bat-pre-trained / trainer_state.json
elena-soare's picture
Upload trainer_state.json
a39bbcf
{
"best_metric": 0.5241779497098646,
"best_model_checkpoint": "/content/drive/MyDrive/datasaur/train-properly/checkpoint-2112",
"epoch": 703.8785714285714,
"global_step": 2112,
"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": 4.6233,
"step": 1
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 3.6654,
"step": 4
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 2.3799,
"step": 8
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 1.7143,
"step": 12
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 1.4283,
"step": 16
},
{
"epoch": 6.59,
"learning_rate": 0.0001,
"loss": 1.0806,
"step": 20
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.9319,
"step": 24
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 0.8745,
"step": 28
},
{
"epoch": 10.59,
"learning_rate": 0.0001,
"loss": 0.7126,
"step": 32
},
{
"epoch": 11.88,
"learning_rate": 0.0001,
"loss": 0.655,
"step": 36
},
{
"epoch": 13.29,
"learning_rate": 0.0001,
"loss": 0.6493,
"step": 40
},
{
"epoch": 14.59,
"learning_rate": 0.0001,
"loss": 0.5586,
"step": 44
},
{
"epoch": 15.88,
"learning_rate": 0.0001,
"loss": 0.5208,
"step": 48
},
{
"epoch": 17.29,
"learning_rate": 0.0001,
"loss": 0.5401,
"step": 52
},
{
"epoch": 18.59,
"learning_rate": 0.0001,
"loss": 0.4716,
"step": 56
},
{
"epoch": 19.88,
"learning_rate": 0.0001,
"loss": 0.4334,
"step": 60
},
{
"epoch": 21.29,
"learning_rate": 0.0001,
"loss": 0.4422,
"step": 64
},
{
"epoch": 21.29,
"eval_exact_match": 0.22920696324951645,
"eval_exec": 0.2572533849129594,
"eval_loss": 0.33955129981040955,
"eval_runtime": 122.338,
"eval_samples_per_second": 8.452,
"step": 64
},
{
"epoch": 22.59,
"learning_rate": 0.0001,
"loss": 0.3947,
"step": 68
},
{
"epoch": 23.88,
"learning_rate": 0.0001,
"loss": 0.3672,
"step": 72
},
{
"epoch": 25.29,
"learning_rate": 0.0001,
"loss": 0.3774,
"step": 76
},
{
"epoch": 26.59,
"learning_rate": 0.0001,
"loss": 0.3324,
"step": 80
},
{
"epoch": 27.88,
"learning_rate": 0.0001,
"loss": 0.3089,
"step": 84
},
{
"epoch": 29.29,
"learning_rate": 0.0001,
"loss": 0.3263,
"step": 88
},
{
"epoch": 30.59,
"learning_rate": 0.0001,
"loss": 0.2813,
"step": 92
},
{
"epoch": 31.88,
"learning_rate": 0.0001,
"loss": 0.2779,
"step": 96
},
{
"epoch": 33.29,
"learning_rate": 0.0001,
"loss": 0.2944,
"step": 100
},
{
"epoch": 34.59,
"learning_rate": 0.0001,
"loss": 0.2548,
"step": 104
},
{
"epoch": 35.88,
"learning_rate": 0.0001,
"loss": 0.2419,
"step": 108
},
{
"epoch": 37.29,
"learning_rate": 0.0001,
"loss": 0.256,
"step": 112
},
{
"epoch": 38.59,
"learning_rate": 0.0001,
"loss": 0.2346,
"step": 116
},
{
"epoch": 39.88,
"learning_rate": 0.0001,
"loss": 0.2312,
"step": 120
},
{
"epoch": 41.29,
"learning_rate": 0.0001,
"loss": 0.2395,
"step": 124
},
{
"epoch": 42.59,
"learning_rate": 0.0001,
"loss": 0.2143,
"step": 128
},
{
"epoch": 42.59,
"eval_exact_match": 0.3065764023210832,
"eval_exec": 0.3413926499032882,
"eval_loss": 0.25483238697052,
"eval_runtime": 153.8574,
"eval_samples_per_second": 6.721,
"step": 128
},
{
"epoch": 43.88,
"learning_rate": 0.0001,
"loss": 0.2018,
"step": 132
},
{
"epoch": 45.29,
"learning_rate": 0.0001,
"loss": 0.2105,
"step": 136
},
{
"epoch": 46.59,
"learning_rate": 0.0001,
"loss": 0.1906,
"step": 140
},
{
"epoch": 47.88,
"learning_rate": 0.0001,
"loss": 0.1876,
"step": 144
},
{
"epoch": 49.29,
"learning_rate": 0.0001,
"loss": 0.1949,
"step": 148
},
{
"epoch": 50.59,
"learning_rate": 0.0001,
"loss": 0.1777,
"step": 152
},
{
"epoch": 51.88,
"learning_rate": 0.0001,
"loss": 0.1672,
"step": 156
},
{
"epoch": 53.29,
"learning_rate": 0.0001,
"loss": 0.178,
"step": 160
},
{
"epoch": 54.59,
"learning_rate": 0.0001,
"loss": 0.1597,
"step": 164
},
{
"epoch": 55.88,
"learning_rate": 0.0001,
"loss": 0.157,
"step": 168
},
{
"epoch": 57.29,
"learning_rate": 0.0001,
"loss": 0.1681,
"step": 172
},
{
"epoch": 58.59,
"learning_rate": 0.0001,
"loss": 0.1467,
"step": 176
},
{
"epoch": 59.88,
"learning_rate": 0.0001,
"loss": 0.1472,
"step": 180
},
{
"epoch": 61.29,
"learning_rate": 0.0001,
"loss": 0.1579,
"step": 184
},
{
"epoch": 62.59,
"learning_rate": 0.0001,
"loss": 0.1413,
"step": 188
},
{
"epoch": 63.88,
"learning_rate": 0.0001,
"loss": 0.1334,
"step": 192
},
{
"epoch": 63.88,
"eval_exact_match": 0.3646034816247582,
"eval_exec": 0.390715667311412,
"eval_loss": 0.23727674782276154,
"eval_runtime": 164.2118,
"eval_samples_per_second": 6.297,
"step": 192
},
{
"epoch": 65.29,
"learning_rate": 0.0001,
"loss": 0.1412,
"step": 196
},
{
"epoch": 66.59,
"learning_rate": 0.0001,
"loss": 0.1256,
"step": 200
},
{
"epoch": 67.88,
"learning_rate": 0.0001,
"loss": 0.1243,
"step": 204
},
{
"epoch": 69.29,
"learning_rate": 0.0001,
"loss": 0.1325,
"step": 208
},
{
"epoch": 70.59,
"learning_rate": 0.0001,
"loss": 0.1194,
"step": 212
},
{
"epoch": 71.88,
"learning_rate": 0.0001,
"loss": 0.1159,
"step": 216
},
{
"epoch": 73.29,
"learning_rate": 0.0001,
"loss": 0.1242,
"step": 220
},
{
"epoch": 74.59,
"learning_rate": 0.0001,
"loss": 0.1106,
"step": 224
},
{
"epoch": 75.88,
"learning_rate": 0.0001,
"loss": 0.1104,
"step": 228
},
{
"epoch": 77.29,
"learning_rate": 0.0001,
"loss": 0.1121,
"step": 232
},
{
"epoch": 78.59,
"learning_rate": 0.0001,
"loss": 0.1021,
"step": 236
},
{
"epoch": 79.88,
"learning_rate": 0.0001,
"loss": 0.1021,
"step": 240
},
{
"epoch": 81.29,
"learning_rate": 0.0001,
"loss": 0.11,
"step": 244
},
{
"epoch": 82.59,
"learning_rate": 0.0001,
"loss": 0.0998,
"step": 248
},
{
"epoch": 83.88,
"learning_rate": 0.0001,
"loss": 0.0933,
"step": 252
},
{
"epoch": 85.29,
"learning_rate": 0.0001,
"loss": 0.0998,
"step": 256
},
{
"epoch": 85.29,
"eval_exact_match": 0.36847195357833656,
"eval_exec": 0.38684719535783363,
"eval_loss": 0.24835824966430664,
"eval_runtime": 185.4895,
"eval_samples_per_second": 5.574,
"step": 256
},
{
"epoch": 86.59,
"learning_rate": 0.0001,
"loss": 0.0915,
"step": 260
},
{
"epoch": 87.88,
