bat-table-aug / trainer_state.json
elena-soare's picture
Upload trainer_state.json
f8d9b8a
raw
history blame
33.8 kB
{
"best_metric": 0.558027079303675,
"best_model_checkpoint": "/train-table-aug/checkpoint-1088",
"epoch": 362.5857142857143,
"global_step": 1088,
"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": 3.5641,
"step": 1
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 3.1639,
"step": 4
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 2.1575,
"step": 8
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 1.5198,
"step": 12
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 1.3031,
"step": 16
},
{
"epoch": 6.59,
"learning_rate": 0.0001,
"loss": 0.981,
"step": 20
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.8521,
"step": 24
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 0.819,
"step": 28
},
{
"epoch": 10.59,
"learning_rate": 0.0001,
"loss": 0.6706,
"step": 32
},
{
"epoch": 11.88,
"learning_rate": 0.0001,
"loss": 0.6109,
"step": 36
},
{
"epoch": 13.29,
"learning_rate": 0.0001,
"loss": 0.6044,
"step": 40
},
{
"epoch": 14.59,
"learning_rate": 0.0001,
"loss": 0.5238,
"step": 44
},
{
"epoch": 15.88,
"learning_rate": 0.0001,
"loss": 0.4993,
"step": 48
},
{
"epoch": 17.29,
"learning_rate": 0.0001,
"loss": 0.5044,
"step": 52
},
{
"epoch": 18.59,
"learning_rate": 0.0001,
"loss": 0.431,
"step": 56
},
{
"epoch": 19.88,
"learning_rate": 0.0001,
"loss": 0.4087,
"step": 60
},
{
"epoch": 21.29,
"learning_rate": 0.0001,
"loss": 0.4225,
"step": 64
},
{
"epoch": 21.29,
"eval_exact_match": 0.17504835589941972,
"eval_exec": 0.20696324951644102,
"eval_loss": 0.31806543469429016,
"eval_runtime": 324.9476,
"eval_samples_per_second": 3.182,
"step": 64
},
{
"epoch": 22.59,
"learning_rate": 0.0001,
"loss": 0.3772,
"step": 68
},
{
"epoch": 23.88,
"learning_rate": 0.0001,
"loss": 0.3538,
"step": 72
},
{
"epoch": 25.29,
"learning_rate": 0.0001,
"loss": 0.3694,
"step": 76
},
{
"epoch": 26.59,
"learning_rate": 0.0001,
"loss": 0.3265,
"step": 80
},
{
"epoch": 27.88,
"learning_rate": 0.0001,
"loss": 0.3045,
"step": 84
},
{
"epoch": 29.29,
"learning_rate": 0.0001,
"loss": 0.3306,
"step": 88
},
{
"epoch": 30.59,
"learning_rate": 0.0001,
"loss": 0.284,
"step": 92
},
{
"epoch": 31.88,
"learning_rate": 0.0001,
"loss": 0.27,
"step": 96
},
{
"epoch": 33.29,
"learning_rate": 0.0001,
"loss": 0.2846,
"step": 100
},
{
"epoch": 34.59,
"learning_rate": 0.0001,
"loss": 0.2554,
"step": 104
},
{
"epoch": 35.88,
"learning_rate": 0.0001,
"loss": 0.2427,
"step": 108
},
{
"epoch": 37.29,
"learning_rate": 0.0001,
"loss": 0.2521,
"step": 112
},
{
"epoch": 38.59,
"learning_rate": 0.0001,
"loss": 0.2282,
"step": 116
},
{
"epoch": 39.88,
"learning_rate": 0.0001,
"loss": 0.226,
"step": 120
},
{
"epoch": 41.29,
"learning_rate": 0.0001,
"loss": 0.2359,
"step": 124
},
{
"epoch": 42.59,
"learning_rate": 0.0001,
"loss": 0.2041,
"step": 128
},
{
"epoch": 42.59,
"eval_exact_match": 0.36750483558994196,
"eval_exec": 0.40135396518375244,
"eval_loss": 0.22024403512477875,
"eval_runtime": 249.5685,
"eval_samples_per_second": 4.143,
