3vnuv1vf / trainer_state.json
tscholak's picture
update T5 model
e1673e3 unverified
raw
history blame
81.3 kB
{
"best_metric": 0.7117988394584139,
"best_model_checkpoint": "/experiments/spider/d6368230-e8a6-4e57-923c-f0938a9bcf7b/checkpoint-2624",
"epoch": 874.5844748858448,
"global_step": 2624,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 3.2183,
"step": 1
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 2.451,
"step": 4
},
{
"epoch": 2.58,
"learning_rate": 0.0001,
"loss": 1.2943,
"step": 8
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 0.8542,
"step": 12
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 0.7239,
"step": 16
},
{
"epoch": 6.58,
"learning_rate": 0.0001,
"loss": 0.5427,
"step": 20
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.4532,
"step": 24
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 0.4275,
"step": 28
},
{
"epoch": 10.58,
"learning_rate": 0.0001,
"loss": 0.3646,
"step": 32
},
{
"epoch": 11.88,
"learning_rate": 0.0001,
"loss": 0.3155,
"step": 36
},
{
"epoch": 13.29,
"learning_rate": 0.0001,
"loss": 0.3455,
"step": 40
},
{
"epoch": 14.58,
"learning_rate": 0.0001,
"loss": 0.2804,
"step": 44
},
{
"epoch": 15.88,
"learning_rate": 0.0001,
"loss": 0.2518,
"step": 48
},
{
"epoch": 17.29,
"learning_rate": 0.0001,
"loss": 0.248,
"step": 52
},
{
"epoch": 18.58,
"learning_rate": 0.0001,
"loss": 0.2021,
"step": 56
},
{
"epoch": 19.88,
"learning_rate": 0.0001,
"loss": 0.212,
"step": 60
},
{
"epoch": 21.29,
"learning_rate": 0.0001,
"loss": 0.203,
"step": 64
},
{
"epoch": 21.29,
"eval_exact_match": 0.42359767891682787,
"eval_exec": 0.4284332688588008,
"eval_loss": 0.1833169162273407,
"eval_runtime": 682.1232,
"eval_samples_per_second": 1.516,
"step": 64
},
{
"epoch": 22.58,
"learning_rate": 0.0001,
"loss": 0.1895,
"step": 68
},
{
"epoch": 23.88,
"learning_rate": 0.0001,
"loss": 0.166,
"step": 72
},
{
"epoch": 25.29,
"learning_rate": 0.0001,
"loss": 0.1833,
"step": 76
},
{
"epoch": 26.58,
"learning_rate": 0.0001,
"loss": 0.1503,
"step": 80
},
{
"epoch": 27.88,
"learning_rate": 0.0001,
"loss": 0.1485,
"step": 84
},
{
"epoch": 29.29,
"learning_rate": 0.0001,
"loss": 0.1574,
"step": 88
},
{
"epoch": 30.58,
"learning_rate": 0.0001,
"loss": 0.1295,
"step": 92
},
{
"epoch": 31.88,
"learning_rate": 0.0001,
"loss": 0.1199,
"step": 96
},
{
"epoch": 33.29,
"learning_rate": 0.0001,
"loss": 0.1262,
"step": 100
},
{
"epoch": 34.58,
"learning_rate": 0.0001,
"loss": 0.1153,
"step": 104
},
{
"epoch": 35.88,
"learning_rate": 0.0001,
"loss": 0.1067,
"step": 108
},
{
"epoch": 37.29,
"learning_rate": 0.0001,
"loss": 0.1086,
"step": 112
},
{
"epoch": 38.58,
"learning_rate": 0.0001,
"loss": 0.0934,
"step": 116
},
{
"epoch": 39.88,
"learning_rate": 0.0001,
"loss": 0.096,
"step": 120
},
{
"epoch": 41.29,
"learning_rate": 0.0001,
"loss": 0.1075,
"step": 124
},
{
"epoch": 42.58,
"learning_rate": 0.0001,
"loss": 0.0984,
"step": 128
},
{
"epoch": 42.58,
"eval_exact_match": 0.5938104448742747,
"eval_exec": 0.5764023210831721,
"eval_loss": 0.16683875024318695,
"eval_runtime": 703.3328,
"eval_samples_per_second": 1.47,
"step": 128
},
{
"epoch": 43.88,
"learning_rate": 0.0001,
"loss": 0.0842,
"step": 132
},
{
"epoch": 45.29,
"learning_rate": 0.0001,
"loss": 0.0954,
"step": 136
},
{
"epoch": 46.58,
"learning_rate": 0.0001,
"loss": 0.0842,
"step": 140
},
{
"epoch": 47.88,
"learning_rate": 0.0001,
"loss": 0.0724,
"step": 144
},
{
"epoch": 49.29,
"learning_rate": 0.0001,
"loss": 0.0805,
"step": 148
},
{
"epoch": 50.58,
"learning_rate": 0.0001,
"loss": 0.0745,
"step": 152
},
{
"epoch": 51.88,
"learning_rate": 0.0001,
"loss": 0.0685,
"step": 156
},
{
"epoch": 53.29,
"learning_rate": 0.0001,
"loss": 0.0709,
"step": 160
},
{
"epoch": 54.58,
"learning_rate": 0.0001,
"loss": 0.0744,
"step": 164
},
{
"epoch": 55.88,
"learning_rate": 0.0001,
"loss": 0.0603,
"step": 168
},
{
"epoch": 57.29,
"learning_rate": 0.0001,
"loss": 0.0607,
"step": 172
},
{
"epoch": 58.58,
"learning_rate": 0.0001,
"loss": 0.0652,
"step": 176
},
{
"epoch": 59.88,
"learning_rate": 0.0001,
"loss": 0.0592,
"step": 180
},
{
"epoch": 61.29,
"learning_rate": 0.0001,
"loss": 0.0584,
"step": 184
},
{
"epoch": 62.58,
"learning_rate": 0.0001,
"loss": 0.0507,
"step": 188
},
{
"epoch": 63.88,
"learning_rate": 0.0001,
"loss": 0.0523,
"step": 192
},
{
"epoch": 63.88,
"eval_exact_match": 0.6266924564796905,
"eval_exec": 0.620889748549323,
"eval_loss": 0.16735364496707916,
"eval_runtime": 843.3561,
"eval_samples_per_second": 1.226,
"step": 192
},
{
"epoch": 65.29,
"learning_rate": 0.0001,
"loss": 0.0576,
"step": 196
},
{
"epoch": 66.58,
"learning_rate": 0.0001,
"loss": 0.0539,
"step": 200
},
{
"epoch": 67.88,
"learning_rate": 0.0001,
"loss": 0.0443,
"step": 204
},
{
"epoch": 69.29,
"learning_rate": 0.0001,
"loss": 0.0518,
"step": 208
},
{
"epoch": 70.58,
"learning_rate": 0.0001,
"loss": 0.0435,
"step": 212
},
{
"epoch": 71.88,
"learning_rate": 0.0001,
"loss": 0.0428,
"step": 216
},
{
"epoch": 73.29,
"learning_rate": 0.0001,
"loss": 0.043,
"step": 220
},
{
"epoch": 74.58,
"learning_rate": 0.0001,
"loss": 0.0383,
"step": 224
},
{
"epoch": 75.88,
"learning_rate": 0.0001,
"loss": 0.0399,
"step": 228
},
{
"epoch": 77.29,
"learning_rate": 0.0001,
"loss": 0.0422,
"step": 232
},
{
"epoch": 78.58,
"learning_rate": 0.0001,
"loss": 0.0357,
"step": 236
},
{
"epoch": 79.88,
"learning_rate": 0.0001,
"loss": 0.0346,
"step": 240
},
{
"epoch": 81.29,
"learning_rate": 0.0001,
"loss": 0.0433,
"step": 244
},
{
"epoch": 82.58,
"learning_rate": 0.0001,
"loss": 0.0339,
"step": 248
},
{
"epoch": 83.88,
"learning_rate": 0.0001,
"loss": 0.0353,
"step": 252
},
{
"epoch": 85.29,
"learning_rate": 0.0001,
"loss": 0.0326,
"step": 256
},
{
"epoch": 85.29,
"eval_exact_match": 0.6586073500967118,
"eval_exec": 0.6450676982591876,
"eval_loss": 0.21498563885688782,
"eval_runtime": 824.5584,
"eval_samples_per_second": 1.254,
"step": 256
},
{
"epoch": 86.58,
"learning_rate": 0.0001,
"loss": 0.0301,
"step": 260
},
{
"epoch": 87.88,
"learning_rate": 0.0001,
"loss": 0.0302,
"step": 264
},
{
"epoch": 89.29,
"learning_rate": 0.0001,
"loss": 0.0322,
"step": 268
},
{
"epoch": 90.58,
"learning_rate": 0.0001,
"loss": 0.0248,
"step": 272
},
{
"epoch": 91.88,
"learning_rate": 0.0001,
"loss": 0.026,
"step": 276
},
{
"epoch": 93.29,
"learning_rate": 0.0001,
"loss": 0.0297,
"step": 280
},
{
"epoch": 94.58,
"learning_rate": 0.0001,
"loss": 0.0276,
"step": 284
},
{
"epoch": 95.88,
"learning_rate": 0.0001,
"loss": 0.0253,
"step": 288
},
{
"epoch": 97.29,
"learning_rate": 0.0001,
"loss": 0.0282,
"step": 292
},
{
"epoch": 98.58,
"learning_rate": 0.0001,
"loss": 0.0252,
"step": 296
},
{
"epoch": 99.88,
"learning_rate": 0.0001,
"loss": 0.0234,
"step": 300
},
{
"epoch": 101.29,
"learning_rate": 0.0001,
"loss": 0.0225,
"step": 304
},
{
"epoch": 102.58,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 308
},
{
"epoch": 103.88,
"learning_rate": 0.0001,
"loss": 0.0201,
"step": 312
},
{
"epoch": 105.29,
"learning_rate": 0.0001,
"loss": 0.022,
"step": 316
},
{
"epoch": 106.58,
"learning_rate": 0.0001,
"loss": 0.0206,
"step": 320
},
{
"epoch": 106.58,
"eval_exact_match": 0.6644100580270793,
"eval_exec": 0.6499032882011605,
"eval_loss": 0.21441736817359924,
"eval_runtime": 835.4598,
"eval_samples_per_second": 1.238,
"step": 320
},
{
"epoch": 107.88,
"learning_rate": 0.0001,
"loss": 0.0178,
"step": 324
},
{
"epoch": 109.29,
