hr16's picture
Training in progress, epoch 2, checkpoint
7b3e922 verified
{
"best_metric": 0.0857774206508638,
"best_model_checkpoint": "PhoWhisper-small-vispeech-classifier-v3/checkpoint-392",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 784,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012755102040816327,
"grad_norm": 48589.94921875,
"learning_rate": 6.377551020408164e-08,
"loss": 2.0884,
"step": 5
},
{
"epoch": 0.025510204081632654,
"grad_norm": 50532.125,
"learning_rate": 1.2755102040816328e-07,
"loss": 2.0887,
"step": 10
},
{
"epoch": 0.03826530612244898,
"grad_norm": 50246.4296875,
"learning_rate": 1.913265306122449e-07,
"loss": 2.0885,
"step": 15
},
{
"epoch": 0.05102040816326531,
"grad_norm": 57370.44140625,
"learning_rate": 2.5510204081632656e-07,
"loss": 2.0908,
"step": 20
},
{
"epoch": 0.06377551020408163,
"grad_norm": 40133.53125,
"learning_rate": 3.188775510204082e-07,
"loss": 2.0889,
"step": 25
},
{
"epoch": 0.07653061224489796,
"grad_norm": 58377.3671875,
"learning_rate": 3.826530612244898e-07,
"loss": 2.0874,
"step": 30
},
{
"epoch": 0.08928571428571429,
"grad_norm": 50888.7421875,
"learning_rate": 4.4642857142857147e-07,
"loss": 2.088,
"step": 35
},
{
"epoch": 0.10204081632653061,
"grad_norm": 44107.75390625,
"learning_rate": 5.102040816326531e-07,
"loss": 2.0872,
"step": 40
},
{
"epoch": 0.11479591836734694,
"grad_norm": 62939.18359375,
"learning_rate": 5.739795918367347e-07,
"loss": 2.0873,
"step": 45
},
{
"epoch": 0.12755102040816327,
"grad_norm": 42077.53515625,
"learning_rate": 6.377551020408164e-07,
"loss": 2.0852,
"step": 50
},
{
"epoch": 0.14030612244897958,
"grad_norm": 50233.00390625,
"learning_rate": 7.015306122448979e-07,
"loss": 2.0861,
"step": 55
},
{
"epoch": 0.15306122448979592,
"grad_norm": 60839.4765625,
"learning_rate": 7.653061224489796e-07,
"loss": 2.0856,
"step": 60
},
{
"epoch": 0.16581632653061223,
"grad_norm": 57499.3515625,
"learning_rate": 8.290816326530612e-07,
"loss": 2.0838,
"step": 65
},
{
"epoch": 0.17857142857142858,
"grad_norm": 65030.765625,
"learning_rate": 8.928571428571429e-07,
"loss": 2.083,
"step": 70
},
{
"epoch": 0.1913265306122449,
"grad_norm": 53192.35546875,
"learning_rate": 9.566326530612244e-07,
"loss": 2.0841,
"step": 75
},
{
"epoch": 0.20408163265306123,
"grad_norm": 52991.80078125,
"learning_rate": 1.0204081632653063e-06,
"loss": 2.0817,
"step": 80
},
{
"epoch": 0.21683673469387754,
"grad_norm": 48656.234375,
"learning_rate": 1.0841836734693879e-06,
"loss": 2.0813,
"step": 85
},
{
"epoch": 0.22959183673469388,
"grad_norm": 63459.2421875,
"learning_rate": 1.1479591836734695e-06,
"loss": 2.081,
"step": 90
},
{
"epoch": 0.2423469387755102,
"grad_norm": 47800.3515625,
"learning_rate": 1.211734693877551e-06,
"loss": 2.0775,
"step": 95
},
{
"epoch": 0.25510204081632654,
"grad_norm": 64353.37890625,
"learning_rate": 1.2755102040816329e-06,
"loss": 2.0772,
"step": 100
},
{
"epoch": 0.26785714285714285,
"grad_norm": 59652.29296875,
"learning_rate": 1.3392857142857143e-06,