"learning_rate": 0.0001,
"loss": 0.0887,
"step": 264
},
{
"epoch": 89.29,
"learning_rate": 0.0001,
"loss": 0.0946,
"step": 268
},
{
"epoch": 90.59,
"learning_rate": 0.0001,
"loss": 0.0866,
"step": 272
},
{
"epoch": 91.88,
"learning_rate": 0.0001,
"loss": 0.0816,
"step": 276
},
{
"epoch": 93.29,
"learning_rate": 0.0001,
"loss": 0.0875,
"step": 280
},
{
"epoch": 94.59,
"learning_rate": 0.0001,
"loss": 0.0782,
"step": 284
},
{
"epoch": 95.88,
"learning_rate": 0.0001,
"loss": 0.0789,
"step": 288
},
{
"epoch": 97.29,
"learning_rate": 0.0001,
"loss": 0.0841,
"step": 292
},
{
"epoch": 98.59,
"learning_rate": 0.0001,
"loss": 0.0754,
"step": 296
},
{
"epoch": 99.88,
"learning_rate": 0.0001,
"loss": 0.0732,
"step": 300
},
{
"epoch": 101.29,
"learning_rate": 0.0001,
"loss": 0.0757,
"step": 304
},
{
"epoch": 102.59,
"learning_rate": 0.0001,
"loss": 0.0685,
"step": 308
},
{
"epoch": 103.88,
"learning_rate": 0.0001,
"loss": 0.0665,
"step": 312
},
{
"epoch": 105.29,
"learning_rate": 0.0001,
"loss": 0.0735,
"step": 316
},
{
"epoch": 106.59,
"learning_rate": 0.0001,
"loss": 0.0686,
"step": 320
},
{
"epoch": 106.59,
"eval_exact_match": 0.3945841392649903,
"eval_exec": 0.43423597678916825,
"eval_loss": 0.25631850957870483,
"eval_runtime": 177.6509,
"eval_samples_per_second": 5.82,
"step": 320
},
{
"epoch": 107.88,
"learning_rate": 0.0001,
"loss": 0.0653,
"step": 324
},
{
"epoch": 109.29,
"learning_rate": 0.0001,
"loss": 0.0685,
"step": 328
},
{
"epoch": 110.59,
"learning_rate": 0.0001,
"loss": 0.0607,
"step": 332
},
{
"epoch": 111.88,
"learning_rate": 0.0001,
"loss": 0.0604,
"step": 336
},
{
"epoch": 113.29,
"learning_rate": 0.0001,
"loss": 0.0634,
"step": 340
},
{
"epoch": 114.59,
"learning_rate": 0.0001,
"loss": 0.0568,
"step": 344
},
{
"epoch": 115.88,
"learning_rate": 0.0001,
"loss": 0.0563,
"step": 348
},
{
"epoch": 117.29,
"learning_rate": 0.0001,
"loss": 0.0596,
"step": 352
},
{
"epoch": 118.59,
"learning_rate": 0.0001,
"loss": 0.0562,
"step": 356
},
{
"epoch": 119.88,
"learning_rate": 0.0001,
"loss": 0.0584,
"step": 360
},
{
"epoch": 121.29,
"learning_rate": 0.0001,
"loss": 0.0579,
"step": 364
},
{
"epoch": 122.59,
"learning_rate": 0.0001,
"loss": 0.0525,
"step": 368
},
{
"epoch": 123.88,
"learning_rate": 0.0001,
"loss": 0.0504,
"step": 372
},
{
"epoch": 125.29,
"learning_rate": 0.0001,
"loss": 0.0541,
"step": 376
},
{
"epoch": 126.59,
"learning_rate": 0.0001,
"loss": 0.0475,
"step": 380
},
{
"epoch": 127.88,
"learning_rate": 0.0001,
"loss": 0.0469,
"step": 384
},
{
"epoch": 127.88,
"eval_exact_match": 0.4796905222437137,
"eval_exec": 0.5019342359767892,
"eval_loss": 0.27194276452064514,
"eval_runtime": 142.4018,
"eval_samples_per_second": 7.261,
"step": 384
},
{
"epoch": 129.29,
"learning_rate": 0.0001,
"loss": 0.0513,
"step": 388
},
{
"epoch": 130.59,
"learning_rate": 0.0001,
"loss": 0.0477,
"step": 392
},
{
"epoch": 131.88,
"learning_rate": 0.0001,
"loss": 0.0443,
"step": 396
},
{
"epoch": 133.29,
"learning_rate": 0.0001,
"loss": 0.047,
"step": 400
},
{
"epoch": 134.59,
"learning_rate": 0.0001,
"loss": 0.0424,
"step": 404
},
{
"epoch": 135.88,
"learning_rate": 0.0001,
"loss": 0.0425,
"step": 408
},
{
"epoch": 137.29,
"learning_rate": 0.0001,
"loss": 0.0474,
"step": 412
},
{
"epoch": 138.59,
"learning_rate": 0.0001,
"loss": 0.0446,
"step": 416
},
{
"epoch": 139.88,
"learning_rate": 0.0001,
"loss": 0.0409,
"step": 420
},
{
"epoch": 141.29,
"learning_rate": 0.0001,
"loss": 0.0416,
"step": 424
},
{
"epoch": 142.59,
"learning_rate": 0.0001,
"loss": 0.0375,
"step": 428
},
{
"epoch": 143.88,
"learning_rate": 0.0001,
"loss": 0.0377,
"step": 432
},
{
"epoch": 145.29,
"learning_rate": 0.0001,
"loss": 0.0398,
"step": 436
},
{
"epoch": 146.59,
"learning_rate": 0.0001,
"loss": 0.0383,
"step": 440
},
{
"epoch": 147.88,
"learning_rate": 0.0001,
"loss": 0.0344,
"step": 444
},
{
"epoch": 149.29,
"learning_rate": 0.0001,
"loss": 0.0372,
"step": 448
},
{
"epoch": 149.29,
"eval_exact_match": 0.47775628626692457,
"eval_exec": 0.5009671179883946,
"eval_loss": 0.29459667205810547,
"eval_runtime": 133.4155,
"eval_samples_per_second": 7.75,
"step": 448
},
{
"epoch": 150.59,
"learning_rate": 0.0001,
"loss": 0.034,
"step": 452
},
{
"epoch": 151.88,
"learning_rate": 0.0001,
"loss": 0.0345,
"step": 456
},
{
"epoch": 153.29,
"learning_rate": 0.0001,
"loss": 0.0394,
"step": 460
},
{
"epoch": 154.59,
"learning_rate": 0.0001,
"loss": 0.0348,
"step": 464
},
{
"epoch": 155.88,
"learning_rate": 0.0001,
"loss": 0.0316,
"step": 468
},
{
"epoch": 157.29,
"learning_rate": 0.0001,
"loss": 0.0361,
"step": 472
},
{
"epoch": 158.59,
"learning_rate": 0.0001,
"loss": 0.034,
"step": 476
},
{
"epoch": 159.88,
"learning_rate": 0.0001,
"loss": 0.0308,
"step": 480
},
{
"epoch": 161.29,
"learning_rate": 0.0001,
"loss": 0.0316,
"step": 484
},
{
"epoch": 162.59,
"learning_rate": 0.0001,
"loss": 0.0282,
"step": 488
},
{
"epoch": 163.88,
"learning_rate": 0.0001,
"loss": 0.0282,
"step": 492
},
{
"epoch": 165.29,
"learning_rate": 0.0001,
"loss": 0.0303,
"step": 496
},
{
"epoch": 166.59,
"learning_rate": 0.0001,
"loss": 0.0287,
"step": 500
},
{
"epoch": 167.88,
"learning_rate": 0.0001,
"loss": 0.0271,
"step": 504
},
{
"epoch": 169.29,
"learning_rate": 0.0001,
"loss": 0.0289,
"step": 508
},
{
"epoch": 170.59,
"learning_rate": 0.0001,
"loss": 0.028,
"step": 512
},
{
"epoch": 170.59,
"eval_exact_match": 0.4738878143133462,
"eval_exec": 0.49709864603481624,
"eval_loss": 0.30677586793899536,
"eval_runtime": 151.116,
"eval_samples_per_second": 6.842,
"step": 512
},
{
"epoch": 171.88,
"learning_rate": 0.0001,
"loss": 0.0295,
"step": 516
},
{
"epoch": 173.29,
"learning_rate": 0.0001,
"loss": 0.0277,
"step": 520
},
{
"epoch": 174.59,
"learning_rate": 0.0001,
"loss": 0.0243,
"step": 524
},
{
"epoch": 175.88,
"learning_rate": 0.0001,
"loss": 0.0241,
"step": 528
},
{
"epoch": 177.29,
"learning_rate": 0.0001,
"loss": 0.0272,
"step": 532
},
{
"epoch": 178.59,
"learning_rate": 0.0001,
"loss": 0.0247,
"step": 536
},
{
