arshsin's picture
Training in progress, epoch 10, checkpoint
6bf1f81 verified
{
"best_metric": 0.9,
"best_model_checkpoint": "ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan/checkpoint-1130",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 1130,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 2.2123893805309734e-06,
"loss": 2.4617,
"step": 5
},
{
"epoch": 0.09,
"learning_rate": 4.424778761061947e-06,
"loss": 2.4041,
"step": 10
},
{
"epoch": 0.13,
"learning_rate": 6.6371681415929215e-06,
"loss": 2.1309,
"step": 15
},
{
"epoch": 0.18,
"learning_rate": 8.849557522123894e-06,
"loss": 2.0045,
"step": 20
},
{
"epoch": 0.22,
"learning_rate": 1.1061946902654869e-05,
"loss": 1.7218,
"step": 25
},
{
"epoch": 0.27,
"learning_rate": 1.3274336283185843e-05,
"loss": 1.3841,
"step": 30
},
{
"epoch": 0.31,
"learning_rate": 1.5486725663716813e-05,
"loss": 1.1939,
"step": 35
},
{
"epoch": 0.35,
"learning_rate": 1.7699115044247787e-05,
"loss": 0.9942,
"step": 40
},
{
"epoch": 0.4,
"learning_rate": 1.991150442477876e-05,
"loss": 1.1275,
"step": 45
},
{
"epoch": 0.44,
"learning_rate": 2.2123893805309738e-05,
"loss": 0.8573,
"step": 50
},
{
"epoch": 0.49,
"learning_rate": 2.433628318584071e-05,
"loss": 0.5421,
"step": 55
},
{
"epoch": 0.53,
"learning_rate": 2.6548672566371686e-05,
"loss": 0.7957,
"step": 60
},
{
"epoch": 0.58,
"learning_rate": 2.8761061946902656e-05,
"loss": 0.633,
"step": 65
},
{
"epoch": 0.62,
"learning_rate": 3.097345132743363e-05,
"loss": 0.641,
"step": 70
},
{
"epoch": 0.66,
"learning_rate": 3.3185840707964604e-05,
"loss": 1.0013,
"step": 75
},
{
"epoch": 0.71,
"learning_rate": 3.5398230088495574e-05,
"loss": 0.8854,
"step": 80
},
{
"epoch": 0.75,
"learning_rate": 3.7610619469026545e-05,
"loss": 0.788,
"step": 85
},
{
"epoch": 0.8,
"learning_rate": 3.982300884955752e-05,
"loss": 0.5631,
"step": 90
},
{
"epoch": 0.84,
"learning_rate": 4.20353982300885e-05,
"loss": 0.6124,
"step": 95
},
{
"epoch": 0.88,
"learning_rate": 4.4247787610619477e-05,
"loss": 0.5238,
"step": 100
},
{
"epoch": 0.93,
"learning_rate": 4.646017699115045e-05,
"loss": 0.852,
"step": 105
},
{
"epoch": 0.97,
"learning_rate": 4.867256637168142e-05,
"loss": 1.0564,
"step": 110
},
{
"epoch": 1.0,
"eval_accuracy": 0.83,
"eval_loss": 0.6135080456733704,
"eval_runtime": 15.6818,
"eval_samples_per_second": 6.377,
"eval_steps_per_second": 0.829,
"step": 113
},
{
"epoch": 1.02,
"learning_rate": 4.990167158308752e-05,
"loss": 0.5449,
"step": 115
},
{
"epoch": 1.06,
"learning_rate": 4.9655850540806295e-05,
"loss": 0.5122,
"step": 120
},
{
"epoch": 1.11,
"learning_rate": 4.941002949852507e-05,
"loss": 0.5462,
"step": 125
},
{
"epoch": 1.15,
"learning_rate": 4.9164208456243856e-05,
"loss": 0.5006,
"step": 130
},
{
