gary109's picture
End of training
ba885ec
{
"best_metric": 1.0162557363510132,
"best_model_checkpoint": "ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v5/checkpoint-2256",
"epoch": 10.0,
"global_step": 3760,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9198,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 8.000000000000001e-06,
"loss": 0.879,
"step": 20
},
{
"epoch": 0.08,
"learning_rate": 1.2e-05,
"loss": 0.8647,
"step": 30
},
{
"epoch": 0.11,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.8746,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 2e-05,
"loss": 0.8716,
"step": 50
},
{
"epoch": 0.16,
"learning_rate": 2.4e-05,
"loss": 0.9164,
"step": 60
},
{
"epoch": 0.19,
"learning_rate": 2.8e-05,
"loss": 0.8862,
"step": 70
},
{
"epoch": 0.21,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.8818,
"step": 80
},
{
"epoch": 0.24,
"learning_rate": 3.6e-05,
"loss": 0.8818,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 4e-05,
"loss": 0.8894,
"step": 100
},
{
"epoch": 0.29,
"learning_rate": 3.989071038251366e-05,
"loss": 0.9504,
"step": 110
},
{
"epoch": 0.32,
"learning_rate": 3.9781420765027323e-05,
"loss": 0.8916,
"step": 120
},
{
"epoch": 0.35,
"learning_rate": 3.9672131147540983e-05,
"loss": 0.8946,
"step": 130
},
{
"epoch": 0.37,
"learning_rate": 3.956284153005465e-05,
"loss": 0.8959,
"step": 140
},
{
"epoch": 0.4,
"learning_rate": 3.945355191256831e-05,
"loss": 0.8869,
"step": 150
},
{
"epoch": 0.43,
"learning_rate": 3.934426229508197e-05,
"loss": 0.9374,
"step": 160
},
{
"epoch": 0.45,
"learning_rate": 3.923497267759563e-05,
"loss": 0.9024,
"step": 170
},
{
"epoch": 0.48,
"learning_rate": 3.912568306010929e-05,
"loss": 0.8983,
"step": 180
},
{
"epoch": 0.51,
"learning_rate": 3.901639344262295e-05,
"loss": 0.8933,
"step": 190
},
{
"epoch": 0.53,
"learning_rate": 3.890710382513661e-05,
"loss": 0.9064,
"step": 200
},
{
"epoch": 0.56,
"learning_rate": 3.879781420765028e-05,
"loss": 0.9612,
"step": 210
},
{
"epoch": 0.59,
"learning_rate": 3.868852459016394e-05,
"loss": 0.8932,
"step": 220
},
{
"epoch": 0.61,
"learning_rate": 3.85792349726776e-05,
"loss": 0.9063,
"step": 230
},
{
"epoch": 0.64,
"learning_rate": 3.846994535519126e-05,
"loss": 0.8773,
"step": 240
},
{
"epoch": 0.66,
"learning_rate": 3.836065573770492e-05,
"loss": 0.8908,
"step": 250
},
{
"epoch": 0.69,
"learning_rate": 3.825136612021858e-05,
"loss": 0.939,
"step": 260
},
{
"epoch": 0.72,
"learning_rate": 3.8142076502732245e-05,
"loss": 0.8949,
"step": 270
},
{
"epoch": 0.74,
"learning_rate": 3.8032786885245905e-05,
"loss": 0.8847,
"step": 280
},
{
"epoch": 0.77,
"learning_rate": 3.7923497267759565e-05,
"loss": 0.8946,
"step": 290
},
{
"epoch": 0.8,
"learning_rate": 3.781420765027323e-05,
"loss": 0.8865,
"step": 300
},
{
"epoch": 0.82,
"learning_rate": 3.770491803278689e-05,
"loss": 0.9316,
"step": 310
},
{
"epoch": 0.85,
"learning_rate": 3.759562841530055e-05,
"loss": 0.8822,
"step": 320
},
{
"epoch": 0.88,
"learning_rate": 3.748633879781421e-05,
"loss": 0.8983,
"step": 330
},
{
"epoch": 0.9,
"learning_rate": 3.737704918032787e-05,
"loss": 0.8889,
"step": 340
},
{
"epoch": 0.93,
"learning_rate": 3.726775956284153e-05,
"loss": 0.8957,
"step": 350
},
{
"epoch": 0.96,
"learning_rate": 3.71584699453552e-05,
"loss": 0.9067,
"step": 360
},
{
"epoch": 0.98,
"learning_rate": 3.704918032786886e-05,
"loss": 0.8867,
"step": 370
},
{
"epoch": 1.0,
"eval_loss": 1.0381758213043213,
"eval_runtime": 348.9535,
"eval_samples_per_second": 7.663,
"eval_steps_per_second": 1.917,
"eval_wer": 0.6820688128905276,
"step": 376
},
{
"epoch": 1.01,
"learning_rate": 3.693989071038252e-05,
"loss": 0.9229,
"step": 380
},
{
"epoch": 1.04,
"learning_rate": 3.683060109289618e-05,
"loss": 0.9061,
"step": 390
},
{
"epoch": 1.06,
"learning_rate": 3.672131147540984e-05,
"loss": 0.8896,
"step": 400
},
{
"epoch": 1.09,
"learning_rate": 3.66120218579235e-05,
"loss": 0.8908,
"step": 410
},
{
"epoch": 1.12,
"learning_rate": 3.650273224043716e-05,
"loss": 0.8999,
"step": 420
},
{
"epoch": 1.14,
"learning_rate": 3.6393442622950826e-05,
"loss": 0.9126,
"step": 430
},
{
"epoch": 1.17,
"learning_rate": 3.6284153005464486e-05,
"loss": 0.9274,
"step": 440
},
{
"epoch": 1.2,
"learning_rate": 3.6174863387978146e-05,
"loss": 0.8986,
"step": 450
},
{
"epoch": 1.22,
"learning_rate": 3.6065573770491806e-05,
"loss": 0.8889,
"step": 460
},
{
"epoch": 1.25,
"learning_rate": 3.5956284153005466e-05,
"loss": 0.89,
"step": 470
},
{
"epoch": 1.28,
