.0008,
"step": 1650
},
{
"epoch": 41.01,
"learning_rate": 7.3911111111111125e-06,
"loss": 0.0008,
"step": 1675
},
{
"epoch": 42.0,
"learning_rate": 7.335555555555556e-06,
"loss": 0.0008,
"step": 1700
},
{
"epoch": 43.0,
"learning_rate": 7.280000000000001e-06,
"loss": 0.0008,
"step": 1725
},
{
"epoch": 43.01,
"learning_rate": 7.224444444444445e-06,
"loss": 0.0007,
"step": 1750
},
{
"epoch": 44.0,
"learning_rate": 7.1688888888888895e-06,
"loss": 0.0007,
"step": 1775
},
{
"epoch": 44.01,
"learning_rate": 7.113333333333334e-06,
"loss": 0.0007,
"step": 1800
},
{
"epoch": 45.01,
"learning_rate": 7.057777777777778e-06,
"loss": 0.0007,
"step": 1825
},
{
"epoch": 46.0,
"learning_rate": 7.0022222222222225e-06,
"loss": 0.0007,
"step": 1850
},
{
"epoch": 46.01,
"learning_rate": 6.946666666666667e-06,
"loss": 0.0007,
"step": 1875
},
{
"epoch": 47.0,
"learning_rate": 6.891111111111111e-06,
"loss": 0.0007,
"step": 1900
},
{
"epoch": 48.0,
"learning_rate": 6.835555555555556e-06,
"loss": 0.0006,
"step": 1925
},
{
"epoch": 48.01,
"learning_rate": 6.780000000000001e-06,
"loss": 0.0006,
"step": 1950
},
{
"epoch": 49.0,
"learning_rate": 6.724444444444444e-06,
"loss": 0.0006,
"step": 1975
},
{
"epoch": 49.01,
"learning_rate": 6.668888888888889e-06,
"loss": 0.0006,
"step": 2000
},
{
"epoch": 49.01,
"eval_loss": 0.5848765969276428,
"eval_runtime": 674.6923,
"eval_samples_per_second": 0.987,
"eval_steps_per_second": 0.031,
"eval_wer": 25.412319084483336,
"step": 2000
},
{
"epoch": 50.01,
"learning_rate": 6.613333333333334e-06,
"loss": 0.0006,
"step": 2025
},
{
"epoch": 51.0,
"learning_rate": 6.557777777777778e-06,
"loss": 0.0006,
"step": 2050
},
{
"epoch": 51.01,
"learning_rate": 6.502222222222223e-06,
"loss": 0.0006,
"step": 2075
},
{
"epoch": 52.0,
"learning_rate": 6.446666666666668e-06,
"loss": 0.0005,
"step": 2100
},
{
"epoch": 53.0,
"learning_rate": 6.391111111111111e-06,
"loss": 0.0005,
"step": 2125
},
{
"epoch": 53.01,
"learning_rate": 6.335555555555556e-06,
"loss": 0.0005,
"step": 2150
},
{
"epoch": 54.0,
"learning_rate": 6.280000000000001e-06,
"loss": 0.0005,
"step": 2175
},
{
"epoch": 54.01,
"learning_rate": 6.224444444444445e-06,
"loss": 0.0005,
"step": 2200
},
{
"epoch": 55.01,
"learning_rate": 6.16888888888889e-06,
"loss": 0.0005,
"step": 2225
},
{
"epoch": 56.0,
"learning_rate": 6.113333333333333e-06,
"loss": 0.0005,
"step": 2250
},
{
"epoch": 56.01,
"learning_rate": 6.057777777777778e-06,
"loss": 0.0005,
"step": 2275
},
{
"epoch": 57.0,
"learning_rate": 6.002222222222223e-06,
"loss": 0.0005,
"step": 2300
},
{
"epoch": 58.0,
"learning_rate": 5.946666666666668e-06,
"loss": 0.0005,