"epoch": 1.19,
"learning_rate": 4.891838741396263e-05,
"loss": 0.4551,
"step": 135
},
{
"epoch": 1.24,
"learning_rate": 4.867256637168142e-05,
"loss": 0.7397,
"step": 140
},
{
"epoch": 1.28,
"learning_rate": 4.8426745329400195e-05,
"loss": 0.4615,
"step": 145
},
{
"epoch": 1.33,
"learning_rate": 4.818092428711898e-05,
"loss": 0.3942,
"step": 150
},
{
"epoch": 1.37,
"learning_rate": 4.7935103244837756e-05,
"loss": 0.4799,
"step": 155
},
{
"epoch": 1.42,
"learning_rate": 4.768928220255654e-05,
"loss": 0.421,
"step": 160
},
{
"epoch": 1.46,
"learning_rate": 4.7443461160275324e-05,
"loss": 0.694,
"step": 165
},
{
"epoch": 1.5,
"learning_rate": 4.71976401179941e-05,
"loss": 0.3993,
"step": 170
},
{
"epoch": 1.55,
"learning_rate": 4.6951819075712886e-05,
"loss": 0.5977,
"step": 175
},
{
"epoch": 1.59,
"learning_rate": 4.670599803343166e-05,
"loss": 0.974,
"step": 180
},
{
"epoch": 1.64,
"learning_rate": 4.646017699115045e-05,
"loss": 0.5518,
"step": 185
},
{
"epoch": 1.68,
"learning_rate": 4.6214355948869224e-05,
"loss": 0.5082,
"step": 190
},
{
"epoch": 1.73,
"learning_rate": 4.596853490658801e-05,
"loss": 0.5166,
"step": 195
},
{
"epoch": 1.77,
"learning_rate": 4.5722713864306786e-05,
"loss": 0.6408,
"step": 200
},
{
"epoch": 1.81,
"learning_rate": 4.547689282202557e-05,
"loss": 0.6056,
"step": 205
},
{
"epoch": 1.86,
"learning_rate": 4.523107177974435e-05,
"loss": 0.6339,
"step": 210
},
{
"epoch": 1.9,
"learning_rate": 4.498525073746313e-05,
"loss": 0.7673,
"step": 215
},
{
"epoch": 1.95,
"learning_rate": 4.473942969518191e-05,
"loss": 0.2352,
"step": 220
},
{
"epoch": 1.99,
"learning_rate": 4.449360865290069e-05,
"loss": 0.3513,
"step": 225
},
{
"epoch": 2.0,
"eval_accuracy": 0.87,
"eval_loss": 0.5030723810195923,
"eval_runtime": 15.1706,
"eval_samples_per_second": 6.592,
"eval_steps_per_second": 0.857,
"step": 226
},
{
"epoch": 2.04,
"learning_rate": 4.4247787610619477e-05,
"loss": 0.2137,
"step": 230
},
{
"epoch": 2.08,
"learning_rate": 4.4001966568338254e-05,
"loss": 0.1571,
"step": 235
},
{
"epoch": 2.12,
"learning_rate": 4.375614552605704e-05,
"loss": 0.1857,
"step": 240
},
{
"epoch": 2.17,
"learning_rate": 4.351032448377581e-05,
"loss": 0.1805,
"step": 245
},
{
"epoch": 2.21,
"learning_rate": 4.326450344149459e-05,
"loss": 0.0654,
"step": 250
},
{
"epoch": 2.26,
"learning_rate": 4.301868239921337e-05,
"loss": 0.2904,
"step": 255
},
{
"epoch": 2.3,
"learning_rate": 4.2772861356932154e-05,
"loss": 0.1252,
"step": 260
},
{
"epoch": 2.35,
"learning_rate": 4.252704031465093e-05,
"loss": 0.0476,
"step": 265
},
{
"epoch": 2.39,
"learning_rate": 4.2281219272369715e-05,
"loss": 0.3448,
"step": 270
},
{
"epoch": 2.43,
"learning_rate": 4.20353982300885e-05,
"loss": 0.3744,
"step": 275
},
{