"learning_rate": 3.5846994535519126e-05,
"loss": 0.9142,
"step": 480
},
{
"epoch": 1.3,
"learning_rate": 3.5737704918032786e-05,
"loss": 0.9122,
"step": 490
},
{
"epoch": 1.33,
"learning_rate": 3.562841530054645e-05,
"loss": 0.8805,
"step": 500
},
{
"epoch": 1.36,
"learning_rate": 3.551912568306011e-05,
"loss": 0.878,
"step": 510
},
{
"epoch": 1.38,
"learning_rate": 3.5409836065573773e-05,
"loss": 0.8903,
"step": 520
},
{
"epoch": 1.41,
"learning_rate": 3.5300546448087433e-05,
"loss": 0.9098,
"step": 530
},
{
"epoch": 1.44,
"learning_rate": 3.5191256830601094e-05,
"loss": 0.918,
"step": 540
},
{
"epoch": 1.46,
"learning_rate": 3.5081967213114754e-05,
"loss": 0.8911,
"step": 550
},
{
"epoch": 1.49,
"learning_rate": 3.4972677595628414e-05,
"loss": 0.8767,
"step": 560
},
{
"epoch": 1.52,
"learning_rate": 3.486338797814208e-05,
"loss": 0.8821,
"step": 570
},
{
"epoch": 1.54,
"learning_rate": 3.475409836065574e-05,
"loss": 0.9001,
"step": 580
},
{
"epoch": 1.57,
"learning_rate": 3.46448087431694e-05,
"loss": 0.8989,
"step": 590
},
{
"epoch": 1.6,
"learning_rate": 3.453551912568306e-05,
"loss": 0.8716,
"step": 600
},
{
"epoch": 1.62,
"learning_rate": 3.442622950819672e-05,
"loss": 0.8965,
"step": 610
},
{
"epoch": 1.65,
"learning_rate": 3.431693989071038e-05,
"loss": 0.9048,
"step": 620
},
{
"epoch": 1.68,
"learning_rate": 3.420765027322405e-05,
"loss": 0.9245,
"step": 630
},
{
"epoch": 1.7,
"learning_rate": 3.409836065573771e-05,
"loss": 0.9237,
"step": 640
},
{
"epoch": 1.73,
"learning_rate": 3.398907103825137e-05,
"loss": 0.9033,
"step": 650
},
{
"epoch": 1.76,
"learning_rate": 3.3879781420765035e-05,
"loss": 0.8863,
"step": 660
},
{
"epoch": 1.78,
"learning_rate": 3.3770491803278695e-05,
"loss": 0.8961,
"step": 670
},
{
"epoch": 1.81,
"learning_rate": 3.3661202185792355e-05,
"loss": 0.9243,
"step": 680
},
{
"epoch": 1.84,
"learning_rate": 3.3551912568306015e-05,
"loss": 0.9223,
"step": 690
},
{
"epoch": 1.86,
"learning_rate": 3.3442622950819675e-05,
"loss": 0.8865,
"step": 700
},
{
"epoch": 1.89,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.893,
"step": 710
},
{
"epoch": 1.91,
"learning_rate": 3.3224043715847e-05,
"loss": 0.892,
"step": 720
},
{
"epoch": 1.94,
"learning_rate": 3.311475409836066e-05,
"loss": 0.9133,
"step": 730
},
{
"epoch": 1.97,
"learning_rate": 3.300546448087432e-05,
"loss": 0.8801,
"step": 740
},
{
"epoch": 1.99,
"learning_rate": 3.289617486338798e-05,
"loss": 0.8861,
"step": 750
},
{
"epoch": 2.0,
"eval_loss": 1.0259734392166138,
"eval_runtime": 341.2083,
"eval_samples_per_second": 7.837,
"eval_steps_per_second": 1.961,
"eval_wer": 0.6686301931036431,
"step": 752
},
{
"epoch": 2.02,
"learning_rate": 3.278688524590164e-05,
"loss": 0.9331,
"step": 760
},
{
"epoch": 2.05,
"learning_rate": 3.26775956284153e-05,
"loss": 0.8923,
"step": 770
},
{
"epoch": 2.07,
"learning_rate": 3.256830601092896e-05,
"loss": 0.871,
"step": 780
},
{
"epoch": 2.1,
"learning_rate": 3.245901639344263e-05,
"loss": 0.8728,
"step": 790
},
{
"epoch": 2.13,
"learning_rate": 3.234972677595629e-05,
"loss": 0.897,
"step": 800
},
{
"epoch": 2.15,
"learning_rate": 3.224043715846995e-05,
"loss": 0.9309,
"step": 810
},
{
"epoch": 2.18,
"learning_rate": 3.213114754098361e-05,
"loss": 0.8783,
"step": 820
},
{
"epoch": 2.21,
"learning_rate": 3.202185792349727e-05,
"loss": 0.8631,
"step": 830
},
{
"epoch": 2.23,
"learning_rate": 3.191256830601093e-05,
"loss": 0.8903,
"step": 840
},
{
"epoch": 2.26,
"learning_rate": 3.180327868852459e-05,
"loss": 0.8706,
"step": 850
},
{
"epoch": 2.29,
"learning_rate": 3.1693989071038256e-05,
"loss": 0.9252,
"step": 860
},
{
"epoch": 2.31,
"learning_rate": 3.1584699453551916e-05,
"loss": 0.8834,
"step": 870
},
{
"epoch": 2.34,
"learning_rate": 3.1475409836065576e-05,
"loss": 0.8802,
"step": 880
},
{
"epoch": 2.37,
"learning_rate": 3.1366120218579236e-05,
"loss": 0.8935,
"step": 890
},
{
"epoch": 2.39,
"learning_rate": 3.1256830601092896e-05,
"loss": 0.8759,
"step": 900
},
{
"epoch": 2.42,
"learning_rate": 3.1147540983606557e-05,
"loss": 0.9278,
"step": 910
},
{
"epoch": 2.45,
"learning_rate": 3.103825136612022e-05,
"loss": 0.8689,
"step": 920
},
{
"epoch": 2.47,
"learning_rate": 3.0928961748633883e-05,
"loss": 0.8675,
"step": 930
},
{
"epoch": 2.5,
"learning_rate": 3.0819672131147544e-05,
"loss": 0.8751,
"step": 940
},
{
"epoch": 2.53,
"learning_rate": 3.0710382513661204e-05,
"loss": 0.877,
"step": 950
},
{
"epoch": 2.55,
"learning_rate": 3.0601092896174864e-05,
"loss": 0.9216,
