dfm_cosql / trainer_state.json
wowcz
dfm_cosql
5efae8b
{
"best_metric": 0.4657398212512413,
"best_model_checkpoint": "/mnt/chenzhi/dialogzoo/finetune/txt2sql_picard_cosql/checkpoint-6848",
"epoch": 855.9933373712902,
"global_step": 6848,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 8.9198,
"step": 1
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 4.4541,
"step": 4
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 2.0276,
"step": 8
},
{
"epoch": 1.5,
"learning_rate": 0.0001,
"loss": 1.1989,
"step": 12
},
{
"epoch": 1.99,
"learning_rate": 0.0001,
"loss": 0.8306,
"step": 16
},
{
"epoch": 2.5,
"learning_rate": 0.0001,
"loss": 0.6585,
"step": 20
},
{
"epoch": 2.99,
"learning_rate": 0.0001,
"loss": 0.5417,
"step": 24
},
{
"epoch": 3.5,
"learning_rate": 0.0001,
"loss": 0.4681,
"step": 28
},
{
"epoch": 3.99,
"learning_rate": 0.0001,
"loss": 0.4011,
"step": 32
},
{
"epoch": 4.5,
"learning_rate": 0.0001,
"loss": 0.3661,
"step": 36
},
{
"epoch": 4.99,
"learning_rate": 0.0001,
"loss": 0.3404,
"step": 40
},
{
"epoch": 5.5,
"learning_rate": 0.0001,
"loss": 0.3268,
"step": 44
},
{
"epoch": 5.99,
"learning_rate": 0.0001,
"loss": 0.2935,
"step": 48
},
{
"epoch": 6.5,
"learning_rate": 0.0001,
"loss": 0.2853,
"step": 52
},
{
"epoch": 6.99,
"learning_rate": 0.0001,
"loss": 0.2694,
"step": 56
},
{
"epoch": 7.5,
"learning_rate": 0.0001,
"loss": 0.2601,
"step": 60
},
{
"epoch": 7.99,
"learning_rate": 0.0001,
"loss": 0.2487,
"step": 64
},
{
"epoch": 7.99,
"eval_exact_match": 0.24726911618669314,
"eval_exec": 0.30883813306852037,
"eval_loss": 0.32532989978790283,
"eval_runtime": 219.0487,
"eval_samples_per_second": 5.935,
"step": 64
},
{
"epoch": 8.5,
"learning_rate": 0.0001,
"loss": 0.2352,
"step": 68
},
{
"epoch": 8.99,
"learning_rate": 0.0001,
"loss": 0.2257,
"step": 72
},
{
"epoch": 9.5,
"learning_rate": 0.0001,
"loss": 0.222,
"step": 76
},
{
"epoch": 9.99,
"learning_rate": 0.0001,
"loss": 0.2146,
"step": 80
},
{
"epoch": 10.5,
"learning_rate": 0.0001,
"loss": 0.2115,
"step": 84
},
{
"epoch": 10.99,
"learning_rate": 0.0001,
"loss": 0.2032,
"step": 88
},
{
"epoch": 11.5,
"learning_rate": 0.0001,
"loss": 0.1954,
"step": 92
},
{
"epoch": 11.99,
"learning_rate": 0.0001,
"loss": 0.186,
"step": 96
},
{
"epoch": 12.5,
"learning_rate": 0.0001,
"loss": 0.1808,
"step": 100
},
{
"epoch": 12.99,
"learning_rate": 0.0001,
"loss": 0.18,
"step": 104
},
{
"epoch": 13.5,
"learning_rate": 0.0001,
"loss": 0.177,
"step": 108
},
{
"epoch": 13.99,
"learning_rate": 0.0001,
"loss": 0.1714,
"step": 112
},
{
"epoch": 14.5,
"learning_rate": 0.0001,
"loss": 0.1714,
"step": 116
},
{
"epoch": 14.99,
"learning_rate": 0.0001,
"loss": 0.1615,
"step": 120
},
{
"epoch": 15.5,
"learning_rate": 0.0001,
"loss": 0.1599,
"step": 124
},
{
"epoch": 15.99,
"learning_rate": 0.0001,
"loss": 0.1565,
"step": 128
},
{
"epoch": 15.99,
"eval_exact_match": 0.33068520357497516,