"step": 128
},
{
"epoch": 43.88,
"learning_rate": 0.0001,
"loss": 0.1946,
"step": 132
},
{
"epoch": 45.29,
"learning_rate": 0.0001,
"loss": 0.2117,
"step": 136
},
{
"epoch": 46.59,
"learning_rate": 0.0001,
"loss": 0.1981,
"step": 140
},
{
"epoch": 47.88,
"learning_rate": 0.0001,
"loss": 0.1884,
"step": 144
},
{
"epoch": 49.29,
"learning_rate": 0.0001,
"loss": 0.1965,
"step": 148
},
{
"epoch": 50.59,
"learning_rate": 0.0001,
"loss": 0.1792,
"step": 152
},
{
"epoch": 51.88,
"learning_rate": 0.0001,
"loss": 0.1776,
"step": 156
},
{
"epoch": 53.29,
"learning_rate": 0.0001,
"loss": 0.1819,
"step": 160
},
{
"epoch": 54.59,
"learning_rate": 0.0001,
"loss": 0.1587,
"step": 164
},
{
"epoch": 55.88,
"learning_rate": 0.0001,
"loss": 0.1564,
"step": 168
},
{
"epoch": 57.29,
"learning_rate": 0.0001,
"loss": 0.1679,
"step": 172
},
{
"epoch": 58.59,
"learning_rate": 0.0001,
"loss": 0.154,
"step": 176
},
{
"epoch": 59.88,
"learning_rate": 0.0001,
"loss": 0.1488,
"step": 180
},
{
"epoch": 61.29,
"learning_rate": 0.0001,
"loss": 0.1562,
"step": 184
},
{
"epoch": 62.59,
"learning_rate": 0.0001,
"loss": 0.1465,
"step": 188
},
{
"epoch": 63.88,
"learning_rate": 0.0001,
"loss": 0.1367,
"step": 192
},
{
"epoch": 63.88,
"eval_exact_match": 0.42166344294003866,
"eval_exec": 0.45551257253384914,
"eval_loss": 0.20915372669696808,
"eval_runtime": 231.5673,
"eval_samples_per_second": 4.465,
"step": 192
},
{
"epoch": 65.29,
"learning_rate": 0.0001,
"loss": 0.1473,
"step": 196
},
{
"epoch": 66.59,
"learning_rate": 0.0001,
"loss": 0.1346,
"step": 200
},
{
"epoch": 67.88,
"learning_rate": 0.0001,
"loss": 0.1296,
"step": 204
},
{
"epoch": 69.29,
"learning_rate": 0.0001,
"loss": 0.1369,
"step": 208
},
{
"epoch": 70.59,
"learning_rate": 0.0001,
"loss": 0.1236,
"step": 212
},
{
"epoch": 71.88,
"learning_rate": 0.0001,
"loss": 0.1208,
"step": 216
},
{
"epoch": 73.29,
"learning_rate": 0.0001,
"loss": 0.1289,
"step": 220
},
{
"epoch": 74.59,
"learning_rate": 0.0001,
"loss": 0.1196,
"step": 224
},
{
"epoch": 75.88,
"learning_rate": 0.0001,
"loss": 0.1126,
"step": 228
},
{
"epoch": 77.29,
"learning_rate": 0.0001,
"loss": 0.1179,
"step": 232
},
{
"epoch": 78.59,
"learning_rate": 0.0001,
"loss": 0.1111,
"step": 236
},
{
"epoch": 79.88,
"learning_rate": 0.0001,
"loss": 0.1089,
"step": 240
},
{
"epoch": 81.29,
"learning_rate": 0.0001,
"loss": 0.1174,
"step": 244
},
{
"epoch": 82.59,
"learning_rate": 0.0001,
"loss": 0.1067,
"step": 248
},
{
"epoch": 83.88,
"learning_rate": 0.0001,
"loss": 0.1006,
"step": 252
},
{
"epoch": 85.29,
"learning_rate": 0.0001,
"loss": 0.106,
"step": 256
},
{
"epoch": 85.29,
"eval_exact_match": 0.42649903288201163,
"eval_exec": 0.4787234042553192,
"eval_loss": 0.21962527930736542,
"eval_runtime": 294.0508,
"eval_samples_per_second": 3.516,
"step": 256
},
{
"epoch": 86.59,
"learning_rate": 0.0001,
"loss": 0.0987,
"step": 260
},
{
"epoch": 87.88,
"learning_rate": 0.0001,
"loss": 0.097,
"step": 264
},
{
"epoch": 89.29,
"learning_rate": 0.0001,
"loss": 0.1015,
"step": 268
},
{
"epoch": 90.59,