"step": 960
},
{
"epoch": 2.58,
"learning_rate": 3.0491803278688527e-05,
"loss": 0.8636,
"step": 970
},
{
"epoch": 2.61,
"learning_rate": 3.0382513661202187e-05,
"loss": 0.8748,
"step": 980
},
{
"epoch": 2.63,
"learning_rate": 3.0273224043715847e-05,
"loss": 0.8876,
"step": 990
},
{
"epoch": 2.66,
"learning_rate": 3.0163934426229507e-05,
"loss": 0.8637,
"step": 1000
},
{
"epoch": 2.69,
"learning_rate": 3.005464480874317e-05,
"loss": 0.9266,
"step": 1010
},
{
"epoch": 2.71,
"learning_rate": 2.9945355191256834e-05,
"loss": 0.8768,
"step": 1020
},
{
"epoch": 2.74,
"learning_rate": 2.9836065573770498e-05,
"loss": 0.8833,
"step": 1030
},
{
"epoch": 2.77,
"learning_rate": 2.9726775956284158e-05,
"loss": 0.878,
"step": 1040
},
{
"epoch": 2.79,
"learning_rate": 2.9617486338797818e-05,
"loss": 0.8862,
"step": 1050
},
{
"epoch": 2.82,
"learning_rate": 2.9508196721311478e-05,
"loss": 0.9319,
"step": 1060
},
{
"epoch": 2.85,
"learning_rate": 2.939890710382514e-05,
"loss": 0.8807,
"step": 1070
},
{
"epoch": 2.87,
"learning_rate": 2.92896174863388e-05,
"loss": 0.9018,
"step": 1080
},
{
"epoch": 2.9,
"learning_rate": 2.918032786885246e-05,
"loss": 0.8827,
"step": 1090
},
{
"epoch": 2.93,
"learning_rate": 2.9071038251366125e-05,
"loss": 0.8759,
"step": 1100
},
{
"epoch": 2.95,
"learning_rate": 2.8961748633879785e-05,
"loss": 0.9162,
"step": 1110
},
{
"epoch": 2.98,
"learning_rate": 2.8852459016393445e-05,
"loss": 0.8682,
"step": 1120
},
{
"epoch": 3.0,
"eval_loss": 1.0357706546783447,
"eval_runtime": 341.6621,
"eval_samples_per_second": 7.826,
"eval_steps_per_second": 1.958,
"eval_wer": 0.6603899742434302,
"step": 1128
},
{
"epoch": 3.01,
"learning_rate": 2.874316939890711e-05,
"loss": 0.9038,
"step": 1130
},
{
"epoch": 3.03,
"learning_rate": 2.863387978142077e-05,
"loss": 0.9097,
"step": 1140
},
{
"epoch": 3.06,
"learning_rate": 2.852459016393443e-05,
"loss": 0.891,
"step": 1150
},
{
"epoch": 3.09,
"learning_rate": 2.841530054644809e-05,
"loss": 0.8733,
"step": 1160
},
{
"epoch": 3.11,
"learning_rate": 2.8306010928961752e-05,
"loss": 0.8789,
"step": 1170
},
{
"epoch": 3.14,
"learning_rate": 2.8196721311475412e-05,
"loss": 0.8846,
"step": 1180
},
{
"epoch": 3.16,
"learning_rate": 2.8087431693989072e-05,
"loss": 0.9069,
"step": 1190
},
{
"epoch": 3.19,
"learning_rate": 2.7978142076502736e-05,
"loss": 0.8742,
"step": 1200
},
{
"epoch": 3.22,
"learning_rate": 2.7868852459016396e-05,
"loss": 0.8769,
"step": 1210
},
{
"epoch": 3.24,
"learning_rate": 2.7759562841530056e-05,
"loss": 0.876,
"step": 1220
},
{
"epoch": 3.27,
"learning_rate": 2.765027322404372e-05,
"loss": 0.8952,
"step": 1230
},
{
"epoch": 3.3,
"learning_rate": 2.754098360655738e-05,
"loss": 0.898,
"step": 1240
},
{
"epoch": 3.32,
"learning_rate": 2.743169398907104e-05,
"loss": 0.8642,
"step": 1250
},
{
"epoch": 3.35,
"learning_rate": 2.73224043715847e-05,
"loss": 0.8772,
"step": 1260
},
{
"epoch": 3.38,
"learning_rate": 2.7213114754098363e-05,
"loss": 0.8589,
"step": 1270
},
{
"epoch": 3.4,
"learning_rate": 2.7103825136612023e-05,
"loss": 0.8754,
"step": 1280
},
{
"epoch": 3.43,
"learning_rate": 2.6994535519125683e-05,
"loss": 0.9035,
"step": 1290
},
{
"epoch": 3.46,
"learning_rate": 2.6885245901639346e-05,
"loss": 0.8784,
"step": 1300
},
{
"epoch": 3.48,
"learning_rate": 2.6775956284153007e-05,
"loss": 0.8698,
"step": 1310
},
{
"epoch": 3.51,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.8671,
"step": 1320
},
{
"epoch": 3.54,
"learning_rate": 2.655737704918033e-05,
"loss": 0.8834,
"step": 1330
},
{
"epoch": 3.56,
"learning_rate": 2.644808743169399e-05,
"loss": 0.9126,
"step": 1340
},
{
"epoch": 3.59,
"learning_rate": 2.633879781420765e-05,
"loss": 0.8678,
"step": 1350
},
{
"epoch": 3.62,
"learning_rate": 2.622950819672131e-05,
"loss": 0.8769,
"step": 1360
},
{
"epoch": 3.64,
"learning_rate": 2.6120218579234974e-05,
"loss": 0.8687,
"step": 1370
},
{
"epoch": 3.67,
"learning_rate": 2.6010928961748634e-05,
"loss": 0.8817,
"step": 1380
},
{
"epoch": 3.7,
"learning_rate": 2.59016393442623e-05,
"loss": 0.9162,
"step": 1390
},
{
"epoch": 3.72,
"learning_rate": 2.579234972677596e-05,
"loss": 0.8587,
"step": 1400
},
{
"epoch": 3.75,
"learning_rate": 2.568306010928962e-05,
"loss": 0.8572,
"step": 1410
},
{
"epoch": 3.78,
"learning_rate": 2.5573770491803284e-05,
"loss": 0.8629,
"step": 1420
},
{
"epoch": 3.8,
"learning_rate": 2.5464480874316944e-05,
"loss": 0.8755,
"step": 1430
},
{
"epoch": 3.83,
"learning_rate": 2.5355191256830604e-05,
"loss": 0.9048,