"eval_exec": 0.3843098311817279,
"eval_loss": 0.29061898589134216,
"eval_runtime": 200.5643,
"eval_samples_per_second": 6.482,
"step": 128
},
{
"epoch": 16.5,
"learning_rate": 0.0001,
"loss": 0.1513,
"step": 132
},
{
"epoch": 16.99,
"learning_rate": 0.0001,
"loss": 0.143,
"step": 136
},
{
"epoch": 17.5,
"learning_rate": 0.0001,
"loss": 0.1426,
"step": 140
},
{
"epoch": 17.99,
"learning_rate": 0.0001,
"loss": 0.1403,
"step": 144
},
{
"epoch": 18.5,
"learning_rate": 0.0001,
"loss": 0.1441,
"step": 148
},
{
"epoch": 18.99,
"learning_rate": 0.0001,
"loss": 0.1378,
"step": 152
},
{
"epoch": 19.5,
"learning_rate": 0.0001,
"loss": 0.1344,
"step": 156
},
{
"epoch": 19.99,
"learning_rate": 0.0001,
"loss": 0.1293,
"step": 160
},
{
"epoch": 20.5,
"learning_rate": 0.0001,
"loss": 0.1314,
"step": 164
},
{
"epoch": 20.99,
"learning_rate": 0.0001,
"loss": 0.1219,
"step": 168
},
{
"epoch": 21.5,
"learning_rate": 0.0001,
"loss": 0.1196,
"step": 172
},
{
"epoch": 21.99,
"learning_rate": 0.0001,
"loss": 0.1192,
"step": 176
},
{
"epoch": 22.5,
"learning_rate": 0.0001,
"loss": 0.1203,
"step": 180
},
{
"epoch": 22.99,
"learning_rate": 0.0001,
"loss": 0.1189,
"step": 184
},
{
"epoch": 23.5,
"learning_rate": 0.0001,
"loss": 0.1154,
"step": 188
},
{
"epoch": 23.99,
"learning_rate": 0.0001,
"loss": 0.1142,
"step": 192
},
{
"epoch": 23.99,
"eval_exact_match": 0.3426017874875869,
"eval_exec": 0.4011916583912612,
"eval_loss": 0.28066790103912354,
"eval_runtime": 235.2994,
"eval_samples_per_second": 5.525,
"step": 192
},
{
"epoch": 24.5,
"learning_rate": 0.0001,
"loss": 0.1104,
"step": 196
},
{
"epoch": 24.99,
"learning_rate": 0.0001,
"loss": 0.1092,
"step": 200
},
{
"epoch": 25.5,
"learning_rate": 0.0001,
"loss": 0.1079,
"step": 204
},
{
"epoch": 25.99,
"learning_rate": 0.0001,
"loss": 0.1043,
"step": 208
},
{
"epoch": 26.5,
"learning_rate": 0.0001,
"loss": 0.1068,
"step": 212
},
{
"epoch": 26.99,
"learning_rate": 0.0001,
"loss": 0.1009,
"step": 216
},
{
"epoch": 27.5,
"learning_rate": 0.0001,
"loss": 0.1033,
"step": 220
},
{
"epoch": 27.99,
"learning_rate": 0.0001,
"loss": 0.1013,
"step": 224
},
{
"epoch": 28.5,
"learning_rate": 0.0001,
"loss": 0.0986,
"step": 228
},
{
"epoch": 28.99,
"learning_rate": 0.0001,
"loss": 0.0951,
"step": 232
},
{
"epoch": 29.5,
"learning_rate": 0.0001,
"loss": 0.0947,
"step": 236
},
{
"epoch": 29.99,
"learning_rate": 0.0001,
"loss": 0.0917,
"step": 240
},
{
"epoch": 30.5,
"learning_rate": 0.0001,
"loss": 0.0959,
"step": 244
},
{
"epoch": 30.99,
"learning_rate": 0.0001,
"loss": 0.0922,
"step": 248
},
{
"epoch": 31.5,
"learning_rate": 0.0001,
"loss": 0.0892,
"step": 252
},
{
"epoch": 31.99,
"learning_rate": 0.0001,
"loss": 0.0885,
"step": 256
},
{
"epoch": 31.99,
"eval_exact_match": 0.36742800397219466,
"eval_exec": 0.41509433962264153,
"eval_loss": 0.28681814670562744,
"eval_runtime": 236.9193,
"eval_samples_per_second": 5.487,
"step": 256
