mt5-large-spider / trainer_state.json
Peng
Update
acdde37
{
"best_metric": 0.6876208897485493,
"best_model_checkpoint": "spider_mt5-large_train_2/checkpoint-1664",
"epoch": 575.8732876712329,
"global_step": 1728,
"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": 28.8064,
"step": 1
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 25.0484,
"step": 4
},
{
"epoch": 2.58,
"learning_rate": 0.0001,
"loss": 18.7727,
"step": 8
},
{
"epoch": 3.87,
"learning_rate": 0.0001,
"loss": 15.4019,
"step": 12
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 16.1009,
"step": 16
},
{
"epoch": 6.58,
"learning_rate": 0.0001,
"loss": 12.2971,
"step": 20
},
{
"epoch": 7.87,
"learning_rate": 0.0001,
"loss": 11.3401,
"step": 24
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 11.1614,
"step": 28
},
{
"epoch": 10.58,
"learning_rate": 0.0001,
"loss": 8.5996,
"step": 32
},
{
"epoch": 11.87,
"learning_rate": 0.0001,
"loss": 8.5339,
"step": 36
},
{
"epoch": 13.29,
"learning_rate": 0.0001,
"loss": 9.5784,
"step": 40
},
{
"epoch": 14.58,
"learning_rate": 0.0001,
"loss": 8.6372,
"step": 44
},
{
"epoch": 15.87,
"learning_rate": 0.0001,
"loss": 8.6748,
"step": 48
},
{
"epoch": 17.29,
"learning_rate": 0.0001,
"loss": 9.7059,
"step": 52
},
{
"epoch": 18.58,
"learning_rate": 0.0001,
"loss": 8.0709,
"step": 56
},
{
"epoch": 19.87,
"learning_rate": 0.0001,
"loss": 4.5224,
"step": 60
},
{
"epoch": 21.29,
"learning_rate": 0.0001,
"loss": 4.4262,
"step": 64
},
{
"epoch": 21.29,
"eval_exact_match": 0.0,
"eval_exec": 0.0,
"eval_loss": 2.7989840507507324,
"eval_runtime": 1066.0098,
"eval_samples_per_second": 0.97,
"step": 64
},
{
"epoch": 22.58,
"learning_rate": 0.0001,
"loss": 4.8377,
"step": 68
},
{
"epoch": 23.87,
"learning_rate": 0.0001,
"loss": 5.1646,
"step": 72
},
{
"epoch": 25.29,
"learning_rate": 0.0001,
"loss": 5.1508,
"step": 76
},
{
"epoch": 26.58,
"learning_rate": 0.0001,
"loss": 4.2013,
"step": 80
},
{
"epoch": 27.87,
"learning_rate": 0.0001,
"loss": 3.9399,
"step": 84
},
{
"epoch": 29.29,
"learning_rate": 0.0001,
"loss": 4.236,
"step": 88
},
{
"epoch": 30.58,
"learning_rate": 0.0001,
"loss": 3.7905,
"step": 92
},
{
"epoch": 31.87,
"learning_rate": 0.0001,
"loss": 3.8221,
"step": 96
},
{
"epoch": 33.29,
"learning_rate": 0.0001,
"loss": 4.1696,
"step": 100
},
{
"epoch": 34.58,
"learning_rate": 0.0001,
"loss": 3.6,
"step": 104
},
{
"epoch": 35.87,
"learning_rate": 0.0001,
"loss": 3.0025,
"step": 108
},
{
"epoch": 37.29,
"learning_rate": 0.0001,
"loss": 2.8865,
"step": 112
},
{
"epoch": 38.58,
"learning_rate": 0.0001,
"loss": 2.0248,
"step": 116
},
{
"epoch": 39.87,
"learning_rate": 0.0001,
"loss": 1.8247,
"step": 120
},
{
"epoch": 41.29,
"learning_rate": 0.0001,
"loss": 1.8201,
"step": 124
},
{
"epoch": 42.58,
"learning_rate": 0.0001,
"loss": 1.6674,
"step": 128
},
{
"epoch": 42.58,
"eval_exact_match": 0.03868471953578337,
"eval_exec": 0.058027079303675046,
"eval_loss": 1.1517833471298218,
"eval_runtime": 576.6657,
"eval_samples_per_second": 1.793,
"step": 128
},
{
"epoch": 43.87,
"learning_rate": 0.0001,
"loss": 2.0219,
"step": 132
},
{
"epoch": 45.29,
"learning_rate": 0.0001,
"loss": 2.4727,
"step": 136
},
{
"epoch": 46.58,
"learning_rate": 0.0001,
"loss": 1.7297,
"step": 140
},
{
"epoch": 47.87,
"learning_rate": 0.0001,
"loss": 1.7429,
"step": 144
},
{
"epoch": 49.29,
"learning_rate": 0.0001,
"loss": 1.9368,
"step": 148
},
{
"epoch": 50.58,
"learning_rate": 0.0001,
"loss": 1.5402,
"step": 152
},
{
"epoch": 51.87,
"learning_rate": 0.0001,
"loss": 1.2995,
"step": 156
},
{
"epoch": 53.29,
"learning_rate": 0.0001,
"loss": 1.2078,
"step": 160
},
{
"epoch": 54.58,
"learning_rate": 0.0001,
"loss": 0.9458,
"step": 164
},
{
"epoch": 55.87,
"learning_rate": 0.0001,
"loss": 0.8168,
"step": 168
},
{
"epoch": 57.29,
"learning_rate": 0.0001,
"loss": 0.7603,
"step": 172
},
{
"epoch": 58.58,
"learning_rate": 0.0001,
"loss": 0.6747,
"step": 176
},
{
"epoch": 59.87,
"learning_rate": 0.0001,
"loss": 0.649,
"step": 180
},
{
"epoch": 61.29,
"learning_rate": 0.0001,
"loss": 0.7529,
"step": 184
},
{
"epoch": 62.58,
"learning_rate": 0.0001,
"loss": 0.7392,
"step": 188
},
{
"epoch": 63.87,
"learning_rate": 0.0001,
"loss": 0.6694,
"step": 192
},
{
"epoch": 63.87,
"eval_exact_match": 0.12959381044487428,
"eval_exec": 0.15377176015473887,
"eval_loss": 0.3512875437736511,
"eval_runtime": 521.2463,
"eval_samples_per_second": 1.984,
"step": 192
},
{
"epoch": 65.29,
"learning_rate": 0.0001,
"loss": 1.0501,
"step": 196
},
{
"epoch": 66.58,
"learning_rate": 0.0001,
"loss": 1.3722,
"step": 200
},
{
"epoch": 67.87,
"learning_rate": 0.0001,
"loss": 1.36,
"step": 204
},
{
"epoch": 69.29,
"learning_rate": 0.0001,
"loss": 1.0248,
"step": 208
},
{
"epoch": 70.58,
"learning_rate": 0.0001,
"loss": 0.6822,
"step": 212
},
{
"epoch": 71.87,
"learning_rate": 0.0001,
"loss": 0.7294,
"step": 216
},
{
"epoch": 73.29,
