common6 / trainer_state.json
ghofrani's picture
End of training
57c9bd6
raw
history blame
127 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 199.99750623441398,
"global_step": 10000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"learning_rate": 6e-06,
"loss": 1.0901,
"step": 10
},
{
"epoch": 0.4,
"learning_rate": 1.2e-05,
"loss": 1.0728,
"step": 20
},
{
"epoch": 0.6,
"learning_rate": 1.8e-05,
"loss": 1.0838,
"step": 30
},
{
"epoch": 0.8,
"learning_rate": 2.4e-05,
"loss": 1.0591,
"step": 40
},
{
"epoch": 1.0,
"learning_rate": 3e-05,
"loss": 1.0419,
"step": 50
},
{
"epoch": 1.2,
"learning_rate": 3.6e-05,
"loss": 1.0973,
"step": 60
},
{
"epoch": 1.4,
"learning_rate": 4.2e-05,
"loss": 1.07,
"step": 70
},
{
"epoch": 1.6,
"learning_rate": 4.8e-05,
"loss": 1.0816,
"step": 80
},
{
"epoch": 1.8,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.0822,
"step": 90
},
{
"epoch": 2.0,
"learning_rate": 6e-05,
"loss": 1.0825,
"step": 100
},
{
"epoch": 2.2,
"learning_rate": 5.9877551020408165e-05,
"loss": 1.1134,
"step": 110
},
{
"epoch": 2.4,
"learning_rate": 5.975510204081633e-05,
"loss": 1.1079,
"step": 120
},
{
"epoch": 2.6,
"learning_rate": 5.963265306122449e-05,
"loss": 1.1017,
"step": 130
},
{
"epoch": 2.8,
"learning_rate": 5.9510204081632654e-05,
"loss": 1.1001,
"step": 140
},
{
"epoch": 3.0,
"learning_rate": 5.938775510204082e-05,
"loss": 1.0689,
"step": 150
},
{
"epoch": 3.2,
"learning_rate": 5.926530612244898e-05,
"loss": 1.1165,
"step": 160
},
{
"epoch": 3.4,
"learning_rate": 5.914285714285715e-05,
"loss": 1.0812,
"step": 170
},
{
"epoch": 3.6,
"learning_rate": 5.9020408163265306e-05,
"loss": 1.0963,
"step": 180
},
{
"epoch": 3.8,
"learning_rate": 5.889795918367347e-05,
"loss": 1.0757,
"step": 190
},
{
"epoch": 4.0,
"learning_rate": 5.877551020408163e-05,
"loss": 1.0759,
"step": 200
},
{
"epoch": 4.2,
"learning_rate": 5.8653061224489795e-05,
"loss": 1.1081,
"step": 210
},
{
"epoch": 4.4,
"learning_rate": 5.8530612244897965e-05,
"loss": 1.0893,
"step": 220
},
{
"epoch": 4.6,
"learning_rate": 5.840816326530613e-05,
"loss": 1.0849,
"step": 230
},
{
"epoch": 4.8,
"learning_rate": 5.8285714285714284e-05,
"loss": 1.0753,
"step": 240
},
{
"epoch": 5.0,
"learning_rate": 5.816326530612245e-05,
"loss": 1.0611,
"step": 250
},
{
"epoch": 5.2,
"learning_rate": 5.804081632653062e-05,
"loss": 1.0977,
"step": 260
},
{
"epoch": 5.4,
"learning_rate": 5.791836734693878e-05,
"loss": 1.0702,
"step": 270
},
{
"epoch": 5.6,
"learning_rate": 5.779591836734694e-05,
"loss": 1.0886,
"step": 280
},
{
"epoch": 5.8,
"learning_rate": 5.76734693877551e-05,
"loss": 1.073,
"step": 290
},
{
"epoch": 6.0,
"learning_rate": 5.755102040816326e-05,
"loss": 1.0663,
"step": 300
},
{
"epoch": 6.2,
"learning_rate": 5.742857142857143e-05,
"loss": 1.0989,
"step": 310
},
{
"epoch": 6.4,
"learning_rate": 5.7306122448979596e-05,
"loss": 1.0773,
"step": 320
},
{
"epoch": 6.6,
"learning_rate": 5.718367346938776e-05,
"loss": 1.0682,
"step": 330
},
{
"epoch": 6.8,
"learning_rate": 5.7061224489795915e-05,
"loss": 1.0759,
"step": 340
},
{
"epoch": 7.0,
"learning_rate": 5.6938775510204085e-05,
"loss": 1.0497,
"step": 350
},
{
"epoch": 7.2,
"learning_rate": 5.681632653061225e-05,
"loss": 1.0923,
"step": 360
},
{
"epoch": 7.4,
"learning_rate": 5.669387755102041e-05,
"loss": 1.0503,
"step": 370
},
{
"epoch": 7.6,
"learning_rate": 5.6571428571428574e-05,
"loss": 1.0539,
"step": 380
},
{
"epoch": 7.8,
"learning_rate": 5.644897959183674e-05,
"loss": 1.0693,
"step": 390
},
{
"epoch": 8.0,
"learning_rate": 5.63265306122449e-05,
"loss": 1.0338,
"step": 400
},
{
"epoch": 8.2,
"learning_rate": 5.620408163265306e-05,
"loss": 1.0612,
"step": 410
},
{
"epoch": 8.4,
"learning_rate": 5.6081632653061226e-05,
"loss": 1.0647,
"step": 420
},
{
"epoch": 8.6,
"learning_rate": 5.595918367346939e-05,
"loss": 1.064,
"step": 430
},
{
"epoch": 8.8,
"learning_rate": 5.583673469387755e-05,
"loss": 1.0591,
"step": 440
},
{
"epoch": 9.0,
"learning_rate": 5.5714285714285715e-05,
"loss": 1.0207,
"step": 450
},
{
"epoch": 9.2,
"learning_rate": 5.559183673469388e-05,
"loss": 1.0733,
"step": 460
},
{
"epoch": 9.4,
"learning_rate": 5.546938775510204e-05,
"loss": 1.0442,
"step": 470
},
{
"epoch": 9.6,
"learning_rate": 5.5346938775510204e-05,
"loss": 1.0697,
"step": 480
},
{
"epoch": 9.8,
"learning_rate": 5.5224489795918374e-05,
"loss": 1.0628,
"step": 490
},
{
"epoch": 10.0,
"learning_rate": 5.510204081632653e-05,
"loss": 1.0344,
"step": 500
},
{
"epoch": 10.0,
"eval_loss": 0.40431472659111023,
"eval_runtime": 247.681,
"eval_samples_per_second": 21.043,
"eval_steps_per_second": 1.316,
"eval_wer": 0.451111573905347,
"step": 500
},
{
"epoch": 10.2,
"learning_rate": 5.4979591836734694e-05,
"loss": 1.0725,
"step": 510
},
{
"epoch": 10.4,
"learning_rate": 5.4857142857142857e-05,
"loss": 1.0514,
"step": 520
},
{
"epoch": 10.6,
"learning_rate": 5.473469387755102e-05,
"loss": 1.0477,
"step": 530
},
{
"epoch": 10.8,
"learning_rate": 5.461224489795919e-05,
"loss": 1.0551,
"step": 540
},
{
"epoch": 11.0,
"learning_rate": 5.4489795918367346e-05,
"loss": 1.0322,
"step": 550
},
{
"epoch": 11.2,
"learning_rate": 5.436734693877551e-05,
"loss": 1.0435,
"step": 560
},
{
"epoch": 11.4,
"learning_rate": 5.424489795918367e-05,
"loss": 1.0594,
"step": 570
},
{
"epoch": 11.6,
"learning_rate": 5.412244897959184e-05,
"loss": 1.0419,
"step": 580
},
{
"epoch": 11.8,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.0291,
"step": 590
},
{
"epoch": 12.0,
"learning_rate": 5.387755102040817e-05,
"loss": 1.0314,
"step": 600
},
{
"epoch": 12.2,
"learning_rate": 5.3755102040816324e-05,
"loss": 1.0598,
"step": 610
},
{
"epoch": 12.4,
"learning_rate": 5.363265306122449e-05,
"loss": 1.0412,
"step": 620
},
{
"epoch": 12.6,
"learning_rate": 5.351020408163266e-05,
"loss": 1.0483,
"step": 630
},
{
"epoch": 12.8,
"learning_rate": 5.338775510204082e-05,
"loss": 1.0448,
"step": 640
},
{
"epoch": 13.0,
"learning_rate": 5.326530612244898e-05,
"loss": 0.9938,
"step": 650
},
{
"epoch": 13.2,
"learning_rate": 5.314285714285714e-05,
"loss": 1.053,
"step": 660
},
{
"epoch": 13.4,
"learning_rate": 5.302040816326531e-05,
"loss": 1.0178,
"step": 670
},
{
"epoch": 13.6,
"learning_rate": 5.289795918367347e-05,
"loss": 1.0174,
"step": 680
},
{
"epoch": 13.8,
"learning_rate": 5.2775510204081635e-05,
"loss": 1.0231,
"step": 690
},
{
"epoch": 14.0,
"learning_rate": 5.26530612244898e-05,
"loss": 1.0033,
"step": 700
},
{
"epoch": 14.2,
"learning_rate": 5.2530612244897955e-05,
"loss": 1.0444,
"step": 710
},
{
"epoch": 14.4,
"learning_rate": 5.2408163265306124e-05,
"loss": 0.9893,
"step": 720
},
{
"epoch": 14.6,
"learning_rate": 5.228571428571429e-05,
"loss": 1.0216,
"step": 730
},
{
"epoch": 14.8,
"learning_rate": 5.216326530612245e-05,
"loss": 1.0247,
"step": 740
},
{
"epoch": 15.0,
"learning_rate": 5.2040816326530614e-05,
"loss": 1.0022,
"step": 750
},
{
"epoch": 15.2,
"learning_rate": 5.191836734693878e-05,
"loss": 1.032,
"step": 760
},
{
"epoch": 15.4,
"learning_rate": 5.179591836734694e-05,
"loss": 0.9963,
"step": 770
},
{
"epoch": 15.6,
"learning_rate": 5.16734693877551e-05,
"loss": 0.9952,
"step": 780
},
{
"epoch": 15.8,
"learning_rate": 5.1551020408163266e-05,
"loss": 1.0021,
"step": 790
},
{
"epoch": 16.0,
"learning_rate": 5.142857142857143e-05,
"loss": 1.0134,
"step": 800
},
{
"epoch": 16.2,
"learning_rate": 5.13061224489796e-05,
"loss": 1.0319,
"step": 810
},
{
"epoch": 16.4,
"learning_rate": 5.1183673469387755e-05,
"loss": 0.9963,
"step": 820
},
{
"epoch": 16.6,
"learning_rate": 5.106122448979592e-05,
"loss": 0.9966,
"step": 830
},
{
"epoch": 16.8,
"learning_rate": 5.093877551020408e-05,
"loss": 1.0023,
"step": 840
},
{
"epoch": 17.0,
"learning_rate": 5.081632653061225e-05,
"loss": 0.9739,
"step": 850
},
{
"epoch": 17.2,
"learning_rate": 5.0693877551020414e-05,
"loss": 1.0182,
"step": 860
},
{
"epoch": 17.4,
"learning_rate": 5.057142857142857e-05,
"loss": 0.9884,
"step": 870
},
{
"epoch": 17.6,
"learning_rate": 5.044897959183673e-05,
"loss": 0.9623,
"step": 880
},
{
"epoch": 17.8,
"learning_rate": 5.0326530612244896e-05,
"loss": 1.0061,
"step": 890
},
{
"epoch": 18.0,
"learning_rate": 5.0204081632653066e-05,
"loss": 0.9684,
"step": 900
},
{
"epoch": 18.2,
"learning_rate": 5.008163265306123e-05,
"loss": 1.0066,
"step": 910
},
{
"epoch": 18.4,
"learning_rate": 4.9959183673469386e-05,
"loss": 0.9779,
"step": 920
},
{
"epoch": 18.6,
"learning_rate": 4.983673469387755e-05,
"loss": 0.9784,
"step": 930
},
{
"epoch": 18.8,
"learning_rate": 4.971428571428572e-05,
"loss": 0.9869,
"step": 940
},
{
"epoch": 19.0,
"learning_rate": 4.959183673469388e-05,
"loss": 0.9561,
"step": 950
},
{
"epoch": 19.2,
"learning_rate": 4.9469387755102045e-05,
"loss": 1.0003,
"step": 960
},
{
"epoch": 19.4,
"learning_rate": 4.93469387755102e-05,
"loss": 0.9838,
"step": 970
},
{
"epoch": 19.6,
"learning_rate": 4.9224489795918364e-05,
"loss": 0.9969,
"step": 980
},
{
"epoch": 19.8,
"learning_rate": 4.9102040816326534e-05,
"loss": 1.0037,
"step": 990
},
{
"epoch": 20.0,
"learning_rate": 4.89795918367347e-05,
"loss": 0.9651,
"step": 1000
},
{
"epoch": 20.0,
"eval_loss": 0.3793290853500366,
"eval_runtime": 244.7376,
"eval_samples_per_second": 21.296,
"eval_steps_per_second": 1.332,
"eval_wer": 0.4159421044410892,
"step": 1000
},
{
"epoch": 20.2,
"learning_rate": 4.885714285714286e-05,
"loss": 1.0027,
"step": 1010
},
{
"epoch": 20.4,
"learning_rate": 4.873469387755102e-05,
"loss": 0.9598,
"step": 1020
},
{
"epoch": 20.6,
"learning_rate": 4.862448979591836e-05,
"loss": 0.979,
"step": 1030
},
{
"epoch": 20.8,
"learning_rate": 4.850204081632653e-05,
"loss": 0.9886,
"step": 1040
},
{
"epoch": 21.0,
"learning_rate": 4.8379591836734696e-05,
"loss": 0.9584,
"step": 1050
},
{
"epoch": 21.2,
"learning_rate": 4.825714285714286e-05,
"loss": 0.984,
"step": 1060
},
{
"epoch": 21.4,
"learning_rate": 4.813469387755102e-05,
"loss": 0.9586,
"step": 1070
},
{
"epoch": 21.6,
"learning_rate": 4.8012244897959185e-05,
"loss": 0.9669,
"step": 1080
},
{
"epoch": 21.8,
"learning_rate": 4.788979591836735e-05,
"loss": 0.9629,
"step": 1090
},
{
"epoch": 22.0,
"learning_rate": 4.776734693877551e-05,
"loss": 0.9468,
"step": 1100
},
{
"epoch": 22.2,
"learning_rate": 4.7644897959183674e-05,
"loss": 1.0055,
"step": 1110
},
{
"epoch": 22.4,
"learning_rate": 4.752244897959184e-05,
"loss": 0.9698,
"step": 1120
},
{
"epoch": 22.6,
"learning_rate": 4.74e-05,
"loss": 0.9557,
"step": 1130
},
{
"epoch": 22.8,
"learning_rate": 4.727755102040816e-05,
"loss": 0.9648,
"step": 1140
},
{
"epoch": 23.0,
"learning_rate": 4.7155102040816326e-05,
"loss": 0.9681,
"step": 1150
},
{
"epoch": 23.2,
"learning_rate": 4.703265306122449e-05,
"loss": 0.995,
"step": 1160
},
{
"epoch": 23.4,
"learning_rate": 4.691020408163266e-05,
"loss": 0.9415,
"step": 1170
},
{
"epoch": 23.6,
"learning_rate": 4.678775510204082e-05,
"loss": 0.955,
"step": 1180
},
{
"epoch": 23.8,
"learning_rate": 4.666530612244898e-05,
"loss": 0.9647,
"step": 1190
},
{
"epoch": 24.0,
"learning_rate": 4.654285714285714e-05,
"loss": 0.9572,
"step": 1200
},
{
"epoch": 24.2,
"learning_rate": 4.6420408163265305e-05,
"loss": 1.0043,
"step": 1210
},
{
"epoch": 24.4,
"learning_rate": 4.6297959183673474e-05,
"loss": 0.9545,
"step": 1220
},
{
"epoch": 24.6,
"learning_rate": 4.617551020408164e-05,
"loss": 0.9603,
"step": 1230
},
{
"epoch": 24.8,
"learning_rate": 4.6053061224489794e-05,
"loss": 0.9563,
"step": 1240
},
{
"epoch": 25.0,
"learning_rate": 4.593061224489796e-05,
"loss": 0.939,
"step": 1250
},
{
"epoch": 25.2,
"learning_rate": 4.580816326530613e-05,
"loss": 0.9755,
"step": 1260
},
{
"epoch": 25.4,
"learning_rate": 4.568571428571429e-05,
"loss": 0.9619,
"step": 1270
},
{
"epoch": 25.6,
"learning_rate": 4.556326530612245e-05,
"loss": 0.951,
"step": 1280