},
{
"epoch": 32.5,
"learning_rate": 0.0001,
"loss": 0.087,
"step": 260
},
{
"epoch": 32.99,
"learning_rate": 0.0001,
"loss": 0.0853,
"step": 264
},
{
"epoch": 33.5,
"learning_rate": 0.0001,
"loss": 0.0847,
"step": 268
},
{
"epoch": 33.99,
"learning_rate": 0.0001,
"loss": 0.0821,
"step": 272
},
{
"epoch": 34.5,
"learning_rate": 0.0001,
"loss": 0.0802,
"step": 276
},
{
"epoch": 34.99,
"learning_rate": 0.0001,
"loss": 0.084,
"step": 280
},
{
"epoch": 35.5,
"learning_rate": 0.0001,
"loss": 0.0844,
"step": 284
},
{
"epoch": 35.99,
"learning_rate": 0.0001,
"loss": 0.0803,
"step": 288
},
{
"epoch": 36.5,
"learning_rate": 0.0001,
"loss": 0.0786,
"step": 292
},
{
"epoch": 36.99,
"learning_rate": 0.0001,
"loss": 0.0735,
"step": 296
},
{
"epoch": 37.5,
"learning_rate": 0.0001,
"loss": 0.0784,
"step": 300
},
{
"epoch": 37.99,
"learning_rate": 0.0001,
"loss": 0.0733,
"step": 304
},
{
"epoch": 38.5,
"learning_rate": 0.0001,
"loss": 0.075,
"step": 308
},
{
"epoch": 38.99,
"learning_rate": 0.0001,
"loss": 0.0747,
"step": 312
},
{
"epoch": 39.5,
"learning_rate": 0.0001,
"loss": 0.0733,
"step": 316
},
{
"epoch": 39.99,
"learning_rate": 0.0001,
"loss": 0.0712,
"step": 320
},
{
"epoch": 39.99,
"eval_exact_match": 0.407149950347567,
"eval_exec": 0.44885799404170806,
"eval_loss": 0.29831913113594055,
"eval_runtime": 183.5809,
"eval_samples_per_second": 7.081,
"step": 320
},
{
"epoch": 40.5,
"learning_rate": 0.0001,
"loss": 0.0706,
"step": 324
},
{
"epoch": 40.99,
"learning_rate": 0.0001,
"loss": 0.071,
"step": 328
},
{
"epoch": 41.5,
"learning_rate": 0.0001,
"loss": 0.0675,
"step": 332
},
{
"epoch": 41.99,
"learning_rate": 0.0001,
"loss": 0.0663,
"step": 336
},
{
"epoch": 42.5,
"learning_rate": 0.0001,
"loss": 0.0652,
"step": 340
},
{
"epoch": 42.99,
"learning_rate": 0.0001,
"loss": 0.068,
"step": 344
},
{
"epoch": 43.5,
"learning_rate": 0.0001,
"loss": 0.066,
"step": 348
},
{
"epoch": 43.99,
"learning_rate": 0.0001,
"loss": 0.0658,
"step": 352
},
{
"epoch": 44.5,
"learning_rate": 0.0001,
"loss": 0.0628,
"step": 356
},
{
"epoch": 44.99,
"learning_rate": 0.0001,
"loss": 0.063,
"step": 360
},
{
"epoch": 45.5,
"learning_rate": 0.0001,
"loss": 0.0607,
"step": 364
},
{
"epoch": 45.99,
"learning_rate": 0.0001,
"loss": 0.0605,
"step": 368
},
{
"epoch": 46.5,
"learning_rate": 0.0001,
"loss": 0.06,
"step": 372
},
{
"epoch": 46.99,
"learning_rate": 0.0001,
"loss": 0.0618,
"step": 376
},
{
"epoch": 47.5,
"learning_rate": 0.0001,
"loss": 0.0605,
"step": 380
},
{
"epoch": 47.99,
"learning_rate": 0.0001,
"loss": 0.0586,
"step": 384
},
{
"epoch": 47.99,
"eval_exact_match": 0.423038728897716,
"eval_exec": 0.4637537239324727,
"eval_loss": 0.31259259581565857,
"eval_runtime": 192.9699,
"eval_samples_per_second": 6.737,
"step": 384
},
{
"epoch": 48.5,
"learning_rate": 0.0001,
"loss": 0.058,
"step": 388
},
{
"epoch": 48.99,
"learning_rate": 0.0001,
"loss": 0.0573,
"step": 392