"learning_rate": 0.0001,
"loss": 0.0922,
"step": 272
},
{
"epoch": 91.88,
"learning_rate": 0.0001,
"loss": 0.0875,
"step": 276
},
{
"epoch": 93.29,
"learning_rate": 0.0001,
"loss": 0.0956,
"step": 280
},
{
"epoch": 94.59,
"learning_rate": 0.0001,
"loss": 0.0871,
"step": 284
},
{
"epoch": 95.88,
"learning_rate": 0.0001,
"loss": 0.0833,
"step": 288
},
{
"epoch": 97.29,
"learning_rate": 0.0001,
"loss": 0.0917,
"step": 292
},
{
"epoch": 98.59,
"learning_rate": 0.0001,
"loss": 0.0843,
"step": 296
},
{
"epoch": 99.88,
"learning_rate": 0.0001,
"loss": 0.0833,
"step": 300
},
{
"epoch": 101.29,
"learning_rate": 0.0001,
"loss": 0.0884,
"step": 304
},
{
"epoch": 102.59,
"learning_rate": 0.0001,
"loss": 0.0779,
"step": 308
},
{
"epoch": 103.88,
"learning_rate": 0.0001,
"loss": 0.0757,
"step": 312
},
{
"epoch": 105.29,
"learning_rate": 0.0001,
"loss": 0.0819,
"step": 316
},
{
"epoch": 106.59,
"learning_rate": 0.0001,
"loss": 0.0734,
"step": 320
},
{
"epoch": 106.59,
"eval_exact_match": 0.4835589941972921,
"eval_exec": 0.5241779497098646,
"eval_loss": 0.233274906873703,
"eval_runtime": 239.6929,
"eval_samples_per_second": 4.314,
"step": 320
},
{
"epoch": 107.88,
"learning_rate": 0.0001,
"loss": 0.0717,
"step": 324
},
{
"epoch": 109.29,
"learning_rate": 0.0001,
"loss": 0.078,
"step": 328
},
{
"epoch": 110.59,
"learning_rate": 0.0001,
"loss": 0.0723,
"step": 332
},
{
"epoch": 111.88,
"learning_rate": 0.0001,
"loss": 0.0686,
"step": 336
},
{
"epoch": 113.29,
"learning_rate": 0.0001,
"loss": 0.0731,
"step": 340
},
{
"epoch": 114.59,
"learning_rate": 0.0001,
"loss": 0.0673,
"step": 344
},
{
"epoch": 115.88,
"learning_rate": 0.0001,
"loss": 0.0638,
"step": 348
},
{
"epoch": 117.29,
"learning_rate": 0.0001,
"loss": 0.0702,
"step": 352
},
{
"epoch": 118.59,
"learning_rate": 0.0001,
"loss": 0.0621,
"step": 356
},
{
"epoch": 119.88,
"learning_rate": 0.0001,
"loss": 0.0594,
"step": 360
},
{
"epoch": 121.29,
"learning_rate": 0.0001,
"loss": 0.0655,
"step": 364
},
{
"epoch": 122.59,
"learning_rate": 0.0001,
"loss": 0.0635,
"step": 368
},
{
"epoch": 123.88,
"learning_rate": 0.0001,
"loss": 0.0594,
"step": 372
},
{
"epoch": 125.29,
"learning_rate": 0.0001,
"loss": 0.0637,
"step": 376
},
{
"epoch": 126.59,
"learning_rate": 0.0001,
"loss": 0.0572,
"step": 380
},
{
"epoch": 127.88,
"learning_rate": 0.0001,
"loss": 0.0538,
"step": 384
},
{
"epoch": 127.88,
"eval_exact_match": 0.4990328820116054,
"eval_exec": 0.5425531914893617,
"eval_loss": 0.24243316054344177,
"eval_runtime": 230.8248,
"eval_samples_per_second": 4.48,
"step": 384
},
{
"epoch": 129.29,
"learning_rate": 0.0001,
"loss": 0.0522,
"step": 388
},
{
"epoch": 130.59,
"learning_rate": 0.0001,
"loss": 0.0513,
"step": 392
},
{
"epoch": 131.88,
"learning_rate": 0.0001,
"loss": 0.0556,
"step": 396
},
{
"epoch": 133.29,
"learning_rate": 0.0001,
"loss": 0.0574,
"step": 400
},
{
"epoch": 134.59,
"learning_rate": 0.0001,
"loss": 0.0519,
"step": 404
},
{
"epoch": 135.88,
"learning_rate": 0.0001,
"loss": 0.0517,
"step": 408
},
{
"epoch": 137.29,
"learning_rate": 0.0001,
"loss": 0.0537,