"epoch": 179.88,
"learning_rate": 0.0001,
"loss": 0.0238,
"step": 540
},
{
"epoch": 181.29,
"learning_rate": 0.0001,
"loss": 0.0247,
"step": 544
},
{
"epoch": 182.59,
"learning_rate": 0.0001,
"loss": 0.0222,
"step": 548
},
{
"epoch": 183.88,
"learning_rate": 0.0001,
"loss": 0.0224,
"step": 552
},
{
"epoch": 185.29,
"learning_rate": 0.0001,
"loss": 0.024,
"step": 556
},
{
"epoch": 186.59,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 560
},
{
"epoch": 187.88,
"learning_rate": 0.0001,
"loss": 0.0241,
"step": 564
},
{
"epoch": 189.29,
"learning_rate": 0.0001,
"loss": 0.024,
"step": 568
},
{
"epoch": 190.59,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 572
},
{
"epoch": 191.88,
"learning_rate": 0.0001,
"loss": 0.0197,
"step": 576
},
{
"epoch": 191.88,
"eval_exact_match": 0.47775628626692457,
"eval_exec": 0.5009671179883946,
"eval_loss": 0.3227923512458801,
"eval_runtime": 165.1002,
"eval_samples_per_second": 6.263,
"step": 576
},
{
"epoch": 193.29,
"learning_rate": 0.0001,
"loss": 0.0205,
"step": 580
},
{
"epoch": 194.59,
"learning_rate": 0.0001,
"loss": 0.0192,
"step": 584
},
{
"epoch": 195.88,
"learning_rate": 0.0001,
"loss": 0.0187,
"step": 588
},
{
"epoch": 197.29,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 592
},
{
"epoch": 198.59,
"learning_rate": 0.0001,
"loss": 0.0181,
"step": 596
},
{
"epoch": 199.88,
"learning_rate": 0.0001,
"loss": 0.018,
"step": 600
},
{
"epoch": 201.29,
"learning_rate": 0.0001,
"loss": 0.0193,
"step": 604
},
{
"epoch": 202.59,
"learning_rate": 0.0001,
"loss": 0.0173,
"step": 608
},
{
"epoch": 203.88,
"learning_rate": 0.0001,
"loss": 0.0176,
"step": 612
},
{
"epoch": 205.29,
"learning_rate": 0.0001,
"loss": 0.0186,
"step": 616
},
{
"epoch": 206.59,
"learning_rate": 0.0001,
"loss": 0.0195,
"step": 620
},
{
"epoch": 207.88,
"learning_rate": 0.0001,
"loss": 0.0174,
"step": 624
},
{
"epoch": 209.29,
"learning_rate": 0.0001,
"loss": 0.0174,
"step": 628
},
{
"epoch": 210.59,
"learning_rate": 0.0001,
"loss": 0.0163,
"step": 632
},
{
"epoch": 211.88,
"learning_rate": 0.0001,
"loss": 0.0162,
"step": 636
},
{
"epoch": 213.29,
"learning_rate": 0.0001,
"loss": 0.0175,
"step": 640
},
{
"epoch": 213.29,
"eval_exact_match": 0.4661508704061896,
"eval_exec": 0.48452611218568664,
"eval_loss": 0.33815476298332214,
"eval_runtime": 159.4098,
"eval_samples_per_second": 6.486,
"step": 640
},
{
"epoch": 214.59,
"learning_rate": 0.0001,
"loss": 0.0157,
"step": 644
},
{
"epoch": 215.88,
"learning_rate": 0.0001,
"loss": 0.015,
"step": 648
},
{
"epoch": 217.29,
"learning_rate": 0.0001,
"loss": 0.0156,
"step": 652
},
{
"epoch": 218.59,
"learning_rate": 0.0001,
"loss": 0.014,
"step": 656
},
{
"epoch": 219.88,
"learning_rate": 0.0001,
"loss": 0.0148,
"step": 660
},
{
"epoch": 221.29,
"learning_rate": 0.0001,
"loss": 0.0155,
"step": 664
},
{
"epoch": 222.59,
"learning_rate": 0.0001,
"loss": 0.0141,
"step": 668
},
{
"epoch": 223.88,
"learning_rate": 0.0001,
"loss": 0.0133,
"step": 672
},
{
"epoch": 225.29,
"learning_rate": 0.0001,
"loss": 0.0144,
"step": 676
},
{
"epoch": 226.59,
"learning_rate": 0.0001,
"loss": 0.0134,
"step": 680
},
{
"epoch": 227.88,
"learning_rate": 0.0001,
"loss": 0.0143,
"step": 684
},
{
"epoch": 229.29,
"learning_rate": 0.0001,
"loss": 0.0137,
"step": 688
},
{
"epoch": 230.59,
"learning_rate": 0.0001,
"loss": 0.0127,
"step": 692
},
{
"epoch": 231.88,
"learning_rate": 0.0001,
"loss": 0.0125,
"step": 696
},
{
"epoch": 233.29,
"learning_rate": 0.0001,
"loss": 0.0136,
"step": 700
},
{
"epoch": 234.59,
"learning_rate": 0.0001,
"loss": 0.0126,
"step": 704
},
{
"epoch": 234.59,
"eval_exact_match": 0.49032882011605416,
"eval_exec": 0.5019342359767892,
"eval_loss": 0.35344886779785156,
"eval_runtime": 194.4016,
"eval_samples_per_second": 5.319,
"step": 704
},
{
"epoch": 235.88,
"learning_rate": 0.0001,
"loss": 0.0127,
"step": 708
},
{
"epoch": 237.29,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 712
},
{
"epoch": 238.59,
"learning_rate": 0.0001,
"loss": 0.0117,
"step": 716
},
{
"epoch": 239.88,
"learning_rate": 0.0001,
"loss": 0.0117,
"step": 720
},
{
"epoch": 241.29,
"learning_rate": 0.0001,
"loss": 0.0148,
"step": 724
},
{
"epoch": 242.59,
"learning_rate": 0.0001,
"loss": 0.0121,
"step": 728
},
{
"epoch": 243.88,
"learning_rate": 0.0001,
"loss": 0.0106,
"step": 732
},
{
"epoch": 245.29,
"learning_rate": 0.0001,
"loss": 0.0122,
"step": 736
},
{
"epoch": 246.59,
"learning_rate": 0.0001,
"loss": 0.0113,
"step": 740
},
{
"epoch": 247.88,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 744
},
{
"epoch": 249.29,
"learning_rate": 0.0001,
"loss": 0.0109,
"step": 748
},
{
"epoch": 250.59,
"learning_rate": 0.0001,
"loss": 0.0103,
"step": 752
},
{
"epoch": 251.88,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 756
},
{
"epoch": 253.29,
"learning_rate": 0.0001,
"loss": 0.0104,
"step": 760
},
{
"epoch": 254.59,
"learning_rate": 0.0001,
"loss": 0.0091,
"step": 764
},
{
"epoch": 255.88,
"learning_rate": 0.0001,
"loss": 0.0093,
"step": 768
},
{
"epoch": 255.88,
"eval_exact_match": 0.4990328820116054,
"eval_exec": 0.5096711798839458,
"eval_loss": 0.36643365025520325,
"eval_runtime": 176.9801,
"eval_samples_per_second": 5.842,
"step": 768
},
{
"epoch": 257.29,
"learning_rate": 0.0001,
"loss": 0.0106,
"step": 772
},
{
"epoch": 258.59,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 776
},
{
"epoch": 259.88,
"learning_rate": 0.0001,
"loss": 0.0094,
"step": 780
},
{
"epoch": 261.29,
"learning_rate": 0.0001,
"loss": 0.0106,
"step": 784
},
{
"epoch": 262.59,
"learning_rate": 0.0001,
"loss": 0.0096,
"step": 788
},
{
"epoch": 263.88,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 792
},
{
"epoch": 265.29,
"learning_rate": 0.0001,
"loss": 0.0094,
"step": 796
},
{
"epoch": 266.59,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 800
},
{
"epoch": 267.88,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 804
},
{
"epoch": 269.29,
"learning_rate": 0.0001,
"loss": 0.0092,
"step": 808
},
{