},
{
"epoch": 25.8,
"learning_rate": 4.544081632653061e-05,
"loss": 0.9442,
"step": 1290
},
{
"epoch": 26.0,
"learning_rate": 4.531836734693877e-05,
"loss": 0.9448,
"step": 1300
},
{
"epoch": 26.2,
"learning_rate": 4.519591836734694e-05,
"loss": 0.984,
"step": 1310
},
{
"epoch": 26.4,
"learning_rate": 4.5073469387755105e-05,
"loss": 0.9407,
"step": 1320
},
{
"epoch": 26.6,
"learning_rate": 4.495102040816327e-05,
"loss": 0.9506,
"step": 1330
},
{
"epoch": 26.8,
"learning_rate": 4.4828571428571424e-05,
"loss": 0.9393,
"step": 1340
},
{
"epoch": 27.0,
"learning_rate": 4.4706122448979594e-05,
"loss": 0.9513,
"step": 1350
},
{
"epoch": 27.2,
"learning_rate": 4.458367346938776e-05,
"loss": 0.9636,
"step": 1360
},
{
"epoch": 27.4,
"learning_rate": 4.446122448979592e-05,
"loss": 0.9441,
"step": 1370
},
{
"epoch": 27.6,
"learning_rate": 4.433877551020408e-05,
"loss": 0.9476,
"step": 1380
},
{
"epoch": 27.8,
"learning_rate": 4.4216326530612246e-05,
"loss": 0.9438,
"step": 1390
},
{
"epoch": 28.0,
"learning_rate": 4.409387755102041e-05,
"loss": 0.9376,
"step": 1400
},
{
"epoch": 28.2,
"learning_rate": 4.397142857142857e-05,
"loss": 0.9699,
"step": 1410
},
{
"epoch": 28.4,
"learning_rate": 4.3848979591836736e-05,
"loss": 0.9719,
"step": 1420
},
{
"epoch": 28.6,
"learning_rate": 4.37265306122449e-05,
"loss": 0.9481,
"step": 1430
},
{
"epoch": 28.8,
"learning_rate": 4.360408163265307e-05,
"loss": 0.9495,
"step": 1440
},
{
"epoch": 29.0,
"learning_rate": 4.3481632653061225e-05,
"loss": 0.9208,
"step": 1450
},
{
"epoch": 29.2,
"learning_rate": 4.335918367346939e-05,
"loss": 0.9725,
"step": 1460
},
{
"epoch": 29.4,
"learning_rate": 4.323673469387755e-05,
"loss": 0.9317,
"step": 1470
},
{
"epoch": 29.6,
"learning_rate": 4.3114285714285714e-05,
"loss": 0.9402,
"step": 1480
},
{
"epoch": 29.8,
"learning_rate": 4.2991836734693884e-05,
"loss": 0.9431,
"step": 1490
},
{
"epoch": 30.0,
"learning_rate": 4.286938775510204e-05,
"loss": 0.9125,
"step": 1500
},
{
"epoch": 30.0,
"eval_loss": 0.3755570352077484,
"eval_runtime": 246.7652,
"eval_samples_per_second": 21.121,
"eval_steps_per_second": 1.321,
"eval_wer": 0.4046441401572343,
"step": 1500
},
{
"epoch": 30.2,
"learning_rate": 4.27469387755102e-05,
"loss": 0.9531,
"step": 1510
},
{
"epoch": 30.4,
"learning_rate": 4.2624489795918366e-05,
"loss": 0.9172,
"step": 1520
},
{
"epoch": 30.6,
"learning_rate": 4.250204081632653e-05,
"loss": 0.9438,
"step": 1530
},
{
"epoch": 30.8,
"learning_rate": 4.23795918367347e-05,
"loss": 0.9405,
"step": 1540
},
{
"epoch": 31.0,
"learning_rate": 4.2257142857142855e-05,
"loss": 0.9209,
"step": 1550
},
{
"epoch": 31.2,
"learning_rate": 4.213469387755102e-05,
"loss": 0.9827,
"step": 1560
},
{
"epoch": 31.4,
"learning_rate": 4.201224489795918e-05,
"loss": 0.9163,
"step": 1570
},
{
"epoch": 31.6,
"learning_rate": 4.188979591836735e-05,
"loss": 0.9175,
"step": 1580
},
{
"epoch": 31.8,
"learning_rate": 4.1767346938775514e-05,
"loss": 0.9288,
"step": 1590
},
{
"epoch": 32.0,
"learning_rate": 4.164489795918368e-05,
"loss": 0.8951,
"step": 1600
},
{
"epoch": 32.2,
"learning_rate": 4.1522448979591834e-05,
"loss": 0.9582,
"step": 1610
},
{
"epoch": 32.4,
"learning_rate": 4.14e-05,
"loss": 0.9183,
"step": 1620
},
{
"epoch": 32.6,
"learning_rate": 4.1277551020408166e-05,
"loss": 0.9113,
"step": 1630
},
{
"epoch": 32.8,
"learning_rate": 4.115510204081633e-05,
"loss": 0.9305,
"step": 1640
},
{
"epoch": 33.0,
"learning_rate": 4.103265306122449e-05,
"loss": 0.9159,
"step": 1650
},
{
"epoch": 33.2,
"learning_rate": 4.091020408163265e-05,
"loss": 0.9706,
"step": 1660
},
{
"epoch": 33.4,
"learning_rate": 4.078775510204082e-05,
"loss": 0.9359,
"step": 1670
},
{
"epoch": 33.6,
"learning_rate": 4.066530612244898e-05,
"loss": 0.916,
"step": 1680
},
{
"epoch": 33.8,
"learning_rate": 4.0542857142857145e-05,
"loss": 0.9333,
"step": 1690
},
{
"epoch": 34.0,
"learning_rate": 4.042040816326531e-05,
"loss": 0.892,
"step": 1700
},
{
"epoch": 34.2,
"learning_rate": 4.0297959183673464e-05,
"loss": 0.9556,
"step": 1710
},
{
"epoch": 34.4,
"learning_rate": 4.0175510204081634e-05,
"loss": 0.8906,
"step": 1720
},
{
"epoch": 34.6,
"learning_rate": 4.00530612244898e-05,
"loss": 0.9183,
"step": 1730
},
{
"epoch": 34.8,
"learning_rate": 3.993061224489796e-05,
"loss": 0.9262,
"step": 1740
},
{
"epoch": 35.0,
"learning_rate": 3.980816326530612e-05,
"loss": 0.9276,
"step": 1750
},
{
"epoch": 35.2,
"learning_rate": 3.968571428571429e-05,
"loss": 0.9383,
"step": 1760
},
{
"epoch": 35.4,
"learning_rate": 3.956326530612245e-05,
"loss": 0.9247,
"step": 1770
},
{
"epoch": 35.6,
"learning_rate": 3.944081632653061e-05,
"loss": 0.9339,
"step": 1780
},
{
"epoch": 35.8,
"learning_rate": 3.9318367346938775e-05,
"loss": 0.8878,
"step": 1790
},
{
"epoch": 36.0,
"learning_rate": 3.919591836734694e-05,
"loss": 0.9035,
"step": 1800
},
{
"epoch": 36.2,
"learning_rate": 3.907346938775511e-05,
"loss": 0.9587,
"step": 1810
},
{
"epoch": 36.4,
"learning_rate": 3.8951020408163265e-05,
"loss": 0.8989,
"step": 1820
},
{
"epoch": 36.6,
"learning_rate": 3.882857142857143e-05,
"loss": 0.922,
"step": 1830
},
{
"epoch": 36.8,
"learning_rate": 3.870612244897959e-05,
"loss": 0.9278,
"step": 1840
},
{
"epoch": 37.0,
"learning_rate": 3.858367346938776e-05,
"loss": 0.8979,
"step": 1850
},
{
"epoch": 37.2,
"learning_rate": 3.8461224489795924e-05,
"loss": 0.9302,
"step": 1860
},
{
"epoch": 37.4,
"learning_rate": 3.833877551020408e-05,
"loss": 0.9078,
"step": 1870
},
{
"epoch": 37.6,
"learning_rate": 3.821632653061224e-05,
"loss": 0.919,
"step": 1880
},
{
"epoch": 37.8,
"learning_rate": 3.8093877551020406e-05,
"loss": 0.9152,
"step": 1890
},
{
"epoch": 38.0,
"learning_rate": 3.7971428571428576e-05,
"loss": 0.8914,
"step": 1900
},
{
"epoch": 38.2,
"learning_rate": 3.784897959183674e-05,
"loss": 0.9297,
"step": 1910
},
{
"epoch": 38.4,
"learning_rate": 3.7726530612244895e-05,
"loss": 0.9091,
"step": 1920
},
{
"epoch": 38.6,
"learning_rate": 3.760408163265306e-05,
"loss": 0.9085,
"step": 1930
},
{
"epoch": 38.8,
"learning_rate": 3.748163265306123e-05,
"loss": 0.9078,
"step": 1940
},
{
"epoch": 39.0,
"learning_rate": 3.735918367346939e-05,
"loss": 0.8804,
"step": 1950
},
{
"epoch": 39.2,
"learning_rate": 3.7236734693877554e-05,
"loss": 0.9208,
"step": 1960
},
{
"epoch": 39.4,
"learning_rate": 3.711428571428572e-05,
"loss": 0.8786,
"step": 1970
},
{
"epoch": 39.6,
"learning_rate": 3.6991836734693873e-05,
"loss": 0.8991,
"step": 1980
},
{
"epoch": 39.8,
"learning_rate": 3.686938775510204e-05,
"loss": 0.9153,
"step": 1990
},
{
"epoch": 40.0,
"learning_rate": 3.6746938775510206e-05,
"loss": 0.8831,
"step": 2000
},
{
"epoch": 40.0,
"eval_loss": 0.3649730086326599,
"eval_runtime": 244.6059,
"eval_samples_per_second": 21.308,
"eval_steps_per_second": 1.333,
"eval_wer": 0.3875930650283751,
"step": 2000
},
{
"epoch": 40.2,
"learning_rate": 3.662448979591837e-05,
"loss": 0.8995,
"step": 2010
},
{
"epoch": 40.4,
"learning_rate": 3.650204081632653e-05,
"loss": 0.91,
"step": 2020
},
{
"epoch": 40.6,
"learning_rate": 3.6379591836734695e-05,
"loss": 0.9105,
"step": 2030
},
{
"epoch": 40.8,
"learning_rate": 3.625714285714286e-05,
"loss": 0.897,
"step": 2040
},
{
"epoch": 41.0,
"learning_rate": 3.613469387755102e-05,
"loss": 0.8869,
"step": 2050
},
{
"epoch": 41.2,
"learning_rate": 3.6012244897959185e-05,
"loss": 0.9227,
"step": 2060
},
{
"epoch": 41.4,
"learning_rate": 3.588979591836735e-05,
"loss": 0.8919,
"step": 2070
},
{
"epoch": 41.6,
"learning_rate": 3.576734693877551e-05,
"loss": 0.8926,
"step": 2080
},
{
"epoch": 41.8,
"learning_rate": 3.5644897959183674e-05,
"loss": 0.8912,
"step": 2090
},
{
"epoch": 42.0,
"learning_rate": 3.552244897959184e-05,
"loss": 0.8841,
"step": 2100
},
{
"epoch": 42.2,
"learning_rate": 3.54e-05,
"loss": 0.9165,
"step": 2110
},
{
"epoch": 42.4,
"learning_rate": 3.527755102040817e-05,
"loss": 0.8981,
"step": 2120
},
{
"epoch": 42.6,
"learning_rate": 3.5155102040816326e-05,
"loss": 0.9079,
"step": 2130
},
{
"epoch": 42.8,
"learning_rate": 3.503265306122449e-05,
"loss": 0.9017,
"step": 2140
},
{
"epoch": 43.0,
"learning_rate": 3.491020408163265e-05,
"loss": 0.8534,
"step": 2150
},
{
"epoch": 43.2,
"learning_rate": 3.4787755102040815e-05,
"loss": 0.9108,
"step": 2160
},
{
"epoch": 43.4,
"learning_rate": 3.4665306122448985e-05,
"loss": 0.8763,
"step": 2170
},
{
"epoch": 43.6,
"learning_rate": 3.454285714285715e-05,
"loss": 0.903,
"step": 2180
},
{
"epoch": 43.8,
"learning_rate": 3.4420408163265304e-05,
"loss": 0.8842,
"step": 2190
},
{
"epoch": 44.0,
"learning_rate": 3.429795918367347e-05,
"loss": 0.8646,
"step": 2200
},
{
"epoch": 44.2,
"learning_rate": 3.417551020408163e-05,
"loss": 0.921,
"step": 2210
},
{
"epoch": 44.4,
"learning_rate": 3.40530612244898e-05,
"loss": 0.8833,
"step": 2220
},
{
"epoch": 44.6,
"learning_rate": 3.393061224489796e-05,
"loss": 0.8826,
"step": 2230
},
{
"epoch": 44.8,
"learning_rate": 3.380816326530612e-05,
"loss": 0.8892,
"step": 2240
},
{
"epoch": 45.0,
"learning_rate": 3.368571428571428e-05,
"loss": 0.8688,
"step": 2250
},
{
"epoch": 45.2,
"learning_rate": 3.356326530612245e-05,
"loss": 0.92,
"step": 2260
},
{
"epoch": 45.4,
"learning_rate": 3.3440816326530616e-05,
"loss": 0.8728,
"step": 2270
},
{
"epoch": 45.6,
"learning_rate": 3.331836734693878e-05,
"loss": 0.8921,
"step": 2280
},
{
"epoch": 45.8,
"learning_rate": 3.3195918367346935e-05,
"loss": 0.9218,
"step": 2290
},
{
"epoch": 46.0,
"learning_rate": 3.30734693877551e-05,
"loss": 0.8695,
"step": 2300
},
{
"epoch": 46.2,
"learning_rate": 3.295102040816327e-05,
"loss": 0.9205,
"step": 2310
},
{
"epoch": 46.4,
"learning_rate": 3.282857142857143e-05,
"loss": 0.8813,
"step": 2320
},
{
"epoch": 46.6,
"learning_rate": 3.2706122448979594e-05,
"loss": 0.881,
"step": 2330
},
{
"epoch": 46.8,
"learning_rate": 3.258367346938776e-05,
"loss": 0.8744,
"step": 2340
},
{
"epoch": 47.0,
"learning_rate": 3.246122448979592e-05,
"loss": 0.8419,
"step": 2350
},
{
"epoch": 47.2,
"learning_rate": 3.233877551020408e-05,
"loss": 0.8919,
"step": 2360
},
{
"epoch": 47.4,
"learning_rate": 3.2216326530612246e-05,
"loss": 0.8741,
"step": 2370
},
{
"epoch": 47.6,
"learning_rate": 3.209387755102041e-05,
"loss": 0.8904,
"step": 2380
},
{
"epoch": 47.8,
"learning_rate": 3.197142857142857e-05,
"loss": 0.8948,
"step": 2390
},
{
"epoch": 48.0,
"learning_rate": 3.1848979591836735e-05,
"loss": 0.8513,
"step": 2400
},
{
"epoch": 48.2,
"learning_rate": 3.17265306122449e-05,
"loss": 0.89,
"step": 2410
},
{
"epoch": 48.4,
"learning_rate": 3.160408163265306e-05,
"loss": 0.8818,
"step": 2420
},
{
"epoch": 48.6,
"learning_rate": 3.1481632653061224e-05,
"loss": 0.8772,
"step": 2430
},
{
"epoch": 48.8,
"learning_rate": 3.1359183673469394e-05,
"loss": 0.8851,
"step": 2440
},
{
"epoch": 49.0,
"learning_rate": 3.123673469387755e-05,
"loss": 0.8568,
"step": 2450
},
{
"epoch": 49.2,
"learning_rate": 3.1114285714285714e-05,
"loss": 0.8949,
"step": 2460
},
{
"epoch": 49.4,
"learning_rate": 3.099183673469388e-05,
"loss": 0.8748,
"step": 2470
},
{
"epoch": 49.6,
"learning_rate": 3.086938775510204e-05,
"loss": 0.861,
"step": 2480
},
{
"epoch": 49.8,
"learning_rate": 3.074693877551021e-05,
"loss": 0.8878,
"step": 2490
},
{
"epoch": 50.0,
"learning_rate": 3.0624489795918366e-05,
"loss": 0.8399,
"step": 2500
},
{
"epoch": 50.0,
"eval_loss": 0.3605365753173828,
"eval_runtime": 244.9656,
"eval_samples_per_second": 21.276,
"eval_steps_per_second": 1.331,
"eval_wer": 0.377206226896444,
"step": 2500
},
{
"epoch": 50.2,
"learning_rate": 3.0502040816326532e-05,
"loss": 0.877,
"step": 2510
},
{
"epoch": 50.4,
"learning_rate": 3.0379591836734692e-05,
"loss": 0.8843,
"step": 2520
},
{
"epoch": 50.6,
"learning_rate": 3.0257142857142862e-05,
"loss": 0.8654,
"step": 2530
},
{
"epoch": 50.8,