"step": 2325
},
{
"epoch": 58.01,
"learning_rate": 5.891111111111112e-06,
"loss": 0.0005,
"step": 2350
},
{
"epoch": 59.0,
"learning_rate": 5.8355555555555565e-06,
"loss": 0.0004,
"step": 2375
},
{
"epoch": 59.01,
"learning_rate": 5.78e-06,
"loss": 0.0004,
"step": 2400
},
{
"epoch": 60.01,
"learning_rate": 5.724444444444445e-06,
"loss": 0.0004,
"step": 2425
},
{
"epoch": 61.0,
"learning_rate": 5.6688888888888895e-06,
"loss": 0.0004,
"step": 2450
},
{
"epoch": 61.01,
"learning_rate": 5.613333333333334e-06,
"loss": 0.0004,
"step": 2475
},
{
"epoch": 62.0,
"learning_rate": 5.557777777777778e-06,
"loss": 0.0004,
"step": 2500
},
{
"epoch": 63.0,
"learning_rate": 5.5022222222222224e-06,
"loss": 0.0004,
"step": 2525
},
{
"epoch": 63.01,
"learning_rate": 5.4466666666666665e-06,
"loss": 0.0004,
"step": 2550
},
{
"epoch": 64.0,
"learning_rate": 5.391111111111111e-06,
"loss": 0.0004,
"step": 2575
},
{
"epoch": 64.01,
"learning_rate": 5.335555555555556e-06,
"loss": 0.0004,
"step": 2600
},
{
"epoch": 65.0,
"learning_rate": 5.28e-06,
"loss": 0.0004,
"step": 2625
},
{
"epoch": 66.0,
"learning_rate": 5.224444444444445e-06,
"loss": 0.0004,
"step": 2650
},
{
"epoch": 66.01,
"learning_rate": 5.168888888888889e-06,
"loss": 0.0004,
"step": 2675
},
{
"epoch": 67.0,
"learning_rate": 5.113333333333333e-06,
"loss": 0.0004,
"step": 2700
},
{
"epoch": 68.0,
"learning_rate": 5.057777777777778e-06,
"loss": 0.0004,
"step": 2725
},
{
"epoch": 68.01,
"learning_rate": 5.002222222222223e-06,
"loss": 0.0004,
"step": 2750
},
{
"epoch": 69.0,
"learning_rate": 4.946666666666667e-06,
"loss": 0.0003,
"step": 2775
},
{
"epoch": 69.01,
"learning_rate": 4.891111111111111e-06,
"loss": 0.0003,
"step": 2800
},
{
"epoch": 70.0,
"learning_rate": 4.835555555555556e-06,
"loss": 0.0003,
"step": 2825
},
{
"epoch": 71.0,
"learning_rate": 4.78e-06,
"loss": 0.0003,
"step": 2850
},
{
"epoch": 71.01,
"learning_rate": 4.724444444444445e-06,
"loss": 0.0003,
"step": 2875
},
{
"epoch": 72.0,
"learning_rate": 4.66888888888889e-06,
"loss": 0.0003,
"step": 2900
},
{
"epoch": 73.0,
"learning_rate": 4.613333333333334e-06,
"loss": 0.0003,
"step": 2925
},
{
"epoch": 73.01,
"learning_rate": 4.557777777777778e-06,
"loss": 0.0003,
"step": 2950
},
{
"epoch": 74.0,
"learning_rate": 4.502222222222223e-06,
"loss": 0.0003,
"step": 2975
},
{
"epoch": 74.01,
"learning_rate": 4.446666666666667e-06,
"loss": 0.0003,
"step": 3000
},
{
"epoch": 74.01,
"eval_loss": 0.6140743494033813,
"eval_runtime": 663.2632,
"eval_samples_per_second": 1.004,
"eval_steps_per_second": 0.032,
"eval_wer": 25.631100639515314,
"step": 3000
},
{
"epoch": 75.0,
"learning_rate": 4.391111111111112e-06,