"epoch": 270.59,
"learning_rate": 0.0001,
"loss": 0.0084,
"step": 812
},
{
"epoch": 271.88,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 816
},
{
"epoch": 273.29,
"learning_rate": 0.0001,
"loss": 0.009,
"step": 820
},
{
"epoch": 274.59,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 824
},
{
"epoch": 275.88,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 828
},
{
"epoch": 277.29,
"learning_rate": 0.0001,
"loss": 0.0082,
"step": 832
},
{
"epoch": 277.29,
"eval_exact_match": 0.49806576402321084,
"eval_exec": 0.5096711798839458,
"eval_loss": 0.3839401602745056,
"eval_runtime": 178.4278,
"eval_samples_per_second": 5.795,
"step": 832
},
{
"epoch": 278.59,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 836
},
{
"epoch": 279.88,
"learning_rate": 0.0001,
"loss": 0.0076,
"step": 840
},
{
"epoch": 281.29,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 844
},
{
"epoch": 282.59,
"learning_rate": 0.0001,
"loss": 0.0076,
"step": 848
},
{
"epoch": 283.88,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 852
},
{
"epoch": 285.29,
"learning_rate": 0.0001,
"loss": 0.0132,
"step": 856
},
{
"epoch": 286.59,
"learning_rate": 0.0001,
"loss": 0.0084,
"step": 860
},
{
"epoch": 287.88,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 864
},
{
"epoch": 289.29,
"learning_rate": 0.0001,
"loss": 0.0072,
"step": 868
},
{
"epoch": 290.59,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 872
},
{
"epoch": 291.88,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 876
},
{
"epoch": 293.29,
"learning_rate": 0.0001,
"loss": 0.0074,
"step": 880
},
{
"epoch": 294.59,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 884
},
{
"epoch": 295.88,
"learning_rate": 0.0001,
"loss": 0.0062,
"step": 888
},
{
"epoch": 297.29,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 892
},
{
"epoch": 298.59,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 896
},
{
"epoch": 298.59,
"eval_exact_match": 0.504835589941973,
"eval_exec": 0.5241779497098646,
"eval_loss": 0.3868894875049591,
"eval_runtime": 176.2661,
"eval_samples_per_second": 5.866,
"step": 896
},
{
"epoch": 299.88,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 900
},
{
"epoch": 301.29,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 904
},
{
"epoch": 302.59,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 908
},
{
"epoch": 303.88,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 912
},
{
"epoch": 305.29,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 916
},
{
"epoch": 306.59,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 920
},
{
"epoch": 307.88,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 924
},
{
"epoch": 309.29,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 928
},
{
"epoch": 310.59,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 932
},
{
"epoch": 311.88,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 936
},
{
"epoch": 313.29,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 940
},
{
"epoch": 314.59,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 944
},
{
"epoch": 315.88,
"learning_rate": 0.0001,
"loss": 0.0056,
"step": 948
},
{
"epoch": 317.29,
"learning_rate": 0.0001,
"loss": 0.0056,
"step": 952
},
{
"epoch": 318.59,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 956
},
{
"epoch": 319.88,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 960
},
{
"epoch": 319.88,
"eval_exact_match": 0.5009671179883946,
"eval_exec": 0.5135396518375241,
"eval_loss": 0.39836612343788147,
"eval_runtime": 183.0329,
"eval_samples_per_second": 5.649,
"step": 960
},
{
"epoch": 321.29,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 964
},
{
"epoch": 322.59,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 968
},
{
"epoch": 323.88,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 972
},
{
"epoch": 325.29,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 976
},
{
"epoch": 326.59,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 980
},
{
"epoch": 327.88,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 984
},
{
"epoch": 329.29,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 988
},
{
"epoch": 330.59,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 992
},
{
"epoch": 331.88,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 996
},
{
"epoch": 333.29,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 1000
},
{
"epoch": 334.59,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1004
},
{
"epoch": 335.88,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1008
},
{
"epoch": 337.29,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1012
},
{
"epoch": 338.59,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1016
},
{
"epoch": 339.88,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1020
},
{
"epoch": 341.29,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 1024
},
{
"epoch": 341.29,
"eval_exact_match": 0.5125725338491296,
"eval_exec": 0.5193423597678917,
"eval_loss": 0.40509259700775146,
"eval_runtime": 174.5602,
"eval_samples_per_second": 5.923,
"step": 1024
},
{
"epoch": 342.59,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1028
},
{
"epoch": 343.88,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1032
},
{
"epoch": 345.29,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1036
},
{
"epoch": 346.59,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1040
},
{
"epoch": 347.88,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1044
},
{
"epoch": 349.29,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 1048
},
{
"epoch": 350.59,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1052
},
{
"epoch": 351.88,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1056
},
{
"epoch": 353.29,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 1060
},
{
"epoch": 354.59,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1064
},
{
"epoch": 355.88,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1068
},
{
"epoch": 357.29,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1072