"learning_rate": 3.013469387755102e-05,
"loss": 0.8465,
"step": 2540
},
{
"epoch": 51.0,
"learning_rate": 3.0012244897959184e-05,
"loss": 0.8448,
"step": 2550
},
{
"epoch": 51.2,
"learning_rate": 2.9889795918367348e-05,
"loss": 0.8887,
"step": 2560
},
{
"epoch": 51.4,
"learning_rate": 2.976734693877551e-05,
"loss": 0.8518,
"step": 2570
},
{
"epoch": 51.6,
"learning_rate": 2.9644897959183674e-05,
"loss": 0.887,
"step": 2580
},
{
"epoch": 51.8,
"learning_rate": 2.952244897959184e-05,
"loss": 0.8628,
"step": 2590
},
{
"epoch": 52.0,
"learning_rate": 2.94e-05,
"loss": 0.8681,
"step": 2600
},
{
"epoch": 52.2,
"learning_rate": 2.9277551020408166e-05,
"loss": 0.8941,
"step": 2610
},
{
"epoch": 52.4,
"learning_rate": 2.9155102040816326e-05,
"loss": 0.8754,
"step": 2620
},
{
"epoch": 52.6,
"learning_rate": 2.903265306122449e-05,
"loss": 0.8573,
"step": 2630
},
{
"epoch": 52.8,
"learning_rate": 2.8910204081632655e-05,
"loss": 0.8689,
"step": 2640
},
{
"epoch": 53.0,
"learning_rate": 2.8787755102040815e-05,
"loss": 0.8664,
"step": 2650
},
{
"epoch": 53.2,
"learning_rate": 2.866530612244898e-05,
"loss": 0.8923,
"step": 2660
},
{
"epoch": 53.4,
"learning_rate": 2.854285714285714e-05,
"loss": 0.8735,
"step": 2670
},
{
"epoch": 53.6,
"learning_rate": 2.8420408163265308e-05,
"loss": 0.8717,
"step": 2680
},
{
"epoch": 53.8,
"learning_rate": 2.829795918367347e-05,
"loss": 0.8558,
"step": 2690
},
{
"epoch": 54.0,
"learning_rate": 2.8175510204081634e-05,
"loss": 0.8226,
"step": 2700
},
{
"epoch": 54.2,
"learning_rate": 2.8053061224489797e-05,
"loss": 0.8947,
"step": 2710
},
{
"epoch": 54.4,
"learning_rate": 2.793061224489796e-05,
"loss": 0.8509,
"step": 2720
},
{
"epoch": 54.6,
"learning_rate": 2.7808163265306123e-05,
"loss": 0.8551,
"step": 2730
},
{
"epoch": 54.8,
"learning_rate": 2.7685714285714286e-05,
"loss": 0.8705,
"step": 2740
},
{
"epoch": 55.0,
"learning_rate": 2.756326530612245e-05,
"loss": 0.815,
"step": 2750
},
{
"epoch": 55.2,
"learning_rate": 2.7440816326530612e-05,
"loss": 0.8939,
"step": 2760
},
{
"epoch": 55.4,
"learning_rate": 2.731836734693878e-05,
"loss": 0.859,
"step": 2770
},
{
"epoch": 55.6,
"learning_rate": 2.7195918367346938e-05,
"loss": 0.8567,
"step": 2780
},
{
"epoch": 55.8,
"learning_rate": 2.7073469387755105e-05,
"loss": 0.8599,
"step": 2790
},
{
"epoch": 56.0,
"learning_rate": 2.6951020408163268e-05,
"loss": 0.8171,
"step": 2800
},
{
"epoch": 56.2,
"learning_rate": 2.6828571428571427e-05,
"loss": 0.896,
"step": 2810
},
{
"epoch": 56.4,
"learning_rate": 2.6706122448979594e-05,
"loss": 0.8554,
"step": 2820
},
{
"epoch": 56.6,
"learning_rate": 2.6583673469387753e-05,
"loss": 0.877,
"step": 2830
},
{
"epoch": 56.8,
"learning_rate": 2.646122448979592e-05,
"loss": 0.8576,
"step": 2840
},
{
"epoch": 57.0,
"learning_rate": 2.6338775510204083e-05,
"loss": 0.8321,
"step": 2850
},
{
"epoch": 57.2,
"learning_rate": 2.6216326530612246e-05,
"loss": 0.8606,
"step": 2860
},
{
"epoch": 57.4,
"learning_rate": 2.609387755102041e-05,
"loss": 0.8409,
"step": 2870
},
{
"epoch": 57.6,
"learning_rate": 2.5971428571428575e-05,
"loss": 0.8469,
"step": 2880
},
{
"epoch": 57.8,
"learning_rate": 2.5848979591836735e-05,
"loss": 0.8546,
"step": 2890
},
{
"epoch": 58.0,
"learning_rate": 2.5726530612244898e-05,
"loss": 0.829,
"step": 2900
},
{
"epoch": 58.2,
"learning_rate": 2.560408163265306e-05,
"loss": 0.8659,
"step": 2910
},
{
"epoch": 58.4,
"learning_rate": 2.5481632653061224e-05,
"loss": 0.877,
"step": 2920
},
{
"epoch": 58.6,
"learning_rate": 2.535918367346939e-05,
"loss": 0.8537,
"step": 2930
},
{
"epoch": 58.8,
"learning_rate": 2.523673469387755e-05,
"loss": 0.8489,
"step": 2940
},
{
"epoch": 59.0,
"learning_rate": 2.5114285714285717e-05,
"loss": 0.8184,
"step": 2950
},
{
"epoch": 59.2,
"learning_rate": 2.4991836734693876e-05,
"loss": 0.8597,
"step": 2960
},
{
"epoch": 59.4,
"learning_rate": 2.486938775510204e-05,
"loss": 0.8621,
"step": 2970
},
{
"epoch": 59.6,
"learning_rate": 2.4746938775510206e-05,
"loss": 0.8553,
"step": 2980
},
{
"epoch": 59.8,
"learning_rate": 2.4624489795918366e-05,
"loss": 0.8628,
"step": 2990
},
{
"epoch": 60.0,
"learning_rate": 2.4502040816326532e-05,
"loss": 0.819,
"step": 3000
},
{
"epoch": 60.0,
"eval_loss": 0.3622128367424011,
"eval_runtime": 245.6109,
"eval_samples_per_second": 21.221,
"eval_steps_per_second": 1.327,
"eval_wer": 0.3714270838756703,
"step": 3000
},
{
"epoch": 60.2,
"learning_rate": 2.4379591836734695e-05,
"loss": 0.8644,
"step": 3010
},
{
"epoch": 60.4,
"learning_rate": 2.4257142857142858e-05,
"loss": 0.8434,
"step": 3020
},
{
"epoch": 60.6,
"learning_rate": 2.413469387755102e-05,
"loss": 0.8402,
"step": 3030
},
{
"epoch": 60.8,
"learning_rate": 2.4012244897959184e-05,
"loss": 0.8412,
"step": 3040
},
{
"epoch": 61.0,
"learning_rate": 2.3889795918367347e-05,
"loss": 0.7999,
"step": 3050
},
{
"epoch": 61.2,
"learning_rate": 2.376734693877551e-05,
"loss": 0.8662,
"step": 3060
},
{
"epoch": 61.4,
"learning_rate": 2.3644897959183673e-05,
"loss": 0.8329,
"step": 3070
},
{
"epoch": 61.6,
"learning_rate": 2.3522448979591837e-05,
"loss": 0.8458,
"step": 3080
},
{
"epoch": 61.8,
"learning_rate": 2.3400000000000003e-05,
"loss": 0.8423,
"step": 3090
},
{
"epoch": 62.0,
"learning_rate": 2.3277551020408163e-05,
"loss": 0.8163,
"step": 3100
},
{
"epoch": 62.2,
"learning_rate": 2.315510204081633e-05,
"loss": 0.8645,
"step": 3110
},
{
"epoch": 62.4,
"learning_rate": 2.303265306122449e-05,
"loss": 0.8425,
"step": 3120
},
{
"epoch": 62.6,
"learning_rate": 2.2910204081632655e-05,
"loss": 0.8474,
"step": 3130
},
{
"epoch": 62.8,
"learning_rate": 2.2787755102040818e-05,
"loss": 0.8289,
"step": 3140
},
{
"epoch": 63.0,
"learning_rate": 2.2665306122448978e-05,
"loss": 0.8156,
"step": 3150
},
{
"epoch": 63.2,
"learning_rate": 2.2542857142857144e-05,
"loss": 0.8886,
"step": 3160
},
{
"epoch": 63.4,
"learning_rate": 2.243265306122449e-05,
"loss": 0.8355,
"step": 3170
},
{
"epoch": 63.6,
"learning_rate": 2.2310204081632654e-05,
"loss": 0.8291,
"step": 3180
},
{
"epoch": 63.8,
"learning_rate": 2.2187755102040817e-05,
"loss": 0.8588,
"step": 3190
},
{
"epoch": 64.0,
"learning_rate": 2.206530612244898e-05,
"loss": 0.8194,
"step": 3200
},
{
"epoch": 64.2,
"learning_rate": 2.1942857142857143e-05,
"loss": 0.8688,
"step": 3210
},
{
"epoch": 64.4,
"learning_rate": 2.1820408163265306e-05,
"loss": 0.8319,
"step": 3220
},
{
"epoch": 64.6,
"learning_rate": 2.169795918367347e-05,
"loss": 0.8505,
"step": 3230
},
{
"epoch": 64.8,
"learning_rate": 2.1575510204081632e-05,
"loss": 0.8435,
"step": 3240
},
{
"epoch": 65.0,
"learning_rate": 2.14530612244898e-05,
"loss": 0.8047,
"step": 3250
},
{
"epoch": 65.2,
"learning_rate": 2.133061224489796e-05,
"loss": 0.8568,
"step": 3260
},
{
"epoch": 65.4,
"learning_rate": 2.1208163265306125e-05,
"loss": 0.8305,
"step": 3270
},
{
"epoch": 65.6,
"learning_rate": 2.1085714285714285e-05,
"loss": 0.8424,
"step": 3280
},
{
"epoch": 65.8,
"learning_rate": 2.096326530612245e-05,
"loss": 0.8319,
"step": 3290
},
{
"epoch": 66.0,
"learning_rate": 2.0840816326530614e-05,
"loss": 0.823,
"step": 3300
},
{
"epoch": 66.2,
"learning_rate": 2.0718367346938774e-05,
"loss": 0.8754,
"step": 3310
},
{
"epoch": 66.4,
"learning_rate": 2.059591836734694e-05,
"loss": 0.8253,
"step": 3320
},
{
"epoch": 66.6,
"learning_rate": 2.04734693877551e-05,
"loss": 0.8429,
"step": 3330
},
{
"epoch": 66.8,
"learning_rate": 2.0351020408163266e-05,
"loss": 0.8286,
"step": 3340
},
{
"epoch": 67.0,
"learning_rate": 2.022857142857143e-05,
"loss": 0.8149,
"step": 3350
},
{
"epoch": 67.2,
"learning_rate": 2.0106122448979593e-05,
"loss": 0.8683,
"step": 3360
},
{
"epoch": 67.4,
"learning_rate": 1.9983673469387756e-05,
"loss": 0.8284,
"step": 3370
},
{
"epoch": 67.6,
"learning_rate": 1.986122448979592e-05,
"loss": 0.8363,
"step": 3380
},
{
"epoch": 67.8,
"learning_rate": 1.973877551020408e-05,
"loss": 0.8364,
"step": 3390
},
{
"epoch": 68.0,
"learning_rate": 1.9616326530612245e-05,
"loss": 0.8126,
"step": 3400
},
{
"epoch": 68.2,
"learning_rate": 1.9493877551020408e-05,
"loss": 0.8599,
"step": 3410
},
{
"epoch": 68.4,
"learning_rate": 1.937142857142857e-05,
"loss": 0.8182,
"step": 3420
},
{
"epoch": 68.6,
"learning_rate": 1.9248979591836737e-05,
"loss": 0.8344,
"step": 3430
},
{
"epoch": 68.8,
"learning_rate": 1.9126530612244897e-05,
"loss": 0.8158,
"step": 3440
},
{
"epoch": 69.0,
"learning_rate": 1.9004081632653063e-05,
"loss": 0.8117,
"step": 3450
},
{
"epoch": 69.2,
"learning_rate": 1.8881632653061226e-05,
"loss": 0.8421,
"step": 3460
},
{
"epoch": 69.4,
"learning_rate": 1.8759183673469386e-05,
"loss": 0.8264,
"step": 3470
},
{
"epoch": 69.6,
"learning_rate": 1.8636734693877553e-05,
"loss": 0.8356,
"step": 3480
},
{
"epoch": 69.8,
"learning_rate": 1.8514285714285712e-05,
"loss": 0.8316,
"step": 3490
},
{
"epoch": 70.0,
"learning_rate": 1.839183673469388e-05,
"loss": 0.8029,
"step": 3500
},
{
"epoch": 70.0,
"eval_loss": 0.3561089038848877,
"eval_runtime": 245.8818,
"eval_samples_per_second": 21.197,
"eval_steps_per_second": 1.326,
"eval_wer": 0.3663768417764357,
"step": 3500
},
{
"epoch": 70.2,
"learning_rate": 3.934545454545455e-05,
"loss": 0.8492,
"step": 3510
},
{
"epoch": 70.4,
"learning_rate": 3.928484848484849e-05,
"loss": 0.8477,
"step": 3520
},
{
"epoch": 70.6,
"learning_rate": 3.9224242424242426e-05,
"loss": 0.8657,
"step": 3530
},
{
"epoch": 70.8,
"learning_rate": 3.9163636363636364e-05,
"loss": 0.8734,
"step": 3540
},
{
"epoch": 71.0,
"learning_rate": 3.91030303030303e-05,
"loss": 0.8092,
"step": 3550
},
{
"epoch": 71.2,
"learning_rate": 3.904242424242424e-05,
"loss": 0.8904,
"step": 3560
},
{
"epoch": 71.4,
"learning_rate": 3.898181818181818e-05,
"loss": 0.8585,
"step": 3570
},
{
"epoch": 71.6,
"learning_rate": 3.892121212121212e-05,
"loss": 0.8565,
"step": 3580
},
{
"epoch": 71.8,
"learning_rate": 3.8860606060606056e-05,
"loss": 0.8823,
"step": 3590
},
{
"epoch": 72.0,
"learning_rate": 3.8799999999999994e-05,
"loss": 0.8282,
"step": 3600
},
{
"epoch": 72.2,
"learning_rate": 3.8739393939393946e-05,
"loss": 0.8659,
"step": 3610
},
{
"epoch": 72.4,
"learning_rate": 3.8678787878787885e-05,
"loss": 0.8746,
"step": 3620
},
{
"epoch": 72.6,
"learning_rate": 3.861818181818182e-05,
"loss": 0.8536,
"step": 3630
},
{
"epoch": 72.8,
"learning_rate": 3.855757575757576e-05,
"loss": 0.8535,
"step": 3640
},
{
"epoch": 73.0,
"learning_rate": 3.84969696969697e-05,
"loss": 0.8332,
"step": 3650
},
{
"epoch": 73.2,
"learning_rate": 3.843636363636364e-05,
"loss": 0.8779,
"step": 3660
},
{
"epoch": 73.4,
"learning_rate": 3.8375757575757576e-05,
"loss": 0.85,
"step": 3670
},
{
"epoch": 73.6,
"learning_rate": 3.8315151515151515e-05,
"loss": 0.8533,
"step": 3680
},
{
"epoch": 73.8,
"learning_rate": 3.825454545454545e-05,
"loss": 0.8542,
"step": 3690
},
{
"epoch": 74.0,
"learning_rate": 3.819393939393939e-05,
"loss": 0.8341,
"step": 3700
},
{
"epoch": 74.2,
"learning_rate": 3.8133333333333336e-05,
"loss": 0.8832,
"step": 3710
},
{
"epoch": 74.4,
"learning_rate": 3.8072727272727275e-05,
"loss": 0.8531,
"step": 3720
},
{
"epoch": 74.6,
"learning_rate": 3.801212121212121e-05,
"loss": 0.8413,
"step": 3730
},
{
"epoch": 74.8,
"learning_rate": 3.795151515151515e-05,
"loss": 0.8696,
"step": 3740
},
{
"epoch": 75.0,
"learning_rate": 3.789090909090909e-05,
"loss": 0.8196,
"step": 3750
},
{
"epoch": 75.2,
"learning_rate": 3.783030303030303e-05,
"loss": 0.8754,
"step": 3760
},
{
"epoch": 75.4,
"learning_rate": 3.7769696969696966e-05,
"loss": 0.8501,
"step": 3770
},
{
"epoch": 75.6,
"learning_rate": 3.770909090909091e-05,
"loss": 0.8606,
"step": 3780
},
{
"epoch": 75.8,
"learning_rate": 3.764848484848485e-05,
"loss": 0.836,
"step": 3790
},
{
"epoch": 76.0,
"learning_rate": 3.758787878787879e-05,
"loss": 0.814,
"step": 3800
},
{
"epoch": 76.2,