"step": 1440
},
{
"epoch": 3.86,
"learning_rate": 2.5245901639344264e-05,
"loss": 0.8635,
"step": 1450
},
{
"epoch": 3.88,
"learning_rate": 2.5136612021857928e-05,
"loss": 0.8618,
"step": 1460
},
{
"epoch": 3.91,
"learning_rate": 2.5027322404371588e-05,
"loss": 0.8637,
"step": 1470
},
{
"epoch": 3.94,
"learning_rate": 2.4918032786885248e-05,
"loss": 0.8885,
"step": 1480
},
{
"epoch": 3.96,
"learning_rate": 2.480874316939891e-05,
"loss": 0.8829,
"step": 1490
},
{
"epoch": 3.99,
"learning_rate": 2.469945355191257e-05,
"loss": 0.8662,
"step": 1500
},
{
"epoch": 4.0,
"eval_loss": 1.0233858823776245,
"eval_runtime": 343.724,
"eval_samples_per_second": 7.779,
"eval_steps_per_second": 1.946,
"eval_wer": 0.6664547753245469,
"step": 1504
},
{
"epoch": 4.02,
"learning_rate": 2.459016393442623e-05,
"loss": 0.9061,
"step": 1510
},
{
"epoch": 4.04,
"learning_rate": 2.448087431693989e-05,
"loss": 0.8684,
"step": 1520
},
{
"epoch": 4.07,
"learning_rate": 2.4371584699453555e-05,
"loss": 0.8616,
"step": 1530
},
{
"epoch": 4.1,
"learning_rate": 2.4262295081967215e-05,
"loss": 0.8718,
"step": 1540
},
{
"epoch": 4.12,
"learning_rate": 2.4153005464480875e-05,
"loss": 0.8663,
"step": 1550
},
{
"epoch": 4.15,
"learning_rate": 2.404371584699454e-05,
"loss": 0.9004,
"step": 1560
},
{
"epoch": 4.18,
"learning_rate": 2.39344262295082e-05,
"loss": 0.8659,
"step": 1570
},
{
"epoch": 4.2,
"learning_rate": 2.382513661202186e-05,
"loss": 0.8569,
"step": 1580
},
{
"epoch": 4.23,
"learning_rate": 2.3715846994535522e-05,
"loss": 0.8574,
"step": 1590
},
{
"epoch": 4.26,
"learning_rate": 2.3606557377049182e-05,
"loss": 0.8702,
"step": 1600
},
{
"epoch": 4.28,
"learning_rate": 2.3497267759562842e-05,
"loss": 0.9054,
"step": 1610
},
{
"epoch": 4.31,
"learning_rate": 2.3387978142076502e-05,
"loss": 0.8777,
"step": 1620
},
{
"epoch": 4.34,
"learning_rate": 2.3278688524590166e-05,
"loss": 0.8657,
"step": 1630
},
{
"epoch": 4.36,
"learning_rate": 2.3169398907103826e-05,
"loss": 0.8712,
"step": 1640
},
{
"epoch": 4.39,
"learning_rate": 2.3060109289617486e-05,
"loss": 0.8578,
"step": 1650
},
{
"epoch": 4.41,
"learning_rate": 2.295081967213115e-05,
"loss": 0.8931,
"step": 1660
},
{
"epoch": 4.44,
"learning_rate": 2.284153005464481e-05,
"loss": 0.8734,
"step": 1670
},
{
"epoch": 4.47,
"learning_rate": 2.273224043715847e-05,
"loss": 0.8715,
"step": 1680
},
{
"epoch": 4.49,
"learning_rate": 2.2622950819672133e-05,
"loss": 0.8578,
"step": 1690
},
{
"epoch": 4.52,
"learning_rate": 2.2513661202185793e-05,
"loss": 0.8612,
"step": 1700
},
{
"epoch": 4.55,
"learning_rate": 2.2404371584699453e-05,
"loss": 0.8929,
"step": 1710
},
{
"epoch": 4.57,
"learning_rate": 2.2295081967213113e-05,
"loss": 0.8684,
"step": 1720
},
{
"epoch": 4.6,
"learning_rate": 2.2185792349726777e-05,
"loss": 0.87,
"step": 1730
},
{
"epoch": 4.63,
"learning_rate": 2.2076502732240437e-05,
"loss": 0.8621,
"step": 1740
},
{
"epoch": 4.65,
"learning_rate": 2.1967213114754104e-05,
"loss": 0.8569,
"step": 1750
},
{
"epoch": 4.68,
"learning_rate": 2.1857923497267764e-05,
"loss": 0.9089,
"step": 1760
},
{
"epoch": 4.71,
"learning_rate": 2.1748633879781424e-05,
"loss": 0.8664,
"step": 1770
},
{
"epoch": 4.73,
"learning_rate": 2.1639344262295087e-05,
"loss": 0.872,
"step": 1780
},
{
"epoch": 4.76,
"learning_rate": 2.1530054644808747e-05,
"loss": 0.8537,
"step": 1790
},
{
"epoch": 4.79,
"learning_rate": 2.1420765027322407e-05,
"loss": 0.8592,
"step": 1800
},
{
"epoch": 4.81,
"learning_rate": 2.1311475409836067e-05,
"loss": 0.9015,
"step": 1810
},
{
"epoch": 4.84,
"learning_rate": 2.120218579234973e-05,
"loss": 0.8788,
"step": 1820
},
{
"epoch": 4.87,
"learning_rate": 2.109289617486339e-05,
"loss": 0.8552,
"step": 1830
},
{
"epoch": 4.89,
"learning_rate": 2.098360655737705e-05,
"loss": 0.8587,
"step": 1840
},
{
"epoch": 4.92,
"learning_rate": 2.0874316939890714e-05,
"loss": 0.8552,
"step": 1850
},
{
"epoch": 4.95,
"learning_rate": 2.0765027322404374e-05,
"loss": 0.8833,
"step": 1860
},
{
"epoch": 4.97,
"learning_rate": 2.0655737704918034e-05,
"loss": 0.8501,
"step": 1870
},
{
"epoch": 5.0,
"learning_rate": 2.0546448087431698e-05,
"loss": 0.8463,
"step": 1880
},
{
"epoch": 5.0,
"eval_loss": 1.0332772731781006,
"eval_runtime": 349.3455,
"eval_samples_per_second": 7.654,
"eval_steps_per_second": 1.915,
"eval_wer": 0.6666054536122765,
"step": 1880
},
{
"epoch": 5.03,
"learning_rate": 2.0437158469945358e-05,
"loss": 0.9174,
"step": 1890
},
{
"epoch": 5.05,
"learning_rate": 2.0327868852459018e-05,