},
{
"epoch": 358.59,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1076
},
{
"epoch": 359.88,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1080
},
{
"epoch": 361.29,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1084
},
{
"epoch": 362.59,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1088
},
{
"epoch": 362.59,
"eval_exact_match": 0.5038684719535783,
"eval_exec": 0.5154738878143134,
"eval_loss": 0.41651493310928345,
"eval_runtime": 179.3833,
"eval_samples_per_second": 5.764,
"step": 1088
},
{
"epoch": 363.88,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1092
},
{
"epoch": 365.29,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1096
},
{
"epoch": 366.59,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1100
},
{
"epoch": 367.88,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1104
},
{
"epoch": 369.29,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1108
},
{
"epoch": 370.59,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1112
},
{
"epoch": 371.88,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1116
},
{
"epoch": 373.29,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1120
},
{
"epoch": 374.59,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1124
},
{
"epoch": 375.88,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1128
},
{
"epoch": 377.29,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1132
},
{
"epoch": 378.59,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1136
},
{
"epoch": 379.88,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 1140
},
{
"epoch": 381.29,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1144
},
{
"epoch": 382.59,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1148
},
{
"epoch": 383.88,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 1152
},
{
"epoch": 383.88,
"eval_exact_match": 0.5009671179883946,
"eval_exec": 0.5135396518375241,
"eval_loss": 0.4194105863571167,
"eval_runtime": 187.7814,
"eval_samples_per_second": 5.506,
"step": 1152
},
{
"epoch": 385.29,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1156
},
{
"epoch": 386.59,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1160
},
{
"epoch": 387.88,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1164
},
{
"epoch": 389.29,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 1168
},
{
"epoch": 390.59,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1172
},
{
"epoch": 391.88,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1176
},
{
"epoch": 393.29,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 1180
},
{
"epoch": 394.59,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1184
},
{
"epoch": 395.88,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 1188
},
{
"epoch": 397.29,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1192
},
{
"epoch": 398.59,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1196
},
{
"epoch": 399.88,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1200
},
{
"epoch": 401.29,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1204
},
{
"epoch": 402.59,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 1208
},
{
"epoch": 403.88,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1212
},
{
"epoch": 405.29,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 1216
},
{
"epoch": 405.29,
"eval_exact_match": 0.5125725338491296,
"eval_exec": 0.5193423597678917,
"eval_loss": 0.42960309982299805,
"eval_runtime": 173.0051,
"eval_samples_per_second": 5.977,
"step": 1216
},
{
"epoch": 406.59,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1220
},
{
"epoch": 407.88,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1224
},
{
"epoch": 409.29,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 1228
},
{
"epoch": 410.59,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1232
},
{
"epoch": 411.88,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1236
},
{
"epoch": 413.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1240
},
{
"epoch": 414.59,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1244
},
{
"epoch": 415.88,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1248
},
{
"epoch": 417.29,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1252
},
{
"epoch": 418.59,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1256
},
{
"epoch": 419.88,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1260
},
{
"epoch": 421.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1264
},
{
"epoch": 422.59,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1268
},
{
"epoch": 423.88,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1272
},
{
"epoch": 425.29,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1276
},
{
"epoch": 426.59,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1280
},
{
"epoch": 426.59,
"eval_exact_match": 0.4922630560928433,
"eval_exec": 0.5029013539651838,
"eval_loss": 0.42588016390800476,
"eval_runtime": 182.0847,
"eval_samples_per_second": 5.679,
"step": 1280
},
{
"epoch": 427.88,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1284
},
{
"epoch": 429.29,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1288
},
{
"epoch": 430.59,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1292
},
{
"epoch": 431.88,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1296
},
{
"epoch": 433.29,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1300
},
{
"epoch": 434.59,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1304
},
{
"epoch": 435.88,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1308
},
{
"epoch": 437.29,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1312
},
{
"epoch": 438.59,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1316
},
{
"epoch": 439.88,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1320
},
{
"epoch": 441.29,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 1324
},
{
"epoch": 442.59,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1328
},
{
"epoch": 443.88,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1332