"epoch": 2.48,
"learning_rate": 4.178957718780728e-05,
"loss": 0.3611,
"step": 280
},
{
"epoch": 2.52,
"learning_rate": 4.154375614552606e-05,
"loss": 0.1921,
"step": 285
},
{
"epoch": 2.57,
"learning_rate": 4.129793510324484e-05,
"loss": 0.2178,
"step": 290
},
{
"epoch": 2.61,
"learning_rate": 4.105211406096362e-05,
"loss": 0.5523,
"step": 295
},
{
"epoch": 2.65,
"learning_rate": 4.08062930186824e-05,
"loss": 0.0661,
"step": 300
},
{
"epoch": 2.7,
"learning_rate": 4.0560471976401183e-05,
"loss": 0.2874,
"step": 305
},
{
"epoch": 2.74,
"learning_rate": 4.031465093411996e-05,
"loss": 0.5938,
"step": 310
},
{
"epoch": 2.79,
"learning_rate": 4.0068829891838745e-05,
"loss": 0.4356,
"step": 315
},
{
"epoch": 2.83,
"learning_rate": 3.982300884955752e-05,
"loss": 0.38,
"step": 320
},
{
"epoch": 2.88,
"learning_rate": 3.9577187807276306e-05,
"loss": 0.4589,
"step": 325
},
{
"epoch": 2.92,
"learning_rate": 3.9331366764995083e-05,
"loss": 0.1924,
"step": 330
},
{
"epoch": 2.96,
"learning_rate": 3.908554572271387e-05,
"loss": 0.3781,
"step": 335
},
{
"epoch": 3.0,
"eval_accuracy": 0.89,
"eval_loss": 0.43871718645095825,
"eval_runtime": 15.1905,
"eval_samples_per_second": 6.583,
"eval_steps_per_second": 0.856,
"step": 339
},
{
"epoch": 3.01,
"learning_rate": 3.883972468043265e-05,
"loss": 0.2607,
"step": 340
},
{
"epoch": 3.05,
"learning_rate": 3.859390363815143e-05,
"loss": 0.2316,
"step": 345
},
{
"epoch": 3.1,
"learning_rate": 3.834808259587021e-05,
"loss": 0.0272,
"step": 350
},
{
"epoch": 3.14,
"learning_rate": 3.810226155358899e-05,
"loss": 0.1928,
"step": 355
},
{
"epoch": 3.19,
"learning_rate": 3.7856440511307774e-05,
"loss": 0.0225,
"step": 360
},
{
"epoch": 3.23,
"learning_rate": 3.7610619469026545e-05,
"loss": 0.0359,
"step": 365
},
{
"epoch": 3.27,
"learning_rate": 3.736479842674533e-05,
"loss": 0.0208,
"step": 370
},
{
"epoch": 3.32,
"learning_rate": 3.711897738446411e-05,
"loss": 0.0131,
"step": 375
},
{
"epoch": 3.36,
"learning_rate": 3.687315634218289e-05,
"loss": 0.0209,
"step": 380
},
{
"epoch": 3.41,
"learning_rate": 3.6627335299901674e-05,
"loss": 0.1438,
"step": 385
},
{
"epoch": 3.45,
"learning_rate": 3.638151425762045e-05,
"loss": 0.4599,
"step": 390
},
{
"epoch": 3.5,
"learning_rate": 3.6135693215339236e-05,
"loss": 0.0166,
"step": 395
},
{
"epoch": 3.54,
"learning_rate": 3.588987217305801e-05,
"loss": 0.0156,
"step": 400
},
{
"epoch": 3.58,
"learning_rate": 3.56440511307768e-05,
"loss": 0.0039,
"step": 405
},
{
"epoch": 3.63,
"learning_rate": 3.5398230088495574e-05,
"loss": 0.0753,
"step": 410
},
{
"epoch": 3.67,
"learning_rate": 3.515240904621436e-05,
"loss": 0.0047,
"step": 415
},
{
"epoch": 3.72,
"learning_rate": 3.4906588003933136e-05,
"loss": 0.1596,
"step": 420
},
{