"loss": 0.8478,
"step": 1900
},
{
"epoch": 5.08,
"learning_rate": 2.0218579234972678e-05,
"loss": 0.8535,
"step": 1910
},
{
"epoch": 5.11,
"learning_rate": 2.010928961748634e-05,
"loss": 0.8651,
"step": 1920
},
{
"epoch": 5.13,
"learning_rate": 2e-05,
"loss": 0.8535,
"step": 1930
},
{
"epoch": 5.16,
"learning_rate": 1.9890710382513662e-05,
"loss": 0.9069,
"step": 1940
},
{
"epoch": 5.19,
"learning_rate": 1.9781420765027325e-05,
"loss": 0.8565,
"step": 1950
},
{
"epoch": 5.21,
"learning_rate": 1.9672131147540985e-05,
"loss": 0.8713,
"step": 1960
},
{
"epoch": 5.24,
"learning_rate": 1.9562841530054645e-05,
"loss": 0.8545,
"step": 1970
},
{
"epoch": 5.27,
"learning_rate": 1.9453551912568305e-05,
"loss": 0.8637,
"step": 1980
},
{
"epoch": 5.29,
"learning_rate": 1.934426229508197e-05,
"loss": 0.9046,
"step": 1990
},
{
"epoch": 5.32,
"learning_rate": 1.923497267759563e-05,
"loss": 0.8542,
"step": 2000
},
{
"epoch": 5.35,
"learning_rate": 1.912568306010929e-05,
"loss": 0.8442,
"step": 2010
},
{
"epoch": 5.37,
"learning_rate": 1.9027322404371588e-05,
"loss": 0.8502,
"step": 2020
},
{
"epoch": 5.4,
"learning_rate": 1.8918032786885248e-05,
"loss": 0.8663,
"step": 2030
},
{
"epoch": 5.43,
"learning_rate": 1.8808743169398908e-05,
"loss": 0.8946,
"step": 2040
},
{
"epoch": 5.45,
"learning_rate": 1.869945355191257e-05,
"loss": 0.8449,
"step": 2050
},
{
"epoch": 5.48,
"learning_rate": 1.859016393442623e-05,
"loss": 0.8443,
"step": 2060
},
{
"epoch": 5.51,
"learning_rate": 1.848087431693989e-05,
"loss": 0.8446,
"step": 2070
},
{
"epoch": 5.53,
"learning_rate": 1.837158469945355e-05,
"loss": 0.859,
"step": 2080
},
{
"epoch": 5.56,
"learning_rate": 1.8262295081967215e-05,
"loss": 0.9006,
"step": 2090
},
{
"epoch": 5.59,
"learning_rate": 1.8153005464480875e-05,
"loss": 0.8588,
"step": 2100
},
{
"epoch": 5.61,
"learning_rate": 1.8043715846994535e-05,
"loss": 0.8568,
"step": 2110
},
{
"epoch": 5.64,
"learning_rate": 1.79344262295082e-05,
"loss": 0.8614,
"step": 2120
},
{
"epoch": 5.66,
"learning_rate": 1.782513661202186e-05,
"loss": 0.8447,
"step": 2130
},
{
"epoch": 5.69,
"learning_rate": 1.7715846994535522e-05,
"loss": 0.9098,
"step": 2140
},
{
"epoch": 5.72,
"learning_rate": 1.7606557377049182e-05,
"loss": 0.8408,
"step": 2150
},
{
"epoch": 5.74,
"learning_rate": 1.7497267759562842e-05,
"loss": 0.8611,
"step": 2160
},
{
"epoch": 5.77,
"learning_rate": 1.7387978142076506e-05,
"loss": 0.8524,
"step": 2170
},
{
"epoch": 5.8,
"learning_rate": 1.7278688524590166e-05,
"loss": 0.859,
"step": 2180
},
{
"epoch": 5.82,
"learning_rate": 1.7169398907103826e-05,
"loss": 0.9099,
"step": 2190
},
{
"epoch": 5.85,
"learning_rate": 1.706010928961749e-05,
"loss": 0.8534,
"step": 2200
},
{
"epoch": 5.88,
"learning_rate": 1.695081967213115e-05,
"loss": 0.8525,
"step": 2210
},
{
"epoch": 5.9,
"learning_rate": 1.684153005464481e-05,
"loss": 0.8426,
"step": 2220
},
{
"epoch": 5.93,
"learning_rate": 1.6732240437158473e-05,
"loss": 0.8708,
"step": 2230
},
{
"epoch": 5.96,
"learning_rate": 1.6622950819672133e-05,
"loss": 0.8648,
"step": 2240
},
{
"epoch": 5.98,
"learning_rate": 1.6513661202185793e-05,
"loss": 0.8573,
"step": 2250
},
{
"epoch": 6.0,
"eval_loss": 1.0162557363510132,
"eval_runtime": 338.1768,
"eval_samples_per_second": 7.907,
"eval_steps_per_second": 1.978,
"eval_wer": 0.6621886963032024,
"step": 2256
},
{
"epoch": 6.01,
"learning_rate": 1.6404371584699453e-05,
"loss": 0.8838,
"step": 2260
},
{
"epoch": 6.04,
"learning_rate": 1.6295081967213116e-05,
"loss": 0.8716,
"step": 2270
},
{
"epoch": 6.06,
"learning_rate": 1.6185792349726776e-05,
"loss": 0.8522,
"step": 2280
},
{
"epoch": 6.09,
"learning_rate": 1.6076502732240437e-05,
"loss": 0.8475,
"step": 2290
},
{
"epoch": 6.12,
"learning_rate": 1.59672131147541e-05,
"loss": 0.8533,
"step": 2300
},
{
"epoch": 6.14,
"learning_rate": 1.585792349726776e-05,
"loss": 0.8867,
"step": 2310
},
{
"epoch": 6.17,
"learning_rate": 1.5748633879781424e-05,
"loss": 0.8741,
"step": 2320
},
{
"epoch": 6.2,
"learning_rate": 1.5639344262295084e-05,
"loss": 0.8564,
"step": 2330
},
{
"epoch": 6.22,
"learning_rate": 1.5530054644808744e-05,
"loss": 0.8445,
"step": 2340
},
{
"epoch": 6.25,
"learning_rate": 1.5420765027322407e-05,
"loss": 0.8345,
"step": 2350
},
{
"epoch": 6.28,
"learning_rate": 1.5311475409836067e-05,
"loss": 0.8805,
"step": 2360
},
{
"epoch": 6.3,
"learning_rate": 1.5202185792349729e-05,
"loss": 0.8609,
"step": 2370
},
{
"epoch": 6.33,
"learning_rate": 1.5092896174863389e-05,