"learning_rate": 0.0001,
"loss": 0.8418,
"step": 220
},
{
"epoch": 74.58,
"learning_rate": 0.0001,
"loss": 0.7134,
"step": 224
},
{
"epoch": 75.87,
"learning_rate": 0.0001,
"loss": 0.6444,
"step": 228
},
{
"epoch": 77.29,
"learning_rate": 0.0001,
"loss": 0.6836,
"step": 232
},
{
"epoch": 78.58,
"learning_rate": 0.0001,
"loss": 0.6034,
"step": 236
},
{
"epoch": 79.87,
"learning_rate": 0.0001,
"loss": 0.564,
"step": 240
},
{
"epoch": 81.29,
"learning_rate": 0.0001,
"loss": 0.5818,
"step": 244
},
{
"epoch": 82.58,
"learning_rate": 0.0001,
"loss": 0.4964,
"step": 248
},
{
"epoch": 83.87,
"learning_rate": 0.0001,
"loss": 0.4724,
"step": 252
},
{
"epoch": 85.29,
"learning_rate": 0.0001,
"loss": 0.4921,
"step": 256
},
{
"epoch": 85.29,
"eval_exact_match": 0.218568665377176,
"eval_exec": 0.26692456479690524,
"eval_loss": 0.2768532335758209,
"eval_runtime": 509.4242,
"eval_samples_per_second": 2.03,
"step": 256
},
{
"epoch": 86.58,
"learning_rate": 0.0001,
"loss": 0.4023,
"step": 260
},
{
"epoch": 87.87,
"learning_rate": 0.0001,
"loss": 0.3712,
"step": 264
},
{
"epoch": 89.29,
"learning_rate": 0.0001,
"loss": 0.3795,
"step": 268
},
{
"epoch": 90.58,
"learning_rate": 0.0001,
"loss": 0.3192,
"step": 272
},
{
"epoch": 91.87,
"learning_rate": 0.0001,
"loss": 0.3111,
"step": 276
},
{
"epoch": 93.29,
"learning_rate": 0.0001,
"loss": 0.3228,
"step": 280
},
{
"epoch": 94.58,
"learning_rate": 0.0001,
"loss": 0.281,
"step": 284
},
{
"epoch": 95.87,
"learning_rate": 0.0001,
"loss": 0.2615,
"step": 288
},
{
"epoch": 97.29,
"learning_rate": 0.0001,
"loss": 0.273,
"step": 292
},
{
"epoch": 98.58,
"learning_rate": 0.0001,
"loss": 0.2408,
"step": 296
},
{
"epoch": 99.87,
"learning_rate": 0.0001,
"loss": 0.223,
"step": 300
},
{
"epoch": 101.29,
"learning_rate": 0.0001,
"loss": 0.2331,
"step": 304
},
{
"epoch": 102.58,
"learning_rate": 0.0001,
"loss": 0.2043,
"step": 308
},
{
"epoch": 103.87,
"learning_rate": 0.0001,
"loss": 0.1914,
"step": 312
},
{
"epoch": 105.29,
"learning_rate": 0.0001,
"loss": 0.2019,
"step": 316
},
{
"epoch": 106.58,
"learning_rate": 0.0001,
"loss": 0.1745,
"step": 320
},
{
"epoch": 106.58,
"eval_exact_match": 0.4961315280464217,
"eval_exec": 0.5261121856866537,
"eval_loss": 0.17989404499530792,
"eval_runtime": 153.2046,
"eval_samples_per_second": 6.749,
"step": 320
},
{
"epoch": 107.87,
"learning_rate": 0.0001,
"loss": 0.1671,
"step": 324
},
{
"epoch": 109.29,
"learning_rate": 0.0001,
"loss": 0.1767,
"step": 328
},
{
"epoch": 110.58,
"learning_rate": 0.0001,
"loss": 0.1555,
"step": 332
},
{
"epoch": 111.87,
"learning_rate": 0.0001,
"loss": 0.1452,
"step": 336
},
{
"epoch": 113.29,
"learning_rate": 0.0001,
"loss": 0.1539,
"step": 340
},
{
"epoch": 114.58,
"learning_rate": 0.0001,
"loss": 0.1405,
"step": 344
},
{
"epoch": 115.87,
"learning_rate": 0.0001,
"loss": 0.1347,
"step": 348
},
{
"epoch": 117.29,
"learning_rate": 0.0001,
"loss": 0.1371,
"step": 352
},
{
"epoch": 118.58,
"learning_rate": 0.0001,
"loss": 0.1222,
"step": 356
},
{
"epoch": 119.87,
"learning_rate": 0.0001,
"loss": 0.1198,
"step": 360
},
{
"epoch": 121.29,
"learning_rate": 0.0001,
"loss": 0.1264,
"step": 364
},
{
"epoch": 122.58,
"learning_rate": 0.0001,
"loss": 0.1163,
"step": 368
},
{
"epoch": 123.87,
"learning_rate": 0.0001,
"loss": 0.1093,
"step": 372
},
{
"epoch": 125.29,
"learning_rate": 0.0001,
"loss": 0.112,
"step": 376
},
{
"epoch": 126.58,
"learning_rate": 0.0001,
"loss": 0.1001,
"step": 380
},
{
"epoch": 127.87,
"learning_rate": 0.0001,
"loss": 0.1012,
"step": 384
},
{
"epoch": 127.87,
"eval_exact_match": 0.5319148936170213,
"eval_exec": 0.5773694390715667,
"eval_loss": 0.16839821636676788,
"eval_runtime": 192.7863,
"eval_samples_per_second": 5.363,
"step": 384
},
{
"epoch": 129.29,
"learning_rate": 0.0001,
"loss": 0.107,
"step": 388
},
{
"epoch": 130.58,
"learning_rate": 0.0001,
"loss": 0.0979,
"step": 392
},
{
"epoch": 131.87,
"learning_rate": 0.0001,
"loss": 0.0936,
"step": 396
},
{
"epoch": 133.29,
"learning_rate": 0.0001,
"loss": 0.0949,
"step": 400
},
{
"epoch": 134.58,
"learning_rate": 0.0001,
"loss": 0.0881,
"step": 404
},
{
"epoch": 135.87,
"learning_rate": 0.0001,
"loss": 0.0841,
"step": 408
},
{
"epoch": 137.29,
"learning_rate": 0.0001,
"loss": 0.0899,
"step": 412
},
{
"epoch": 138.58,
"learning_rate": 0.0001,
"loss": 0.0791,
"step": 416
},
{
"epoch": 139.87,
"learning_rate": 0.0001,
"loss": 0.077,
"step": 420
},
{
"epoch": 141.29,
"learning_rate": 0.0001,
"loss": 0.0819,
"step": 424
},
{
"epoch": 142.58,
"learning_rate": 0.0001,
"loss": 0.0752,
"step": 428
},
{
"epoch": 143.87,
"learning_rate": 0.0001,
"loss": 0.0719,
"step": 432
},
{
"epoch": 145.29,
"learning_rate": 0.0001,
"loss": 0.0735,
"step": 436
},
{
"epoch": 146.58,
"learning_rate": 0.0001,
"loss": 0.0673,
"step": 440
},
{
"epoch": 147.87,
"learning_rate": 0.0001,
"loss": 0.0693,
"step": 444
},
{
"epoch": 149.29,