"epoch": 3.76,
"learning_rate": 3.466076696165192e-05,
"loss": 0.409,
"step": 425
},
{
"epoch": 3.81,
"learning_rate": 3.44149459193707e-05,
"loss": 0.0616,
"step": 430
},
{
"epoch": 3.85,
"learning_rate": 3.416912487708948e-05,
"loss": 0.0113,
"step": 435
},
{
"epoch": 3.89,
"learning_rate": 3.3923303834808265e-05,
"loss": 0.107,
"step": 440
},
{
"epoch": 3.94,
"learning_rate": 3.367748279252704e-05,
"loss": 0.0516,
"step": 445
},
{
"epoch": 3.98,
"learning_rate": 3.343166175024583e-05,
"loss": 0.0142,
"step": 450
},
{
"epoch": 4.0,
"eval_accuracy": 0.89,
"eval_loss": 0.6147953271865845,
"eval_runtime": 15.3899,
"eval_samples_per_second": 6.498,
"eval_steps_per_second": 0.845,
"step": 452
},
{
"epoch": 4.03,
"learning_rate": 3.3185840707964604e-05,
"loss": 0.0107,
"step": 455
},
{
"epoch": 4.07,
"learning_rate": 3.294001966568339e-05,
"loss": 0.0747,
"step": 460
},
{
"epoch": 4.12,
"learning_rate": 3.2694198623402165e-05,
"loss": 0.0063,
"step": 465
},
{
"epoch": 4.16,
"learning_rate": 3.244837758112095e-05,
"loss": 0.0002,
"step": 470
},
{
"epoch": 4.2,
"learning_rate": 3.220255653883973e-05,
"loss": 0.0011,
"step": 475
},
{
"epoch": 4.25,
"learning_rate": 3.1956735496558504e-05,
"loss": 0.0488,
"step": 480
},
{
"epoch": 4.29,
"learning_rate": 3.171091445427729e-05,
"loss": 0.0013,
"step": 485
},
{
"epoch": 4.34,
"learning_rate": 3.1465093411996065e-05,
"loss": 0.0015,
"step": 490
},
{
"epoch": 4.38,
"learning_rate": 3.121927236971485e-05,
"loss": 0.1122,
"step": 495
},
{
"epoch": 4.42,
"learning_rate": 3.097345132743363e-05,
"loss": 0.1653,
"step": 500
},
{
"epoch": 4.47,
"learning_rate": 3.072763028515241e-05,
"loss": 0.0001,
"step": 505
},
{
"epoch": 4.51,
"learning_rate": 3.048180924287119e-05,
"loss": 0.0118,
"step": 510
},
{
"epoch": 4.56,
"learning_rate": 3.0235988200589972e-05,
"loss": 0.161,
"step": 515
},
{
"epoch": 4.6,
"learning_rate": 2.9990167158308753e-05,
"loss": 0.1282,
"step": 520
},
{
"epoch": 4.65,
"learning_rate": 2.9744346116027534e-05,
"loss": 0.0003,
"step": 525
},
{
"epoch": 4.69,
"learning_rate": 2.9498525073746314e-05,
"loss": 0.0003,
"step": 530
},
{
"epoch": 4.73,
"learning_rate": 2.9252704031465095e-05,
"loss": 0.0023,
"step": 535
},
{
"epoch": 4.78,
"learning_rate": 2.9006882989183876e-05,
"loss": 0.0124,
"step": 540
},
{
"epoch": 4.82,
"learning_rate": 2.8761061946902656e-05,
"loss": 0.0002,
"step": 545
},
{
"epoch": 4.87,
"learning_rate": 2.8515240904621437e-05,
"loss": 0.0012,
"step": 550
},
{
"epoch": 4.91,
"learning_rate": 2.8269419862340218e-05,
"loss": 0.0,
"step": 555
},
{
"epoch": 4.96,
"learning_rate": 2.8023598820059e-05,
"loss": 0.3903,
"step": 560
},
{
"epoch": 5.0,
"learning_rate": 2.777777777777778e-05,
"loss": 0.188,
"step": 565
},
{