"loss": 0.8438,
"step": 2380
},
{
"epoch": 6.36,
"learning_rate": 1.498360655737705e-05,
"loss": 0.8471,
"step": 2390
},
{
"epoch": 6.38,
"learning_rate": 1.4874316939890713e-05,
"loss": 0.8487,
"step": 2400
},
{
"epoch": 6.41,
"learning_rate": 1.4765027322404373e-05,
"loss": 0.8833,
"step": 2410
},
{
"epoch": 6.44,
"learning_rate": 1.4655737704918034e-05,
"loss": 0.8878,
"step": 2420
},
{
"epoch": 6.46,
"learning_rate": 1.4546448087431694e-05,
"loss": 0.8349,
"step": 2430
},
{
"epoch": 6.49,
"learning_rate": 1.4437158469945356e-05,
"loss": 0.8425,
"step": 2440
},
{
"epoch": 6.52,
"learning_rate": 1.4327868852459016e-05,
"loss": 0.8523,
"step": 2450
},
{
"epoch": 6.54,
"learning_rate": 1.4218579234972678e-05,
"loss": 0.879,
"step": 2460
},
{
"epoch": 6.57,
"learning_rate": 1.410928961748634e-05,
"loss": 0.865,
"step": 2470
},
{
"epoch": 6.6,
"learning_rate": 1.4e-05,
"loss": 0.8514,
"step": 2480
},
{
"epoch": 6.62,
"learning_rate": 1.3890710382513662e-05,
"loss": 0.8625,
"step": 2490
},
{
"epoch": 6.65,
"learning_rate": 1.3781420765027325e-05,
"loss": 0.8543,
"step": 2500
},
{
"epoch": 6.68,
"learning_rate": 1.3672131147540985e-05,
"loss": 0.8793,
"step": 2510
},
{
"epoch": 6.7,
"learning_rate": 1.3562841530054647e-05,
"loss": 0.8603,
"step": 2520
},
{
"epoch": 6.73,
"learning_rate": 1.3453551912568309e-05,
"loss": 0.8584,
"step": 2530
},
{
"epoch": 6.76,
"learning_rate": 1.3344262295081969e-05,
"loss": 0.8384,
"step": 2540
},
{
"epoch": 6.78,
"learning_rate": 1.323497267759563e-05,
"loss": 0.8335,
"step": 2550
},
{
"epoch": 6.81,
"learning_rate": 1.312568306010929e-05,
"loss": 0.8594,
"step": 2560
},
{
"epoch": 6.84,
"learning_rate": 1.3016393442622952e-05,
"loss": 0.8789,
"step": 2570
},
{
"epoch": 6.86,
"learning_rate": 1.2907103825136614e-05,
"loss": 0.8446,
"step": 2580
},
{
"epoch": 6.89,
"learning_rate": 1.2797814207650274e-05,
"loss": 0.8577,
"step": 2590
},
{
"epoch": 6.91,
"learning_rate": 1.2688524590163936e-05,
"loss": 0.8502,
"step": 2600
},
{
"epoch": 6.94,
"learning_rate": 1.2579234972677596e-05,
"loss": 0.8872,
"step": 2610
},
{
"epoch": 6.97,
"learning_rate": 1.2469945355191258e-05,
"loss": 0.8502,
"step": 2620
},
{
"epoch": 6.99,
"learning_rate": 1.236065573770492e-05,
"loss": 0.8628,
"step": 2630
},
{
"epoch": 7.0,
"eval_loss": 1.0209393501281738,
"eval_runtime": 339.6154,
"eval_samples_per_second": 7.874,
"eval_steps_per_second": 1.97,
"eval_wer": 0.6550550211185038,
"step": 2632
},
{
"epoch": 7.02,
"learning_rate": 1.225136612021858e-05,
"loss": 0.9001,
"step": 2640
},
{
"epoch": 7.05,
"learning_rate": 1.2142076502732241e-05,
"loss": 0.8424,
"step": 2650
},
{
"epoch": 7.07,
"learning_rate": 1.2032786885245901e-05,
"loss": 0.8444,
"step": 2660
},
{
"epoch": 7.1,
"learning_rate": 1.1923497267759563e-05,
"loss": 0.8413,
"step": 2670
},
{
"epoch": 7.13,
"learning_rate": 1.1814207650273223e-05,
"loss": 0.8429,
"step": 2680
},
{
"epoch": 7.15,
"learning_rate": 1.1704918032786887e-05,
"loss": 0.904,
"step": 2690
},
{
"epoch": 7.18,
"learning_rate": 1.1595628415300548e-05,
"loss": 0.8378,
"step": 2700
},
{
"epoch": 7.21,
"learning_rate": 1.148633879781421e-05,
"loss": 0.8401,
"step": 2710
},
{
"epoch": 7.23,
"learning_rate": 1.137704918032787e-05,
"loss": 0.8533,
"step": 2720
},
{
"epoch": 7.26,
"learning_rate": 1.1267759562841532e-05,
"loss": 0.8341,
"step": 2730
},
{
"epoch": 7.29,
"learning_rate": 1.1158469945355192e-05,
"loss": 0.8987,
"step": 2740
},
{
"epoch": 7.31,
"learning_rate": 1.1049180327868854e-05,
"loss": 0.8522,
"step": 2750
},
{
"epoch": 7.34,
"learning_rate": 1.0939890710382515e-05,
"loss": 0.8437,
"step": 2760
},
{
"epoch": 7.37,
"learning_rate": 1.0830601092896176e-05,
"loss": 0.8466,
"step": 2770
},
{
"epoch": 7.39,
"learning_rate": 1.0721311475409837e-05,
"loss": 0.8477,
"step": 2780
},
{
"epoch": 7.42,
"learning_rate": 1.0612021857923497e-05,
"loss": 0.9094,
"step": 2790
},
{
"epoch": 7.45,
"learning_rate": 1.0502732240437159e-05,
"loss": 0.8399,
"step": 2800
},
{
"epoch": 7.47,
"learning_rate": 1.0393442622950821e-05,
"loss": 0.855,
"step": 2810
},
{
"epoch": 7.5,
"learning_rate": 1.0284153005464481e-05,
"loss": 0.8448,
"step": 2820
},
{
"epoch": 7.53,
"learning_rate": 1.0174863387978143e-05,
"loss": 0.8438,
"step": 2830
},
{
"epoch": 7.55,
"learning_rate": 1.0065573770491803e-05,
"loss": 0.8951,
"step": 2840
},
{
"epoch": 7.58,
"learning_rate": 9.956284153005466e-06,
"loss": 0.858,
"step": 2850
},
{
"epoch": 7.61,
"learning_rate": 9.846994535519126e-06,