"loss": 0.0003,
"step": 3025
},
{
"epoch": 76.0,
"learning_rate": 4.3355555555555565e-06,
"loss": 0.0003,
"step": 3050
},
{
"epoch": 76.01,
"learning_rate": 4.2800000000000005e-06,
"loss": 0.0003,
"step": 3075
},
{
"epoch": 77.0,
"learning_rate": 4.2244444444444446e-06,
"loss": 0.0003,
"step": 3100
},
{
"epoch": 78.0,
"learning_rate": 4.168888888888889e-06,
"loss": 0.0003,
"step": 3125
},
{
"epoch": 78.01,
"learning_rate": 4.1133333333333335e-06,
"loss": 0.0003,
"step": 3150
},
{
"epoch": 79.0,
"learning_rate": 4.057777777777778e-06,
"loss": 0.0003,
"step": 3175
},
{
"epoch": 79.01,
"learning_rate": 4.002222222222222e-06,
"loss": 0.0003,
"step": 3200
},
{
"epoch": 80.0,
"learning_rate": 3.946666666666667e-06,
"loss": 0.0003,
"step": 3225
},
{
"epoch": 81.0,
"learning_rate": 3.891111111111111e-06,
"loss": 0.0003,
"step": 3250
},
{
"epoch": 81.01,
"learning_rate": 3.835555555555555e-06,
"loss": 0.0003,
"step": 3275
},
{
"epoch": 82.0,
"learning_rate": 3.7800000000000002e-06,
"loss": 0.0003,
"step": 3300
},
{
"epoch": 83.0,
"learning_rate": 3.724444444444445e-06,
"loss": 0.0003,
"step": 3325
},
{
"epoch": 83.01,
"learning_rate": 3.668888888888889e-06,
"loss": 0.0003,
"step": 3350
},
{
"epoch": 84.0,
"learning_rate": 3.6133333333333336e-06,
"loss": 0.0003,
"step": 3375
},
{
"epoch": 84.01,
"learning_rate": 3.5577777777777785e-06,
"loss": 0.0003,
"step": 3400
},
{
"epoch": 85.0,
"learning_rate": 3.5022222222222225e-06,
"loss": 0.0003,
"step": 3425
},
{
"epoch": 86.0,
"learning_rate": 3.446666666666667e-06,
"loss": 0.0002,
"step": 3450
},
{
"epoch": 86.01,
"learning_rate": 3.391111111111111e-06,
"loss": 0.0003,
"step": 3475
},
{
"epoch": 87.0,
"learning_rate": 3.335555555555556e-06,
"loss": 0.0002,
"step": 3500
},
{
"epoch": 88.0,
"learning_rate": 3.2800000000000004e-06,
"loss": 0.0003,
"step": 3525
},
{
"epoch": 88.01,
"learning_rate": 3.2244444444444444e-06,
"loss": 0.0002,
"step": 3550
},
{
"epoch": 89.0,
"learning_rate": 3.1688888888888893e-06,
"loss": 0.0002,
"step": 3575
},
{
"epoch": 89.01,
"learning_rate": 3.1133333333333337e-06,
"loss": 0.0002,
"step": 3600
},
{
"epoch": 90.0,
"learning_rate": 3.0577777777777778e-06,
"loss": 0.0002,
"step": 3625
},
{
"epoch": 91.0,
"learning_rate": 3.0022222222222227e-06,
"loss": 0.0002,
"step": 3650
},
{
"epoch": 91.01,
"learning_rate": 2.946666666666667e-06,
"loss": 0.0002,
"step": 3675
},
{
"epoch": 92.0,
"learning_rate": 2.891111111111111e-06,
"loss": 0.0002,
"step": 3700
},
{
"epoch": 93.0,
"learning_rate": 2.835555555555556e-06,
"loss": 0.0002,
"step": 3725
},
{
"epoch": 93.01,
"learning_rate": 2.7800000000000005e-06,