"learning_rate": 3.752727272727273e-05,
"loss": 0.8881,
"step": 3810
},
{
"epoch": 76.4,
"learning_rate": 3.746666666666667e-05,
"loss": 0.8602,
"step": 3820
},
{
"epoch": 76.6,
"learning_rate": 3.740606060606061e-05,
"loss": 0.8663,
"step": 3830
},
{
"epoch": 76.8,
"learning_rate": 3.734545454545455e-05,
"loss": 0.8413,
"step": 3840
},
{
"epoch": 77.0,
"learning_rate": 3.7284848484848487e-05,
"loss": 0.8251,
"step": 3850
},
{
"epoch": 77.2,
"learning_rate": 3.7224242424242425e-05,
"loss": 0.8757,
"step": 3860
},
{
"epoch": 77.4,
"learning_rate": 3.716363636363636e-05,
"loss": 0.8527,
"step": 3870
},
{
"epoch": 77.6,
"learning_rate": 3.71030303030303e-05,
"loss": 0.8572,
"step": 3880
},
{
"epoch": 77.8,
"learning_rate": 3.704848484848485e-05,
"loss": 0.8577,
"step": 3890
},
{
"epoch": 78.0,
"learning_rate": 3.698787878787879e-05,
"loss": 0.8164,
"step": 3900
},
{
"epoch": 78.2,
"learning_rate": 3.692727272727273e-05,
"loss": 0.8743,
"step": 3910
},
{
"epoch": 78.4,
"learning_rate": 3.686666666666667e-05,
"loss": 0.8553,
"step": 3920
},
{
"epoch": 78.6,
"learning_rate": 3.680606060606061e-05,
"loss": 0.8113,
"step": 3930
},
{
"epoch": 78.8,
"learning_rate": 3.674545454545455e-05,
"loss": 0.867,
"step": 3940
},
{
"epoch": 79.0,
"learning_rate": 3.6684848484848486e-05,
"loss": 0.8343,
"step": 3950
},
{
"epoch": 79.2,
"learning_rate": 3.6624242424242424e-05,
"loss": 0.8653,
"step": 3960
},
{
"epoch": 79.4,
"learning_rate": 3.656363636363636e-05,
"loss": 0.8443,
"step": 3970
},
{
"epoch": 79.6,
"learning_rate": 3.65030303030303e-05,
"loss": 0.8488,
"step": 3980
},
{
"epoch": 79.8,
"learning_rate": 3.644242424242424e-05,
"loss": 0.8573,
"step": 3990
},
{
"epoch": 80.0,
"learning_rate": 3.638181818181818e-05,
"loss": 0.8104,
"step": 4000
},
{
"epoch": 80.0,
"eval_loss": 0.35952043533325195,
"eval_runtime": 247.7629,
"eval_samples_per_second": 21.036,
"eval_steps_per_second": 1.316,
"eval_wer": 0.36596032696412767,
"step": 4000
},
{
"epoch": 80.2,
"learning_rate": 3.632121212121212e-05,
"loss": 0.8759,
"step": 4010
},
{
"epoch": 80.4,
"learning_rate": 3.626060606060606e-05,
"loss": 0.835,
"step": 4020
},
{
"epoch": 80.6,
"learning_rate": 3.6200000000000006e-05,
"loss": 0.8466,
"step": 4030
},
{
"epoch": 80.8,
"learning_rate": 3.6139393939393944e-05,
"loss": 0.8545,
"step": 4040
},
{
"epoch": 81.0,
"learning_rate": 3.607878787878788e-05,
"loss": 0.8075,
"step": 4050
},
{
"epoch": 81.2,
"learning_rate": 3.601818181818182e-05,
"loss": 0.8679,
"step": 4060
},
{
"epoch": 81.4,
"learning_rate": 3.595757575757576e-05,
"loss": 0.8332,
"step": 4070
},
{
"epoch": 81.6,
"learning_rate": 3.58969696969697e-05,
"loss": 0.85,
"step": 4080
},
{
"epoch": 81.8,
"learning_rate": 3.5836363636363636e-05,
"loss": 0.861,
"step": 4090
},
{
"epoch": 82.0,
"learning_rate": 3.5775757575757574e-05,
"loss": 0.8356,
"step": 4100
},
{
"epoch": 82.2,
"learning_rate": 3.571515151515152e-05,
"loss": 0.8513,
"step": 4110
},
{
"epoch": 82.4,
"learning_rate": 3.565454545454546e-05,
"loss": 0.8467,
"step": 4120
},
{
"epoch": 82.6,
"learning_rate": 3.5593939393939396e-05,
"loss": 0.8141,
"step": 4130
},
{
"epoch": 82.8,
"learning_rate": 3.5533333333333334e-05,
"loss": 0.8386,
"step": 4140
},
{
"epoch": 83.0,
"learning_rate": 3.547272727272727e-05,
"loss": 0.8169,
"step": 4150
},
{
"epoch": 83.2,
"learning_rate": 3.541212121212121e-05,
"loss": 0.8609,
"step": 4160
},
{
"epoch": 83.4,
"learning_rate": 3.535151515151515e-05,
"loss": 0.8391,
"step": 4170
},
{
"epoch": 83.6,
"learning_rate": 3.529090909090909e-05,
"loss": 0.8345,
"step": 4180
},
{
"epoch": 83.8,
"learning_rate": 3.5230303030303026e-05,
"loss": 0.8368,
"step": 4190
},
{
"epoch": 84.0,
"learning_rate": 3.516969696969697e-05,
"loss": 0.8145,
"step": 4200
},
{
"epoch": 84.2,
"learning_rate": 3.5109090909090916e-05,
"loss": 0.8446,
"step": 4210
},
{
"epoch": 84.4,
"learning_rate": 3.5048484848484854e-05,
"loss": 0.8176,
"step": 4220
},
{
"epoch": 84.6,
"learning_rate": 3.498787878787879e-05,
"loss": 0.8356,
"step": 4230
},
{
"epoch": 84.8,
"learning_rate": 3.492727272727273e-05,
"loss": 0.8251,
"step": 4240
},
{
"epoch": 85.0,
"learning_rate": 3.486666666666667e-05,
"loss": 0.8151,
"step": 4250
},
{
"epoch": 85.2,
"learning_rate": 3.480606060606061e-05,
"loss": 0.8549,
"step": 4260
},
{
"epoch": 85.4,
"learning_rate": 3.4745454545454546e-05,
"loss": 0.8515,
"step": 4270
},
{
"epoch": 85.6,
"learning_rate": 3.4684848484848484e-05,
"loss": 0.8255,
"step": 4280
},
{
"epoch": 85.8,
"learning_rate": 3.462424242424242e-05,
"loss": 0.8325,
"step": 4290
},
{
"epoch": 86.0,
"learning_rate": 3.456363636363636e-05,
"loss": 0.8162,
"step": 4300
},
{
"epoch": 86.2,
"learning_rate": 3.4503030303030306e-05,
"loss": 0.8628,
"step": 4310
},
{
"epoch": 86.4,
"learning_rate": 3.4442424242424244e-05,
"loss": 0.8125,
"step": 4320
},
{
"epoch": 86.6,
"learning_rate": 3.438181818181818e-05,
"loss": 0.8436,
"step": 4330
},
{
"epoch": 86.8,
"learning_rate": 3.432121212121212e-05,
"loss": 0.8343,
"step": 4340
},
{
"epoch": 87.0,
"learning_rate": 3.426060606060606e-05,
"loss": 0.8063,
"step": 4350
},
{
"epoch": 87.2,
"learning_rate": 3.42e-05,
"loss": 0.8492,
"step": 4360
},
{
"epoch": 87.4,
"learning_rate": 3.4139393939393936e-05,
"loss": 0.8393,
"step": 4370
},
{
"epoch": 87.6,
"learning_rate": 3.407878787878788e-05,
"loss": 0.827,
"step": 4380
},
{
"epoch": 87.8,
"learning_rate": 3.401818181818182e-05,
"loss": 0.8371,
"step": 4390
},
{
"epoch": 88.0,
"learning_rate": 3.395757575757576e-05,
"loss": 0.8047,
"step": 4400
},
{
"epoch": 88.2,
"learning_rate": 3.3896969696969696e-05,
"loss": 0.8506,
"step": 4410
},
{
"epoch": 88.4,
"learning_rate": 3.383636363636364e-05,
"loss": 0.8203,
"step": 4420
},
{
"epoch": 88.6,
"learning_rate": 3.377575757575758e-05,
"loss": 0.8127,
"step": 4430
},
{
"epoch": 88.8,
"learning_rate": 3.371515151515152e-05,
"loss": 0.8318,
"step": 4440
},
{
"epoch": 89.0,
"learning_rate": 3.3654545454545456e-05,
"loss": 0.801,
"step": 4450
},
{
"epoch": 89.2,
"learning_rate": 3.3593939393939395e-05,
"loss": 0.8433,
"step": 4460
},
{
"epoch": 89.4,
"learning_rate": 3.353333333333333e-05,
"loss": 0.8188,
"step": 4470
},
{
"epoch": 89.6,
"learning_rate": 3.347272727272727e-05,
"loss": 0.8296,
"step": 4480
},
{
"epoch": 89.8,
"learning_rate": 3.341212121212121e-05,
"loss": 0.8313,
"step": 4490
},
{
"epoch": 90.0,
"learning_rate": 3.335151515151515e-05,
"loss": 0.8118,
"step": 4500
},
{
"epoch": 90.0,
"eval_loss": 0.3459583818912506,
"eval_runtime": 243.3931,
"eval_samples_per_second": 21.414,
"eval_steps_per_second": 1.339,
"eval_wer": 0.3591659290883532,
"step": 4500
},
{
"epoch": 90.2,
"learning_rate": 3.3290909090909086e-05,
"loss": 0.8586,
"step": 4510
},
{
"epoch": 90.4,
"learning_rate": 3.323030303030303e-05,
"loss": 0.8303,
"step": 4520
},
{
"epoch": 90.6,
"learning_rate": 3.316969696969697e-05,
"loss": 0.8199,
"step": 4530
},
{
"epoch": 90.8,
"learning_rate": 3.310909090909091e-05,
"loss": 0.8272,
"step": 4540
},
{
"epoch": 91.0,
"learning_rate": 3.304848484848485e-05,
"loss": 0.7925,
"step": 4550
},
{
"epoch": 91.2,
"learning_rate": 3.298787878787879e-05,
"loss": 0.8542,
"step": 4560
},
{
"epoch": 91.4,
"learning_rate": 3.292727272727273e-05,
"loss": 0.8222,
"step": 4570
},
{
"epoch": 91.6,
"learning_rate": 3.286666666666667e-05,
"loss": 0.7901,
"step": 4580
},
{
"epoch": 91.8,
"learning_rate": 3.2806060606060607e-05,
"loss": 0.8227,
"step": 4590
},
{
"epoch": 92.0,
"learning_rate": 3.2745454545454545e-05,
"loss": 0.7861,
"step": 4600
},
{
"epoch": 92.2,
"learning_rate": 3.268484848484848e-05,
"loss": 0.8382,
"step": 4610
},
{
"epoch": 92.4,
"learning_rate": 3.262424242424243e-05,
"loss": 0.8279,
"step": 4620
},
{
"epoch": 92.6,
"learning_rate": 3.256363636363637e-05,
"loss": 0.8148,
"step": 4630
},
{
"epoch": 92.8,
"learning_rate": 3.2503030303030305e-05,
"loss": 0.8054,
"step": 4640
},
{
"epoch": 93.0,
"learning_rate": 3.244242424242424e-05,
"loss": 0.8003,
"step": 4650
},
{
"epoch": 93.2,
"learning_rate": 3.238181818181818e-05,
"loss": 0.8252,
"step": 4660
},
{
"epoch": 93.4,
"learning_rate": 3.232121212121212e-05,
"loss": 0.8,
"step": 4670
},
{
"epoch": 93.6,
"learning_rate": 3.226060606060606e-05,
"loss": 0.811,
"step": 4680
},
{
"epoch": 93.8,
"learning_rate": 3.22e-05,
"loss": 0.8202,
"step": 4690
},
{
"epoch": 94.0,
"learning_rate": 3.2139393939393935e-05,
"loss": 0.7872,
"step": 4700
},
{
"epoch": 94.2,
"learning_rate": 3.207878787878787e-05,
"loss": 0.8567,
"step": 4710
},
{
"epoch": 94.4,
"learning_rate": 3.2018181818181825e-05,
"loss": 0.8226,
"step": 4720
},
{
"epoch": 94.6,
"learning_rate": 3.1957575757575764e-05,
"loss": 0.7977,
"step": 4730
},
{
"epoch": 94.8,
"learning_rate": 3.18969696969697e-05,
"loss": 0.8119,
"step": 4740
},
{
"epoch": 95.0,
"learning_rate": 3.183636363636364e-05,
"loss": 0.7972,
"step": 4750
},
{
"epoch": 95.2,
"learning_rate": 3.177575757575758e-05,
"loss": 0.8297,
"step": 4760
},
{
"epoch": 95.4,
"learning_rate": 3.171515151515152e-05,
"loss": 0.8184,
"step": 4770
},
{
"epoch": 95.6,
"learning_rate": 3.1654545454545455e-05,
"loss": 0.8319,
"step": 4780
},
{
"epoch": 95.8,
"learning_rate": 3.1593939393939394e-05,
"loss": 0.7927,
"step": 4790
},
{
"epoch": 96.0,
"learning_rate": 3.153333333333333e-05,
"loss": 0.781,
"step": 4800
},
{
"epoch": 96.2,
"learning_rate": 3.147272727272727e-05,
"loss": 0.8324,
"step": 4810
},
{
"epoch": 96.4,
"learning_rate": 3.1412121212121215e-05,
"loss": 0.8089,
"step": 4820
},
{
"epoch": 96.6,
"learning_rate": 3.1351515151515154e-05,
"loss": 0.8066,
"step": 4830
},
{
"epoch": 96.8,
"learning_rate": 3.129090909090909e-05,
"loss": 0.8038,
"step": 4840
},
{
"epoch": 97.0,
"learning_rate": 3.123030303030303e-05,
"loss": 0.7848,
"step": 4850
},
{
"epoch": 97.2,
"learning_rate": 3.116969696969697e-05,
"loss": 0.7951,
"step": 4860
},
{
"epoch": 97.4,
"learning_rate": 3.110909090909091e-05,
"loss": 0.8023,
"step": 4870
},
{
"epoch": 97.6,
"learning_rate": 3.1048484848484845e-05,
"loss": 0.8058,
"step": 4880
},
{
"epoch": 97.8,
"learning_rate": 3.098787878787879e-05,
"loss": 0.8003,
"step": 4890
},
{
"epoch": 98.0,
"learning_rate": 3.092727272727273e-05,
"loss": 0.7844,
"step": 4900
},
{
"epoch": 98.2,
"learning_rate": 3.086666666666667e-05,
"loss": 0.8175,
"step": 4910
},
{
"epoch": 98.4,
"learning_rate": 3.0806060606060605e-05,
"loss": 0.8186,
"step": 4920
},
{
"epoch": 98.6,
"learning_rate": 3.074545454545455e-05,
"loss": 0.8055,
"step": 4930
},
{
"epoch": 98.8,
"learning_rate": 3.068484848484849e-05,
"loss": 0.8004,
"step": 4940
},
{
"epoch": 99.0,
"learning_rate": 3.062424242424243e-05,
"loss": 0.7751,
"step": 4950
},
{
"epoch": 99.2,
"learning_rate": 3.0563636363636365e-05,
"loss": 0.8077,
"step": 4960
},
{
"epoch": 99.4,
"learning_rate": 3.0503030303030304e-05,
"loss": 0.7806,
"step": 4970
},
{
"epoch": 99.6,
"learning_rate": 3.0442424242424242e-05,
"loss": 0.8005,
"step": 4980
},
{
"epoch": 99.8,
"learning_rate": 3.038181818181818e-05,
"loss": 0.7966,
"step": 4990
},
{
"epoch": 100.0,
"learning_rate": 3.0321212121212122e-05,
"loss": 0.7831,
"step": 5000
},
{
"epoch": 100.0,
"eval_loss": 0.35662171244621277,
"eval_runtime": 244.6026,
"eval_samples_per_second": 21.308,
"eval_steps_per_second": 1.333,
"eval_wer": 0.35934815431873796,
"step": 5000
},
{
"epoch": 100.2,
"learning_rate": 3.026060606060606e-05,
"loss": 0.8186,
"step": 5010
},
{
"epoch": 100.4,
"learning_rate": 3.02e-05,
"loss": 0.7988,
"step": 5020
},
{
"epoch": 100.6,
"learning_rate": 3.0139393939393937e-05,
"loss": 0.7912,
"step": 5030
},
{
"epoch": 100.8,
"learning_rate": 3.0078787878787876e-05,
"loss": 0.7922,
"step": 5040
},
{
"epoch": 101.0,
"learning_rate": 3.0018181818181817e-05,
"loss": 0.8013,
"step": 5050
},
{
"epoch": 101.2,