"epoch": 5.0,
"eval_accuracy": 0.88,
"eval_loss": 0.8578123450279236,
"eval_runtime": 15.4617,
"eval_samples_per_second": 6.468,
"eval_steps_per_second": 0.841,
"step": 565
},
{
"epoch": 5.04,
"learning_rate": 2.753195673549656e-05,
"loss": 0.3239,
"step": 570
},
{
"epoch": 5.09,
"learning_rate": 2.7286135693215344e-05,
"loss": 0.0003,
"step": 575
},
{
"epoch": 5.13,
"learning_rate": 2.7040314650934125e-05,
"loss": 0.0,
"step": 580
},
{
"epoch": 5.18,
"learning_rate": 2.6794493608652905e-05,
"loss": 0.2751,
"step": 585
},
{
"epoch": 5.22,
"learning_rate": 2.6548672566371686e-05,
"loss": 0.0,
"step": 590
},
{
"epoch": 5.27,
"learning_rate": 2.6302851524090467e-05,
"loss": 0.0004,
"step": 595
},
{
"epoch": 5.31,
"learning_rate": 2.605703048180924e-05,
"loss": 0.0,
"step": 600
},
{
"epoch": 5.35,
"learning_rate": 2.581120943952802e-05,
"loss": 0.0,
"step": 605
},
{
"epoch": 5.4,
"learning_rate": 2.5565388397246802e-05,
"loss": 0.0667,
"step": 610
},
{
"epoch": 5.44,
"learning_rate": 2.5319567354965586e-05,
"loss": 0.0,
"step": 615
},
{
"epoch": 5.49,
"learning_rate": 2.5073746312684367e-05,
"loss": 0.0,
"step": 620
},
{
"epoch": 5.53,
"learning_rate": 2.4827925270403147e-05,
"loss": 0.0,
"step": 625
},
{
"epoch": 5.58,
"learning_rate": 2.4582104228121928e-05,
"loss": 0.0,
"step": 630
},
{
"epoch": 5.62,
"learning_rate": 2.433628318584071e-05,
"loss": 0.0,
"step": 635
},
{
"epoch": 5.66,
"learning_rate": 2.409046214355949e-05,
"loss": 0.0,
"step": 640
},
{
"epoch": 5.71,
"learning_rate": 2.384464110127827e-05,
"loss": 0.0,
"step": 645
},
{
"epoch": 5.75,
"learning_rate": 2.359882005899705e-05,
"loss": 0.0044,
"step": 650
},
{
"epoch": 5.8,
"learning_rate": 2.335299901671583e-05,
"loss": 0.0,
"step": 655
},
{
"epoch": 5.84,
"learning_rate": 2.3107177974434612e-05,
"loss": 0.0014,
"step": 660
},
{
"epoch": 5.88,
"learning_rate": 2.2861356932153393e-05,
"loss": 0.0,
"step": 665
},
{
"epoch": 5.93,
"learning_rate": 2.2615535889872174e-05,
"loss": 0.0155,
"step": 670
},
{
"epoch": 5.97,
"learning_rate": 2.2369714847590954e-05,
"loss": 0.0,
"step": 675
},
{
"epoch": 6.0,
"eval_accuracy": 0.89,
"eval_loss": 1.0512733459472656,
"eval_runtime": 15.1736,
"eval_samples_per_second": 6.59,
"eval_steps_per_second": 0.857,
"step": 678
},
{
"epoch": 6.02,
"learning_rate": 2.2123893805309738e-05,
"loss": 0.0,
"step": 680
},
{
"epoch": 6.06,
"learning_rate": 2.187807276302852e-05,
"loss": 0.0,
"step": 685
},
{
"epoch": 6.11,
"learning_rate": 2.1632251720747296e-05,
"loss": 0.0,
"step": 690
},
{
"epoch": 6.15,
"learning_rate": 2.1386430678466077e-05,
"loss": 0.0,
"step": 695
},
{
"epoch": 6.19,
"learning_rate": 2.1140609636184858e-05,
"loss": 0.0,
"step": 700
},
{
"epoch": 6.24,
"learning_rate": 2.089478859390364e-05,