"loss": 2.0779,
"step": 105
},
{
"epoch": 0.28061224489795916,
"grad_norm": 44752.69140625,
"learning_rate": 1.4030612244897959e-06,
"loss": 2.0764,
"step": 110
},
{
"epoch": 0.29336734693877553,
"grad_norm": 49883.0,
"learning_rate": 1.4668367346938777e-06,
"loss": 2.0763,
"step": 115
},
{
"epoch": 0.30612244897959184,
"grad_norm": 65950.28125,
"learning_rate": 1.5306122448979593e-06,
"loss": 2.0739,
"step": 120
},
{
"epoch": 0.31887755102040816,
"grad_norm": 61354.83203125,
"learning_rate": 1.5943877551020409e-06,
"loss": 2.0706,
"step": 125
},
{
"epoch": 0.33163265306122447,
"grad_norm": 53169.91796875,
"learning_rate": 1.6581632653061225e-06,
"loss": 2.0709,
"step": 130
},
{
"epoch": 0.34438775510204084,
"grad_norm": 55883.31640625,
"learning_rate": 1.7219387755102043e-06,
"loss": 2.0695,
"step": 135
},
{
"epoch": 0.35714285714285715,
"grad_norm": 38134.765625,
"learning_rate": 1.7857142857142859e-06,
"loss": 2.0675,
"step": 140
},
{
"epoch": 0.36989795918367346,
"grad_norm": 53920.7265625,
"learning_rate": 1.8494897959183675e-06,
"loss": 2.0659,
"step": 145
},
{
"epoch": 0.3826530612244898,
"grad_norm": 68777.28125,
"learning_rate": 1.913265306122449e-06,
"loss": 2.0638,
"step": 150
},
{
"epoch": 0.39540816326530615,
"grad_norm": 46247.8984375,
"learning_rate": 1.977040816326531e-06,
"loss": 2.0656,
"step": 155
},
{
"epoch": 0.40816326530612246,
"grad_norm": 49636.04296875,
"learning_rate": 2.0408163265306125e-06,
"loss": 2.0621,
"step": 160
},
{
"epoch": 0.42091836734693877,
"grad_norm": 51880.3515625,
"learning_rate": 2.104591836734694e-06,
"loss": 2.057,
"step": 165
},
{
"epoch": 0.4336734693877551,
"grad_norm": 52808.734375,
"learning_rate": 2.1683673469387757e-06,
"loss": 2.0585,
"step": 170
},
{
"epoch": 0.44642857142857145,
"grad_norm": 46398.125,
"learning_rate": 2.2321428571428573e-06,
"loss": 2.0505,
"step": 175
},
{
"epoch": 0.45918367346938777,
"grad_norm": 59347.2578125,
"learning_rate": 2.295918367346939e-06,
"loss": 2.0487,
"step": 180
},
{
"epoch": 0.4719387755102041,
"grad_norm": 58343.73828125,
"learning_rate": 2.3596938775510205e-06,
"loss": 2.0563,
"step": 185
},
{
"epoch": 0.4846938775510204,
"grad_norm": 43836.42578125,
"learning_rate": 2.423469387755102e-06,
"loss": 2.0486,
"step": 190
},
{
"epoch": 0.49744897959183676,
"grad_norm": 69661.5859375,
"learning_rate": 2.487244897959184e-06,
"loss": 2.0443,
"step": 195
},
{
"epoch": 0.5102040816326531,
"grad_norm": 53888.24609375,
"learning_rate": 2.5510204081632657e-06,
"loss": 2.0475,
"step": 200
},
{
"epoch": 0.5229591836734694,
"grad_norm": 50369.1640625,
"learning_rate": 2.6147959183673473e-06,
"loss": 2.035,
"step": 205
},
{
"epoch": 0.5357142857142857,
"grad_norm": 62733.9609375,
"learning_rate": 2.6785714285714285e-06,
"loss": 2.0354,
"step": 210
},
{
"epoch": 0.548469387755102,
"grad_norm": 48340.67578125,
"learning_rate": 2.74234693877551e-06,
"loss": 2.0373,
"step": 215
},
{
"epoch": 0.5612244897959183,
"grad_norm": 50353.734375,
"learning_rate": 2.8061224489795917e-06,