},
{
"epoch": 445.29,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1336
},
{
"epoch": 446.59,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1340
},
{
"epoch": 447.88,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1344
},
{
"epoch": 447.88,
"eval_exact_match": 0.4941972920696325,
"eval_exec": 0.5058027079303675,
"eval_loss": 0.43824511766433716,
"eval_runtime": 181.3806,
"eval_samples_per_second": 5.701,
"step": 1344
},
{
"epoch": 449.29,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1348
},
{
"epoch": 450.59,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1352
},
{
"epoch": 451.88,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1356
},
{
"epoch": 453.29,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1360
},
{
"epoch": 454.59,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1364
},
{
"epoch": 455.88,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1368
},
{
"epoch": 457.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1372
},
{
"epoch": 458.59,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1376
},
{
"epoch": 459.88,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1380
},
{
"epoch": 461.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1384
},
{
"epoch": 462.59,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1388
},
{
"epoch": 463.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1392
},
{
"epoch": 465.29,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1396
},
{
"epoch": 466.59,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1400
},
{
"epoch": 467.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1404
},
{
"epoch": 469.29,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1408
},
{
"epoch": 469.29,
"eval_exact_match": 0.5106382978723404,
"eval_exec": 0.5183752417794971,
"eval_loss": 0.4374188780784607,
"eval_runtime": 174.2227,
"eval_samples_per_second": 5.935,
"step": 1408
},
{
"epoch": 470.59,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1412
},
{
"epoch": 471.88,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1416
},
{
"epoch": 473.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1420
},
{
"epoch": 474.59,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1424
},
{
"epoch": 475.88,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1428
},
{
"epoch": 477.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1432
},
{
"epoch": 478.59,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1436
},
{
"epoch": 479.88,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1440
},
{
"epoch": 481.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1444
},
{
"epoch": 482.59,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1448
},
{
"epoch": 483.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1452
},
{
"epoch": 485.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1456
},
{
"epoch": 486.59,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1460
},
{
"epoch": 487.88,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1464
},
{
"epoch": 489.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1468
},
{
"epoch": 490.59,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1472
},
{
"epoch": 490.59,
"eval_exact_match": 0.5135396518375241,
"eval_exec": 0.5222437137330754,
"eval_loss": 0.4480360150337219,
"eval_runtime": 173.7903,
"eval_samples_per_second": 5.95,
"step": 1472
},
{
"epoch": 491.88,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1476
},
{
"epoch": 493.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1480
},
{
"epoch": 494.59,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1484
},
{
"epoch": 495.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1488
},
{
"epoch": 497.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1492
},
{
"epoch": 498.59,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1496
},
{
"epoch": 499.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1500
},
{
"epoch": 501.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1504
},
{
"epoch": 502.59,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1508
},
{
"epoch": 503.88,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1512
},
{
"epoch": 505.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1516
},
{
"epoch": 506.59,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1520
},
{
"epoch": 507.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1524
},
{
"epoch": 509.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1528
},
{
"epoch": 510.59,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1532
},
{
"epoch": 511.88,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1536
},
{
"epoch": 511.88,
"eval_exact_match": 0.5029013539651838,
"eval_exec": 0.5193423597678917,
"eval_loss": 0.45330750942230225,
"eval_runtime": 174.0196,
"eval_samples_per_second": 5.942,
"step": 1536
},
{
"epoch": 513.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1540
},
{
"epoch": 514.59,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1544
},
{
"epoch": 515.88,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1548
},
{
"epoch": 517.29,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1552
},
{
"epoch": 518.59,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1556
},
{
"epoch": 519.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1560
},
{
"epoch": 521.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1564
},
{
"epoch": 522.59,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1568
},
{
"epoch": 523.88,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1572
},
{
"epoch": 525.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1576
},
{
"epoch": 526.59,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1580
},
{
"epoch": 527.88,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1584
},
{
"epoch": 529.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1588
},
{
"epoch": 530.59,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1592
},
{
"epoch": 531.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1596