"learning_rate": 0.0001,
"loss": 0.0172,
"step": 328
},
{
"epoch": 110.58,
"learning_rate": 0.0001,
"loss": 0.0175,
"step": 332
},
{
"epoch": 111.88,
"learning_rate": 0.0001,
"loss": 0.0155,
"step": 336
},
{
"epoch": 113.29,
"learning_rate": 0.0001,
"loss": 0.0187,
"step": 340
},
{
"epoch": 114.58,
"learning_rate": 0.0001,
"loss": 0.0142,
"step": 344
},
{
"epoch": 115.88,
"learning_rate": 0.0001,
"loss": 0.0149,
"step": 348
},
{
"epoch": 117.29,
"learning_rate": 0.0001,
"loss": 0.0155,
"step": 352
},
{
"epoch": 118.58,
"learning_rate": 0.0001,
"loss": 0.0148,
"step": 356
},
{
"epoch": 119.88,
"learning_rate": 0.0001,
"loss": 0.0138,
"step": 360
},
{
"epoch": 121.29,
"learning_rate": 0.0001,
"loss": 0.0154,
"step": 364
},
{
"epoch": 122.58,
"learning_rate": 0.0001,
"loss": 0.0145,
"step": 368
},
{
"epoch": 123.88,
"learning_rate": 0.0001,
"loss": 0.0172,
"step": 372
},
{
"epoch": 125.29,
"learning_rate": 0.0001,
"loss": 0.0146,
"step": 376
},
{
"epoch": 126.58,
"learning_rate": 0.0001,
"loss": 0.0156,
"step": 380
},
{
"epoch": 127.88,
"learning_rate": 0.0001,
"loss": 0.0177,
"step": 384
},
{
"epoch": 127.88,
"eval_exact_match": 0.6682785299806576,
"eval_exec": 0.6518375241779497,
"eval_loss": 0.24249066412448883,
"eval_runtime": 822.9024,
"eval_samples_per_second": 1.257,
"step": 384
},
{
"epoch": 129.29,
"learning_rate": 0.0001,
"loss": 0.0134,
"step": 388
},
{
"epoch": 130.58,
"learning_rate": 0.0001,
"loss": 0.0119,
"step": 392
},
{
"epoch": 131.88,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 396
},
{
"epoch": 133.29,
"learning_rate": 0.0001,
"loss": 0.0105,
"step": 400
},
{
"epoch": 134.58,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 404
},
{
"epoch": 135.88,
"learning_rate": 0.0001,
"loss": 0.0118,
"step": 408
},
{
"epoch": 137.29,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 412
},
{
"epoch": 138.58,
"learning_rate": 0.0001,
"loss": 0.0102,
"step": 416
},
{
"epoch": 139.88,
"learning_rate": 0.0001,
"loss": 0.0106,
"step": 420
},
{
"epoch": 141.29,
"learning_rate": 0.0001,
"loss": 0.0087,
"step": 424
},
{
"epoch": 142.58,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 428
},
{
"epoch": 143.88,
"learning_rate": 0.0001,
"loss": 0.0099,
"step": 432
},
{
"epoch": 145.29,
"learning_rate": 0.0001,
"loss": 0.0092,
"step": 436
},
{
"epoch": 146.58,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 440
},
{
"epoch": 147.88,
"learning_rate": 0.0001,
"loss": 0.0088,
"step": 444
},
{
"epoch": 149.29,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 448
},
{
"epoch": 149.29,
"eval_exact_match": 0.6499032882011605,
"eval_exec": 0.6353965183752418,
"eval_loss": 0.2822052538394928,
"eval_runtime": 813.617,
"eval_samples_per_second": 1.271,
"step": 448
},
{
"epoch": 150.58,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 452
},
{
"epoch": 151.88,
"learning_rate": 0.0001,
"loss": 0.0075,
"step": 456
},
{
"epoch": 153.29,
"learning_rate": 0.0001,
"loss": 0.0071,
"step": 460
},
{
"epoch": 154.58,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 464
},
{
"epoch": 155.88,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 468
},
{
"epoch": 157.29,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 472
},
{
"epoch": 158.58,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 476
},
{
"epoch": 159.88,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 480
},
{
"epoch": 161.29,
"learning_rate": 0.0001,
"loss": 0.0111,
"step": 484
},
{
"epoch": 162.58,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 488
},
{
"epoch": 163.88,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 492
},
{
"epoch": 165.29,
"learning_rate": 0.0001,
"loss": 0.0121,
"step": 496
},
{
"epoch": 166.58,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 500
},
{
"epoch": 167.88,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 504
},
{
"epoch": 169.29,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 508
},
{
"epoch": 170.58,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 512
},
{
"epoch": 170.58,
"eval_exact_match": 0.660541586073501,
"eval_exec": 0.6479690522243714,
"eval_loss": 0.29858535528182983,
"eval_runtime": 852.1163,
"eval_samples_per_second": 1.213,
"step": 512
},
{
"epoch": 171.88,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 516
},
{
"epoch": 173.29,
"learning_rate": 0.0001,
"loss": 0.0053,
"step": 520
},
{
"epoch": 174.58,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 524
},
{
"epoch": 175.88,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 528
},
{
"epoch": 177.29,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 532
},
{
"epoch": 178.58,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 536
},
{
"epoch": 179.88,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 540
},
{
"epoch": 181.29,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 544
},
{
"epoch": 182.58,
"learning_rate": 0.0001,
"loss": 0.0164,
"step": 548
},
{
"epoch": 183.88,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 552
},
{
"epoch": 185.29,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 556
},
{
"epoch": 186.58,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 560
},
{
"epoch": 187.88,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 564
},
{
"epoch": 189.29,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 568
},
{
"epoch": 190.58,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 572
},
{
"epoch": 191.88,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 576
},
{
"epoch": 191.88,
"eval_exact_match": 0.6663442940038685,
"eval_exec": 0.6479690522243714,
"eval_loss": 0.3111841380596161,
"eval_runtime": 837.4186,
"eval_samples_per_second": 1.235,
"step": 576
},
{
"epoch": 193.29,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 580
},
{
"epoch": 194.58,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 584
},
{
"epoch": 195.88,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 588
},
{
"epoch": 197.29,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 592
},
{
"epoch": 198.58,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 596
},
{
"epoch": 199.88,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 600
},
{
"epoch": 201.29,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 604
},
{
"epoch": 202.58,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 608
},
{
"epoch": 203.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 612
},
{
"epoch": 205.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 616
},
{
"epoch": 206.58,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 620
},
{
"epoch": 207.88,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 624
},
{
"epoch": 209.29,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 628
},
{
"epoch": 210.58,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 632
},
{
"epoch": 211.88,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 636
},
{
"epoch": 213.29,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 640
},
{
"epoch": 213.29,
"eval_exact_match": 0.660541586073501,
"eval_exec": 0.648936170212766,
"eval_loss": 0.3557709753513336,
"eval_runtime": 807.1499,
"eval_samples_per_second": 1.281,
"step": 640
},
{
"epoch": 214.58,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 644
},
{
"epoch": 215.88,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 648
},
{
"epoch": 217.29,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 652
},
{