"learning_rate": 0.0001,
"loss": 0.0744,
"step": 448
},
{
"epoch": 149.29,
"eval_exact_match": 0.6073500967117988,
"eval_exec": 0.6479690522243714,
"eval_loss": 0.18756793439388275,
"eval_runtime": 163.9883,
"eval_samples_per_second": 6.305,
"step": 448
},
{
"epoch": 150.58,
"learning_rate": 0.0001,
"loss": 0.0623,
"step": 452
},
{
"epoch": 151.87,
"learning_rate": 0.0001,
"loss": 0.0612,
"step": 456
},
{
"epoch": 153.29,
"learning_rate": 0.0001,
"loss": 0.0644,
"step": 460
},
{
"epoch": 154.58,
"learning_rate": 0.0001,
"loss": 0.0582,
"step": 464
},
{
"epoch": 155.87,
"learning_rate": 0.0001,
"loss": 0.0588,
"step": 468
},
{
"epoch": 157.29,
"learning_rate": 0.0001,
"loss": 0.0618,
"step": 472
},
{
"epoch": 158.58,
"learning_rate": 0.0001,
"loss": 0.0585,
"step": 476
},
{
"epoch": 159.87,
"learning_rate": 0.0001,
"loss": 0.0522,
"step": 480
},
{
"epoch": 161.29,
"learning_rate": 0.0001,
"loss": 0.0545,
"step": 484
},
{
"epoch": 162.58,
"learning_rate": 0.0001,
"loss": 0.048,
"step": 488
},
{
"epoch": 163.87,
"learning_rate": 0.0001,
"loss": 0.0479,
"step": 492
},
{
"epoch": 165.29,
"learning_rate": 0.0001,
"loss": 0.0539,
"step": 496
},
{
"epoch": 166.58,
"learning_rate": 0.0001,
"loss": 0.0472,
"step": 500
},
{
"epoch": 167.87,
"learning_rate": 0.0001,
"loss": 0.0474,
"step": 504
},
{
"epoch": 169.29,
"learning_rate": 0.0001,
"loss": 0.0497,
"step": 508
},
{
"epoch": 170.58,
"learning_rate": 0.0001,
"loss": 0.0437,
"step": 512
},
{
"epoch": 170.58,
"eval_exact_match": 0.6373307543520309,
"eval_exec": 0.6808510638297872,
"eval_loss": 0.19132167100906372,
"eval_runtime": 188.4194,
"eval_samples_per_second": 5.488,
"step": 512
},
{
"epoch": 171.87,
"learning_rate": 0.0001,
"loss": 0.043,
"step": 516
},
{
"epoch": 173.29,
"learning_rate": 0.0001,
"loss": 0.0484,
"step": 520
},
{
"epoch": 174.58,
"learning_rate": 0.0001,
"loss": 0.0405,
"step": 524
},
{
"epoch": 175.87,
"learning_rate": 0.0001,
"loss": 0.0387,
"step": 528
},
{
"epoch": 177.29,
"learning_rate": 0.0001,
"loss": 0.0408,
"step": 532
},
{
"epoch": 178.58,
"learning_rate": 0.0001,
"loss": 0.0401,
"step": 536
},
{
"epoch": 179.87,
"learning_rate": 0.0001,
"loss": 0.0372,
"step": 540
},
{
"epoch": 181.29,
"learning_rate": 0.0001,
"loss": 0.038,
"step": 544
},
{
"epoch": 182.58,
"learning_rate": 0.0001,
"loss": 0.0342,
"step": 548
},
{
"epoch": 183.87,
"learning_rate": 0.0001,
"loss": 0.0335,
"step": 552
},
{
"epoch": 185.29,
"learning_rate": 0.0001,
"loss": 0.0362,
"step": 556
},
{
"epoch": 186.58,
"learning_rate": 0.0001,
"loss": 0.0392,
"step": 560
},
{
"epoch": 187.87,
"learning_rate": 0.0001,
"loss": 0.0352,
"step": 564
},
{
"epoch": 189.29,
"learning_rate": 0.0001,
"loss": 0.0341,
"step": 568
},
{
"epoch": 190.58,
"learning_rate": 0.0001,
"loss": 0.0325,
"step": 572
},
{
"epoch": 191.87,
"learning_rate": 0.0001,
"loss": 0.0286,
"step": 576
},
{
"epoch": 191.87,
"eval_exact_match": 0.6315280464216635,
"eval_exec": 0.6634429400386848,
"eval_loss": 0.21305637061595917,
"eval_runtime": 175.1232,
"eval_samples_per_second": 5.904,
"step": 576
},
{
"epoch": 193.29,
"learning_rate": 0.0001,
"loss": 0.0315,
"step": 580
},
{
"epoch": 194.58,
"learning_rate": 0.0001,
"loss": 0.0298,
"step": 584
},
{
"epoch": 195.87,
"learning_rate": 0.0001,
"loss": 0.0282,
"step": 588
},
{
"epoch": 197.29,
"learning_rate": 0.0001,
"loss": 0.0293,
"step": 592
},
{
"epoch": 198.58,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 596
},
{
"epoch": 199.87,
"learning_rate": 0.0001,
"loss": 0.0256,
"step": 600
},
{
"epoch": 201.29,
"learning_rate": 0.0001,
"loss": 0.0288,
"step": 604
},
{
"epoch": 202.58,
"learning_rate": 0.0001,
"loss": 0.0283,
"step": 608
},
{
"epoch": 203.87,
"learning_rate": 0.0001,
"loss": 0.0259,
"step": 612
},
{
"epoch": 205.29,
"learning_rate": 0.0001,
"loss": 0.0263,
"step": 616
},
{
"epoch": 206.58,
"learning_rate": 0.0001,
"loss": 0.0228,
"step": 620
},
{
"epoch": 207.87,
"learning_rate": 0.0001,
"loss": 0.0228,
"step": 624
},
{
"epoch": 209.29,
"learning_rate": 0.0001,
"loss": 0.0246,
"step": 628
},
{
"epoch": 210.58,
"learning_rate": 0.0001,
"loss": 0.0225,
"step": 632
},
{
"epoch": 211.87,
"learning_rate": 0.0001,
"loss": 0.0242,
"step": 636
},
{
"epoch": 213.29,
"learning_rate": 0.0001,
"loss": 0.0239,
"step": 640
},
{
"epoch": 213.29,
"eval_exact_match": 0.6624758220502901,
"eval_exec": 0.690522243713733,
"eval_loss": 0.23541121184825897,
"eval_runtime": 171.3767,
"eval_samples_per_second": 6.033,
"step": 640
},
{
"epoch": 214.58,
"learning_rate": 0.0001,
"loss": 0.0197,
"step": 644
},
{
"epoch": 215.87,
"learning_rate": 0.0001,
"loss": 0.0189,
"step": 648
},
{
"epoch": 217.29,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 652
},
{
"epoch": 218.58,
"learning_rate": 0.0001,
"loss": 0.0193,
"step": 656
},
{
"epoch": 219.87,
"learning_rate": 0.0001,
"loss": 0.0191,
"step": 660
},
{
"epoch": 221.29,