},
{
"epoch": 533.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1600
},
{
"epoch": 533.29,
"eval_exact_match": 0.5077369439071566,
"eval_exec": 0.52321083172147,
"eval_loss": 0.45847541093826294,
"eval_runtime": 185.2473,
"eval_samples_per_second": 5.582,
"step": 1600
},
{
"epoch": 534.59,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1604
},
{
"epoch": 535.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1608
},
{
"epoch": 537.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1612
},
{
"epoch": 538.59,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1616
},
{
"epoch": 539.88,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1620
},
{
"epoch": 541.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1624
},
{
"epoch": 542.59,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1628
},
{
"epoch": 543.88,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1632
},
{
"epoch": 545.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1636
},
{
"epoch": 546.59,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1640
},
{
"epoch": 547.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1644
},
{
"epoch": 549.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1648
},
{
"epoch": 550.59,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1652
},
{
"epoch": 551.88,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1656
},
{
"epoch": 553.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1660
},
{
"epoch": 554.59,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1664
},
{
"epoch": 554.59,
"eval_exact_match": 0.511605415860735,
"eval_exec": 0.5241779497098646,
"eval_loss": 0.4577661156654358,
"eval_runtime": 175.2544,
"eval_samples_per_second": 5.9,
"step": 1664
},
{
"epoch": 555.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1668
},
{
"epoch": 557.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1672
},
{
"epoch": 558.59,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1676
},
{
"epoch": 559.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1680
},
{
"epoch": 561.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1684
},
{
"epoch": 562.59,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 1688
},
{
"epoch": 563.88,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1692
},
{
"epoch": 565.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1696
},
{
"epoch": 566.59,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1700
},
{
"epoch": 567.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1704
},
{
"epoch": 569.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1708
},
{
"epoch": 570.59,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1712
},
{
"epoch": 571.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1716
},
{
"epoch": 573.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1720
},
{
"epoch": 574.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1724
},
{
"epoch": 575.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1728
},
{
"epoch": 575.88,
"eval_exact_match": 0.511605415860735,
"eval_exec": 0.52321083172147,
"eval_loss": 0.4673304259777069,
"eval_runtime": 178.9293,
"eval_samples_per_second": 5.779,
"step": 1728
},
{
"epoch": 577.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1732
},
{
"epoch": 578.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1736
},
{
"epoch": 579.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1740
},
{
"epoch": 581.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1744
},
{
"epoch": 582.59,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1748
},
{
"epoch": 583.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1752
},
{
"epoch": 585.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1756
},
{
"epoch": 586.59,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1760
},
{
"epoch": 587.88,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1764
},
{
"epoch": 589.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1768
},
{
"epoch": 590.59,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1772
},
{
"epoch": 591.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1776
},
{
"epoch": 593.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1780
},
{
"epoch": 594.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1784
},
{
"epoch": 595.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1788
},
{
"epoch": 597.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1792
},
{
"epoch": 597.29,
"eval_exact_match": 0.5087040618955513,
"eval_exec": 0.5145067698259188,
"eval_loss": 0.4705192744731903,
"eval_runtime": 176.1126,
"eval_samples_per_second": 5.871,
"step": 1792
},
{
"epoch": 598.59,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1796
},
{
"epoch": 599.88,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1800
},
{
"epoch": 601.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1804
},
{
"epoch": 602.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1808
},
{
"epoch": 603.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1812
},
{
"epoch": 605.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1816
},
{
"epoch": 606.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1820
},
{
"epoch": 607.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1824
},
{
"epoch": 609.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1828
},
{
"epoch": 610.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1832
},
{
"epoch": 611.88,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1836
},
{
"epoch": 613.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1840
},
{
"epoch": 614.59,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1844
},
{
"epoch": 615.88,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1848
},
{
"epoch": 617.29,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1852
},
{
"epoch": 618.59,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1856
},
{
"epoch": 618.59,
"eval_exact_match": 0.5038684719535783,
"eval_exec": 0.511605415860735,
"eval_loss": 0.4638679027557373,