"loss": 0.0,
"step": 705
},
{
"epoch": 6.28,
"learning_rate": 2.064896755162242e-05,
"loss": 0.0,
"step": 710
},
{
"epoch": 6.33,
"learning_rate": 2.04031465093412e-05,
"loss": 0.0,
"step": 715
},
{
"epoch": 6.37,
"learning_rate": 2.015732546705998e-05,
"loss": 0.0,
"step": 720
},
{
"epoch": 6.42,
"learning_rate": 1.991150442477876e-05,
"loss": 0.0,
"step": 725
},
{
"epoch": 6.46,
"learning_rate": 1.9665683382497542e-05,
"loss": 0.0,
"step": 730
},
{
"epoch": 6.5,
"learning_rate": 1.9419862340216326e-05,
"loss": 0.0,
"step": 735
},
{
"epoch": 6.55,
"learning_rate": 1.9174041297935107e-05,
"loss": 0.0,
"step": 740
},
{
"epoch": 6.59,
"learning_rate": 1.8928220255653887e-05,
"loss": 0.0,
"step": 745
},
{
"epoch": 6.64,
"learning_rate": 1.8682399213372664e-05,
"loss": 0.0,
"step": 750
},
{
"epoch": 6.68,
"learning_rate": 1.8436578171091445e-05,
"loss": 0.0,
"step": 755
},
{
"epoch": 6.73,
"learning_rate": 1.8190757128810226e-05,
"loss": 0.0,
"step": 760
},
{
"epoch": 6.77,
"learning_rate": 1.7944936086529007e-05,
"loss": 0.0008,
"step": 765
},
{
"epoch": 6.81,
"learning_rate": 1.7699115044247787e-05,
"loss": 0.1555,
"step": 770
},
{
"epoch": 6.86,
"learning_rate": 1.7453294001966568e-05,
"loss": 0.0,
"step": 775
},
{
"epoch": 6.9,
"learning_rate": 1.720747295968535e-05,
"loss": 0.0,
"step": 780
},
{
"epoch": 6.95,
"learning_rate": 1.6961651917404133e-05,
"loss": 0.0,
"step": 785
},
{
"epoch": 6.99,
"learning_rate": 1.6715830875122913e-05,
"loss": 0.4527,
"step": 790
},
{
"epoch": 7.0,
"eval_accuracy": 0.88,
"eval_loss": 0.9157407283782959,
"eval_runtime": 15.1291,
"eval_samples_per_second": 6.61,
"eval_steps_per_second": 0.859,
"step": 791
},
{
"epoch": 7.04,
"learning_rate": 1.6470009832841694e-05,
"loss": 0.0,
"step": 795
},
{
"epoch": 7.08,
"learning_rate": 1.6224188790560475e-05,
"loss": 0.0,
"step": 800
},
{
"epoch": 7.12,
"learning_rate": 1.5978367748279252e-05,
"loss": 0.0,
"step": 805
},
{
"epoch": 7.17,
"learning_rate": 1.5732546705998033e-05,
"loss": 0.0,
"step": 810
},
{
"epoch": 7.21,
"learning_rate": 1.5486725663716813e-05,
"loss": 0.3651,
"step": 815
},
{
"epoch": 7.26,
"learning_rate": 1.5240904621435596e-05,
"loss": 0.0,
"step": 820
},
{
"epoch": 7.3,
"learning_rate": 1.4995083579154376e-05,
"loss": 0.0,
"step": 825
},
{
"epoch": 7.35,
"learning_rate": 1.4749262536873157e-05,
"loss": 0.0,
"step": 830
},
{
"epoch": 7.39,
"learning_rate": 1.4503441494591938e-05,
"loss": 0.0,
"step": 835
},
{
"epoch": 7.43,
"learning_rate": 1.4257620452310719e-05,
"loss": 0.0,
"step": 840
},
{
"epoch": 7.48,
"learning_rate": 1.40117994100295e-05,
"loss": 0.0,
"step": 845
},
{
"epoch": 7.52,
"learning_rate": 1.376597836774828e-05,
"loss": 0.0,
"step": 850
},
{
"epoch": 7.57,