"step": 412
},
{
"epoch": 138.59,
"learning_rate": 0.0001,
"loss": 0.0515,
"step": 416
},
{
"epoch": 139.88,
"learning_rate": 0.0001,
"loss": 0.0516,
"step": 420
},
{
"epoch": 141.29,
"learning_rate": 0.0001,
"loss": 0.0507,
"step": 424
},
{
"epoch": 142.59,
"learning_rate": 0.0001,
"loss": 0.0452,
"step": 428
},
{
"epoch": 143.88,
"learning_rate": 0.0001,
"loss": 0.0458,
"step": 432
},
{
"epoch": 145.29,
"learning_rate": 0.0001,
"loss": 0.0487,
"step": 436
},
{
"epoch": 146.59,
"learning_rate": 0.0001,
"loss": 0.0469,
"step": 440
},
{
"epoch": 147.88,
"learning_rate": 0.0001,
"loss": 0.0444,
"step": 444
},
{
"epoch": 149.29,
"learning_rate": 0.0001,
"loss": 0.0468,
"step": 448
},
{
"epoch": 149.29,
"eval_exact_match": 0.511605415860735,
"eval_exec": 0.5367504835589942,
"eval_loss": 0.2615728974342346,
"eval_runtime": 272.7262,
"eval_samples_per_second": 3.791,
"step": 448
},
{
"epoch": 150.59,
"learning_rate": 0.0001,
"loss": 0.0436,
"step": 452
},
{
"epoch": 151.88,
"learning_rate": 0.0001,
"loss": 0.0472,
"step": 456
},
{
"epoch": 153.29,
"learning_rate": 0.0001,
"loss": 0.0452,
"step": 460
},
{
"epoch": 154.59,
"learning_rate": 0.0001,
"loss": 0.0395,
"step": 464
},
{
"epoch": 155.88,
"learning_rate": 0.0001,
"loss": 0.0388,
"step": 468
},
{
"epoch": 157.29,
"learning_rate": 0.0001,
"loss": 0.0442,
"step": 472
},
{
"epoch": 158.59,
"learning_rate": 0.0001,
"loss": 0.0415,
"step": 476
},
{
"epoch": 159.88,
"learning_rate": 0.0001,
"loss": 0.0385,
"step": 480
},
{
"epoch": 161.29,
"learning_rate": 0.0001,
"loss": 0.0398,
"step": 484
},
{
"epoch": 162.59,
"learning_rate": 0.0001,
"loss": 0.0348,
"step": 488
},
{
"epoch": 163.88,
"learning_rate": 0.0001,
"loss": 0.0359,
"step": 492
},
{
"epoch": 165.29,
"learning_rate": 0.0001,
"loss": 0.0388,
"step": 496
},
{
"epoch": 166.59,
"learning_rate": 0.0001,
"loss": 0.0335,
"step": 500
},
{
"epoch": 167.88,
"learning_rate": 0.0001,
"loss": 0.0343,
"step": 504
},
{
"epoch": 169.29,
"learning_rate": 0.0001,
"loss": 0.0362,
"step": 508
},
{
"epoch": 170.59,
"learning_rate": 0.0001,
"loss": 0.0361,
"step": 512
},
{
"epoch": 170.59,
"eval_exact_match": 0.5135396518375241,
"eval_exec": 0.5531914893617021,
"eval_loss": 0.2720741927623749,
"eval_runtime": 271.8234,
"eval_samples_per_second": 3.804,
"step": 512
},
{
"epoch": 171.88,
"learning_rate": 0.0001,
"loss": 0.034,
"step": 516
},
{
"epoch": 173.29,
"learning_rate": 0.0001,
"loss": 0.0364,
"step": 520
},
{
"epoch": 174.59,
"learning_rate": 0.0001,
"loss": 0.0316,
"step": 524
},
{
"epoch": 175.88,
"learning_rate": 0.0001,
"loss": 0.0293,
"step": 528
},
{
"epoch": 177.29,
"learning_rate": 0.0001,
"loss": 0.0319,
"step": 532
},
{
"epoch": 178.59,
"learning_rate": 0.0001,
"loss": 0.0298,
"step": 536
},
{
"epoch": 179.88,
"learning_rate": 0.0001,
"loss": 0.0314,
"step": 540
},
{
"epoch": 181.29,
"learning_rate": 0.0001,
"loss": 0.0324,
"step": 544
},
{
"epoch": 182.59,
"learning_rate": 0.0001,
"loss": 0.028,
"step": 548
},
{
"epoch": 183.88,
"learning_rate": 0.0001,
"loss": 0.0281,
"step": 552
},
{