"epoch": 218.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 656
},
{
"epoch": 219.88,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 660
},
{
"epoch": 221.29,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 664
},
{
"epoch": 222.58,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 668
},
{
"epoch": 223.88,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 672
},
{
"epoch": 225.29,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 676
},
{
"epoch": 226.58,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 680
},
{
"epoch": 227.88,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 684
},
{
"epoch": 229.29,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 688
},
{
"epoch": 230.58,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 692
},
{
"epoch": 231.88,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 696
},
{
"epoch": 233.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 700
},
{
"epoch": 234.58,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 704
},
{
"epoch": 234.58,
"eval_exact_match": 0.6682785299806576,
"eval_exec": 0.6528046421663443,
"eval_loss": 0.34394705295562744,
"eval_runtime": 890.2876,
"eval_samples_per_second": 1.161,
"step": 704
},
{
"epoch": 235.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 708
},
{
"epoch": 237.29,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 712
},
{
"epoch": 238.58,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 716
},
{
"epoch": 239.88,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 720
},
{
"epoch": 241.29,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 724
},
{
"epoch": 242.58,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 728
},
{
"epoch": 243.88,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 732
},
{
"epoch": 245.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 736
},
{
"epoch": 246.58,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 740
},
{
"epoch": 247.88,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 744
},
{
"epoch": 249.29,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 748
},
{
"epoch": 250.58,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 752
},
{
"epoch": 251.88,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 756
},
{
"epoch": 253.29,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 760
},
{
"epoch": 254.58,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 764
},
{
"epoch": 255.88,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 768
},
{
"epoch": 255.88,
"eval_exact_match": 0.6702127659574468,
"eval_exec": 0.6576402321083172,
"eval_loss": 0.3505505919456482,
"eval_runtime": 849.5769,
"eval_samples_per_second": 1.217,
"step": 768
},
{
"epoch": 257.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 772
},
{
"epoch": 258.58,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 776
},
{
"epoch": 259.88,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 780
},
{
"epoch": 261.29,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 784
},
{
"epoch": 262.58,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 788
},
{
"epoch": 263.88,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 792
},
{
"epoch": 265.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 796
},
{
"epoch": 266.58,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 800
},
{
"epoch": 267.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 804
},
{
"epoch": 269.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 808
},
{
"epoch": 270.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 812
},
{
"epoch": 271.88,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 816
},
{
"epoch": 273.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 820
},
{
"epoch": 274.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 824
},
{
"epoch": 275.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 828
},
{
"epoch": 277.29,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 832
},
{
"epoch": 277.29,
"eval_exact_match": 0.6789168278529981,
"eval_exec": 0.6615087040618955,
"eval_loss": 0.36397507786750793,
"eval_runtime": 827.3744,
"eval_samples_per_second": 1.25,
"step": 832
},
{
"epoch": 278.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 836
},
{
"epoch": 279.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 840
},
{
"epoch": 281.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 844
},
{
"epoch": 282.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 848
},
{
"epoch": 283.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 852
},
{
"epoch": 285.29,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 856
},
{
"epoch": 286.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 860
},
{
"epoch": 287.88,
"learning_rate": 0.0001,
"loss": 0.0075,
"step": 864
},
{
"epoch": 289.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 868
},
{
"epoch": 290.58,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 872
},
{
"epoch": 291.88,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 876
},
{
"epoch": 293.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 880
},
{
"epoch": 294.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 884
},
{
"epoch": 295.88,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 888
},
{
"epoch": 297.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 892
},
{
"epoch": 298.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 896
},
{
"epoch": 298.58,
"eval_exact_match": 0.6740812379110251,
"eval_exec": 0.6576402321083172,
"eval_loss": 0.39234504103660583,
"eval_runtime": 785.534,
"eval_samples_per_second": 1.316,
"step": 896
},
{
"epoch": 299.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 900
},
{
"epoch": 301.29,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 904
},
{
"epoch": 302.58,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 908
},
{
"epoch": 303.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 912
},
{
"epoch": 305.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 916
},
{
"epoch": 306.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 920
},
{
"epoch": 307.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 924
},
{
"epoch": 309.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 928
},
{
"epoch": 310.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 932
},
{
"epoch": 311.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 936
},
{
"epoch": 313.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 940
},
{
"epoch": 314.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 944
},
{
"epoch": 315.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 948
},
{
"epoch": 317.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 952
},
{
"epoch": 318.58,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 956
},
{
"epoch": 319.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 960
},
{
"epoch": 319.88,
"eval_exact_match": 0.6740812379110251,
"eval_exec": 0.655705996131528,
"eval_loss": 0.40166109800338745,
"eval_runtime": 799.99,
"eval_samples_per_second": 1.293,
"step": 960
},
{
"epoch": 321.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 964
},
{
"epoch": 322.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 968
},
{
"epoch": 323.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 972
},
{
"epoch": 325.29,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 976
},
{
"epoch": 326.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 980
},
{