"learning_rate": 1.3520157325467062e-05,
"loss": 0.0,
"step": 855
},
{
"epoch": 7.61,
"learning_rate": 1.3274336283185843e-05,
"loss": 0.0,
"step": 860
},
{
"epoch": 7.65,
"learning_rate": 1.302851524090462e-05,
"loss": 0.0,
"step": 865
},
{
"epoch": 7.7,
"learning_rate": 1.2782694198623401e-05,
"loss": 0.0,
"step": 870
},
{
"epoch": 7.74,
"learning_rate": 1.2536873156342183e-05,
"loss": 0.0,
"step": 875
},
{
"epoch": 7.79,
"learning_rate": 1.2291052114060964e-05,
"loss": 0.0,
"step": 880
},
{
"epoch": 7.83,
"learning_rate": 1.2045231071779745e-05,
"loss": 0.0,
"step": 885
},
{
"epoch": 7.88,
"learning_rate": 1.1799410029498525e-05,
"loss": 0.0,
"step": 890
},
{
"epoch": 7.92,
"learning_rate": 1.1553588987217306e-05,
"loss": 0.1747,
"step": 895
},
{
"epoch": 7.96,
"learning_rate": 1.1307767944936087e-05,
"loss": 0.0,
"step": 900
},
{
"epoch": 8.0,
"eval_accuracy": 0.85,
"eval_loss": 1.0898141860961914,
"eval_runtime": 15.2351,
"eval_samples_per_second": 6.564,
"eval_steps_per_second": 0.853,
"step": 904
},
{
"epoch": 8.01,
"learning_rate": 1.1061946902654869e-05,
"loss": 0.0,
"step": 905
},
{
"epoch": 8.05,
"learning_rate": 1.0816125860373648e-05,
"loss": 0.0,
"step": 910
},
{
"epoch": 8.1,
"learning_rate": 1.0570304818092429e-05,
"loss": 0.0,
"step": 915
},
{
"epoch": 8.14,
"learning_rate": 1.032448377581121e-05,
"loss": 0.0,
"step": 920
},
{
"epoch": 8.19,
"learning_rate": 1.007866273352999e-05,
"loss": 0.0,
"step": 925
},
{
"epoch": 8.23,
"learning_rate": 9.832841691248771e-06,
"loss": 0.4195,
"step": 930
},
{
"epoch": 8.27,
"learning_rate": 9.587020648967553e-06,
"loss": 0.0,
"step": 935
},
{
"epoch": 8.32,
"learning_rate": 9.341199606686332e-06,
"loss": 0.0,
"step": 940
},
{
"epoch": 8.36,
"learning_rate": 9.095378564405113e-06,
"loss": 0.0,
"step": 945
},
{
"epoch": 8.41,
"learning_rate": 8.849557522123894e-06,
"loss": 0.0,
"step": 950
},
{
"epoch": 8.45,
"learning_rate": 8.603736479842674e-06,
"loss": 0.0,
"step": 955
},
{
"epoch": 8.5,
"learning_rate": 8.357915437561457e-06,
"loss": 0.0,
"step": 960
},
{
"epoch": 8.54,
"learning_rate": 8.112094395280237e-06,
"loss": 0.0,
"step": 965
},
{
"epoch": 8.58,
"learning_rate": 7.866273352999016e-06,
"loss": 0.0,
"step": 970
},
{
"epoch": 8.63,
"learning_rate": 7.620452310717798e-06,
"loss": 0.0,
"step": 975
},
{
"epoch": 8.67,
"learning_rate": 7.374631268436579e-06,
"loss": 0.0,
"step": 980
},
{
"epoch": 8.72,
"learning_rate": 7.128810226155359e-06,
"loss": 0.0,
"step": 985
},
{
"epoch": 8.76,
"learning_rate": 6.88298918387414e-06,
"loss": 0.0,
"step": 990
},
{
"epoch": 8.81,
"learning_rate": 6.6371681415929215e-06,
"loss": 0.0,
"step": 995
},
{
"epoch": 8.85,
"learning_rate": 6.3913470993117005e-06,
"loss": 0.0,
"step": 1000
},
{
"epoch": 8.89,