"epoch": 185.29,
"learning_rate": 0.0001,
"loss": 0.0319,
"step": 556
},
{
"epoch": 186.59,
"learning_rate": 0.0001,
"loss": 0.0274,
"step": 560
},
{
"epoch": 187.88,
"learning_rate": 0.0001,
"loss": 0.0257,
"step": 564
},
{
"epoch": 189.29,
"learning_rate": 0.0001,
"loss": 0.028,
"step": 568
},
{
"epoch": 190.59,
"learning_rate": 0.0001,
"loss": 0.026,
"step": 572
},
{
"epoch": 191.88,
"learning_rate": 0.0001,
"loss": 0.0256,
"step": 576
},
{
"epoch": 191.88,
"eval_exact_match": 0.5367504835589942,
"eval_exec": 0.5618955512572534,
"eval_loss": 0.29810672998428345,
"eval_runtime": 249.3915,
"eval_samples_per_second": 4.146,
"step": 576
},
{
"epoch": 193.29,
"learning_rate": 0.0001,
"loss": 0.0285,
"step": 580
},
{
"epoch": 194.59,
"learning_rate": 0.0001,
"loss": 0.0256,
"step": 584
},
{
"epoch": 195.88,
"learning_rate": 0.0001,
"loss": 0.0259,
"step": 588
},
{
"epoch": 197.29,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 592
},
{
"epoch": 198.59,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 596
},
{
"epoch": 199.88,
"learning_rate": 0.0001,
"loss": 0.0244,
"step": 600
},
{
"epoch": 201.29,
"learning_rate": 0.0001,
"loss": 0.0255,
"step": 604
},
{
"epoch": 202.59,
"learning_rate": 0.0001,
"loss": 0.0241,
"step": 608
},
{
"epoch": 203.88,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 612
},
{
"epoch": 205.29,
"learning_rate": 0.0001,
"loss": 0.0237,
"step": 616
},
{
"epoch": 206.59,
"learning_rate": 0.0001,
"loss": 0.0213,
"step": 620
},
{
"epoch": 207.88,
"learning_rate": 0.0001,
"loss": 0.0215,
"step": 624
},
{
"epoch": 209.29,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 628
},
{
"epoch": 210.59,
"learning_rate": 0.0001,
"loss": 0.0198,
"step": 632
},
{
"epoch": 211.88,
"learning_rate": 0.0001,
"loss": 0.0205,
"step": 636
},
{
"epoch": 213.29,
"learning_rate": 0.0001,
"loss": 0.0221,
"step": 640
},
{
"epoch": 213.29,
"eval_exact_match": 0.5377176015473888,
"eval_exec": 0.5531914893617021,
"eval_loss": 0.3198956549167633,
"eval_runtime": 263.4395,
"eval_samples_per_second": 3.925,
"step": 640
},
{
"epoch": 214.59,
"learning_rate": 0.0001,
"loss": 0.02,
"step": 644
},
{
"epoch": 215.88,
"learning_rate": 0.0001,
"loss": 0.0194,
"step": 648
},
{
"epoch": 217.29,
"learning_rate": 0.0001,
"loss": 0.0201,
"step": 652
},
{
"epoch": 218.59,
"learning_rate": 0.0001,
"loss": 0.0178,
"step": 656
},
{
"epoch": 219.88,
"learning_rate": 0.0001,
"loss": 0.0183,
"step": 660
},
{
"epoch": 221.29,
"learning_rate": 0.0001,
"loss": 0.0187,
"step": 664
},
{
"epoch": 222.59,
"learning_rate": 0.0001,
"loss": 0.018,
"step": 668
},
{
"epoch": 223.88,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 672
},
{
"epoch": 225.29,
"learning_rate": 0.0001,
"loss": 0.0181,
"step": 676
},
{
"epoch": 226.59,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 680
},
{
"epoch": 227.88,
"learning_rate": 0.0001,
"loss": 0.019,
"step": 684
},
{
"epoch": 229.29,
"learning_rate": 0.0001,
"loss": 0.0211,
"step": 688
},
{
"epoch": 230.59,
"learning_rate": 0.0001,
"loss": 0.0169,
"step": 692
},
{
"epoch": 231.88,
