{
  "best_metric": 0.6963249516441006,
  "best_model_checkpoint": "/experiments/spider/d6368230-e8a6-4e57-923c-f0938a9bcf7b/checkpoint-1024",
  "epoch": 341.2922374429224,
  "global_step": 1024,
  "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
    }
  ],
  "max_steps": 9216,
  "num_train_epochs": 3072,
  "total_flos": 4.710057387539562e+18,
  "trial_name": null,
  "trial_params": null
}