"learning_rate": 0.0001,
"loss": 0.0198,
"step": 664
},
{
"epoch": 222.58,
"learning_rate": 0.0001,
"loss": 0.018,
"step": 668
},
{
"epoch": 223.87,
"learning_rate": 0.0001,
"loss": 0.0188,
"step": 672
},
{
"epoch": 225.29,
"learning_rate": 0.0001,
"loss": 0.0189,
"step": 676
},
{
"epoch": 226.58,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 680
},
{
"epoch": 227.87,
"learning_rate": 0.0001,
"loss": 0.0165,
"step": 684
},
{
"epoch": 229.29,
"learning_rate": 0.0001,
"loss": 0.0179,
"step": 688
},
{
"epoch": 230.58,
"learning_rate": 0.0001,
"loss": 0.0177,
"step": 692
},
{
"epoch": 231.87,
"learning_rate": 0.0001,
"loss": 0.0154,
"step": 696
},
{
"epoch": 233.29,
"learning_rate": 0.0001,
"loss": 0.0152,
"step": 700
},
{
"epoch": 234.58,
"learning_rate": 0.0001,
"loss": 0.0141,
"step": 704
},
{
"epoch": 234.58,
"eval_exact_match": 0.6266924564796905,
"eval_exec": 0.6692456479690522,
"eval_loss": 0.2685522735118866,
"eval_runtime": 184.1044,
"eval_samples_per_second": 5.616,
"step": 704
},
{
"epoch": 235.87,
"learning_rate": 0.0001,
"loss": 0.0168,
"step": 708
},
{
"epoch": 237.29,
"learning_rate": 0.0001,
"loss": 0.0194,
"step": 712
},
{
"epoch": 238.58,
"learning_rate": 0.0001,
"loss": 0.0197,
"step": 716
},
{
"epoch": 239.87,
"learning_rate": 0.0001,
"loss": 0.0152,
"step": 720
},
{
"epoch": 241.29,
"learning_rate": 0.0001,
"loss": 0.0148,
"step": 724
},
{
"epoch": 242.58,
"learning_rate": 0.0001,
"loss": 0.0136,
"step": 728
},
{
"epoch": 243.87,
"learning_rate": 0.0001,
"loss": 0.0133,
"step": 732
},
{
"epoch": 245.29,
"learning_rate": 0.0001,
"loss": 0.0144,
"step": 736
},
{
"epoch": 246.58,
"learning_rate": 0.0001,
"loss": 0.0176,
"step": 740
},
{
"epoch": 247.87,
"learning_rate": 0.0001,
"loss": 0.0125,
"step": 744
},
{
"epoch": 249.29,
"learning_rate": 0.0001,
"loss": 0.0126,
"step": 748
},
{
"epoch": 250.58,
"learning_rate": 0.0001,
"loss": 0.0114,
"step": 752
},
{
"epoch": 251.87,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 756
},
{
"epoch": 253.29,
"learning_rate": 0.0001,
"loss": 0.0141,
"step": 760
},
{
"epoch": 254.58,
"learning_rate": 0.0001,
"loss": 0.0102,
"step": 764
},
{
"epoch": 255.87,
"learning_rate": 0.0001,
"loss": 0.0106,
"step": 768
},
{
"epoch": 255.87,
"eval_exact_match": 0.648936170212766,
"eval_exec": 0.6866537717601547,
"eval_loss": 0.28018897771835327,
"eval_runtime": 176.9187,
"eval_samples_per_second": 5.844,
"step": 768
},
{
"epoch": 257.29,
"learning_rate": 0.0001,
"loss": 0.0119,
"step": 772
},
{
"epoch": 258.58,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 776
},
{
"epoch": 259.87,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 780
},
{
"epoch": 261.29,
"learning_rate": 0.0001,
"loss": 0.0108,
"step": 784
},
{
"epoch": 262.58,
"learning_rate": 0.0001,
"loss": 0.0101,
"step": 788
},
{
"epoch": 263.87,
"learning_rate": 0.0001,
"loss": 0.0112,
"step": 792
},
{
"epoch": 265.29,
"learning_rate": 0.0001,
"loss": 0.0108,
"step": 796
},
{
"epoch": 266.58,
"learning_rate": 0.0001,
"loss": 0.0096,
"step": 800
},
{
"epoch": 267.87,
"learning_rate": 0.0001,
"loss": 0.0087,
"step": 804
},
{
"epoch": 269.29,
"learning_rate": 0.0001,
"loss": 0.0105,
"step": 808
},
{
"epoch": 270.58,
"learning_rate": 0.0001,
"loss": 0.0097,
"step": 812
},
{
"epoch": 271.87,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 816
},
{
"epoch": 273.29,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 820
},
{
"epoch": 274.58,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 824
},
{
"epoch": 275.87,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 828
},
{
"epoch": 277.29,
"learning_rate": 0.0001,
"loss": 0.0101,
"step": 832
},
{
"epoch": 277.29,
"eval_exact_match": 0.6760154738878144,
"eval_exec": 0.7050290135396519,
"eval_loss": 0.28687429428100586,
"eval_runtime": 171.0426,
"eval_samples_per_second": 6.045,
"step": 832
},
{
"epoch": 278.58,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 836
},
{
"epoch": 279.87,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 840
},
{
"epoch": 281.29,
"learning_rate": 0.0001,
"loss": 0.0084,
"step": 844
},
{
"epoch": 282.58,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 848
},
{
"epoch": 283.87,
"learning_rate": 0.0001,
"loss": 0.0072,
"step": 852
},
{
"epoch": 285.29,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 856
},
{
"epoch": 286.58,
"learning_rate": 0.0001,
"loss": 0.0075,
"step": 860
},
{
"epoch": 287.87,
"learning_rate": 0.0001,
"loss": 0.0071,
"step": 864
},
{
"epoch": 289.29,
"learning_rate": 0.0001,
"loss": 0.0076,
"step": 868
},
{
"epoch": 290.58,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 872
},
{
"epoch": 291.87,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 876
},
{
"epoch": 293.29,
"learning_rate": 0.0001,
"loss": 0.0075,
"step": 880
},
{
"epoch": 294.58,
"learning_rate": 0.0001,
"loss": 0.0071,
"step": 884
},
{