"loss": 2.0389,
"step": 220
},
{
"epoch": 0.5739795918367347,
"grad_norm": 62351.765625,
"learning_rate": 2.869897959183674e-06,
"loss": 2.0263,
"step": 225
},
{
"epoch": 0.5867346938775511,
"grad_norm": 73855.609375,
"learning_rate": 2.9336734693877553e-06,
"loss": 2.0269,
"step": 230
},
{
"epoch": 0.5994897959183674,
"grad_norm": 84417.859375,
"learning_rate": 2.997448979591837e-06,
"loss": 2.0311,
"step": 235
},
{
"epoch": 0.6122448979591837,
"grad_norm": 57347.55078125,
"learning_rate": 3.0612244897959185e-06,
"loss": 2.0239,
"step": 240
},
{
"epoch": 0.625,
"grad_norm": 65611.1875,
"learning_rate": 3.125e-06,
"loss": 2.0064,
"step": 245
},
{
"epoch": 0.6377551020408163,
"grad_norm": 70810.75,
"learning_rate": 3.1887755102040818e-06,
"loss": 2.0224,
"step": 250
},
{
"epoch": 0.6505102040816326,
"grad_norm": 46479.8828125,
"learning_rate": 3.2525510204081634e-06,
"loss": 2.0057,
"step": 255
},
{
"epoch": 0.6632653061224489,
"grad_norm": 34124.89453125,
"learning_rate": 3.316326530612245e-06,
"loss": 2.0135,
"step": 260
},
{
"epoch": 0.6760204081632653,
"grad_norm": 53196.58203125,
"learning_rate": 3.3801020408163266e-06,
"loss": 2.0087,
"step": 265
},
{
"epoch": 0.6887755102040817,
"grad_norm": 64588.515625,
"learning_rate": 3.4438775510204086e-06,
"loss": 2.0006,
"step": 270
},
{
"epoch": 0.701530612244898,
"grad_norm": 73780.546875,
"learning_rate": 3.50765306122449e-06,
"loss": 1.9965,
"step": 275
},
{
"epoch": 0.7142857142857143,
"grad_norm": 63101.05859375,
"learning_rate": 3.5714285714285718e-06,
"loss": 2.0005,
"step": 280
},
{
"epoch": 0.7270408163265306,
"grad_norm": 78616.109375,
"learning_rate": 3.6352040816326534e-06,
"loss": 1.9904,
"step": 285
},
{
"epoch": 0.7397959183673469,
"grad_norm": 79120.6484375,
"learning_rate": 3.698979591836735e-06,
"loss": 1.9891,
"step": 290
},
{
"epoch": 0.7525510204081632,
"grad_norm": 92711.09375,
"learning_rate": 3.7627551020408166e-06,
"loss": 1.9611,
"step": 295
},
{
"epoch": 0.7653061224489796,
"grad_norm": 77935.4765625,
"learning_rate": 3.826530612244898e-06,
"loss": 1.9746,
"step": 300
},
{
"epoch": 0.7780612244897959,
"grad_norm": 85825.375,
"learning_rate": 3.89030612244898e-06,
"loss": 1.9753,
"step": 305
},
{
"epoch": 0.7908163265306123,
"grad_norm": 65178.671875,
"learning_rate": 3.954081632653062e-06,
"loss": 1.9534,
"step": 310
},
{
"epoch": 0.8035714285714286,
"grad_norm": 71973.671875,
"learning_rate": 4.017857142857143e-06,
"loss": 1.9474,
"step": 315
},
{
"epoch": 0.8163265306122449,
"grad_norm": 88983.125,
"learning_rate": 4.081632653061225e-06,
"loss": 1.9492,
"step": 320
},
{
"epoch": 0.8290816326530612,
"grad_norm": 76345.84375,
"learning_rate": 4.145408163265306e-06,
"loss": 1.9513,
"step": 325
},
{
"epoch": 0.8418367346938775,
"grad_norm": 64801.640625,
"learning_rate": 4.209183673469388e-06,
"loss": 1.9583,
"step": 330
},
{
"epoch": 0.8545918367346939,
"grad_norm": 72903.8203125,
"learning_rate": 4.272959183673469e-06,
"loss": 1.9579,
"step": 335
},
{