"loss": 0.0002,
"step": 3750
},
{
"epoch": 94.0,
"learning_rate": 2.7244444444444445e-06,
"loss": 0.0002,
"step": 3775
},
{
"epoch": 94.01,
"learning_rate": 2.6688888888888894e-06,
"loss": 0.0002,
"step": 3800
},
{
"epoch": 95.0,
"learning_rate": 2.6133333333333334e-06,
"loss": 0.0002,
"step": 3825
},
{
"epoch": 96.0,
"learning_rate": 2.557777777777778e-06,
"loss": 0.0002,
"step": 3850
},
{
"epoch": 96.01,
"learning_rate": 2.5022222222222224e-06,
"loss": 0.0002,
"step": 3875
},
{
"epoch": 97.0,
"learning_rate": 2.446666666666667e-06,
"loss": 0.0002,
"step": 3900
},
{
"epoch": 98.0,
"learning_rate": 2.3911111111111113e-06,
"loss": 0.0002,
"step": 3925
},
{
"epoch": 98.01,
"learning_rate": 2.3355555555555557e-06,
"loss": 0.0002,
"step": 3950
},
{
"epoch": 99.0,
"learning_rate": 2.28e-06,
"loss": 0.0002,
"step": 3975
},
{
"epoch": 99.01,
"learning_rate": 2.2244444444444447e-06,
"loss": 0.0002,
"step": 4000
},
{
"epoch": 99.01,
"eval_loss": 0.6324931383132935,
"eval_runtime": 650.4597,
"eval_samples_per_second": 1.024,
"eval_steps_per_second": 0.032,
"eval_wer": 25.37305060024683,
"step": 4000
},
{
"epoch": 100.0,
"learning_rate": 2.168888888888889e-06,
"loss": 0.0002,
"step": 4025
},
{
"epoch": 101.0,
"learning_rate": 2.1133333333333336e-06,
"loss": 0.0002,
"step": 4050
},
{
"epoch": 101.01,
"learning_rate": 2.057777777777778e-06,
"loss": 0.0002,
"step": 4075
},
{
"epoch": 102.0,
"learning_rate": 2.0022222222222225e-06,
"loss": 0.0002,
"step": 4100
},
{
"epoch": 103.0,
"learning_rate": 1.9466666666666665e-06,
"loss": 0.0002,
"step": 4125
},
{
"epoch": 103.01,
"learning_rate": 1.8911111111111114e-06,
"loss": 0.0002,
"step": 4150
},
{
"epoch": 104.0,
"learning_rate": 1.8355555555555557e-06,
"loss": 0.0002,
"step": 4175
},
{
"epoch": 104.01,
"learning_rate": 1.7800000000000001e-06,
"loss": 0.0002,
"step": 4200
},
{
"epoch": 105.0,
"learning_rate": 1.7244444444444448e-06,
"loss": 0.0002,
"step": 4225
},
{
"epoch": 106.0,
"learning_rate": 1.668888888888889e-06,
"loss": 0.0002,
"step": 4250
},
{
"epoch": 106.01,
"learning_rate": 1.6133333333333335e-06,
"loss": 0.0002,
"step": 4275
},
{
"epoch": 107.0,
"learning_rate": 1.5577777777777777e-06,
"loss": 0.0002,
"step": 4300
},
{
"epoch": 108.0,
"learning_rate": 1.5022222222222224e-06,
"loss": 0.0002,
"step": 4325
},
{
"epoch": 108.01,
"learning_rate": 1.4466666666666669e-06,
"loss": 0.0002,
"step": 4350
},
{
"epoch": 109.0,
"learning_rate": 1.3911111111111111e-06,
"loss": 0.0002,
"step": 4375
},
{
"epoch": 109.01,
"learning_rate": 1.3355555555555558e-06,
"loss": 0.0002,
"step": 4400
},
{
"epoch": 110.0,
"learning_rate": 1.28e-06,