"epoch": 327.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 984
},
{
"epoch": 329.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 988
},
{
"epoch": 330.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 992
},
{
"epoch": 331.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 996
},
{
"epoch": 333.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1000
},
{
"epoch": 334.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1004
},
{
"epoch": 335.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1008
},
{
"epoch": 337.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1012
},
{
"epoch": 338.58,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1016
},
{
"epoch": 339.88,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1020
},
{
"epoch": 341.29,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 1024
},
{
"epoch": 341.29,
"eval_exact_match": 0.6963249516441006,
"eval_exec": 0.6721470019342359,
"eval_loss": 0.3228262662887573,
"eval_runtime": 823.0842,
"eval_samples_per_second": 1.256,
"step": 1024
},
{
"epoch": 342.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1028
},
{
"epoch": 343.88,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1032
},
{
"epoch": 345.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1036
},
{
"epoch": 346.58,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1040
},
{
"epoch": 347.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1044
},
{
"epoch": 349.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1048
},
{
"epoch": 350.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1052
},
{
"epoch": 351.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1056
},
{
"epoch": 353.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1060
},
{
"epoch": 354.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1064
},
{
"epoch": 355.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1068
},
{
"epoch": 357.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1072
},
{
"epoch": 358.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1076
},
{
"epoch": 359.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1080
},
{
"epoch": 361.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1084
},
{
"epoch": 362.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1088
},
{
"epoch": 362.58,
"eval_exact_match": 0.6924564796905223,
"eval_exec": 0.6721470019342359,
"eval_loss": 0.4092560410499573,
"eval_runtime": 834.3948,
"eval_samples_per_second": 1.239,
"step": 1088
},
{
"epoch": 363.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1092
},
{
"epoch": 365.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1096
},
{
"epoch": 366.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1100
},
{
"epoch": 367.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1104
},
{
"epoch": 369.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1108
},
{
"epoch": 370.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1112
},
{
"epoch": 371.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1116
},
{
"epoch": 373.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1120
},
{
"epoch": 374.58,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 1124
},
{
"epoch": 375.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1128
},
{
"epoch": 377.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1132
},
{
"epoch": 378.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1136
},
{
"epoch": 379.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1140
},
{
"epoch": 381.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1144
},
{
"epoch": 382.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1148
},
{
"epoch": 383.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1152
},
{
"epoch": 383.88,
"eval_exact_match": 0.6934235976789168,
"eval_exec": 0.6818181818181818,
"eval_loss": 0.43188637495040894,
"eval_runtime": 827.3576,
"eval_samples_per_second": 1.25,
"step": 1152
},
{
"epoch": 385.29,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1156
},
{
"epoch": 386.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1160
},
{
"epoch": 387.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1164
},
{
"epoch": 389.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1168
},
{
"epoch": 390.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1172
},
{
"epoch": 391.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1176
},
{
"epoch": 393.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1180
},
{
"epoch": 394.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1184
},
{
"epoch": 395.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1188
},
{
"epoch": 397.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1192
},
{
"epoch": 398.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1196
},
{
"epoch": 399.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1200
},
{
"epoch": 401.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1204
},
{
"epoch": 402.58,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1208
},
{
"epoch": 403.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1212
},
{
"epoch": 405.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1216
},
{
"epoch": 405.29,
"eval_exact_match": 0.6750483558994197,
"eval_exec": 0.6624758220502901,
"eval_loss": 0.38173577189445496,
"eval_runtime": 863.9436,
"eval_samples_per_second": 1.197,
"step": 1216
},
{
"epoch": 406.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1220
},
{
"epoch": 407.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1224
},
{
"epoch": 409.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1228
},
{
"epoch": 410.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1232
},
{
"epoch": 411.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1236
},
{
"epoch": 413.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1240
},
{
"epoch": 414.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1244
},
{
"epoch": 415.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1248
},
{
"epoch": 417.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1252
},
{
"epoch": 418.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1256
},
{
"epoch": 419.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1260
},
{
"epoch": 421.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1264
},
{
"epoch": 422.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1268
},
{
"epoch": 423.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1272
},
{
"epoch": 425.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1276
},
{
"epoch": 426.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1280
},
{
"epoch": 426.58,
"eval_exact_match": 0.6808510638297872,
"eval_exec": 0.6644100580270793,
"eval_loss": 0.42931750416755676,
"eval_runtime": 845.9587,
"eval_samples_per_second": 1.222,
"step": 1280
},
{
"epoch": 427.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1284
},
{
"epoch": 429.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1288
},
{
"epoch": 430.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1292
},
{
"epoch": 431.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1296
},
{
"epoch": 433.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1300
},
{
"epoch": 434.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1304
},
{
"epoch": 435.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1308
},
{
"epoch": 437.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1312
},
{