"learning_rate": 0.0001,
"loss": 0.0157,
"step": 696
},
{
"epoch": 233.29,
"learning_rate": 0.0001,
"loss": 0.0173,
"step": 700
},
{
"epoch": 234.59,
"learning_rate": 0.0001,
"loss": 0.0161,
"step": 704
},
{
"epoch": 234.59,
"eval_exact_match": 0.5406189555125726,
"eval_exec": 0.5657640232108317,
"eval_loss": 0.3268744647502899,
"eval_runtime": 253.8947,
"eval_samples_per_second": 4.073,
"step": 704
},
{
"epoch": 235.88,
"learning_rate": 0.0001,
"loss": 0.0155,
"step": 708
},
{
"epoch": 237.29,
"learning_rate": 0.0001,
"loss": 0.0161,
"step": 712
},
{
"epoch": 238.59,
"learning_rate": 0.0001,
"loss": 0.0142,
"step": 716
},
{
"epoch": 239.88,
"learning_rate": 0.0001,
"loss": 0.0154,
"step": 720
},
{
"epoch": 241.29,
"learning_rate": 0.0001,
"loss": 0.0204,
"step": 724
},
{
"epoch": 242.59,
"learning_rate": 0.0001,
"loss": 0.0147,
"step": 728
},
{
"epoch": 243.88,
"learning_rate": 0.0001,
"loss": 0.0135,
"step": 732
},
{
"epoch": 245.29,
"learning_rate": 0.0001,
"loss": 0.0143,
"step": 736
},
{
"epoch": 246.59,
"learning_rate": 0.0001,
"loss": 0.0131,
"step": 740
},
{
"epoch": 247.88,
"learning_rate": 0.0001,
"loss": 0.0132,
"step": 744
},
{
"epoch": 249.29,
"learning_rate": 0.0001,
"loss": 0.0146,
"step": 748
},
{
"epoch": 250.59,
"learning_rate": 0.0001,
"loss": 0.0126,
"step": 752
},
{
"epoch": 251.88,
"learning_rate": 0.0001,
"loss": 0.0122,
"step": 756
},
{
"epoch": 253.29,
"learning_rate": 0.0001,
"loss": 0.0134,
"step": 760
},
{
"epoch": 254.59,
"learning_rate": 0.0001,
"loss": 0.0123,
"step": 764
},
{
"epoch": 255.88,
"learning_rate": 0.0001,
"loss": 0.0117,
"step": 768
},
{
"epoch": 255.88,
"eval_exact_match": 0.539651837524178,
"eval_exec": 0.5647969052224371,
"eval_loss": 0.35621145367622375,
"eval_runtime": 254.8385,
"eval_samples_per_second": 4.057,
"step": 768
},
{
"epoch": 257.29,
"learning_rate": 0.0001,
"loss": 0.0132,
"step": 772
},
{
"epoch": 258.59,
"learning_rate": 0.0001,
"loss": 0.0113,
"step": 776
},
{
"epoch": 259.88,
"learning_rate": 0.0001,
"loss": 0.0162,
"step": 780
},
{
"epoch": 261.29,
"learning_rate": 0.0001,
"loss": 0.0145,
"step": 784
},
{
"epoch": 262.59,
"learning_rate": 0.0001,
"loss": 0.0109,
"step": 788
},
{
"epoch": 263.88,
"learning_rate": 0.0001,
"loss": 0.0108,
"step": 792
},
{
"epoch": 265.29,
"learning_rate": 0.0001,
"loss": 0.012,
"step": 796
},
{
"epoch": 266.59,
"learning_rate": 0.0001,
"loss": 0.0127,
"step": 800
},
{
"epoch": 267.88,
"learning_rate": 0.0001,
"loss": 0.0141,
"step": 804
},
{
"epoch": 269.29,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 808
},
{
"epoch": 270.59,
"learning_rate": 0.0001,
"loss": 0.0104,
"step": 812
},
{
"epoch": 271.88,
"learning_rate": 0.0001,
"loss": 0.0118,
"step": 816
},
{
"epoch": 273.29,
"learning_rate": 0.0001,
"loss": 0.0107,
"step": 820
},
{
"epoch": 274.59,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 824
},
{
"epoch": 275.88,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 828
},
{
"epoch": 277.29,
"learning_rate": 0.0001,
"loss": 0.0101,
"step": 832
},
{
"epoch": 277.29,