"loss": 0.0002,
"step": 4425
},
{
"epoch": 111.0,
"learning_rate": 1.2244444444444445e-06,
"loss": 0.0002,
"step": 4450
},
{
"epoch": 111.01,
"learning_rate": 1.168888888888889e-06,
"loss": 0.0002,
"step": 4475
},
{
"epoch": 112.0,
"learning_rate": 1.1133333333333334e-06,
"loss": 0.0002,
"step": 4500
},
{
"epoch": 113.0,
"learning_rate": 1.0577777777777779e-06,
"loss": 0.0002,
"step": 4525
},
{
"epoch": 113.01,
"learning_rate": 1.0022222222222223e-06,
"loss": 0.0002,
"step": 4550
},
{
"epoch": 114.0,
"learning_rate": 9.466666666666667e-07,
"loss": 0.0002,
"step": 4575
},
{
"epoch": 114.01,
"learning_rate": 8.911111111111112e-07,
"loss": 0.0002,
"step": 4600
},
{
"epoch": 115.0,
"learning_rate": 8.355555555555556e-07,
"loss": 0.0002,
"step": 4625
},
{
"epoch": 116.0,
"learning_rate": 7.8e-07,
"loss": 0.0002,
"step": 4650
},
{
"epoch": 116.01,
"learning_rate": 7.244444444444446e-07,
"loss": 0.0002,
"step": 4675
},
{
"epoch": 117.0,
"learning_rate": 6.68888888888889e-07,
"loss": 0.0002,
"step": 4700
},
{
"epoch": 118.0,
"learning_rate": 6.133333333333333e-07,
"loss": 0.0002,
"step": 4725
},
{
"epoch": 118.01,
"learning_rate": 5.577777777777779e-07,
"loss": 0.0002,
"step": 4750
},
{
"epoch": 119.0,
"learning_rate": 5.022222222222222e-07,
"loss": 0.0002,
"step": 4775
},
{
"epoch": 119.01,
"learning_rate": 4.466666666666667e-07,
"loss": 0.0002,
"step": 4800
},
{
"epoch": 120.0,
"learning_rate": 3.9111111111111115e-07,
"loss": 0.0002,
"step": 4825
},
{
"epoch": 121.0,
"learning_rate": 3.3555555555555556e-07,
"loss": 0.0002,
"step": 4850
},
{
"epoch": 121.01,
"learning_rate": 2.8e-07,
"loss": 0.0002,
"step": 4875
},
{
"epoch": 122.0,
"learning_rate": 2.2444444444444445e-07,
"loss": 0.0002,
"step": 4900
},
{
"epoch": 123.0,
"learning_rate": 1.6888888888888888e-07,
"loss": 0.0002,
"step": 4925
},
{
"epoch": 123.01,
"learning_rate": 1.1333333333333336e-07,
"loss": 0.0002,
"step": 4950
},
{
"epoch": 124.0,
"learning_rate": 5.777777777777778e-08,
"loss": 0.0002,
"step": 4975
},
{
"epoch": 124.01,
"learning_rate": 2.2222222222222225e-09,
"loss": 0.0002,
"step": 5000
},
{
"epoch": 124.01,
"eval_loss": 0.6405040621757507,
"eval_runtime": 648.4677,
"eval_samples_per_second": 1.027,
"eval_steps_per_second": 0.032,
"eval_wer": 25.43475821833277,
"step": 5000
},
{
"epoch": 124.01,
"step": 5000,
"total_flos": 9.205874270208e+19,
"train_loss": 0.04578730283072218,
"train_runtime": 39423.3866,
"train_samples_per_second": 8.117,
"train_steps_per_second": 0.127
}
],
"max_steps": 5000,
"num_train_epochs": 9223372036854775807,
"total_flos": 9.205874270208e+19,
"trial_name": null,
"trial_params": null
}