"learning_rate": 2.995757575757576e-05,
"loss": 0.8025,
"step": 5060
},
{
"epoch": 101.4,
"learning_rate": 2.9896969696969697e-05,
"loss": 0.8028,
"step": 5070
},
{
"epoch": 101.6,
"learning_rate": 2.9836363636363636e-05,
"loss": 0.8106,
"step": 5080
},
{
"epoch": 101.8,
"learning_rate": 2.9775757575757574e-05,
"loss": 0.8195,
"step": 5090
},
{
"epoch": 102.0,
"learning_rate": 2.971515151515152e-05,
"loss": 0.7637,
"step": 5100
},
{
"epoch": 102.2,
"learning_rate": 2.9654545454545457e-05,
"loss": 0.8283,
"step": 5110
},
{
"epoch": 102.4,
"learning_rate": 2.9593939393939396e-05,
"loss": 0.7809,
"step": 5120
},
{
"epoch": 102.6,
"learning_rate": 2.9533333333333334e-05,
"loss": 0.7841,
"step": 5130
},
{
"epoch": 102.8,
"learning_rate": 2.9472727272727272e-05,
"loss": 0.7974,
"step": 5140
},
{
"epoch": 103.0,
"learning_rate": 2.9412121212121214e-05,
"loss": 0.786,
"step": 5150
},
{
"epoch": 103.2,
"learning_rate": 2.9351515151515152e-05,
"loss": 0.8257,
"step": 5160
},
{
"epoch": 103.4,
"learning_rate": 2.929090909090909e-05,
"loss": 0.7662,
"step": 5170
},
{
"epoch": 103.6,
"learning_rate": 2.923030303030303e-05,
"loss": 0.7893,
"step": 5180
},
{
"epoch": 103.8,
"learning_rate": 2.916969696969697e-05,
"loss": 0.7976,
"step": 5190
},
{
"epoch": 104.0,
"learning_rate": 2.910909090909091e-05,
"loss": 0.7868,
"step": 5200
},
{
"epoch": 104.2,
"learning_rate": 2.904848484848485e-05,
"loss": 0.8219,
"step": 5210
},
{
"epoch": 104.4,
"learning_rate": 2.898787878787879e-05,
"loss": 0.7969,
"step": 5220
},
{
"epoch": 104.6,
"learning_rate": 2.8927272727272728e-05,
"loss": 0.7914,
"step": 5230
},
{
"epoch": 104.8,
"learning_rate": 2.8866666666666666e-05,
"loss": 0.7971,
"step": 5240
},
{
"epoch": 105.0,
"learning_rate": 2.8806060606060604e-05,
"loss": 0.7807,
"step": 5250
},
{
"epoch": 105.2,
"learning_rate": 2.8745454545454546e-05,
"loss": 0.803,
"step": 5260
},
{
"epoch": 105.4,
"learning_rate": 2.8684848484848488e-05,
"loss": 0.81,
"step": 5270
},
{
"epoch": 105.6,
"learning_rate": 2.8624242424242426e-05,
"loss": 0.7943,
"step": 5280
},
{
"epoch": 105.8,
"learning_rate": 2.8563636363636364e-05,
"loss": 0.7767,
"step": 5290
},
{
"epoch": 106.0,
"learning_rate": 2.8503030303030303e-05,
"loss": 0.7721,
"step": 5300
},
{
"epoch": 106.2,
"learning_rate": 2.8442424242424244e-05,
"loss": 0.7863,
"step": 5310
},
{
"epoch": 106.4,
"learning_rate": 2.8381818181818183e-05,
"loss": 0.7824,
"step": 5320
},
{
"epoch": 106.6,
"learning_rate": 2.832121212121212e-05,
"loss": 0.8002,
"step": 5330
},
{
"epoch": 106.8,
"learning_rate": 2.826060606060606e-05,
"loss": 0.7921,
"step": 5340
},
{
"epoch": 107.0,
"learning_rate": 2.8199999999999998e-05,
"loss": 0.7757,
"step": 5350
},
{
"epoch": 107.2,
"learning_rate": 2.8139393939393943e-05,
"loss": 0.8046,
"step": 5360
},
{
"epoch": 107.4,
"learning_rate": 2.807878787878788e-05,
"loss": 0.775,
"step": 5370
},
{
"epoch": 107.6,
"learning_rate": 2.801818181818182e-05,
"loss": 0.7975,
"step": 5380
},
{
"epoch": 107.8,
"learning_rate": 2.7957575757575758e-05,
"loss": 0.794,
"step": 5390
},
{
"epoch": 108.0,
"learning_rate": 2.7896969696969696e-05,
"loss": 0.7465,
"step": 5400
},
{
"epoch": 108.2,
"learning_rate": 2.7836363636363638e-05,
"loss": 0.8104,
"step": 5410
},
{
"epoch": 108.4,
"learning_rate": 2.7775757575757576e-05,
"loss": 0.7862,
"step": 5420
},
{
"epoch": 108.6,
"learning_rate": 2.7715151515151514e-05,
"loss": 0.7767,
"step": 5430
},
{
"epoch": 108.8,
"learning_rate": 2.7654545454545456e-05,
"loss": 0.7807,
"step": 5440
},
{
"epoch": 109.0,
"learning_rate": 2.7593939393939395e-05,
"loss": 0.7628,
"step": 5450
},
{
"epoch": 109.2,
"learning_rate": 2.7533333333333336e-05,
"loss": 0.8077,
"step": 5460
},
{
"epoch": 109.4,
"learning_rate": 2.7472727272727275e-05,
"loss": 0.8049,
"step": 5470
},
{
"epoch": 109.6,
"learning_rate": 2.7412121212121213e-05,
"loss": 0.777,
"step": 5480
},
{
"epoch": 109.8,
"learning_rate": 2.735151515151515e-05,
"loss": 0.7799,
"step": 5490
},
{
"epoch": 110.0,
"learning_rate": 2.729090909090909e-05,
"loss": 0.744,
"step": 5500
},
{
"epoch": 110.0,
"eval_loss": 0.35784289240837097,
"eval_runtime": 244.0889,
"eval_samples_per_second": 21.353,
"eval_steps_per_second": 1.336,
"eval_wer": 0.35351694694642577,
"step": 5500
},
{
"epoch": 110.2,
"learning_rate": 2.723030303030303e-05,
"loss": 0.7943,
"step": 5510
},
{
"epoch": 110.4,
"learning_rate": 2.716969696969697e-05,
"loss": 0.7865,
"step": 5520
},
{
"epoch": 110.6,
"learning_rate": 2.710909090909091e-05,
"loss": 0.7929,
"step": 5530
},
{
"epoch": 110.8,
"learning_rate": 2.704848484848485e-05,
"loss": 0.7974,
"step": 5540
},
{
"epoch": 111.0,
"learning_rate": 2.6987878787878788e-05,
"loss": 0.765,
"step": 5550
},
{
"epoch": 111.2,
"learning_rate": 2.692727272727273e-05,
"loss": 0.7867,
"step": 5560
},
{
"epoch": 111.4,
"learning_rate": 2.6866666666666668e-05,
"loss": 0.7903,
"step": 5570
},
{
"epoch": 111.6,
"learning_rate": 2.6806060606060606e-05,
"loss": 0.7852,
"step": 5580
},
{
"epoch": 111.8,
"learning_rate": 2.6745454545454545e-05,
"loss": 0.7745,
"step": 5590
},
{
"epoch": 112.0,
"learning_rate": 2.6684848484848483e-05,
"loss": 0.7464,
"step": 5600
},
{
"epoch": 112.2,
"learning_rate": 2.6624242424242428e-05,
"loss": 0.8193,
"step": 5610
},
{
"epoch": 112.4,
"learning_rate": 2.6563636363636366e-05,
"loss": 0.7732,
"step": 5620
},
{
"epoch": 112.6,
"learning_rate": 2.6503030303030305e-05,
"loss": 0.7941,
"step": 5630
},
{
"epoch": 112.8,
"learning_rate": 2.6442424242424243e-05,
"loss": 0.7822,
"step": 5640
},
{
"epoch": 113.0,
"learning_rate": 2.638181818181818e-05,
"loss": 0.7487,
"step": 5650
},
{
"epoch": 113.2,
"learning_rate": 2.632121212121212e-05,
"loss": 0.7932,
"step": 5660
},
{
"epoch": 113.4,
"learning_rate": 2.626060606060606e-05,
"loss": 0.7677,
"step": 5670
},
{
"epoch": 113.6,
"learning_rate": 2.62e-05,
"loss": 0.7945,
"step": 5680
},
{
"epoch": 113.8,
"learning_rate": 2.6139393939393938e-05,
"loss": 0.781,
"step": 5690
},
{
"epoch": 114.0,
"learning_rate": 2.607878787878788e-05,
"loss": 0.7669,
"step": 5700
},
{
"epoch": 114.2,
"learning_rate": 2.6018181818181818e-05,
"loss": 0.7967,
"step": 5710
},
{
"epoch": 114.4,
"learning_rate": 2.595757575757576e-05,
"loss": 0.7637,
"step": 5720
},
{
"epoch": 114.6,
"learning_rate": 2.58969696969697e-05,
"loss": 0.766,
"step": 5730
},
{
"epoch": 114.8,
"learning_rate": 2.5836363636363637e-05,
"loss": 0.7611,
"step": 5740
},
{
"epoch": 115.0,
"learning_rate": 2.5775757575757575e-05,
"loss": 0.761,
"step": 5750
},
{
"epoch": 115.2,
"learning_rate": 2.5715151515151513e-05,
"loss": 0.7997,
"step": 5760
},
{
"epoch": 115.4,
"learning_rate": 2.5654545454545455e-05,
"loss": 0.773,
"step": 5770
},
{
"epoch": 115.6,
"learning_rate": 2.5593939393939397e-05,
"loss": 0.7727,
"step": 5780
},
{
"epoch": 115.8,
"learning_rate": 2.5533333333333335e-05,
"loss": 0.771,
"step": 5790
},
{
"epoch": 116.0,
"learning_rate": 2.5472727272727273e-05,
"loss": 0.7392,
"step": 5800
},
{
"epoch": 116.2,
"learning_rate": 2.5412121212121212e-05,
"loss": 0.795,
"step": 5810
},
{
"epoch": 116.4,
"learning_rate": 2.5351515151515153e-05,
"loss": 0.7673,
"step": 5820
},
{
"epoch": 116.6,
"learning_rate": 2.5290909090909092e-05,
"loss": 0.7486,
"step": 5830
},
{
"epoch": 116.8,
"learning_rate": 2.523030303030303e-05,
"loss": 0.78,
"step": 5840
},
{
"epoch": 117.0,
"learning_rate": 2.516969696969697e-05,
"loss": 0.7339,
"step": 5850
},
{
"epoch": 117.2,
"learning_rate": 2.5109090909090907e-05,
"loss": 0.8006,
"step": 5860
},
{
"epoch": 117.4,
"learning_rate": 2.5048484848484852e-05,
"loss": 0.7578,
"step": 5870
},
{
"epoch": 117.6,
"learning_rate": 2.498787878787879e-05,
"loss": 0.765,
"step": 5880
},
{
"epoch": 117.8,
"learning_rate": 2.492727272727273e-05,
"loss": 0.7907,
"step": 5890
},
{
"epoch": 118.0,
"learning_rate": 2.4866666666666667e-05,
"loss": 0.7417,
"step": 5900
},
{
"epoch": 118.2,
"learning_rate": 2.4806060606060605e-05,
"loss": 0.7902,
"step": 5910
},
{
"epoch": 118.4,
"learning_rate": 2.4745454545454547e-05,
"loss": 0.7617,
"step": 5920
},
{
"epoch": 118.6,
"learning_rate": 2.4684848484848485e-05,
"loss": 0.771,
"step": 5930
},
{
"epoch": 118.8,
"learning_rate": 2.4624242424242424e-05,
"loss": 0.7884,
"step": 5940
},
{
"epoch": 119.0,
"learning_rate": 2.4563636363636365e-05,
"loss": 0.7506,
"step": 5950
},
{
"epoch": 119.2,
"learning_rate": 2.4503030303030304e-05,
"loss": 0.7876,
"step": 5960
},
{
"epoch": 119.4,
"learning_rate": 2.4442424242424245e-05,
"loss": 0.7781,
"step": 5970
},
{
"epoch": 119.6,
"learning_rate": 2.4381818181818184e-05,
"loss": 0.7787,
"step": 5980
},
{
"epoch": 119.8,
"learning_rate": 2.4321212121212122e-05,
"loss": 0.7615,
"step": 5990
},
{
"epoch": 120.0,
"learning_rate": 2.426060606060606e-05,
"loss": 0.7388,
"step": 6000
},
{
"epoch": 120.0,
"eval_loss": 0.353779673576355,
"eval_runtime": 243.4641,
"eval_samples_per_second": 21.408,
"eval_steps_per_second": 1.339,
"eval_wer": 0.3520331129275785,
"step": 6000
},
{
"epoch": 120.2,
"learning_rate": 2.42e-05,
"loss": 0.7812,
"step": 6010
},
{
"epoch": 120.4,
"learning_rate": 2.413939393939394e-05,
"loss": 0.7723,
"step": 6020
},
{
"epoch": 120.6,
"learning_rate": 2.407878787878788e-05,
"loss": 0.7685,
"step": 6030
},
{
"epoch": 120.8,
"learning_rate": 2.401818181818182e-05,
"loss": 0.7561,
"step": 6040
},
{
"epoch": 121.0,
"learning_rate": 2.395757575757576e-05,
"loss": 0.7497,
"step": 6050
},
{
"epoch": 121.2,
"learning_rate": 2.3896969696969697e-05,
"loss": 0.8065,
"step": 6060
},
{
"epoch": 121.4,
"learning_rate": 2.383636363636364e-05,
"loss": 0.7661,
"step": 6070
},
{
"epoch": 121.6,
"learning_rate": 2.3775757575757577e-05,
"loss": 0.7622,
"step": 6080
},
{
"epoch": 121.8,
"learning_rate": 2.3715151515151516e-05,
"loss": 0.7465,
"step": 6090
},
{
"epoch": 122.0,
"learning_rate": 2.3654545454545454e-05,
"loss": 0.7463,
"step": 6100
},
{
"epoch": 122.2,
"learning_rate": 2.3593939393939392e-05,
"loss": 0.7849,
"step": 6110
},
{
"epoch": 122.4,
"learning_rate": 2.3533333333333337e-05,
"loss": 0.7639,
"step": 6120
},
{
"epoch": 122.6,
"learning_rate": 2.3472727272727276e-05,
"loss": 0.7712,
"step": 6130
},
{
"epoch": 122.8,
"learning_rate": 2.3412121212121214e-05,
"loss": 0.7513,
"step": 6140
},
{
"epoch": 123.0,
"learning_rate": 2.3351515151515152e-05,
"loss": 0.7454,
"step": 6150
},
{
"epoch": 123.2,
"learning_rate": 2.329090909090909e-05,
"loss": 0.7733,
"step": 6160
},
{
"epoch": 123.4,
"learning_rate": 2.323030303030303e-05,
"loss": 0.7506,
"step": 6170
},
{
"epoch": 123.6,
"learning_rate": 2.316969696969697e-05,
"loss": 0.7561,
"step": 6180
},
{
"epoch": 123.8,
"learning_rate": 2.310909090909091e-05,
"loss": 0.7694,
"step": 6190
},
{
"epoch": 124.0,
"learning_rate": 2.3048484848484847e-05,
"loss": 0.7404,
"step": 6200
},
{
"epoch": 124.2,
"learning_rate": 2.298787878787879e-05,
"loss": 0.7819,
"step": 6210
},
{
"epoch": 124.4,
"learning_rate": 2.2927272727272727e-05,
"loss": 0.7499,
"step": 6220
},
{
"epoch": 124.6,
"learning_rate": 2.286666666666667e-05,
"loss": 0.756,
"step": 6230
},
{
"epoch": 124.8,
"learning_rate": 2.2806060606060607e-05,
"loss": 0.7716,
"step": 6240
},
{
"epoch": 125.0,
"learning_rate": 2.2745454545454546e-05,
"loss": 0.7427,
"step": 6250
},
{
"epoch": 125.2,
"learning_rate": 2.2684848484848484e-05,
"loss": 0.7816,
"step": 6260
},
{
"epoch": 125.4,
"learning_rate": 2.2624242424242422e-05,
"loss": 0.7623,
"step": 6270
},
{
"epoch": 125.6,
"learning_rate": 2.2563636363636364e-05,
"loss": 0.7561,
"step": 6280
},
{
"epoch": 125.8,
"learning_rate": 2.2503030303030302e-05,
"loss": 0.7409,
"step": 6290
},
{
"epoch": 126.0,
"learning_rate": 2.2442424242424244e-05,
"loss": 0.7169,
"step": 6300
},
{
"epoch": 126.2,
"learning_rate": 2.2381818181818183e-05,
"loss": 0.7972,
"step": 6310