"epoch": 0.8673469387755102,
"grad_norm": 65284.796875,
"learning_rate": 4.336734693877551e-06,
"loss": 1.9272,
"step": 340
},
{
"epoch": 0.8801020408163265,
"grad_norm": 65237.38671875,
"learning_rate": 4.400510204081633e-06,
"loss": 1.9065,
"step": 345
},
{
"epoch": 0.8928571428571429,
"grad_norm": 79606.9296875,
"learning_rate": 4.464285714285715e-06,
"loss": 1.9013,
"step": 350
},
{
"epoch": 0.9056122448979592,
"grad_norm": 76137.6328125,
"learning_rate": 4.528061224489797e-06,
"loss": 1.8892,
"step": 355
},
{
"epoch": 0.9183673469387755,
"grad_norm": 40717.60546875,
"learning_rate": 4.591836734693878e-06,
"loss": 1.9072,
"step": 360
},
{
"epoch": 0.9311224489795918,
"grad_norm": 110416.125,
"learning_rate": 4.65561224489796e-06,
"loss": 1.9024,
"step": 365
},
{
"epoch": 0.9438775510204082,
"grad_norm": 99101.6875,
"learning_rate": 4.719387755102041e-06,
"loss": 1.8979,
"step": 370
},
{
"epoch": 0.9566326530612245,
"grad_norm": 86707.7109375,
"learning_rate": 4.783163265306123e-06,
"loss": 1.878,
"step": 375
},
{
"epoch": 0.9693877551020408,
"grad_norm": 85074.75,
"learning_rate": 4.846938775510204e-06,
"loss": 1.871,
"step": 380
},
{
"epoch": 0.9821428571428571,
"grad_norm": 47668.7109375,
"learning_rate": 4.910714285714286e-06,
"loss": 1.8762,
"step": 385
},
{
"epoch": 0.9948979591836735,
"grad_norm": 133846.6875,
"learning_rate": 4.974489795918368e-06,
"loss": 1.8344,
"step": 390
},
{
"epoch": 1.0,
"eval_accuracy": 0.0857774206508638,
"eval_loss": 1.9574071168899536,
"eval_runtime": 313.0247,
"eval_samples_per_second": 15.903,
"eval_steps_per_second": 0.53,
"step": 392
},
{
"epoch": 1.0076530612244898,
"grad_norm": 95410.25,
"learning_rate": 5.0382653061224495e-06,
"loss": 1.8635,
"step": 395
},
{
"epoch": 1.0204081632653061,
"grad_norm": 86022.1484375,
"learning_rate": 5.1020408163265315e-06,
"loss": 1.8147,
"step": 400
},
{
"epoch": 1.0331632653061225,
"grad_norm": 154860.171875,
"learning_rate": 5.165816326530613e-06,
"loss": 1.8016,
"step": 405
},
{
"epoch": 1.0459183673469388,
"grad_norm": 105390.4609375,
"learning_rate": 5.229591836734695e-06,
"loss": 1.8458,
"step": 410
},
{
"epoch": 1.058673469387755,
"grad_norm": 94511.6171875,
"learning_rate": 5.293367346938776e-06,
"loss": 1.7888,
"step": 415
},
{
"epoch": 1.0714285714285714,
"grad_norm": 93031.234375,
"learning_rate": 5.357142857142857e-06,
"loss": 1.7809,
"step": 420
},
{
"epoch": 1.0841836734693877,
"grad_norm": 71911.4296875,
"learning_rate": 5.420918367346939e-06,
"loss": 1.8523,
"step": 425
},
{
"epoch": 1.096938775510204,
"grad_norm": 59985.96875,
"learning_rate": 5.48469387755102e-06,
"loss": 1.7427,
"step": 430
},
{
"epoch": 1.1096938775510203,
"grad_norm": 86531.875,
"learning_rate": 5.548469387755102e-06,
"loss": 1.7646,
"step": 435
},
{
"epoch": 1.1224489795918366,
"grad_norm": 90977.859375,
"learning_rate": 5.6122448979591834e-06,
"loss": 1.7529,
"step": 440
},
{
"epoch": 1.135204081632653,
"grad_norm": 70691.375,
"learning_rate": 5.6760204081632655e-06,
"loss": 1.7754,
"step": 445