"learning_rate": 6.145526057030482e-06,
"loss": 0.0,
"step": 1005
},
{
"epoch": 8.94,
"learning_rate": 5.899705014749263e-06,
"loss": 0.2103,
"step": 1010
},
{
"epoch": 8.98,
"learning_rate": 5.653883972468043e-06,
"loss": 0.0,
"step": 1015
},
{
"epoch": 9.0,
"eval_accuracy": 0.89,
"eval_loss": 0.7874658107757568,
"eval_runtime": 14.9655,
"eval_samples_per_second": 6.682,
"eval_steps_per_second": 0.869,
"step": 1017
},
{
"epoch": 9.03,
"learning_rate": 5.408062930186824e-06,
"loss": 0.0,
"step": 1020
},
{
"epoch": 9.07,
"learning_rate": 5.162241887905605e-06,
"loss": 0.0,
"step": 1025
},
{
"epoch": 9.12,
"learning_rate": 4.9164208456243854e-06,
"loss": 0.0,
"step": 1030
},
{
"epoch": 9.16,
"learning_rate": 4.670599803343166e-06,
"loss": 0.0,
"step": 1035
},
{
"epoch": 9.2,
"learning_rate": 4.424778761061947e-06,
"loss": 0.0,
"step": 1040
},
{
"epoch": 9.25,
"learning_rate": 4.178957718780728e-06,
"loss": 0.0,
"step": 1045
},
{
"epoch": 9.29,
"learning_rate": 3.933136676499508e-06,
"loss": 0.0,
"step": 1050
},
{
"epoch": 9.34,
"learning_rate": 3.6873156342182893e-06,
"loss": 0.0,
"step": 1055
},
{
"epoch": 9.38,
"learning_rate": 3.44149459193707e-06,
"loss": 0.0,
"step": 1060
},
{
"epoch": 9.42,
"learning_rate": 3.1956735496558502e-06,
"loss": 0.0,
"step": 1065
},
{
"epoch": 9.47,
"learning_rate": 2.9498525073746313e-06,
"loss": 0.0,
"step": 1070
},
{
"epoch": 9.51,
"learning_rate": 2.704031465093412e-06,
"loss": 0.0332,
"step": 1075
},
{
"epoch": 9.56,
"learning_rate": 2.4582104228121927e-06,
"loss": 0.0,
"step": 1080
},
{
"epoch": 9.6,
"learning_rate": 2.2123893805309734e-06,
"loss": 0.0,
"step": 1085
},
{
"epoch": 9.65,
"learning_rate": 1.966568338249754e-06,
"loss": 0.0,
"step": 1090
},
{
"epoch": 9.69,
"learning_rate": 1.720747295968535e-06,
"loss": 0.3838,
"step": 1095
},
{
"epoch": 9.73,
"learning_rate": 1.4749262536873157e-06,
"loss": 0.0,
"step": 1100
},
{
"epoch": 9.78,
"learning_rate": 1.2291052114060964e-06,
"loss": 0.0,
"step": 1105
},
{
"epoch": 9.82,
"learning_rate": 9.83284169124877e-07,
"loss": 0.0,
"step": 1110
},
{
"epoch": 9.87,
"learning_rate": 7.374631268436578e-07,
"loss": 0.0,
"step": 1115
},
{
"epoch": 9.91,
"learning_rate": 4.916420845624385e-07,
"loss": 0.0,
"step": 1120
},
{
"epoch": 9.96,
"learning_rate": 2.4582104228121926e-07,
"loss": 0.0,
"step": 1125
},
{
"epoch": 10.0,
"learning_rate": 0.0,
"loss": 0.0,
"step": 1130
},
{
"epoch": 10.0,
"eval_accuracy": 0.9,
"eval_loss": 0.7291831970214844,
"eval_runtime": 15.0581,
"eval_samples_per_second": 6.641,
"eval_steps_per_second": 0.863,
"step": 1130
}
],
"logging_steps": 5,
"max_steps": 1130,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 6.094112254328832e+17,
"trial_name": null,
"trial_params": null
}