},
{
"epoch": 126.4,
"learning_rate": 2.232121212121212e-05,
"loss": 0.7426,
"step": 6320
},
{
"epoch": 126.6,
"learning_rate": 2.2260606060606063e-05,
"loss": 0.7575,
"step": 6330
},
{
"epoch": 126.8,
"learning_rate": 2.22e-05,
"loss": 0.7446,
"step": 6340
},
{
"epoch": 127.0,
"learning_rate": 2.213939393939394e-05,
"loss": 0.7381,
"step": 6350
},
{
"epoch": 127.2,
"learning_rate": 2.2078787878787878e-05,
"loss": 0.7664,
"step": 6360
},
{
"epoch": 127.4,
"learning_rate": 2.2018181818181816e-05,
"loss": 0.7522,
"step": 6370
},
{
"epoch": 127.6,
"learning_rate": 2.195757575757576e-05,
"loss": 0.7696,
"step": 6380
},
{
"epoch": 127.8,
"learning_rate": 2.18969696969697e-05,
"loss": 0.7475,
"step": 6390
},
{
"epoch": 128.0,
"learning_rate": 2.1836363636363638e-05,
"loss": 0.7163,
"step": 6400
},
{
"epoch": 128.2,
"learning_rate": 2.1775757575757576e-05,
"loss": 0.7693,
"step": 6410
},
{
"epoch": 128.4,
"learning_rate": 2.1715151515151514e-05,
"loss": 0.7437,
"step": 6420
},
{
"epoch": 128.6,
"learning_rate": 2.1654545454545456e-05,
"loss": 0.7631,
"step": 6430
},
{
"epoch": 128.8,
"learning_rate": 2.1593939393939394e-05,
"loss": 0.7367,
"step": 6440
},
{
"epoch": 129.0,
"learning_rate": 2.1533333333333333e-05,
"loss": 0.7289,
"step": 6450
},
{
"epoch": 129.2,
"learning_rate": 2.147272727272727e-05,
"loss": 0.7635,
"step": 6460
},
{
"epoch": 129.4,
"learning_rate": 2.1412121212121213e-05,
"loss": 0.7493,
"step": 6470
},
{
"epoch": 129.6,
"learning_rate": 2.1351515151515154e-05,
"loss": 0.769,
"step": 6480
},
{
"epoch": 129.8,
"learning_rate": 2.1290909090909093e-05,
"loss": 0.7307,
"step": 6490
},
{
"epoch": 130.0,
"learning_rate": 2.123030303030303e-05,
"loss": 0.714,
"step": 6500
},
{
"epoch": 130.0,
"eval_loss": 0.3682139217853546,
"eval_runtime": 243.0361,
"eval_samples_per_second": 21.445,
"eval_steps_per_second": 1.341,
"eval_wer": 0.3506013432602697,
"step": 6500
},
{
"epoch": 130.2,
"learning_rate": 2.116969696969697e-05,
"loss": 0.7817,
"step": 6510
},
{
"epoch": 130.4,
"learning_rate": 2.1109090909090908e-05,
"loss": 0.7611,
"step": 6520
},
{
"epoch": 130.6,
"learning_rate": 2.104848484848485e-05,
"loss": 0.7488,
"step": 6530
},
{
"epoch": 130.8,
"learning_rate": 2.0987878787878788e-05,
"loss": 0.7409,
"step": 6540
},
{
"epoch": 131.0,
"learning_rate": 2.092727272727273e-05,
"loss": 0.7171,
"step": 6550
},
{
"epoch": 131.2,
"learning_rate": 2.0866666666666668e-05,
"loss": 0.7772,
"step": 6560
},
{
"epoch": 131.4,
"learning_rate": 2.0806060606060606e-05,
"loss": 0.7418,
"step": 6570
},
{
"epoch": 131.6,
"learning_rate": 2.0745454545454548e-05,
"loss": 0.7403,
"step": 6580
},
{
"epoch": 131.8,
"learning_rate": 2.0684848484848486e-05,
"loss": 0.7406,
"step": 6590
},
{
"epoch": 132.0,
"learning_rate": 2.0624242424242425e-05,
"loss": 0.7281,
"step": 6600
},
{
"epoch": 132.2,
"learning_rate": 2.0563636363636363e-05,
"loss": 0.7583,
"step": 6610
},
{
"epoch": 132.4,
"learning_rate": 2.05030303030303e-05,
"loss": 0.7586,
"step": 6620
},
{
"epoch": 132.6,
"learning_rate": 2.0442424242424243e-05,
"loss": 0.7361,
"step": 6630
},
{
"epoch": 132.8,
"learning_rate": 2.0381818181818185e-05,
"loss": 0.7476,
"step": 6640
},
{
"epoch": 133.0,
"learning_rate": 2.0321212121212123e-05,
"loss": 0.7112,
"step": 6650
},
{
"epoch": 133.2,
"learning_rate": 2.026060606060606e-05,
"loss": 0.762,
"step": 6660
},
{
"epoch": 133.4,
"learning_rate": 2.02e-05,
"loss": 0.7406,
"step": 6670
},
{
"epoch": 133.6,
"learning_rate": 2.0139393939393938e-05,
"loss": 0.7421,
"step": 6680
},
{
"epoch": 133.8,
"learning_rate": 2.007878787878788e-05,
"loss": 0.7531,
"step": 6690
},
{
"epoch": 134.0,
"learning_rate": 2.0018181818181818e-05,
"loss": 0.7052,
"step": 6700
},
{
"epoch": 134.2,
"learning_rate": 1.9957575757575756e-05,
"loss": 0.7579,
"step": 6710
},
{
"epoch": 134.4,
"learning_rate": 1.9896969696969698e-05,
"loss": 0.7309,
"step": 6720
},
{
"epoch": 134.6,
"learning_rate": 1.9836363636363636e-05,
"loss": 0.7491,
"step": 6730
},
{
"epoch": 134.8,
"learning_rate": 1.9775757575757578e-05,
"loss": 0.7368,
"step": 6740
},
{
"epoch": 135.0,
"learning_rate": 1.9715151515151517e-05,
"loss": 0.6959,
"step": 6750
},
{
"epoch": 135.2,
"learning_rate": 1.9654545454545455e-05,
"loss": 0.7675,
"step": 6760
},
{
"epoch": 135.4,
"learning_rate": 1.9593939393939393e-05,
"loss": 0.7377,
"step": 6770
},
{
"epoch": 135.6,
"learning_rate": 1.953333333333333e-05,
"loss": 0.7589,
"step": 6780
},
{
"epoch": 135.8,
"learning_rate": 1.9472727272727273e-05,
"loss": 0.7398,
"step": 6790
},
{
"epoch": 136.0,
"learning_rate": 1.941212121212121e-05,
"loss": 0.7044,
"step": 6800
},
{
"epoch": 136.2,
"learning_rate": 1.9351515151515153e-05,
"loss": 0.759,
"step": 6810
},
{
"epoch": 136.4,
"learning_rate": 1.929090909090909e-05,
"loss": 0.7356,
"step": 6820
},
{
"epoch": 136.6,
"learning_rate": 1.923030303030303e-05,
"loss": 0.7181,
"step": 6830
},
{
"epoch": 136.8,
"learning_rate": 1.916969696969697e-05,
"loss": 0.7349,
"step": 6840
},
{
"epoch": 137.0,
"learning_rate": 1.910909090909091e-05,
"loss": 0.7004,
"step": 6850
},
{
"epoch": 137.2,
"learning_rate": 1.904848484848485e-05,
"loss": 0.7531,
"step": 6860
},
{
"epoch": 137.4,
"learning_rate": 1.8987878787878787e-05,
"loss": 0.749,
"step": 6870
},
{
"epoch": 137.6,
"learning_rate": 1.8927272727272725e-05,
"loss": 0.7306,
"step": 6880
},
{
"epoch": 137.8,
"learning_rate": 1.886666666666667e-05,
"loss": 0.7281,
"step": 6890
},
{
"epoch": 138.0,
"learning_rate": 1.880606060606061e-05,
"loss": 0.7322,
"step": 6900
},
{
"epoch": 138.2,
"learning_rate": 1.8745454545454547e-05,
"loss": 0.7754,
"step": 6910
},
{
"epoch": 138.4,
"learning_rate": 1.8684848484848485e-05,
"loss": 0.7235,
"step": 6920
},
{
"epoch": 138.6,
"learning_rate": 1.8624242424242423e-05,
"loss": 0.7408,
"step": 6930
},
{
"epoch": 138.8,
"learning_rate": 1.8563636363636365e-05,
"loss": 0.7376,
"step": 6940
},
{
"epoch": 139.0,
"learning_rate": 1.8503030303030303e-05,
"loss": 0.7067,
"step": 6950
},
{
"epoch": 139.2,
"learning_rate": 1.8442424242424242e-05,
"loss": 0.7594,
"step": 6960
},
{
"epoch": 139.4,
"learning_rate": 1.838181818181818e-05,
"loss": 0.7245,
"step": 6970
},
{
"epoch": 139.6,
"learning_rate": 1.8321212121212122e-05,
"loss": 0.7527,
"step": 6980
},
{
"epoch": 139.8,
"learning_rate": 1.8260606060606064e-05,
"loss": 0.7291,
"step": 6990
},
{
"epoch": 140.0,
"learning_rate": 1.8200000000000002e-05,
"loss": 0.7291,
"step": 7000
},
{
"epoch": 140.0,
"eval_loss": 0.36252087354660034,
"eval_runtime": 244.2417,
"eval_samples_per_second": 21.34,
"eval_steps_per_second": 1.335,
"eval_wer": 0.3504972145571927,
"step": 7000
},
{
"epoch": 140.2,
"learning_rate": 1.813939393939394e-05,
"loss": 0.7564,
"step": 7010
},
{
"epoch": 140.4,
"learning_rate": 1.807878787878788e-05,
"loss": 0.7686,
"step": 7020
},
{
"epoch": 140.6,
"learning_rate": 1.8018181818181817e-05,
"loss": 0.7334,
"step": 7030
},
{
"epoch": 140.8,
"learning_rate": 1.795757575757576e-05,
"loss": 0.7459,
"step": 7040
},
{
"epoch": 141.0,
"learning_rate": 1.7896969696969697e-05,
"loss": 0.7179,
"step": 7050
},
{
"epoch": 141.2,
"learning_rate": 1.783636363636364e-05,
"loss": 0.7633,
"step": 7060
},
{
"epoch": 141.4,
"learning_rate": 1.7775757575757577e-05,
"loss": 0.7249,
"step": 7070
},
{
"epoch": 141.6,
"learning_rate": 1.7715151515151515e-05,
"loss": 0.726,
"step": 7080
},
{
"epoch": 141.8,
"learning_rate": 1.7654545454545457e-05,
"loss": 0.7401,
"step": 7090
},
{
"epoch": 142.0,
"learning_rate": 1.7593939393939395e-05,
"loss": 0.7075,
"step": 7100
},
{
"epoch": 142.2,
"learning_rate": 1.7533333333333334e-05,
"loss": 0.7549,
"step": 7110
},
{
"epoch": 142.4,
"learning_rate": 1.7472727272727272e-05,
"loss": 0.7279,
"step": 7120
},
{
"epoch": 142.6,
"learning_rate": 1.741212121212121e-05,
"loss": 0.7364,
"step": 7130
},
{
"epoch": 142.8,
"learning_rate": 1.7351515151515152e-05,
"loss": 0.7469,
"step": 7140
},
{
"epoch": 143.0,
"learning_rate": 1.7290909090909094e-05,
"loss": 0.7131,
"step": 7150
},
{
"epoch": 143.2,
"learning_rate": 1.7230303030303032e-05,
"loss": 0.751,
"step": 7160
},
{
"epoch": 143.4,
"learning_rate": 1.716969696969697e-05,
"loss": 0.7274,
"step": 7170
},
{
"epoch": 143.6,
"learning_rate": 1.710909090909091e-05,
"loss": 0.7217,
"step": 7180
},
{
"epoch": 143.8,
"learning_rate": 1.7048484848484847e-05,
"loss": 0.7416,
"step": 7190
},
{
"epoch": 144.0,
"learning_rate": 1.698787878787879e-05,
"loss": 0.6873,
"step": 7200
},
{
"epoch": 144.2,
"learning_rate": 1.6927272727272727e-05,
"loss": 0.7562,
"step": 7210
},
{
"epoch": 144.4,
"learning_rate": 1.6866666666666666e-05,
"loss": 0.7104,
"step": 7220
},
{
"epoch": 144.6,
"learning_rate": 1.6806060606060607e-05,
"loss": 0.7403,
"step": 7230
},
{
"epoch": 144.8,
"learning_rate": 1.6745454545454546e-05,
"loss": 0.7242,
"step": 7240
},
{
"epoch": 145.0,
"learning_rate": 1.6684848484848487e-05,
"loss": 0.7091,
"step": 7250
},
{
"epoch": 145.2,
"learning_rate": 1.6624242424242426e-05,
"loss": 0.7634,
"step": 7260
},
{
"epoch": 145.4,
"learning_rate": 1.6563636363636364e-05,
"loss": 0.7249,
"step": 7270
},
{
"epoch": 145.6,
"learning_rate": 1.6503030303030302e-05,
"loss": 0.7354,
"step": 7280
},
{
"epoch": 145.8,
"learning_rate": 1.644242424242424e-05,
"loss": 0.7336,
"step": 7290
},
{
"epoch": 146.0,
"learning_rate": 1.6381818181818182e-05,
"loss": 0.69,
"step": 7300
},
{
"epoch": 146.2,
"learning_rate": 1.632121212121212e-05,
"loss": 0.7587,
"step": 7310
},
{
"epoch": 146.4,
"learning_rate": 1.6260606060606062e-05,
"loss": 0.7295,
"step": 7320
},
{
"epoch": 146.6,
"learning_rate": 1.62e-05,
"loss": 0.733,
"step": 7330
},
{
"epoch": 146.8,
"learning_rate": 1.613939393939394e-05,
"loss": 0.7043,
"step": 7340
},
{
"epoch": 147.0,
"learning_rate": 1.607878787878788e-05,
"loss": 0.6902,
"step": 7350
},
{
"epoch": 147.2,
"learning_rate": 1.601818181818182e-05,
"loss": 0.7559,
"step": 7360
},
{
"epoch": 147.4,
"learning_rate": 1.5957575757575757e-05,
"loss": 0.733,
"step": 7370
},
{
"epoch": 147.6,
"learning_rate": 1.5896969696969696e-05,
"loss": 0.7107,
"step": 7380
},
{
"epoch": 147.8,
"learning_rate": 1.5836363636363634e-05,
"loss": 0.7186,
"step": 7390
},
{
"epoch": 148.0,
"learning_rate": 1.577575757575758e-05,
"loss": 0.6978,
"step": 7400
},
{
"epoch": 148.2,
"learning_rate": 1.5715151515151518e-05,
"loss": 0.7545,
"step": 7410
},
{
"epoch": 148.4,
"learning_rate": 1.5654545454545456e-05,
"loss": 0.7321,
"step": 7420
},
{
"epoch": 148.6,
"learning_rate": 1.5593939393939394e-05,
"loss": 0.7223,
"step": 7430
},
{
"epoch": 148.8,
"learning_rate": 1.5533333333333333e-05,
"loss": 0.7216,
"step": 7440
},
{
"epoch": 149.0,
"learning_rate": 1.5472727272727274e-05,
"loss": 0.7029,
"step": 7450
},
{
"epoch": 149.2,
"learning_rate": 1.5412121212121213e-05,
"loss": 0.7595,
"step": 7460
},
{
"epoch": 149.4,
"learning_rate": 1.535151515151515e-05,
"loss": 0.7406,
"step": 7470
},
{
"epoch": 149.6,
"learning_rate": 1.529090909090909e-05,
"loss": 0.7215,
"step": 7480
},
{
"epoch": 149.8,
"learning_rate": 1.5230303030303033e-05,
"loss": 0.7085,
"step": 7490
},
{
"epoch": 150.0,
"learning_rate": 1.5169696969696971e-05,
"loss": 0.697,
"step": 7500
},
{
"epoch": 150.0,
"eval_loss": 0.36194926500320435,
"eval_runtime": 244.3442,
"eval_samples_per_second": 21.331,
"eval_steps_per_second": 1.334,
"eval_wer": 0.3479460613318061,
"step": 7500
},
{
"epoch": 150.2,
"learning_rate": 1.510909090909091e-05,
"loss": 0.7518,
"step": 7510
},
{
"epoch": 150.4,
"learning_rate": 1.504848484848485e-05,
"loss": 0.7236,
"step": 7520
},
{
"epoch": 150.6,
"learning_rate": 1.4987878787878788e-05,
"loss": 0.7105,
"step": 7530
},
{
"epoch": 150.8,
"learning_rate": 1.4927272727272728e-05,
"loss": 0.7035,
"step": 7540
},
{
"epoch": 151.0,