},
{
"epoch": 1.1479591836734695,
"grad_norm": 137077.8125,
"learning_rate": 5.739795918367348e-06,
"loss": 1.73,
"step": 450
},
{
"epoch": 1.1607142857142858,
"grad_norm": 133976.8125,
"learning_rate": 5.8035714285714295e-06,
"loss": 1.7906,
"step": 455
},
{
"epoch": 1.1734693877551021,
"grad_norm": 84754.7421875,
"learning_rate": 5.867346938775511e-06,
"loss": 1.7722,
"step": 460
},
{
"epoch": 1.1862244897959184,
"grad_norm": 67924.859375,
"learning_rate": 5.931122448979593e-06,
"loss": 1.8274,
"step": 465
},
{
"epoch": 1.1989795918367347,
"grad_norm": 110309.015625,
"learning_rate": 5.994897959183674e-06,
"loss": 1.7558,
"step": 470
},
{
"epoch": 1.211734693877551,
"grad_norm": 108489.703125,
"learning_rate": 6.058673469387756e-06,
"loss": 1.7387,
"step": 475
},
{
"epoch": 1.2244897959183674,
"grad_norm": 99533.59375,
"learning_rate": 6.122448979591837e-06,
"loss": 1.7367,
"step": 480
},
{
"epoch": 1.2372448979591837,
"grad_norm": 85590.296875,
"learning_rate": 6.186224489795919e-06,
"loss": 1.7304,
"step": 485
},
{
"epoch": 1.25,
"grad_norm": 242811.53125,
"learning_rate": 6.25e-06,
"loss": 1.6764,
"step": 490
},
{
"epoch": 1.2627551020408163,
"grad_norm": 88326.6171875,
"learning_rate": 6.313775510204082e-06,
"loss": 1.7684,
"step": 495
},
{
"epoch": 1.2755102040816326,
"grad_norm": 64742.67578125,
"learning_rate": 6.3775510204081635e-06,
"loss": 1.788,
"step": 500
},
{
"epoch": 1.288265306122449,
"grad_norm": 130764.1015625,
"learning_rate": 6.4413265306122455e-06,
"loss": 1.6374,
"step": 505
},
{
"epoch": 1.3010204081632653,
"grad_norm": 105262.7578125,
"learning_rate": 6.505102040816327e-06,
"loss": 1.7669,
"step": 510
},
{
"epoch": 1.3137755102040816,
"grad_norm": 132783.3125,
"learning_rate": 6.568877551020409e-06,
"loss": 1.7428,
"step": 515
},
{
"epoch": 1.3265306122448979,
"grad_norm": 109851.921875,
"learning_rate": 6.63265306122449e-06,
"loss": 1.7023,
"step": 520
},
{
"epoch": 1.3392857142857144,
"grad_norm": 65197.0859375,
"learning_rate": 6.696428571428571e-06,
"loss": 1.7407,
"step": 525
},
{
"epoch": 1.3520408163265305,
"grad_norm": 158283.9375,
"learning_rate": 6.760204081632653e-06,
"loss": 1.7629,
"step": 530
},
{
"epoch": 1.364795918367347,
"grad_norm": 121252.4140625,
"learning_rate": 6.823979591836736e-06,
"loss": 1.7242,
"step": 535
},
{
"epoch": 1.3775510204081631,
"grad_norm": 110898.328125,
"learning_rate": 6.887755102040817e-06,
"loss": 1.6922,
"step": 540
},
{
"epoch": 1.3903061224489797,
"grad_norm": 127766.8046875,
"learning_rate": 6.951530612244899e-06,
"loss": 1.7274,
"step": 545
},
{
"epoch": 1.403061224489796,
"grad_norm": 138821.59375,
"learning_rate": 7.01530612244898e-06,
"loss": 1.6859,
"step": 550
},
{
"epoch": 1.4158163265306123,
"grad_norm": 154254.75,
"learning_rate": 7.079081632653062e-06,
"loss": 1.6988,
"step": 555
},
{
"epoch": 1.4285714285714286,
"grad_norm": 122805.65625,
"learning_rate": 7.1428571428571436e-06,
"loss": 1.7003,
"step": 560
},
{
"epoch": 1.441326530612245,
"grad_norm": 35300.796875,