"epoch": 438.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1316
},
{
"epoch": 439.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1320
},
{
"epoch": 441.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1324
},
{
"epoch": 442.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1328
},
{
"epoch": 443.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1332
},
{
"epoch": 445.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1336
},
{
"epoch": 446.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1340
},
{
"epoch": 447.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1344
},
{
"epoch": 447.88,
"eval_exact_match": 0.6518375241779497,
"eval_exec": 0.6499032882011605,
"eval_loss": 0.416789174079895,
"eval_runtime": 773.9784,
"eval_samples_per_second": 1.336,
"step": 1344
},
{
"epoch": 449.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1348
},
{
"epoch": 450.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1352
},
{
"epoch": 451.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1356
},
{
"epoch": 453.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1360
},
{
"epoch": 454.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1364
},
{
"epoch": 455.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1368
},
{
"epoch": 457.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1372
},
{
"epoch": 458.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1376
},
{
"epoch": 459.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1380
},
{
"epoch": 461.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1384
},
{
"epoch": 462.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1388
},
{
"epoch": 463.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1392
},
{
"epoch": 465.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1396
},
{
"epoch": 466.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1400
},
{
"epoch": 467.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1404
},
{
"epoch": 469.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1408
},
{
"epoch": 469.29,
"eval_exact_match": 0.6750483558994197,
"eval_exec": 0.6673114119922631,
"eval_loss": 0.36535608768463135,
"eval_runtime": 954.0188,
"eval_samples_per_second": 1.084,
"step": 1408
},
{
"epoch": 470.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1412
},
{
"epoch": 471.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1416
},
{
"epoch": 473.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1420
},
{
"epoch": 474.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1424
},
{
"epoch": 475.88,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 1428
},
{
"epoch": 477.29,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1432
},
{
"epoch": 478.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1436
},
{
"epoch": 479.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1440
},
{
"epoch": 481.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1444
},
{
"epoch": 482.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1448
},
{
"epoch": 483.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1452
},
{
"epoch": 485.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1456
},
{
"epoch": 486.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1460
},
{
"epoch": 487.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1464
},
{
"epoch": 489.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1468
},
{
"epoch": 490.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1472
},
{
"epoch": 490.58,
"eval_exact_match": 0.6818181818181818,
"eval_exec": 0.6740812379110251,
"eval_loss": 0.41243937611579895,
"eval_runtime": 955.6213,
"eval_samples_per_second": 1.082,
"step": 1472
},
{
"epoch": 491.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1476
},
{
"epoch": 493.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1480
},
{
"epoch": 494.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1484
},
{
"epoch": 495.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1488
},
{
"epoch": 497.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1492
},
{
"epoch": 498.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1496
},
{
"epoch": 499.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1500
},
{
"epoch": 501.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1504
},
{
"epoch": 502.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1508
},
{
"epoch": 503.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1512
},
{
"epoch": 505.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1516
},
{
"epoch": 506.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1520
},
{
"epoch": 507.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1524
},
{
"epoch": 509.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1528
},
{
"epoch": 510.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1532
},
{
"epoch": 511.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1536
},
{
"epoch": 511.88,
"eval_exact_match": 0.6856866537717602,
"eval_exec": 0.6798839458413927,
"eval_loss": 0.4265560507774353,
"eval_runtime": 1299.537,
"eval_samples_per_second": 0.796,
"step": 1536
},
{
"epoch": 513.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1540
},
{
"epoch": 514.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1544
},
{
"epoch": 515.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1548
},
{
"epoch": 517.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1552
},
{
"epoch": 518.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1556
},
{
"epoch": 519.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1560
},
{
"epoch": 521.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1564
},
{
"epoch": 522.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1568
},
{
"epoch": 523.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1572
},
{
"epoch": 525.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1576
},
{
"epoch": 526.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1580
},
{
"epoch": 527.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1584
},
{
"epoch": 529.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1588
},
{
"epoch": 530.58,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1592
},
{
"epoch": 531.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1596
},
{
"epoch": 533.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1600
},
{
"epoch": 533.29,
"eval_exact_match": 0.6856866537717602,
"eval_exec": 0.6779497098646035,
"eval_loss": 0.4029601216316223,
"eval_runtime": 999.4683,
"eval_samples_per_second": 1.035,
"step": 1600
},
{
"epoch": 534.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1604
},
{
"epoch": 535.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1608
},
{
"epoch": 537.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1612
},
{
"epoch": 538.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1616
},
{
"epoch": 539.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1620
},
{
"epoch": 541.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1624
},
{
"epoch": 542.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1628
},
{
"epoch": 543.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1632
},
{
"epoch": 545.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1636
},
{
"epoch": 546.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1640
},
{
"epoch": 547.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1644
},
{