"epoch": 295.87,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 888
},
{
"epoch": 297.29,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 892
},
{
"epoch": 298.58,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 896
},
{
"epoch": 298.58,
"eval_exact_match": 0.6460348162475822,
"eval_exec": 0.6914893617021277,
"eval_loss": 0.31529420614242554,
"eval_runtime": 178.51,
"eval_samples_per_second": 5.792,
"step": 896
},
{
"epoch": 299.87,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 900
},
{
"epoch": 301.29,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 904
},
{
"epoch": 302.58,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 908
},
{
"epoch": 303.87,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 912
},
{
"epoch": 305.29,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 916
},
{
"epoch": 306.58,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 920
},
{
"epoch": 307.87,
"learning_rate": 0.0001,
"loss": 0.0053,
"step": 924
},
{
"epoch": 309.29,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 928
},
{
"epoch": 310.58,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 932
},
{
"epoch": 311.87,
"learning_rate": 0.0001,
"loss": 0.0057,
"step": 936
},
{
"epoch": 313.29,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 940
},
{
"epoch": 314.58,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 944
},
{
"epoch": 315.87,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 948
},
{
"epoch": 317.29,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 952
},
{
"epoch": 318.58,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 956
},
{
"epoch": 319.87,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 960
},
{
"epoch": 319.87,
"eval_exact_match": 0.6576402321083172,
"eval_exec": 0.6914893617021277,
"eval_loss": 0.3037155270576477,
"eval_runtime": 178.5948,
"eval_samples_per_second": 5.79,
"step": 960
},
{
"epoch": 321.29,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 964
},
{
"epoch": 322.58,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 968
},
{
"epoch": 323.87,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 972
},
{
"epoch": 325.29,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 976
},
{
"epoch": 326.58,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 980
},
{
"epoch": 327.87,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 984
},
{
"epoch": 329.29,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 988
},
{
"epoch": 330.58,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 992
},
{
"epoch": 331.87,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 996
},
{
"epoch": 333.29,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1000
},
{
"epoch": 334.58,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1004
},
{
"epoch": 335.87,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1008
},
{
"epoch": 337.29,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1012
},
{
"epoch": 338.58,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1016
},
{
"epoch": 339.87,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1020
},
{
"epoch": 341.29,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1024
},
{
"epoch": 341.29,
"eval_exact_match": 0.6586073500967118,
"eval_exec": 0.6924564796905223,
"eval_loss": 0.33920130133628845,
"eval_runtime": 178.406,
"eval_samples_per_second": 5.796,
"step": 1024
},
{
"epoch": 342.58,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1028
},
{
"epoch": 343.87,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1032
},
{
"epoch": 345.29,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1036
},
{
"epoch": 346.58,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1040
},
{
"epoch": 347.87,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1044
},
{
"epoch": 349.29,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1048
},
{
"epoch": 350.58,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1052
},
{
"epoch": 351.87,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1056
},
{
"epoch": 353.29,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1060
},
{
"epoch": 354.58,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 1064
},
{
"epoch": 355.87,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1068
},
{
"epoch": 357.29,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1072
},
{
"epoch": 358.58,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1076
},
{
"epoch": 359.87,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 1080
},
{
"epoch": 361.29,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1084
},
{
"epoch": 362.58,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1088
},
{
"epoch": 362.58,
"eval_exact_match": 0.6644100580270793,
"eval_exec": 0.6934235976789168,
"eval_loss": 0.3492871820926666,
"eval_runtime": 178.1643,
"eval_samples_per_second": 5.804,
"step": 1088
},
{
"epoch": 363.87,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1092