"learning_rate": 7.206632653061226e-06,
"loss": 1.7224,
"step": 565
},
{
"epoch": 1.4540816326530612,
"grad_norm": 125603.1015625,
"learning_rate": 7.270408163265307e-06,
"loss": 1.8201,
"step": 570
},
{
"epoch": 1.4668367346938775,
"grad_norm": 167185.671875,
"learning_rate": 7.334183673469388e-06,
"loss": 1.7959,
"step": 575
},
{
"epoch": 1.4795918367346939,
"grad_norm": 59943.359375,
"learning_rate": 7.39795918367347e-06,
"loss": 1.6133,
"step": 580
},
{
"epoch": 1.4923469387755102,
"grad_norm": 197770.234375,
"learning_rate": 7.461734693877551e-06,
"loss": 1.709,
"step": 585
},
{
"epoch": 1.5051020408163265,
"grad_norm": 182674.5,
"learning_rate": 7.525510204081633e-06,
"loss": 1.688,
"step": 590
},
{
"epoch": 1.5178571428571428,
"grad_norm": 90262.0390625,
"learning_rate": 7.589285714285714e-06,
"loss": 1.7639,
"step": 595
},
{
"epoch": 1.5306122448979593,
"grad_norm": 119569.0859375,
"learning_rate": 7.653061224489796e-06,
"loss": 1.7587,
"step": 600
},
{
"epoch": 1.5433673469387754,
"grad_norm": 134583.546875,
"learning_rate": 7.716836734693878e-06,
"loss": 1.7174,
"step": 605
},
{
"epoch": 1.556122448979592,
"grad_norm": 123799.515625,
"learning_rate": 7.78061224489796e-06,
"loss": 1.668,
"step": 610
},
{
"epoch": 1.568877551020408,
"grad_norm": 124765.65625,
"learning_rate": 7.844387755102042e-06,
"loss": 1.691,
"step": 615
},
{
"epoch": 1.5816326530612246,
"grad_norm": 180459.28125,
"learning_rate": 7.908163265306124e-06,
"loss": 1.6133,
"step": 620
},
{
"epoch": 1.5943877551020407,
"grad_norm": 115367.0859375,
"learning_rate": 7.971938775510205e-06,
"loss": 1.7529,
"step": 625
},
{
"epoch": 1.6071428571428572,
"grad_norm": 66548.40625,
"learning_rate": 8.035714285714286e-06,
"loss": 1.7157,
"step": 630
},
{
"epoch": 1.6198979591836735,
"grad_norm": 152392.640625,
"learning_rate": 8.099489795918369e-06,
"loss": 1.7417,
"step": 635
},
{
"epoch": 1.6326530612244898,
"grad_norm": 131193.015625,
"learning_rate": 8.16326530612245e-06,
"loss": 1.7704,
"step": 640
},
{
"epoch": 1.6454081632653061,
"grad_norm": 154705.71875,
"learning_rate": 8.227040816326531e-06,
"loss": 1.6573,
"step": 645
},
{
"epoch": 1.6581632653061225,
"grad_norm": 113254.484375,
"learning_rate": 8.290816326530612e-06,
"loss": 1.6394,
"step": 650
},
{
"epoch": 1.6709183673469388,
"grad_norm": 163821.484375,
"learning_rate": 8.354591836734695e-06,
"loss": 1.6884,
"step": 655
},
{
"epoch": 1.683673469387755,
"grad_norm": 141981.828125,
"learning_rate": 8.418367346938776e-06,
"loss": 1.5955,
"step": 660
},
{
"epoch": 1.6964285714285714,
"grad_norm": 158287.6875,
"learning_rate": 8.482142857142858e-06,
"loss": 1.6885,
"step": 665
},
{
"epoch": 1.7091836734693877,
"grad_norm": 166876.4375,
"learning_rate": 8.545918367346939e-06,
"loss": 1.7253,
"step": 670
},
{
"epoch": 1.7219387755102042,
"grad_norm": 111882.171875,
"learning_rate": 8.609693877551022e-06,
"loss": 1.7057,
"step": 675
},
{
"epoch": 1.7346938775510203,
"grad_norm": 237840.828125,
"learning_rate": 8.673469387755103e-06,