"eval_exact_match": 0.539651837524178,
"eval_exec": 0.562862669245648,
"eval_loss": 0.36498865485191345,
"eval_runtime": 267.4044,
"eval_samples_per_second": 3.867,
"step": 832
},
{
"epoch": 278.59,
"learning_rate": 0.0001,
"loss": 0.009,
"step": 836
},
{
"epoch": 279.88,
"learning_rate": 0.0001,
"loss": 0.0091,
"step": 840
},
{
"epoch": 281.29,
"learning_rate": 0.0001,
"loss": 0.0101,
"step": 844
},
{
"epoch": 282.59,
"learning_rate": 0.0001,
"loss": 0.0088,
"step": 848
},
{
"epoch": 283.88,
"learning_rate": 0.0001,
"loss": 0.009,
"step": 852
},
{
"epoch": 285.29,
"learning_rate": 0.0001,
"loss": 0.0099,
"step": 856
},
{
"epoch": 286.59,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 860
},
{
"epoch": 287.88,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 864
},
{
"epoch": 289.29,
"learning_rate": 0.0001,
"loss": 0.0093,
"step": 868
},
{
"epoch": 290.59,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 872
},
{
"epoch": 291.88,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 876
},
{
"epoch": 293.29,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 880
},
{
"epoch": 294.59,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 884
},
{
"epoch": 295.88,
"learning_rate": 0.0001,
"loss": 0.0082,
"step": 888
},
{
"epoch": 297.29,
"learning_rate": 0.0001,
"loss": 0.0092,
"step": 892
},
{
"epoch": 298.59,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 896
},
{
"epoch": 298.59,
"eval_exact_match": 0.5270793036750484,
"eval_exec": 0.5676982591876208,
"eval_loss": 0.3560219705104828,
"eval_runtime": 285.5101,
"eval_samples_per_second": 3.622,
"step": 896
},
{
"epoch": 299.88,
"learning_rate": 0.0001,
"loss": 0.0083,
"step": 900
},
{
"epoch": 301.29,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 904
},
{
"epoch": 302.59,
"learning_rate": 0.0001,
"loss": 0.0076,
"step": 908
},
{
"epoch": 303.88,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 912
},
{
"epoch": 305.29,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 916
},
{
"epoch": 306.59,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 920
},
{
"epoch": 307.88,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 924
},
{
"epoch": 309.29,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 928
},
{
"epoch": 310.59,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 932
},
{
"epoch": 311.88,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 936
},
{
"epoch": 313.29,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 940
},
{
"epoch": 314.59,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 944
},
{
"epoch": 315.88,
"learning_rate": 0.0001,
"loss": 0.0067,
"step": 948
},
{
"epoch": 317.29,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 952
},
{
"epoch": 318.59,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 956
},
{
"epoch": 319.88,
"learning_rate": 0.0001,
"loss": 0.0067,
"step": 960
},
{
"epoch": 319.88,
"eval_exact_match": 0.5473887814313346,
"eval_exec": 0.5735009671179884,
"eval_loss": 0.389277845621109,
"eval_runtime": 259.1605,
"eval_samples_per_second": 3.99,
"step": 960
},