"epoch": 549.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1648
},
{
"epoch": 550.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1652
},
{
"epoch": 551.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1656
},
{
"epoch": 553.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1660
},
{
"epoch": 554.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1664
},
{
"epoch": 554.58,
"eval_exact_match": 0.6934235976789168,
"eval_exec": 0.6827852998065764,
"eval_loss": 0.44639065861701965,
"eval_runtime": 1031.7773,
"eval_samples_per_second": 1.002,
"step": 1664
},
{
"epoch": 555.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1668
},
{
"epoch": 557.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1672
},
{
"epoch": 558.58,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1676
},
{
"epoch": 559.88,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1680
},
{
"epoch": 561.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1684
},
{
"epoch": 562.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1688
},
{
"epoch": 563.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1692
},
{
"epoch": 565.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1696
},
{
"epoch": 566.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1700
},
{
"epoch": 567.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1704
},
{
"epoch": 569.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1708
},
{
"epoch": 570.58,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1712
},
{
"epoch": 571.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1716
},
{
"epoch": 573.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1720
},
{
"epoch": 574.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1724
},
{
"epoch": 575.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1728
},
{
"epoch": 575.88,
"eval_exact_match": 0.6876208897485493,
"eval_exec": 0.6760154738878144,
"eval_loss": 0.41115066409111023,
"eval_runtime": 1007.2726,
"eval_samples_per_second": 1.027,
"step": 1728
},
{
"epoch": 577.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1732
},
{
"epoch": 578.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1736
},
{
"epoch": 579.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1740
},
{
"epoch": 581.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1744
},
{
"epoch": 582.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1748
},
{
"epoch": 583.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1752
},
{
"epoch": 585.29,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1756
},
{
"epoch": 586.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1760
},
{
"epoch": 587.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1764
},
{
"epoch": 589.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1768
},
{
"epoch": 590.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1772
},
{
"epoch": 591.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1776
},
{
"epoch": 593.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1780
},
{
"epoch": 594.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1784
},
{
"epoch": 595.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1788
},
{
"epoch": 597.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1792
},
{
"epoch": 597.29,
"eval_exact_match": 0.6943907156673114,
"eval_exec": 0.6779497098646035,
"eval_loss": 0.4605121910572052,
"eval_runtime": 1298.121,
"eval_samples_per_second": 0.797,
"step": 1792
},
{
"epoch": 598.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1796
},
{
"epoch": 599.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1800
},
{
"epoch": 601.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1804
},
{
"epoch": 602.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1808
},
{
"epoch": 603.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1812
},
{
"epoch": 605.29,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1816
},
{
"epoch": 606.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1820
},
{
"epoch": 607.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1824
},
{
"epoch": 609.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1828
},
{
"epoch": 610.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1832
},
{
"epoch": 611.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1836
},
{
"epoch": 613.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1840
},
{
"epoch": 614.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1844
},
{
"epoch": 615.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1848
},
{
"epoch": 617.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1852
},
{
"epoch": 618.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1856
},
{
"epoch": 618.58,
"eval_exact_match": 0.6982591876208898,
"eval_exec": 0.683752417794971,
"eval_loss": 0.4248420000076294,
"eval_runtime": 1371.1332,
"eval_samples_per_second": 0.754,
"step": 1856
},
{
"epoch": 619.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1860
},
{
"epoch": 621.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1864
},
{
"epoch": 622.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1868
},
{
"epoch": 623.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1872
},
{
"epoch": 625.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1876
},
{
"epoch": 626.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1880
},
{
"epoch": 627.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1884
},
{
"epoch": 629.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1888
},
{
"epoch": 630.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1892
},
{
"epoch": 631.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1896
},
{
"epoch": 633.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1900
},
{
"epoch": 634.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1904
},
{
"epoch": 635.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1908
},
{
"epoch": 637.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1912
},
{
"epoch": 638.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1916
},
{
"epoch": 639.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1920
},
{
"epoch": 639.88,
"eval_exact_match": 0.6847195357833655,
"eval_exec": 0.6769825918762089,
"eval_loss": 0.45460787415504456,
"eval_runtime": 1038.9518,
"eval_samples_per_second": 0.995,
"step": 1920
},
{
"epoch": 641.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1924
},
{
"epoch": 642.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1928
},
{
"epoch": 643.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1932
},
{
"epoch": 645.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1936
},
{
"epoch": 646.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1940
},
{
"epoch": 647.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1944
},
{
"epoch": 649.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1948
},
{
"epoch": 650.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1952
},
{
"epoch": 651.88,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1956
},
{
"epoch": 653.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1960
},
{
"epoch": 654.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1964
},
{
"epoch": 655.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1968
},
{
"epoch": 657.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1972
},
{
"epoch": 658.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1976
},
{