"loss": 0.8505,
"step": 2860
},
{
"epoch": 7.63,
"learning_rate": 9.737704918032788e-06,
"loss": 0.8452,
"step": 2870
},
{
"epoch": 7.66,
"learning_rate": 9.628415300546448e-06,
"loss": 0.8374,
"step": 2880
},
{
"epoch": 7.69,
"learning_rate": 9.51912568306011e-06,
"loss": 0.8905,
"step": 2890
},
{
"epoch": 7.71,
"learning_rate": 9.409836065573772e-06,
"loss": 0.8538,
"step": 2900
},
{
"epoch": 7.74,
"learning_rate": 9.300546448087432e-06,
"loss": 0.848,
"step": 2910
},
{
"epoch": 7.77,
"learning_rate": 9.191256830601093e-06,
"loss": 0.844,
"step": 2920
},
{
"epoch": 7.79,
"learning_rate": 9.081967213114755e-06,
"loss": 0.8375,
"step": 2930
},
{
"epoch": 7.82,
"learning_rate": 8.972677595628417e-06,
"loss": 0.8901,
"step": 2940
},
{
"epoch": 7.85,
"learning_rate": 8.863387978142077e-06,
"loss": 0.8564,
"step": 2950
},
{
"epoch": 7.87,
"learning_rate": 8.754098360655739e-06,
"loss": 0.8372,
"step": 2960
},
{
"epoch": 7.9,
"learning_rate": 8.644808743169399e-06,
"loss": 0.8338,
"step": 2970
},
{
"epoch": 7.93,
"learning_rate": 8.53551912568306e-06,
"loss": 0.8386,
"step": 2980
},
{
"epoch": 7.95,
"learning_rate": 8.426229508196722e-06,
"loss": 0.8699,
"step": 2990
},
{
"epoch": 7.98,
"learning_rate": 8.316939890710382e-06,
"loss": 0.8493,
"step": 3000
},
{
"epoch": 8.0,
"eval_loss": 1.0525248050689697,
"eval_runtime": 343.4159,
"eval_samples_per_second": 7.786,
"eval_steps_per_second": 1.948,
"eval_wer": 0.6581815955888931,
"step": 3008
},
{
"epoch": 8.01,
"learning_rate": 8.207650273224044e-06,
"loss": 0.8601,
"step": 3010
},
{
"epoch": 8.03,
"learning_rate": 8.098360655737706e-06,
"loss": 0.8718,
"step": 3020
},
{
"epoch": 8.06,
"learning_rate": 7.989071038251368e-06,
"loss": 0.8381,
"step": 3030
},
{
"epoch": 8.09,
"learning_rate": 7.879781420765028e-06,
"loss": 0.8315,
"step": 3040
},
{
"epoch": 8.11,
"learning_rate": 7.77049180327869e-06,
"loss": 0.8324,
"step": 3050
},
{
"epoch": 8.14,
"learning_rate": 7.66120218579235e-06,
"loss": 0.8601,
"step": 3060
},
{
"epoch": 8.16,
"learning_rate": 7.551912568306011e-06,
"loss": 0.8776,
"step": 3070
},
{
"epoch": 8.19,
"learning_rate": 7.442622950819672e-06,
"loss": 0.8488,
"step": 3080
},
{
"epoch": 8.22,
"learning_rate": 7.333333333333333e-06,
"loss": 0.8432,
"step": 3090
},
{
"epoch": 8.24,
"learning_rate": 7.224043715846996e-06,
"loss": 0.8341,
"step": 3100
},
{
"epoch": 8.27,
"learning_rate": 7.114754098360657e-06,
"loss": 0.8486,
"step": 3110
},
{
"epoch": 8.3,
"learning_rate": 7.0054644808743176e-06,
"loss": 0.885,
"step": 3120
},
{
"epoch": 8.32,
"learning_rate": 6.8961748633879785e-06,
"loss": 0.8465,
"step": 3130
},
{
"epoch": 8.35,
"learning_rate": 6.78688524590164e-06,
"loss": 0.8395,
"step": 3140
},
{
"epoch": 8.38,
"learning_rate": 6.677595628415301e-06,
"loss": 0.8381,
"step": 3150
},
{
"epoch": 8.4,
"learning_rate": 6.568306010928962e-06,
"loss": 0.8614,
"step": 3160
},
{
"epoch": 8.43,
"learning_rate": 6.459016393442623e-06,
"loss": 0.8787,
"step": 3170
},
{
"epoch": 8.46,
"learning_rate": 6.349726775956284e-06,
"loss": 0.83,
"step": 3180
},
{
"epoch": 8.48,
"learning_rate": 6.2404371584699465e-06,
"loss": 0.848,
"step": 3190
},
{
"epoch": 8.51,
"learning_rate": 6.131147540983607e-06,
"loss": 0.8501,
"step": 3200
},
{
"epoch": 8.54,
"learning_rate": 6.021857923497268e-06,
"loss": 0.8618,
"step": 3210
},
{
"epoch": 8.56,
"learning_rate": 5.912568306010929e-06,
"loss": 0.8855,
"step": 3220
},
{
"epoch": 8.59,
"learning_rate": 5.803278688524591e-06,
"loss": 0.8357,
"step": 3230
},
{
"epoch": 8.62,
"learning_rate": 5.693989071038252e-06,
"loss": 0.8365,
"step": 3240
},
{
"epoch": 8.64,
"learning_rate": 5.584699453551913e-06,
"loss": 0.8537,
"step": 3250
},
{
"epoch": 8.67,
"learning_rate": 5.475409836065574e-06,
"loss": 0.8565,
"step": 3260
},
{
"epoch": 8.7,
"learning_rate": 5.366120218579235e-06,
"loss": 0.8691,
"step": 3270
},
{
"epoch": 8.72,
"learning_rate": 5.256830601092897e-06,
"loss": 0.8333,
"step": 3280
},
{
"epoch": 8.75,
"learning_rate": 5.147540983606558e-06,
"loss": 0.8268,
"step": 3290
},
{
"epoch": 8.78,
"learning_rate": 5.038251366120219e-06,
"loss": 0.8405,
"step": 3300
},
{
"epoch": 8.8,
"learning_rate": 4.92896174863388e-06,
"loss": 0.8438,
"step": 3310
},
{
"epoch": 8.83,
"learning_rate": 4.819672131147542e-06,
"loss": 0.8763,
"step": 3320
},
{
"epoch": 8.86,
"learning_rate": 4.710382513661203e-06,
"loss": 0.841,
"step": 3330
},
{
"epoch": 8.88,
"learning_rate": 4.6010928961748635e-06,