{
"epoch": 321.29,
"learning_rate": 0.0001,
"loss": 0.0071,
"step": 964
},
{
"epoch": 322.59,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 968
},
{
"epoch": 323.88,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 972
},
{
"epoch": 325.29,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 976
},
{
"epoch": 326.59,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 980
},
{
"epoch": 327.88,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 984
},
{
"epoch": 329.29,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 988
},
{
"epoch": 330.59,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 992
},
{
"epoch": 331.88,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 996
},
{
"epoch": 333.29,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 1000
},
{
"epoch": 334.59,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 1004
},
{
"epoch": 335.88,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 1008
},
{
"epoch": 337.29,
"learning_rate": 0.0001,
"loss": 0.0057,
"step": 1012
},
{
"epoch": 338.59,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 1016
},
{
"epoch": 339.88,
"learning_rate": 0.0001,
"loss": 0.0056,
"step": 1020
},
{
"epoch": 341.29,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 1024
},
{
"epoch": 341.29,
"eval_exact_match": 0.5483558994197292,
"eval_exec": 0.5667311411992263,
"eval_loss": 0.3951364755630493,
"eval_runtime": 254.3286,
"eval_samples_per_second": 4.066,
"step": 1024
},
{
"epoch": 342.59,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 1028
},
{
"epoch": 343.88,
"learning_rate": 0.0001,
"loss": 0.0057,
"step": 1032
},
{
"epoch": 345.29,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 1036
},
{
"epoch": 346.59,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 1040
},
{
"epoch": 347.88,
"learning_rate": 0.0001,
"loss": 0.0053,
"step": 1044
},
{
"epoch": 349.29,
"learning_rate": 0.0001,
"loss": 0.0056,
"step": 1048
},
{
"epoch": 350.59,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1052
},
{
"epoch": 351.88,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1056
},
{
"epoch": 353.29,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1060
},
{
"epoch": 354.59,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1064
},
{
"epoch": 355.88,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1068
},
{
"epoch": 357.29,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1072
},
{
"epoch": 358.59,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 1076
},
{
"epoch": 359.88,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1080
},
{
"epoch": 361.29,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1084
},
{
"epoch": 362.59,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1088
},
{
"epoch": 362.59,
"eval_exact_match": 0.558027079303675,
"eval_exec": 0.5822050290135397,
"eval_loss": 0.40082696080207825,
"eval_runtime": 260.2738,
"eval_samples_per_second": 3.973,
"step": 1088
}
],
"max_steps": 9216,
"num_train_epochs": 3072,
"total_flos": 1.945310283417047e+18,
"trial_name": null,
"trial_params": null
}