"epoch": 659.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1980
},
{
"epoch": 661.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1984
},
{
"epoch": 661.29,
"eval_exact_match": 0.6856866537717602,
"eval_exec": 0.6808510638297872,
"eval_loss": 0.4657697379589081,
"eval_runtime": 1097.6691,
"eval_samples_per_second": 0.942,
"step": 1984
},
{
"epoch": 662.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1988
},
{
"epoch": 663.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1992
},
{
"epoch": 665.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1996
},
{
"epoch": 666.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2000
},
{
"epoch": 667.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2004
},
{
"epoch": 669.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2008
},
{
"epoch": 670.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2012
},
{
"epoch": 671.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2016
},
{
"epoch": 673.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2020
},
{
"epoch": 674.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2024
},
{
"epoch": 675.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2028
},
{
"epoch": 677.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2032
},
{
"epoch": 678.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2036
},
{
"epoch": 679.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2040
},
{
"epoch": 681.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2044
},
{
"epoch": 682.58,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 2048
},
{
"epoch": 682.58,
"eval_exact_match": 0.6914893617021277,
"eval_exec": 0.690522243713733,
"eval_loss": 0.4180769622325897,
"eval_runtime": 1092.62,
"eval_samples_per_second": 0.946,
"step": 2048
},
{
"epoch": 683.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2052
},
{
"epoch": 685.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2056
},
{
"epoch": 686.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2060
},
{
"epoch": 687.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 2064
},
{
"epoch": 689.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 2068
},
{
"epoch": 690.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2072
},
{
"epoch": 691.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2076
},
{
"epoch": 693.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2080
},
{
"epoch": 694.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2084
},
{
"epoch": 695.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2088
},
{
"epoch": 697.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2092
},
{
"epoch": 698.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 2096
},
{
"epoch": 699.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 2100
},
{
"epoch": 701.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2104
},
{
"epoch": 702.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2108
},
{
"epoch": 703.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2112
},
{
"epoch": 703.88,
"eval_exact_match": 0.6943907156673114,
"eval_exec": 0.6924564796905223,
"eval_loss": 0.44465285539627075,
"eval_runtime": 999.8273,
"eval_samples_per_second": 1.034,
"step": 2112
},
{
"epoch": 705.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2116
},
{
"epoch": 706.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2120
},
{
"epoch": 707.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2124
},
{
"epoch": 709.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2128
},
{
"epoch": 710.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2132
},
{
"epoch": 711.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2136
},
{
"epoch": 713.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2140
},
{
"epoch": 714.58,
"learning_rate": 0.0001,
"loss": 0.0053,
"step": 2144
},
{
"epoch": 715.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2148
},
{
"epoch": 717.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2152
},
{
"epoch": 718.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2156
},
{
"epoch": 719.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2160
},
{
"epoch": 721.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2164
},
{
"epoch": 722.58,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 2168
},
{
"epoch": 723.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2172
},
{
"epoch": 725.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2176
},
{
"epoch": 725.29,
"eval_exact_match": 0.6992263056092843,
"eval_exec": 0.6876208897485493,
"eval_loss": 0.4321630299091339,
"eval_runtime": 878.8579,
"eval_samples_per_second": 1.177,
"step": 2176
},
{
"epoch": 726.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2180
},
{
"epoch": 727.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2184
},
{
"epoch": 729.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2188
},
{
"epoch": 730.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2192
},
{
"epoch": 731.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2196
},
{
"epoch": 733.29,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 2200
},
{
"epoch": 734.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2204
},
{
"epoch": 735.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2208
},
{
"epoch": 737.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2212
},
{
"epoch": 738.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2216
},
{
"epoch": 739.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2220
},
{
"epoch": 741.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2224
},
{
"epoch": 742.58,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2228
},
{
"epoch": 743.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2232
},
{
"epoch": 745.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2236
},
{
"epoch": 746.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2240
},
{
"epoch": 746.58,
"eval_exact_match": 0.6963249516441006,
"eval_exec": 0.6789168278529981,
"eval_loss": 0.45437225699424744,
"eval_runtime": 864.1019,
"eval_samples_per_second": 1.197,
"step": 2240
},
{
"epoch": 747.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2244
},
{
"epoch": 749.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2248
},
{
"epoch": 750.58,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2252
},
{
"epoch": 751.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2256
},
{
"epoch": 753.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2260
},
{
"epoch": 754.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2264
},
{
"epoch": 755.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2268
},
{
"epoch": 757.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2272
},
{
"epoch": 758.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2276
},
{
"epoch": 759.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2280
},
{
"epoch": 761.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2284
},
{
"epoch": 762.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2288
},
{
"epoch": 763.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2292
},
{
"epoch": 765.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2296
},
{
"epoch": 766.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2300
},
{
"epoch": 767.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2304
},
{
"epoch": 767.88,
"eval_exact_match": 0.6963249516441006,
"eval_exec": 0.6866537717601547,
"eval_loss": 0.4832020401954651,