},
{
"epoch": 365.29,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1096
},
{
"epoch": 366.58,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1100
},
{
"epoch": 367.87,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1104
},
{
"epoch": 369.29,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1108
},
{
"epoch": 370.58,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1112
},
{
"epoch": 371.87,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1116
},
{
"epoch": 373.29,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1120
},
{
"epoch": 374.58,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1124
},
{
"epoch": 375.87,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1128
},
{
"epoch": 377.29,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1132
},
{
"epoch": 378.58,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1136
},
{
"epoch": 379.87,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1140
},
{
"epoch": 381.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1144
},
{
"epoch": 382.58,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1148
},
{
"epoch": 383.87,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1152
},
{
"epoch": 383.87,
"eval_exact_match": 0.6595744680851063,
"eval_exec": 0.690522243713733,
"eval_loss": 0.3714405298233032,
"eval_runtime": 175.1619,
"eval_samples_per_second": 5.903,
"step": 1152
},
{
"epoch": 385.29,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 1156
},
{
"epoch": 386.58,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1160
},
{
"epoch": 387.87,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1164
},
{
"epoch": 389.29,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1168
},
{
"epoch": 390.58,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1172
},
{
"epoch": 391.87,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1176
},
{
"epoch": 393.29,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1180
},
{
"epoch": 394.58,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1184
},
{
"epoch": 395.87,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1188
},
{
"epoch": 397.29,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 1192
},
{
"epoch": 398.58,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1196
},
{
"epoch": 399.87,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1200
},
{
"epoch": 401.29,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1204
},
{
"epoch": 402.58,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1208
},
{
"epoch": 403.87,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1212
},
{
"epoch": 405.29,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 1216
},
{
"epoch": 405.29,
"eval_exact_match": 0.6586073500967118,
"eval_exec": 0.6856866537717602,
"eval_loss": 0.37175869941711426,
"eval_runtime": 170.7264,
"eval_samples_per_second": 6.056,
"step": 1216
},
{
"epoch": 406.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1220
},
{
"epoch": 407.87,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1224
},
{
"epoch": 409.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1228
},
{
"epoch": 410.58,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1232
},
{
"epoch": 411.87,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1236
},
{
"epoch": 413.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1240
},
{
"epoch": 414.58,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1244
},
{
"epoch": 415.87,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1248
},
{
"epoch": 417.29,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1252
},
{
"epoch": 418.58,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1256
},
{
"epoch": 419.87,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1260
},
{
"epoch": 421.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1264
},
{
"epoch": 422.58,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1268
},
{
"epoch": 423.87,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1272
},
{
"epoch": 425.29,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1276
},
{
"epoch": 426.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1280
},
{
"epoch": 426.58,
"eval_exact_match": 0.6624758220502901,
"eval_exec": 0.6914893617021277,
"eval_loss": 0.38388630747795105,
"eval_runtime": 174.5992,
"eval_samples_per_second": 5.922,
"step": 1280
},
{
"epoch": 427.87,
"learning_rate": 0.0001,
"loss": 0.0113,
"step": 1284
},
{
"epoch": 429.29,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 1288
},
{
"epoch": 430.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1292
},
{
"epoch": 431.87,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1296
},
{
"epoch": 433.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1300
},
{
"epoch": 434.58,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1304
},
{
"epoch": 435.87,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1308