"loss": 1.7132,
"step": 680
},
{
"epoch": 1.7474489795918369,
"grad_norm": 83344.59375,
"learning_rate": 8.737244897959184e-06,
"loss": 1.733,
"step": 685
},
{
"epoch": 1.760204081632653,
"grad_norm": 30312.462890625,
"learning_rate": 8.801020408163265e-06,
"loss": 1.7926,
"step": 690
},
{
"epoch": 1.7729591836734695,
"grad_norm": 89868.9609375,
"learning_rate": 8.864795918367348e-06,
"loss": 1.6389,
"step": 695
},
{
"epoch": 1.7857142857142856,
"grad_norm": 182723.09375,
"learning_rate": 8.92857142857143e-06,
"loss": 1.7533,
"step": 700
},
{
"epoch": 1.7984693877551021,
"grad_norm": 104328.2421875,
"learning_rate": 8.992346938775512e-06,
"loss": 1.7424,
"step": 705
},
{
"epoch": 1.8112244897959182,
"grad_norm": 110120.609375,
"learning_rate": 9.056122448979593e-06,
"loss": 1.6961,
"step": 710
},
{
"epoch": 1.8239795918367347,
"grad_norm": 114349.7578125,
"learning_rate": 9.119897959183674e-06,
"loss": 1.7753,
"step": 715
},
{
"epoch": 1.836734693877551,
"grad_norm": 103603.8828125,
"learning_rate": 9.183673469387756e-06,
"loss": 1.777,
"step": 720
},
{
"epoch": 1.8494897959183674,
"grad_norm": 173858.828125,
"learning_rate": 9.247448979591837e-06,
"loss": 1.7218,
"step": 725
},
{
"epoch": 1.8622448979591837,
"grad_norm": 255108.96875,
"learning_rate": 9.31122448979592e-06,
"loss": 1.7319,
"step": 730
},
{
"epoch": 1.875,
"grad_norm": 38653.734375,
"learning_rate": 9.375000000000001e-06,
"loss": 1.6574,
"step": 735
},
{
"epoch": 1.8877551020408163,
"grad_norm": 141534.234375,
"learning_rate": 9.438775510204082e-06,
"loss": 1.7595,
"step": 740
},
{
"epoch": 1.9005102040816326,
"grad_norm": 182591.890625,
"learning_rate": 9.502551020408163e-06,
"loss": 1.6796,
"step": 745
},
{
"epoch": 1.913265306122449,
"grad_norm": 75052.21875,
"learning_rate": 9.566326530612246e-06,
"loss": 1.754,
"step": 750
},
{
"epoch": 1.9260204081632653,
"grad_norm": 108983.921875,
"learning_rate": 9.630102040816327e-06,
"loss": 1.6907,
"step": 755
},
{
"epoch": 1.9387755102040818,
"grad_norm": 110641.828125,
"learning_rate": 9.693877551020408e-06,
"loss": 1.7041,
"step": 760
},
{
"epoch": 1.9515306122448979,
"grad_norm": 119189.8203125,
"learning_rate": 9.75765306122449e-06,
"loss": 1.6054,
"step": 765
},
{
"epoch": 1.9642857142857144,
"grad_norm": 62365.9453125,
"learning_rate": 9.821428571428573e-06,
"loss": 1.6862,
"step": 770
},
{
"epoch": 1.9770408163265305,
"grad_norm": 103043.6171875,
"learning_rate": 9.885204081632654e-06,
"loss": 1.6596,
"step": 775
},
{
"epoch": 1.989795918367347,
"grad_norm": 117368.546875,
"learning_rate": 9.948979591836737e-06,
"loss": 1.6737,
"step": 780
},
{
"epoch": 2.0,
"eval_accuracy": 0.0857774206508638,
"eval_loss": 1.8835231065750122,
"eval_runtime": 308.4538,
"eval_samples_per_second": 16.139,
"eval_steps_per_second": 0.538,
"step": 784
}
],
"logging_steps": 5,
"max_steps": 3920,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.99358138673152e+18,
"train_batch_size": 30,
"trial_name": null,
"trial_params": null
}