"loss": 0.8371,
"step": 3340
},
{
"epoch": 8.91,
"learning_rate": 4.491803278688525e-06,
"loss": 0.8287,
"step": 3350
},
{
"epoch": 8.94,
"learning_rate": 4.382513661202186e-06,
"loss": 0.8526,
"step": 3360
},
{
"epoch": 8.96,
"learning_rate": 4.273224043715847e-06,
"loss": 0.8507,
"step": 3370
},
{
"epoch": 8.99,
"learning_rate": 4.163934426229508e-06,
"loss": 0.8371,
"step": 3380
},
{
"epoch": 9.0,
"eval_loss": 1.0408543348312378,
"eval_runtime": 348.0788,
"eval_samples_per_second": 7.682,
"eval_steps_per_second": 1.922,
"eval_wer": 0.651471703088434,
"step": 3384
},
{
"epoch": 9.02,
"learning_rate": 4.05464480874317e-06,
"loss": 0.8875,
"step": 3390
},
{
"epoch": 9.04,
"learning_rate": 3.945355191256831e-06,
"loss": 0.8507,
"step": 3400
},
{
"epoch": 9.07,
"learning_rate": 3.8360655737704925e-06,
"loss": 0.8481,
"step": 3410
},
{
"epoch": 9.1,
"learning_rate": 3.7267759562841534e-06,
"loss": 0.843,
"step": 3420
},
{
"epoch": 9.12,
"learning_rate": 3.6174863387978143e-06,
"loss": 0.8397,
"step": 3430
},
{
"epoch": 9.15,
"learning_rate": 3.508196721311476e-06,
"loss": 0.8743,
"step": 3440
},
{
"epoch": 9.18,
"learning_rate": 3.398907103825137e-06,
"loss": 0.8453,
"step": 3450
},
{
"epoch": 9.2,
"learning_rate": 3.2896174863387983e-06,
"loss": 0.8378,
"step": 3460
},
{
"epoch": 9.23,
"learning_rate": 3.180327868852459e-06,
"loss": 0.8245,
"step": 3470
},
{
"epoch": 9.26,
"learning_rate": 3.07103825136612e-06,
"loss": 0.8337,
"step": 3480
},
{
"epoch": 9.28,
"learning_rate": 2.961748633879782e-06,
"loss": 0.8748,
"step": 3490
},
{
"epoch": 9.31,
"learning_rate": 2.8524590163934428e-06,
"loss": 0.8398,
"step": 3500
},
{
"epoch": 9.34,
"learning_rate": 2.743169398907104e-06,
"loss": 0.8387,
"step": 3510
},
{
"epoch": 9.36,
"learning_rate": 2.633879781420765e-06,
"loss": 0.8413,
"step": 3520
},
{
"epoch": 9.39,
"learning_rate": 2.5245901639344268e-06,
"loss": 0.8338,
"step": 3530
},
{
"epoch": 9.41,
"learning_rate": 2.4153005464480877e-06,
"loss": 0.8767,
"step": 3540
},
{
"epoch": 9.44,
"learning_rate": 2.306010928961749e-06,
"loss": 0.8293,
"step": 3550
},
{
"epoch": 9.47,
"learning_rate": 2.19672131147541e-06,
"loss": 0.839,
"step": 3560
},
{
"epoch": 9.49,
"learning_rate": 2.0874316939890713e-06,
"loss": 0.8318,
"step": 3570
},
{
"epoch": 9.52,
"learning_rate": 1.978142076502732e-06,
"loss": 0.8353,
"step": 3580
},
{
"epoch": 9.55,
"learning_rate": 1.8688524590163937e-06,
"loss": 0.8795,
"step": 3590
},
{
"epoch": 9.57,
"learning_rate": 1.7595628415300548e-06,
"loss": 0.8441,
"step": 3600
},
{
"epoch": 9.6,
"learning_rate": 1.6502732240437162e-06,
"loss": 0.8318,
"step": 3610
},
{
"epoch": 9.63,
"learning_rate": 1.540983606557377e-06,
"loss": 0.8313,
"step": 3620
},
{
"epoch": 9.65,
"learning_rate": 1.4316939890710382e-06,
"loss": 0.8372,
"step": 3630
},
{
"epoch": 9.68,
"learning_rate": 1.3224043715846995e-06,
"loss": 0.8708,
"step": 3640
},
{
"epoch": 9.71,
"learning_rate": 1.2131147540983609e-06,
"loss": 0.8448,
"step": 3650
},
{
"epoch": 9.73,
"learning_rate": 1.103825136612022e-06,
"loss": 0.837,
"step": 3660
},
{
"epoch": 9.76,
"learning_rate": 9.945355191256831e-07,
"loss": 0.8315,
"step": 3670
},
{
"epoch": 9.79,
"learning_rate": 8.852459016393443e-07,
"loss": 0.8322,
"step": 3680
},
{
"epoch": 9.81,
"learning_rate": 7.759562841530055e-07,
"loss": 0.8701,
"step": 3690
},
{
"epoch": 9.84,
"learning_rate": 6.666666666666667e-07,
"loss": 0.8334,
"step": 3700
},
{
"epoch": 9.87,
"learning_rate": 5.573770491803279e-07,
"loss": 0.8416,
"step": 3710
},
{
"epoch": 9.89,
"learning_rate": 4.480874316939891e-07,
"loss": 0.8386,
"step": 3720
},
{
"epoch": 9.92,
"learning_rate": 3.387978142076503e-07,
"loss": 0.8322,
"step": 3730
},
{
"epoch": 9.95,
"learning_rate": 2.295081967213115e-07,
"loss": 0.8574,
"step": 3740
},
{
"epoch": 9.97,
"learning_rate": 1.202185792349727e-07,
"loss": 0.8294,
"step": 3750
},
{
"epoch": 10.0,
"learning_rate": 1.0928961748633881e-08,
"loss": 0.8229,
"step": 3760
},
{
"epoch": 10.0,
"eval_loss": 1.059747576713562,
"eval_runtime": 346.8481,
"eval_samples_per_second": 7.709,
"eval_steps_per_second": 1.929,
"eval_wer": 0.6522768901884891,
"step": 3760
},
{
"epoch": 10.0,
"step": 3760,
"total_flos": 7.29061419637639e+19,
"train_loss": 0.8711832551245994,
"train_runtime": 72833.4219,
"train_samples_per_second": 3.304,
"train_steps_per_second": 0.052
}
],
"max_steps": 3760,
"num_train_epochs": 10,
"total_flos": 7.29061419637639e+19,
"trial_name": null,
"trial_params": null
}