},
{
"epoch": 437.29,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1312
},
{
"epoch": 438.58,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1316
},
{
"epoch": 439.87,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 1320
},
{
"epoch": 441.29,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1324
},
{
"epoch": 442.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1328
},
{
"epoch": 443.87,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1332
},
{
"epoch": 445.29,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1336
},
{
"epoch": 446.58,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1340
},
{
"epoch": 447.87,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1344
},
{
"epoch": 447.87,
"eval_exact_match": 0.6673114119922631,
"eval_exec": 0.7040618955512572,
"eval_loss": 0.3832179009914398,
"eval_runtime": 175.6301,
"eval_samples_per_second": 5.887,
"step": 1344
},
{
"epoch": 449.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1348
},
{
"epoch": 450.58,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1352
},
{
"epoch": 451.87,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1356
},
{
"epoch": 453.29,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1360
},
{
"epoch": 454.58,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1364
},
{
"epoch": 455.87,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1368
},
{
"epoch": 457.29,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1372
},
{
"epoch": 458.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1376
},
{
"epoch": 459.87,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 1380
},
{
"epoch": 461.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1384
},
{
"epoch": 462.58,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 1388
},
{
"epoch": 463.87,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1392
},
{
"epoch": 465.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1396
},
{
"epoch": 466.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1400
},
{
"epoch": 467.87,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1404
},
{
"epoch": 469.29,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1408
},
{
"epoch": 469.29,
"eval_exact_match": 0.6431334622823984,
"eval_exec": 0.688588007736944,
"eval_loss": 0.35097846388816833,
"eval_runtime": 179.7423,
"eval_samples_per_second": 5.753,
"step": 1408
},
{
"epoch": 470.58,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1412
},
{
"epoch": 471.87,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1416
},
{
"epoch": 473.29,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1420
},
{
"epoch": 474.58,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1424
},
{
"epoch": 475.87,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1428
},
{
"epoch": 477.29,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1432
},
{
"epoch": 478.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1436
},
{
"epoch": 479.87,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1440
},
{
"epoch": 481.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1444
},
{
"epoch": 482.58,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1448
},
{
"epoch": 483.87,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 1452
},
{
"epoch": 485.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1456
},
{
"epoch": 486.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1460
},
{
"epoch": 487.87,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1464
},
{
"epoch": 489.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1468
},
{
"epoch": 490.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1472
},
{
"epoch": 490.58,
"eval_exact_match": 0.6663442940038685,
"eval_exec": 0.6982591876208898,
"eval_loss": 0.38962414860725403,
"eval_runtime": 177.5423,
"eval_samples_per_second": 5.824,
"step": 1472
},
{
"epoch": 491.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1476
},
{
"epoch": 493.29,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1480
},
{
"epoch": 494.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1484
},
{
"epoch": 495.87,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1488
},
{
"epoch": 497.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1492
},
{
"epoch": 498.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1496
},
{
"epoch": 499.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1500
},
{
"epoch": 501.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1504
},
{
"epoch": 502.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1508
},
{
"epoch": 503.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1512
},
{
"epoch": 505.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1516
},
{
"epoch": 506.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1520
},
{
"epoch": 507.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1524
},
{