"eval_runtime": 178.5071,
"eval_samples_per_second": 5.792,
"step": 1856
},
{
"epoch": 619.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1860
},
{
"epoch": 621.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1864
},
{
"epoch": 622.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1868
},
{
"epoch": 623.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1872
},
{
"epoch": 625.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1876
},
{
"epoch": 626.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1880
},
{
"epoch": 627.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1884
},
{
"epoch": 629.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1888
},
{
"epoch": 630.59,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1892
},
{
"epoch": 631.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1896
},
{
"epoch": 633.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1900
},
{
"epoch": 634.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1904
},
{
"epoch": 635.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1908
},
{
"epoch": 637.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1912
},
{
"epoch": 638.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1916
},
{
"epoch": 639.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1920
},
{
"epoch": 639.88,
"eval_exact_match": 0.5096711798839458,
"eval_exec": 0.5193423597678917,
"eval_loss": 0.47883152961730957,
"eval_runtime": 183.0234,
"eval_samples_per_second": 5.65,
"step": 1920
},
{
"epoch": 641.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1924
},
{
"epoch": 642.59,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1928
},
{
"epoch": 643.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1932
},
{
"epoch": 645.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1936
},
{
"epoch": 646.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1940
},
{
"epoch": 647.88,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1944
},
{
"epoch": 649.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1948
},
{
"epoch": 650.59,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1952
},
{
"epoch": 651.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1956
},
{
"epoch": 653.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1960
},
{
"epoch": 654.59,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1964
},
{
"epoch": 655.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1968
},
{
"epoch": 657.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1972
},
{
"epoch": 658.59,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1976
},
{
"epoch": 659.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1980
},
{
"epoch": 661.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1984
},
{
"epoch": 661.29,
"eval_exact_match": 0.504835589941973,
"eval_exec": 0.5203094777562862,
"eval_loss": 0.4922162890434265,
"eval_runtime": 181.7058,
"eval_samples_per_second": 5.691,
"step": 1984
},
{
"epoch": 662.59,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1988
},
{
"epoch": 663.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1992
},
{
"epoch": 665.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1996
},
{
"epoch": 666.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2000
},
{
"epoch": 667.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 2004
},
{
"epoch": 669.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2008
},
{
"epoch": 670.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2012
},
{
"epoch": 671.88,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 2016
},
{
"epoch": 673.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2020
},
{
"epoch": 674.59,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2024
},
{
"epoch": 675.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2028
},
{
"epoch": 677.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2032
},
{
"epoch": 678.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2036
},
{
"epoch": 679.88,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2040
},
{
"epoch": 681.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2044
},
{
"epoch": 682.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2048
},
{
"epoch": 682.59,
"eval_exact_match": 0.5164410058027079,
"eval_exec": 0.5290135396518375,
"eval_loss": 0.47683951258659363,
"eval_runtime": 185.6081,
"eval_samples_per_second": 5.571,
"step": 2048
},
{
"epoch": 683.88,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2052
},
{
"epoch": 685.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 2056
},
{
"epoch": 686.59,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2060
},
{
"epoch": 687.88,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 2064
},
{
"epoch": 689.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2068
},
{
"epoch": 690.59,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 2072
},
{
"epoch": 691.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2076
},
{
"epoch": 693.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2080
},
{
"epoch": 694.59,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2084
},
{
"epoch": 695.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2088
},
{
"epoch": 697.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2092
},
{
"epoch": 698.59,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 2096
},
{
"epoch": 699.88,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2100
},
{
"epoch": 701.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2104
},
{
"epoch": 702.59,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 2108
},
{
"epoch": 703.88,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 2112
},
{
"epoch": 703.88,
"eval_exact_match": 0.5241779497098646,
"eval_exec": 0.5338491295938105,
"eval_loss": 0.47757720947265625,
"eval_runtime": 180.9881,
"eval_samples_per_second": 5.713,
"step": 2112
}
],
"max_steps": 9216,
"num_train_epochs": 3072,
"total_flos": 2.1502023256705536e+18,
"trial_name": null,
"trial_params": null
}