"learning_rate": 1.4866666666666668e-05,
"loss": 0.7026,
"step": 7550
},
{
"epoch": 151.2,
"learning_rate": 1.4806060606060606e-05,
"loss": 0.7266,
"step": 7560
},
{
"epoch": 151.4,
"learning_rate": 1.4745454545454546e-05,
"loss": 0.7391,
"step": 7570
},
{
"epoch": 151.6,
"learning_rate": 1.4684848484848484e-05,
"loss": 0.7343,
"step": 7580
},
{
"epoch": 151.8,
"learning_rate": 1.4624242424242424e-05,
"loss": 0.7262,
"step": 7590
},
{
"epoch": 152.0,
"learning_rate": 1.4563636363636364e-05,
"loss": 0.697,
"step": 7600
},
{
"epoch": 152.2,
"learning_rate": 1.4503030303030303e-05,
"loss": 0.7542,
"step": 7610
},
{
"epoch": 152.4,
"learning_rate": 1.4442424242424243e-05,
"loss": 0.716,
"step": 7620
},
{
"epoch": 152.6,
"learning_rate": 1.4381818181818181e-05,
"loss": 0.7246,
"step": 7630
},
{
"epoch": 152.8,
"learning_rate": 1.4321212121212123e-05,
"loss": 0.7253,
"step": 7640
},
{
"epoch": 153.0,
"learning_rate": 1.4260606060606061e-05,
"loss": 0.684,
"step": 7650
},
{
"epoch": 153.2,
"learning_rate": 1.42e-05,
"loss": 0.7596,
"step": 7660
},
{
"epoch": 153.4,
"learning_rate": 1.413939393939394e-05,
"loss": 0.7173,
"step": 7670
},
{
"epoch": 153.6,
"learning_rate": 1.407878787878788e-05,
"loss": 0.7008,
"step": 7680
},
{
"epoch": 153.8,
"learning_rate": 1.401818181818182e-05,
"loss": 0.7028,
"step": 7690
},
{
"epoch": 154.0,
"learning_rate": 1.3957575757575758e-05,
"loss": 0.6925,
"step": 7700
},
{
"epoch": 154.2,
"learning_rate": 1.3896969696969696e-05,
"loss": 0.7455,
"step": 7710
},
{
"epoch": 154.4,
"learning_rate": 1.3836363636363636e-05,
"loss": 0.7204,
"step": 7720
},
{
"epoch": 154.6,
"learning_rate": 1.3775757575757576e-05,
"loss": 0.7157,
"step": 7730
},
{
"epoch": 154.8,
"learning_rate": 1.3715151515151516e-05,
"loss": 0.7088,
"step": 7740
},
{
"epoch": 155.0,
"learning_rate": 1.3654545454545455e-05,
"loss": 0.7002,
"step": 7750
},
{
"epoch": 155.2,
"learning_rate": 1.3593939393939393e-05,
"loss": 0.7425,
"step": 7760
},
{
"epoch": 155.4,
"learning_rate": 1.3533333333333335e-05,
"loss": 0.737,
"step": 7770
},
{
"epoch": 155.6,
"learning_rate": 1.3472727272727273e-05,
"loss": 0.7224,
"step": 7780
},
{
"epoch": 155.8,
"learning_rate": 1.3412121212121211e-05,
"loss": 0.7324,
"step": 7790
},
{
"epoch": 156.0,
"learning_rate": 1.3351515151515151e-05,
"loss": 0.6667,
"step": 7800
},
{
"epoch": 156.2,
"learning_rate": 1.3290909090909091e-05,
"loss": 0.7378,
"step": 7810
},
{
"epoch": 156.4,
"learning_rate": 1.3230303030303032e-05,
"loss": 0.7136,
"step": 7820
},
{
"epoch": 156.6,
"learning_rate": 1.316969696969697e-05,
"loss": 0.7082,
"step": 7830
},
{
"epoch": 156.8,
"learning_rate": 1.3109090909090908e-05,
"loss": 0.6986,
"step": 7840
},
{
"epoch": 157.0,
"learning_rate": 1.304848484848485e-05,
"loss": 0.6915,
"step": 7850
},
{
"epoch": 157.2,
"learning_rate": 1.2987878787878788e-05,
"loss": 0.7195,
"step": 7860
},
{
"epoch": 157.4,
"learning_rate": 1.2927272727272728e-05,
"loss": 0.7176,
"step": 7870
},
{
"epoch": 157.6,
"learning_rate": 1.2866666666666667e-05,
"loss": 0.7083,
"step": 7880
},
{
"epoch": 157.8,
"learning_rate": 1.2806060606060605e-05,
"loss": 0.7098,
"step": 7890
},
{
"epoch": 158.0,
"learning_rate": 1.2745454545454547e-05,
"loss": 0.6857,
"step": 7900
},
{
"epoch": 158.2,
"learning_rate": 1.2684848484848485e-05,
"loss": 0.7282,
"step": 7910
},
{
"epoch": 158.4,
"learning_rate": 1.2624242424242425e-05,
"loss": 0.7154,
"step": 7920
},
{
"epoch": 158.6,
"learning_rate": 1.2563636363636363e-05,
"loss": 0.706,
"step": 7930
},
{
"epoch": 158.8,
"learning_rate": 1.2503030303030303e-05,
"loss": 0.722,
"step": 7940
},
{
"epoch": 159.0,
"learning_rate": 1.2442424242424243e-05,
"loss": 0.6904,
"step": 7950
},
{
"epoch": 159.2,
"learning_rate": 1.2381818181818182e-05,
"loss": 0.7324,
"step": 7960
},
{
"epoch": 159.4,
"learning_rate": 1.2321212121212122e-05,
"loss": 0.723,
"step": 7970
},
{
"epoch": 159.6,
"learning_rate": 1.2260606060606062e-05,
"loss": 0.7141,
"step": 7980
},
{
"epoch": 159.8,
"learning_rate": 1.22e-05,
"loss": 0.7177,
"step": 7990
},
{
"epoch": 160.0,
"learning_rate": 1.213939393939394e-05,
"loss": 0.6811,
"step": 8000
},
{
"epoch": 160.0,
"eval_loss": 0.36307966709136963,
"eval_runtime": 242.5601,
"eval_samples_per_second": 21.487,
"eval_steps_per_second": 1.344,
"eval_wer": 0.3440412349664185,
"step": 8000
},
{
"epoch": 160.2,
"learning_rate": 1.2078787878787878e-05,
"loss": 0.7477,
"step": 8010
},
{
"epoch": 160.4,
"learning_rate": 1.2018181818181818e-05,
"loss": 0.7098,
"step": 8020
},
{
"epoch": 160.6,
"learning_rate": 1.1957575757575758e-05,
"loss": 0.6994,
"step": 8030
},
{
"epoch": 160.8,
"learning_rate": 1.1896969696969697e-05,
"loss": 0.7192,
"step": 8040
},
{
"epoch": 161.0,
"learning_rate": 1.1836363636363637e-05,
"loss": 0.6757,
"step": 8050
},
{
"epoch": 161.2,
"learning_rate": 1.1775757575757575e-05,
"loss": 0.7521,
"step": 8060
},
{
"epoch": 161.4,
"learning_rate": 1.1715151515151515e-05,
"loss": 0.6944,
"step": 8070
},
{
"epoch": 161.6,
"learning_rate": 1.1654545454545455e-05,
"loss": 0.7216,
"step": 8080
},
{
"epoch": 161.8,
"learning_rate": 1.1593939393939394e-05,
"loss": 0.7034,
"step": 8090
},
{
"epoch": 162.0,
"learning_rate": 1.1533333333333334e-05,
"loss": 0.6685,
"step": 8100
},
{
"epoch": 162.2,
"learning_rate": 1.1478787878787879e-05,
"loss": 0.7395,
"step": 8110
},
{
"epoch": 162.4,
"learning_rate": 1.1418181818181819e-05,
"loss": 0.7139,
"step": 8120
},
{
"epoch": 162.6,
"learning_rate": 1.1357575757575757e-05,
"loss": 0.6898,
"step": 8130
},
{
"epoch": 162.8,
"learning_rate": 1.1296969696969697e-05,
"loss": 0.7013,
"step": 8140
},
{
"epoch": 163.0,
"learning_rate": 1.1236363636363638e-05,
"loss": 0.6784,
"step": 8150
},
{
"epoch": 163.2,
"learning_rate": 1.1175757575757576e-05,
"loss": 0.7114,
"step": 8160
},
{
"epoch": 163.4,
"learning_rate": 1.1115151515151516e-05,
"loss": 0.7094,
"step": 8170
},
{
"epoch": 163.6,
"learning_rate": 1.1054545454545454e-05,
"loss": 0.7064,
"step": 8180
},
{
"epoch": 163.8,
"learning_rate": 1.0993939393939394e-05,
"loss": 0.6946,
"step": 8190
},
{
"epoch": 164.0,
"learning_rate": 1.0933333333333334e-05,
"loss": 0.6638,
"step": 8200
},
{
"epoch": 164.2,
"learning_rate": 1.0872727272727273e-05,
"loss": 0.7257,
"step": 8210
},
{
"epoch": 164.4,
"learning_rate": 1.0812121212121213e-05,
"loss": 0.7131,
"step": 8220
},
{
"epoch": 164.6,
"learning_rate": 1.0751515151515151e-05,
"loss": 0.7032,
"step": 8230
},
{
"epoch": 164.8,
"learning_rate": 1.0690909090909091e-05,
"loss": 0.707,
"step": 8240
},
{
"epoch": 165.0,
"learning_rate": 1.0630303030303031e-05,
"loss": 0.6797,
"step": 8250
},
{
"epoch": 165.2,
"learning_rate": 1.056969696969697e-05,
"loss": 0.7334,
"step": 8260
},
{
"epoch": 165.4,
"learning_rate": 1.050909090909091e-05,
"loss": 0.7339,
"step": 8270
},
{
"epoch": 165.6,
"learning_rate": 1.044848484848485e-05,
"loss": 0.7148,
"step": 8280
},
{
"epoch": 165.8,
"learning_rate": 1.0387878787878788e-05,
"loss": 0.7074,
"step": 8290
},
{
"epoch": 166.0,
"learning_rate": 1.0327272727272728e-05,
"loss": 0.6874,
"step": 8300
},
{
"epoch": 166.2,
"learning_rate": 1.0266666666666666e-05,
"loss": 0.7472,
"step": 8310
},
{
"epoch": 166.4,
"learning_rate": 1.0206060606060608e-05,
"loss": 0.711,
"step": 8320
},
{
"epoch": 166.6,
"learning_rate": 1.0145454545454546e-05,
"loss": 0.707,
"step": 8330
},
{
"epoch": 166.8,
"learning_rate": 1.0084848484848484e-05,
"loss": 0.7023,
"step": 8340
},
{
"epoch": 167.0,
"learning_rate": 1.0024242424242424e-05,
"loss": 0.6812,
"step": 8350
},
{
"epoch": 167.2,
"learning_rate": 9.963636363636363e-06,
"loss": 0.7549,
"step": 8360
},
{
"epoch": 167.4,
"learning_rate": 9.903030303030305e-06,
"loss": 0.69,
"step": 8370
},
{
"epoch": 167.6,
"learning_rate": 9.842424242424243e-06,
"loss": 0.6981,
"step": 8380
},
{
"epoch": 167.8,
"learning_rate": 9.781818181818181e-06,
"loss": 0.7245,
"step": 8390
},
{
"epoch": 168.0,
"learning_rate": 9.721212121212121e-06,
"loss": 0.6736,
"step": 8400
},
{
"epoch": 168.2,
"learning_rate": 9.660606060606061e-06,
"loss": 0.7403,
"step": 8410
},
{
"epoch": 168.4,
"learning_rate": 9.600000000000001e-06,
"loss": 0.68,
"step": 8420
},
{
"epoch": 168.6,
"learning_rate": 9.53939393939394e-06,
"loss": 0.7077,
"step": 8430
},
{
"epoch": 168.8,
"learning_rate": 9.478787878787878e-06,
"loss": 0.6924,
"step": 8440
},
{
"epoch": 169.0,
"learning_rate": 9.41818181818182e-06,
"loss": 0.679,
"step": 8450
},
{
"epoch": 169.2,
"learning_rate": 9.357575757575758e-06,
"loss": 0.7259,
"step": 8460
},
{
"epoch": 169.4,
"learning_rate": 9.296969696969696e-06,
"loss": 0.7021,
"step": 8470
},
{
"epoch": 169.6,
"learning_rate": 9.236363636363636e-06,
"loss": 0.6986,
"step": 8480
},
{
"epoch": 169.8,
"learning_rate": 9.175757575757576e-06,
"loss": 0.6945,
"step": 8490
},
{
"epoch": 170.0,
"learning_rate": 9.115151515151516e-06,
"loss": 0.6841,
"step": 8500
},
{
"epoch": 170.0,
"eval_loss": 0.3671566843986511,
"eval_runtime": 243.7376,
"eval_samples_per_second": 21.384,
"eval_steps_per_second": 1.338,
"eval_wer": 0.3460457125006508,
"step": 8500
},
{
"epoch": 170.2,
"learning_rate": 9.054545454545455e-06,
"loss": 0.7282,
"step": 8510
},
{
"epoch": 170.4,
"learning_rate": 8.993939393939393e-06,
"loss": 0.6899,
"step": 8520
},
{
"epoch": 170.6,
"learning_rate": 8.933333333333333e-06,
"loss": 0.7181,
"step": 8530
},
{
"epoch": 170.8,
"learning_rate": 8.872727272727273e-06,
"loss": 0.6958,
"step": 8540
},
{
"epoch": 171.0,
"learning_rate": 8.812121212121213e-06,
"loss": 0.6931,
"step": 8550
},
{
"epoch": 171.2,
"learning_rate": 8.751515151515151e-06,
"loss": 0.7227,
"step": 8560
},
{
"epoch": 171.4,
"learning_rate": 8.69090909090909e-06,
"loss": 0.7281,
"step": 8570
},
{
"epoch": 171.6,
"learning_rate": 8.630303030303032e-06,
"loss": 0.7049,
"step": 8580
},
{
"epoch": 171.8,
"learning_rate": 8.56969696969697e-06,
"loss": 0.7046,
"step": 8590
},
{
"epoch": 172.0,
"learning_rate": 8.50909090909091e-06,
"loss": 0.661,
"step": 8600
},
{
"epoch": 172.2,
"learning_rate": 8.448484848484848e-06,
"loss": 0.723,
"step": 8610
},
{
"epoch": 172.4,
"learning_rate": 8.387878787878788e-06,
"loss": 0.7063,
"step": 8620
},
{
"epoch": 172.6,
"learning_rate": 8.327272727272728e-06,
"loss": 0.7094,
"step": 8630
},
{
"epoch": 172.8,
"learning_rate": 8.266666666666667e-06,
"loss": 0.7137,
"step": 8640
},
{
"epoch": 173.0,
"learning_rate": 8.206060606060607e-06,
"loss": 0.6544,
"step": 8650
},
{
"epoch": 173.2,
"learning_rate": 8.145454545454547e-06,
"loss": 0.7202,
"step": 8660
},
{
"epoch": 173.4,
"learning_rate": 8.084848484848485e-06,
"loss": 0.6964,
"step": 8670
},
{
"epoch": 173.6,
"learning_rate": 8.024242424242425e-06,
"loss": 0.7093,
"step": 8680
},
{
"epoch": 173.8,
"learning_rate": 7.963636363636363e-06,
"loss": 0.6938,
"step": 8690
},
{
"epoch": 174.0,
"learning_rate": 7.903030303030303e-06,
"loss": 0.6669,
"step": 8700
},
{
"epoch": 174.2,
"learning_rate": 7.842424242424243e-06,
"loss": 0.7225,
"step": 8710
},
{
"epoch": 174.4,
"learning_rate": 7.781818181818182e-06,
"loss": 0.7163,
"step": 8720
},
{
"epoch": 174.6,
"learning_rate": 7.721212121212122e-06,
"loss": 0.6901,
"step": 8730
},
{
"epoch": 174.8,
"learning_rate": 7.66060606060606e-06,
"loss": 0.6937,
"step": 8740
},
{
"epoch": 175.0,
"learning_rate": 7.600000000000001e-06,
"loss": 0.6705,
"step": 8750
},
{
"epoch": 175.2,
"learning_rate": 7.53939393939394e-06,
"loss": 0.7241,
"step": 8760
},
{
"epoch": 175.4,
"learning_rate": 7.4787878787878784e-06,
"loss": 0.6951,
"step": 8770
},
{
"epoch": 175.6,
"learning_rate": 7.4181818181818185e-06,
"loss": 0.6993,
"step": 8780
},
{
"epoch": 175.8,
"learning_rate": 7.357575757575758e-06,
"loss": 0.7076,
"step": 8790
},
{
"epoch": 176.0,
"learning_rate": 7.296969696969698e-06,
"loss": 0.6692,
"step": 8800
},
{