"eval_runtime": 816.387,
"eval_samples_per_second": 1.267,
"step": 2304
},
{
"epoch": 769.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2308
},
{
"epoch": 770.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2312
},
{
"epoch": 771.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2316
},
{
"epoch": 773.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2320
},
{
"epoch": 774.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2324
},
{
"epoch": 775.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2328
},
{
"epoch": 777.29,
"learning_rate": 0.0001,
"loss": 0.0211,
"step": 2332
},
{
"epoch": 778.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2336
},
{
"epoch": 779.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2340
},
{
"epoch": 781.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2344
},
{
"epoch": 782.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2348
},
{
"epoch": 783.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2352
},
{
"epoch": 785.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2356
},
{
"epoch": 786.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2360
},
{
"epoch": 787.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2364
},
{
"epoch": 789.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2368
},
{
"epoch": 789.29,
"eval_exact_match": 0.6924564796905223,
"eval_exec": 0.6779497098646035,
"eval_loss": 0.47273918986320496,
"eval_runtime": 826.2169,
"eval_samples_per_second": 1.251,
"step": 2368
},
{
"epoch": 790.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2372
},
{
"epoch": 791.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2376
},
{
"epoch": 793.29,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2380
},
{
"epoch": 794.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2384
},
{
"epoch": 795.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2388
},
{
"epoch": 797.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2392
},
{
"epoch": 798.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2396
},
{
"epoch": 799.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2400
},
{
"epoch": 801.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2404
},
{
"epoch": 802.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2408
},
{
"epoch": 803.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2412
},
{
"epoch": 805.29,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2416
},
{
"epoch": 806.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2420
},
{
"epoch": 807.88,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2424
},
{
"epoch": 809.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2428
},
{
"epoch": 810.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2432
},
{
"epoch": 810.58,
"eval_exact_match": 0.6808510638297872,
"eval_exec": 0.6692456479690522,
"eval_loss": 0.48608434200286865,
"eval_runtime": 825.1274,
"eval_samples_per_second": 1.253,
"step": 2432
},
{
"epoch": 811.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2436
},
{
"epoch": 813.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2440
},
{
"epoch": 814.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2444
},
{
"epoch": 815.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2448
},
{
"epoch": 817.29,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2452
},
{
"epoch": 818.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2456
},
{
"epoch": 819.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2460
},
{
"epoch": 821.29,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2464
},
{
"epoch": 822.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2468
},
{
"epoch": 823.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2472
},
{
"epoch": 825.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2476
},
{
"epoch": 826.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2480
},
{
"epoch": 827.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2484
},
{
"epoch": 829.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2488
},
{
"epoch": 830.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2492
},
{
"epoch": 831.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2496
},
{
"epoch": 831.88,
"eval_exact_match": 0.6934235976789168,
"eval_exec": 0.6750483558994197,
"eval_loss": 0.47877049446105957,
"eval_runtime": 803.416,
"eval_samples_per_second": 1.287,
"step": 2496
},
{
"epoch": 833.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2500
},
{
"epoch": 834.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2504
},
{
"epoch": 835.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2508
},
{
"epoch": 837.29,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2512
},
{
"epoch": 838.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2516
},
{
"epoch": 839.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2520
},
{
"epoch": 841.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2524
},
{
"epoch": 842.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2528
},
{
"epoch": 843.88,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2532
},
{
"epoch": 845.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2536
},
{
"epoch": 846.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2540
},
{
"epoch": 847.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2544
},
{
"epoch": 849.29,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2548
},
{
"epoch": 850.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2552
},
{
"epoch": 851.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2556
},
{
"epoch": 853.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2560
},
{
"epoch": 853.29,
"eval_exact_match": 0.6914893617021277,
"eval_exec": 0.6779497098646035,
"eval_loss": 0.4677638113498688,
"eval_runtime": 845.5605,
"eval_samples_per_second": 1.223,
"step": 2560
},
{
"epoch": 854.58,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2564
},
{
"epoch": 855.88,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2568
},
{
"epoch": 857.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 2572
},
{
"epoch": 858.58,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2576
},
{
"epoch": 859.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2580
},
{
"epoch": 861.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2584
},
{
"epoch": 862.58,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2588
},
{
"epoch": 863.88,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2592
},
{
"epoch": 865.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2596
},
{
"epoch": 866.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2600
},
{
"epoch": 867.88,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2604
},
{
"epoch": 869.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2608
},
{
"epoch": 870.58,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2612
},
{
"epoch": 871.88,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2616
},
{
"epoch": 873.29,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2620
},
{
"epoch": 874.58,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2624
},
{
"epoch": 874.58,
"eval_exact_match": 0.7117988394584139,
"eval_exec": 0.695357833655706,
"eval_loss": 0.487076997756958,
"eval_runtime": 1063.4572,
"eval_samples_per_second": 0.972,
"step": 2624
}
],
"max_steps": 9216,
"num_train_epochs": 3072,
"total_flos": 1.20676205882696e+19,
"trial_name": null,
"trial_params": null
}