"epoch": 509.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1528
},
{
"epoch": 510.58,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1532
},
{
"epoch": 511.87,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1536
},
{
"epoch": 511.87,
"eval_exact_match": 0.6750483558994197,
"eval_exec": 0.6963249516441006,
"eval_loss": 0.3574667274951935,
"eval_runtime": 173.0162,
"eval_samples_per_second": 5.976,
"step": 1536
},
{
"epoch": 513.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1540
},
{
"epoch": 514.58,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1544
},
{
"epoch": 515.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1548
},
{
"epoch": 517.29,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1552
},
{
"epoch": 518.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1556
},
{
"epoch": 519.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1560
},
{
"epoch": 521.29,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1564
},
{
"epoch": 522.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1568
},
{
"epoch": 523.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1572
},
{
"epoch": 525.29,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1576
},
{
"epoch": 526.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1580
},
{
"epoch": 527.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1584
},
{
"epoch": 529.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1588
},
{
"epoch": 530.58,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1592
},
{
"epoch": 531.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1596
},
{
"epoch": 533.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1600
},
{
"epoch": 533.29,
"eval_exact_match": 0.6644100580270793,
"eval_exec": 0.6982591876208898,
"eval_loss": 0.40679118037223816,
"eval_runtime": 180.9433,
"eval_samples_per_second": 5.714,
"step": 1600
},
{
"epoch": 534.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1604
},
{
"epoch": 535.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1608
},
{
"epoch": 537.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1612
},
{
"epoch": 538.58,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1616
},
{
"epoch": 539.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1620
},
{
"epoch": 541.29,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 1624
},
{
"epoch": 542.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1628
},
{
"epoch": 543.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1632
},
{
"epoch": 545.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1636
},
{
"epoch": 546.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1640
},
{
"epoch": 547.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1644
},
{
"epoch": 549.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1648
},
{
"epoch": 550.58,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 1652
},
{
"epoch": 551.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1656
},
{
"epoch": 553.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1660
},
{
"epoch": 554.58,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1664
},
{
"epoch": 554.58,
"eval_exact_match": 0.6876208897485493,
"eval_exec": 0.7156673114119922,
"eval_loss": 0.4119175374507904,
"eval_runtime": 172.8345,
"eval_samples_per_second": 5.983,
"step": 1664
},
{
"epoch": 555.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1668
},
{
"epoch": 557.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1672
},
{
"epoch": 558.58,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1676
},
{
"epoch": 559.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1680
},
{
"epoch": 561.29,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1684
},
{
"epoch": 562.58,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1688
},
{
"epoch": 563.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1692
},
{
"epoch": 565.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1696
},
{
"epoch": 566.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1700
},
{
"epoch": 567.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1704
},
{
"epoch": 569.29,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1708
},
{
"epoch": 570.58,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1712
},
{
"epoch": 571.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1716
},
{
"epoch": 573.29,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 1720
},
{
"epoch": 574.58,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1724
},
{
"epoch": 575.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 1728
},
{
"epoch": 575.87,
"eval_exact_match": 0.6624758220502901,
"eval_exec": 0.6818181818181818,
"eval_loss": 0.40822312235832214,
"eval_runtime": 173.4405,
"eval_samples_per_second": 5.962,
"step": 1728
}
],
"max_steps": 9216,
"num_train_epochs": 3072,
"total_flos": 1.2117197167159542e+19,
"trial_name": null,
"trial_params": null
}