"epoch": 176.2,
"learning_rate": 7.236363636363637e-06,
"loss": 0.7284,
"step": 8810
},
{
"epoch": 176.4,
"learning_rate": 7.175757575757576e-06,
"loss": 0.6959,
"step": 8820
},
{
"epoch": 176.6,
"learning_rate": 7.115151515151515e-06,
"loss": 0.678,
"step": 8830
},
{
"epoch": 176.8,
"learning_rate": 7.054545454545454e-06,
"loss": 0.7012,
"step": 8840
},
{
"epoch": 177.0,
"learning_rate": 6.993939393939394e-06,
"loss": 0.6797,
"step": 8850
},
{
"epoch": 177.2,
"learning_rate": 6.933333333333334e-06,
"loss": 0.7238,
"step": 8860
},
{
"epoch": 177.4,
"learning_rate": 6.872727272727273e-06,
"loss": 0.6986,
"step": 8870
},
{
"epoch": 177.6,
"learning_rate": 6.812121212121212e-06,
"loss": 0.7004,
"step": 8880
},
{
"epoch": 177.8,
"learning_rate": 6.751515151515152e-06,
"loss": 0.6681,
"step": 8890
},
{
"epoch": 178.0,
"learning_rate": 6.690909090909091e-06,
"loss": 0.6817,
"step": 8900
},
{
"epoch": 178.2,
"learning_rate": 6.63030303030303e-06,
"loss": 0.7241,
"step": 8910
},
{
"epoch": 178.4,
"learning_rate": 6.5696969696969695e-06,
"loss": 0.7102,
"step": 8920
},
{
"epoch": 178.6,
"learning_rate": 6.5090909090909095e-06,
"loss": 0.6847,
"step": 8930
},
{
"epoch": 178.8,
"learning_rate": 6.448484848484849e-06,
"loss": 0.7004,
"step": 8940
},
{
"epoch": 179.0,
"learning_rate": 6.387878787878789e-06,
"loss": 0.6661,
"step": 8950
},
{
"epoch": 179.2,
"learning_rate": 6.327272727272727e-06,
"loss": 0.7154,
"step": 8960
},
{
"epoch": 179.4,
"learning_rate": 6.266666666666667e-06,
"loss": 0.69,
"step": 8970
},
{
"epoch": 179.6,
"learning_rate": 6.206060606060606e-06,
"loss": 0.6799,
"step": 8980
},
{
"epoch": 179.8,
"learning_rate": 6.1454545454545454e-06,
"loss": 0.6946,
"step": 8990
},
{
"epoch": 180.0,
"learning_rate": 6.0848484848484855e-06,
"loss": 0.6616,
"step": 9000
},
{
"epoch": 180.0,
"eval_loss": 0.36765044927597046,
"eval_runtime": 243.8885,
"eval_samples_per_second": 21.37,
"eval_steps_per_second": 1.337,
"eval_wer": 0.34099547040141615,
"step": 9000
},
{
"epoch": 180.2,
"learning_rate": 6.024242424242424e-06,
"loss": 0.718,
"step": 9010
},
{
"epoch": 180.4,
"learning_rate": 5.963636363636364e-06,
"loss": 0.7075,
"step": 9020
},
{
"epoch": 180.6,
"learning_rate": 5.903030303030303e-06,
"loss": 0.7133,
"step": 9030
},
{
"epoch": 180.8,
"learning_rate": 5.842424242424243e-06,
"loss": 0.698,
"step": 9040
},
{
"epoch": 181.0,
"learning_rate": 5.781818181818181e-06,
"loss": 0.6749,
"step": 9050
},
{
"epoch": 181.2,
"learning_rate": 5.721212121212121e-06,
"loss": 0.7197,
"step": 9060
},
{
"epoch": 181.4,
"learning_rate": 5.6606060606060606e-06,
"loss": 0.7206,
"step": 9070
},
{
"epoch": 181.6,
"learning_rate": 5.600000000000001e-06,
"loss": 0.6867,
"step": 9080
},
{
"epoch": 181.8,
"learning_rate": 5.53939393939394e-06,
"loss": 0.6846,
"step": 9090
},
{
"epoch": 182.0,
"learning_rate": 5.478787878787879e-06,
"loss": 0.6683,
"step": 9100
},
{
"epoch": 182.2,
"learning_rate": 5.418181818181818e-06,
"loss": 0.7129,
"step": 9110
},
{
"epoch": 182.4,
"learning_rate": 5.357575757575758e-06,
"loss": 0.6931,
"step": 9120
},
{
"epoch": 182.6,
"learning_rate": 5.296969696969697e-06,
"loss": 0.6892,
"step": 9130
},
{
"epoch": 182.8,
"learning_rate": 5.2363636363636365e-06,
"loss": 0.6927,
"step": 9140
},
{
"epoch": 183.0,
"learning_rate": 5.175757575757576e-06,
"loss": 0.6858,
"step": 9150
},
{
"epoch": 183.2,
"learning_rate": 5.115151515151515e-06,
"loss": 0.726,
"step": 9160
},
{
"epoch": 183.4,
"learning_rate": 5.054545454545455e-06,
"loss": 0.6908,
"step": 9170
},
{
"epoch": 183.6,
"learning_rate": 4.993939393939394e-06,
"loss": 0.7123,
"step": 9180
},
{
"epoch": 183.8,
"learning_rate": 4.933333333333333e-06,
"loss": 0.7041,
"step": 9190
},
{
"epoch": 184.0,
"learning_rate": 4.8727272727272724e-06,
"loss": 0.6502,
"step": 9200
},
{
"epoch": 184.2,
"learning_rate": 4.8121212121212125e-06,
"loss": 0.7302,
"step": 9210
},
{
"epoch": 184.4,
"learning_rate": 4.751515151515152e-06,
"loss": 0.6944,
"step": 9220
},
{
"epoch": 184.6,
"learning_rate": 4.690909090909092e-06,
"loss": 0.6774,
"step": 9230
},
{
"epoch": 184.8,
"learning_rate": 4.63030303030303e-06,
"loss": 0.6884,
"step": 9240
},
{
"epoch": 185.0,
"learning_rate": 4.56969696969697e-06,
"loss": 0.6506,
"step": 9250
},
{
"epoch": 185.2,
"learning_rate": 4.509090909090909e-06,
"loss": 0.7361,
"step": 9260
},
{
"epoch": 185.4,
"learning_rate": 4.448484848484849e-06,
"loss": 0.6978,
"step": 9270
},
{
"epoch": 185.6,
"learning_rate": 4.3878787878787876e-06,
"loss": 0.68,
"step": 9280
},
{
"epoch": 185.8,
"learning_rate": 4.327272727272728e-06,
"loss": 0.6859,
"step": 9290
},
{
"epoch": 186.0,
"learning_rate": 4.266666666666667e-06,
"loss": 0.6716,
"step": 9300
},
{
"epoch": 186.2,
"learning_rate": 4.206060606060606e-06,
"loss": 0.6995,
"step": 9310
},
{
"epoch": 186.4,
"learning_rate": 4.145454545454546e-06,
"loss": 0.7181,
"step": 9320
},
{
"epoch": 186.6,
"learning_rate": 4.084848484848484e-06,
"loss": 0.7069,
"step": 9330
},
{
"epoch": 186.8,
"learning_rate": 4.024242424242424e-06,
"loss": 0.7083,
"step": 9340
},
{
"epoch": 187.0,
"learning_rate": 3.9636363636363635e-06,
"loss": 0.662,
"step": 9350
},
{
"epoch": 187.2,
"learning_rate": 3.9030303030303035e-06,
"loss": 0.7155,
"step": 9360
},
{
"epoch": 187.4,
"learning_rate": 3.842424242424243e-06,
"loss": 0.7061,
"step": 9370
},
{
"epoch": 187.6,
"learning_rate": 3.7818181818181823e-06,
"loss": 0.6878,
"step": 9380
},
{
"epoch": 187.8,
"learning_rate": 3.721212121212121e-06,
"loss": 0.687,
"step": 9390
},
{
"epoch": 188.0,
"learning_rate": 3.6606060606060607e-06,
"loss": 0.6586,
"step": 9400
},
{
"epoch": 188.2,
"learning_rate": 3.6e-06,
"loss": 0.6959,
"step": 9410
},
{
"epoch": 188.4,
"learning_rate": 3.5393939393939394e-06,
"loss": 0.698,
"step": 9420
},
{
"epoch": 188.6,
"learning_rate": 3.4787878787878786e-06,
"loss": 0.6989,
"step": 9430
},
{
"epoch": 188.8,
"learning_rate": 3.4181818181818182e-06,
"loss": 0.6927,
"step": 9440
},
{
"epoch": 189.0,
"learning_rate": 3.357575757575758e-06,
"loss": 0.6649,
"step": 9450
},
{
"epoch": 189.2,
"learning_rate": 3.296969696969697e-06,
"loss": 0.715,
"step": 9460
},
{
"epoch": 189.4,
"learning_rate": 3.2363636363636366e-06,
"loss": 0.694,
"step": 9470
},
{
"epoch": 189.6,
"learning_rate": 3.1757575757575758e-06,
"loss": 0.7162,
"step": 9480
},
{
"epoch": 189.8,
"learning_rate": 3.1151515151515154e-06,
"loss": 0.685,
"step": 9490
},
{
"epoch": 190.0,
"learning_rate": 3.0545454545454546e-06,
"loss": 0.6471,
"step": 9500
},
{
"epoch": 190.0,
"eval_loss": 0.37067291140556335,
"eval_runtime": 243.2712,
"eval_samples_per_second": 21.425,
"eval_steps_per_second": 1.34,
"eval_wer": 0.3420367574321862,
"step": 9500
},
{
"epoch": 190.2,
"learning_rate": 2.993939393939394e-06,
"loss": 0.7389,
"step": 9510
},
{
"epoch": 190.4,
"learning_rate": 2.9333333333333338e-06,
"loss": 0.6763,
"step": 9520
},
{
"epoch": 190.6,
"learning_rate": 2.872727272727273e-06,
"loss": 0.6837,
"step": 9530
},
{
"epoch": 190.8,
"learning_rate": 2.8121212121212125e-06,
"loss": 0.6793,
"step": 9540
},
{
"epoch": 191.0,
"learning_rate": 2.7515151515151513e-06,
"loss": 0.6621,
"step": 9550
},
{
"epoch": 191.2,
"learning_rate": 2.690909090909091e-06,
"loss": 0.7213,
"step": 9560
},
{
"epoch": 191.4,
"learning_rate": 2.63030303030303e-06,
"loss": 0.6993,
"step": 9570
},
{
"epoch": 191.6,
"learning_rate": 2.5696969696969697e-06,
"loss": 0.6682,
"step": 9580
},
{
"epoch": 191.8,
"learning_rate": 2.5090909090909093e-06,
"loss": 0.6759,
"step": 9590
},
{
"epoch": 192.0,
"learning_rate": 2.4484848484848485e-06,
"loss": 0.6718,
"step": 9600
},
{
"epoch": 192.2,
"learning_rate": 2.387878787878788e-06,
"loss": 0.7276,
"step": 9610
},
{
"epoch": 192.4,
"learning_rate": 2.3272727272727272e-06,
"loss": 0.6857,
"step": 9620
},
{
"epoch": 192.6,
"learning_rate": 2.266666666666667e-06,
"loss": 0.6914,
"step": 9630
},
{
"epoch": 192.8,
"learning_rate": 2.206060606060606e-06,
"loss": 0.7176,
"step": 9640
},
{
"epoch": 193.0,
"learning_rate": 2.1454545454545456e-06,
"loss": 0.6491,
"step": 9650
},
{
"epoch": 193.2,
"learning_rate": 2.084848484848485e-06,
"loss": 0.6961,
"step": 9660
},
{
"epoch": 193.4,
"learning_rate": 2.0242424242424244e-06,
"loss": 0.7066,
"step": 9670
},
{
"epoch": 193.6,
"learning_rate": 1.963636363636364e-06,
"loss": 0.6874,
"step": 9680
},
{
"epoch": 193.8,
"learning_rate": 1.9030303030303032e-06,
"loss": 0.7069,
"step": 9690
},
{
"epoch": 194.0,
"learning_rate": 1.8424242424242424e-06,
"loss": 0.6636,
"step": 9700
},
{
"epoch": 194.2,
"learning_rate": 1.781818181818182e-06,
"loss": 0.7159,
"step": 9710
},
{
"epoch": 194.4,
"learning_rate": 1.7212121212121214e-06,
"loss": 0.6926,
"step": 9720
},
{
"epoch": 194.6,
"learning_rate": 1.6606060606060607e-06,
"loss": 0.6831,
"step": 9730
},
{
"epoch": 194.8,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.6727,
"step": 9740
},
{
"epoch": 195.0,
"learning_rate": 1.5393939393939393e-06,
"loss": 0.6714,
"step": 9750
},
{
"epoch": 195.2,
"learning_rate": 1.4787878787878787e-06,
"loss": 0.7056,
"step": 9760
},
{
"epoch": 195.4,
"learning_rate": 1.418181818181818e-06,
"loss": 0.68,
"step": 9770
},
{
"epoch": 195.6,
"learning_rate": 1.3575757575757577e-06,
"loss": 0.6768,
"step": 9780
},
{
"epoch": 195.8,
"learning_rate": 1.296969696969697e-06,
"loss": 0.6806,
"step": 9790
},
{
"epoch": 196.0,
"learning_rate": 1.2363636363636365e-06,
"loss": 0.6654,
"step": 9800
},
{
"epoch": 196.2,
"learning_rate": 1.1757575757575759e-06,
"loss": 0.7139,
"step": 9810
},
{
"epoch": 196.4,
"learning_rate": 1.1151515151515153e-06,
"loss": 0.6718,
"step": 9820
},
{
"epoch": 196.6,
"learning_rate": 1.0545454545454544e-06,
"loss": 0.6785,
"step": 9830
},
{
"epoch": 196.8,
"learning_rate": 9.939393939393938e-07,
"loss": 0.6821,
"step": 9840
},
{
"epoch": 197.0,
"learning_rate": 9.333333333333333e-07,
"loss": 0.6711,
"step": 9850
},
{
"epoch": 197.2,
"learning_rate": 8.727272727272727e-07,
"loss": 0.7221,
"step": 9860
},
{
"epoch": 197.4,
"learning_rate": 8.121212121212122e-07,
"loss": 0.6933,
"step": 9870
},
{
"epoch": 197.6,
"learning_rate": 7.515151515151516e-07,
"loss": 0.6855,
"step": 9880
},
{
"epoch": 197.8,
"learning_rate": 6.909090909090909e-07,
"loss": 0.6902,
"step": 9890
},
{
"epoch": 198.0,
"learning_rate": 6.303030303030303e-07,
"loss": 0.6686,
"step": 9900
},
{
"epoch": 198.2,
"learning_rate": 5.696969696969698e-07,
"loss": 0.7282,
"step": 9910
},
{
"epoch": 198.4,
"learning_rate": 5.090909090909092e-07,
"loss": 0.6848,
"step": 9920
},
{
"epoch": 198.6,
"learning_rate": 4.484848484848485e-07,
"loss": 0.6939,
"step": 9930
},
{
"epoch": 198.8,
"learning_rate": 3.878787878787879e-07,
"loss": 0.6961,
"step": 9940
},
{
"epoch": 199.0,
"learning_rate": 3.3333333333333335e-07,
"loss": 0.6564,
"step": 9950
},
{
"epoch": 199.2,
"learning_rate": 2.7272727272727274e-07,
"loss": 0.7132,
"step": 9960
},
{
"epoch": 199.4,
"learning_rate": 2.1212121212121213e-07,
"loss": 0.6813,
"step": 9970
},
{
"epoch": 199.6,
"learning_rate": 1.5151515151515152e-07,
"loss": 0.6865,
"step": 9980
},
{
"epoch": 199.8,
"learning_rate": 9.090909090909091e-08,
"loss": 0.6773,
"step": 9990
},
{
"epoch": 200.0,
"learning_rate": 3.0303030303030305e-08,
"loss": 0.6759,
"step": 10000
},
{
"epoch": 200.0,
"eval_loss": 0.37058258056640625,
"eval_runtime": 244.1231,
"eval_samples_per_second": 21.35,
"eval_steps_per_second": 1.335,
"eval_wer": 0.3420888217837247,
"step": 10000
},
{
"epoch": 200.0,
"step": 10000,
"total_flos": 3.2791120983682476e+20,
"train_loss": 0.48956193776130674,
"train_runtime": 78626.4431,
"train_samples_per_second": 32.574,
"train_steps_per_second": 0.127
}
],
"max_steps": 10000,
"num_train_epochs": 200,
"total_flos": 3.2791120983682476e+20,
"trial_name": null,
"trial_params": null
}