},
{
"epoch": 49.5,
"learning_rate": 0.0001,
"loss": 0.0594,
"step": 396
},
{
"epoch": 49.99,
"learning_rate": 0.0001,
"loss": 0.0552,
"step": 400
},
{
"epoch": 50.5,
"learning_rate": 0.0001,
"loss": 0.056,
"step": 404
},
{
"epoch": 50.99,
"learning_rate": 0.0001,
"loss": 0.0537,
"step": 408
},
{
"epoch": 51.5,
"learning_rate": 0.0001,
"loss": 0.054,
"step": 412
},
{
"epoch": 51.99,
"learning_rate": 0.0001,
"loss": 0.0555,
"step": 416
},
{
"epoch": 52.5,
"learning_rate": 0.0001,
"loss": 0.0515,
"step": 420
},
{
"epoch": 52.99,
"learning_rate": 0.0001,
"loss": 0.0522,
"step": 424
},
{
"epoch": 53.5,
"learning_rate": 0.0001,
"loss": 0.0507,
"step": 428
},
{
"epoch": 53.99,
"learning_rate": 0.0001,
"loss": 0.051,
"step": 432
},
{
"epoch": 54.5,
"learning_rate": 0.0001,
"loss": 0.0492,
"step": 436
},
{
"epoch": 54.99,
"learning_rate": 0.0001,
"loss": 0.0503,
"step": 440
},
{
"epoch": 55.5,
"learning_rate": 0.0001,
"loss": 0.0484,
"step": 444
},
{
"epoch": 55.99,
"learning_rate": 0.0001,
"loss": 0.0486,
"step": 448
},
{
"epoch": 55.99,
"eval_exact_match": 0.4270109235352532,
"eval_exec": 0.4657398212512413,
"eval_loss": 0.32657375931739807,
"eval_runtime": 181.0806,
"eval_samples_per_second": 7.179,
"step": 448
},
{
"epoch": 56.5,
"learning_rate": 0.0001,
"loss": 0.0491,
"step": 452
},
{
"epoch": 56.99,
"learning_rate": 0.0001,
"loss": 0.0505,
"step": 456
},
{
"epoch": 57.5,
"learning_rate": 0.0001,
"loss": 0.0491,
"step": 460
},
{
"epoch": 57.99,
"learning_rate": 0.0001,
"loss": 0.0487,
"step": 464
},
{
"epoch": 58.5,
"learning_rate": 0.0001,
"loss": 0.0456,
"step": 468
},
{
"epoch": 58.99,
"learning_rate": 0.0001,
"loss": 0.0454,
"step": 472
},
{
"epoch": 59.5,
"learning_rate": 0.0001,
"loss": 0.0449,
"step": 476
},
{
"epoch": 59.99,
"learning_rate": 0.0001,
"loss": 0.0429,
"step": 480
},
{
"epoch": 60.5,
"learning_rate": 0.0001,
"loss": 0.0441,
"step": 484
},
{
"epoch": 60.99,
"learning_rate": 0.0001,
"loss": 0.0451,
"step": 488
},
{
"epoch": 61.5,
"learning_rate": 0.0001,
"loss": 0.0447,
"step": 492
},
{
"epoch": 61.99,
"learning_rate": 0.0001,
"loss": 0.0423,
"step": 496
},
{
"epoch": 62.5,
"learning_rate": 0.0001,
"loss": 0.0429,
"step": 500
},
{
"epoch": 62.99,
"learning_rate": 0.0001,
"loss": 0.0412,
"step": 504
},
{
"epoch": 63.5,
"learning_rate": 0.0001,
"loss": 0.0423,
"step": 508
},
{
"epoch": 63.99,
"learning_rate": 0.0001,
"loss": 0.0412,
"step": 512
},
{
"epoch": 63.99,
"eval_exact_match": 0.40913604766633566,
"eval_exec": 0.45878848063555117,
"eval_loss": 0.3272022306919098,
"eval_runtime": 205.684,
"eval_samples_per_second": 6.32,
"step": 512
},
{
"epoch": 64.5,
"learning_rate": 0.0001,
"loss": 0.0397,
"step": 516
},
{
"epoch": 64.99,
"learning_rate": 0.0001,
"loss": 0.0394,
"step": 520
},
{
"epoch": 65.5,
"learning_rate": 0.0001,
"loss": 0.0411,
"step": 524
},
{
"epoch": 65.99,
"learning_rate": 0.0001,
"loss": 0.0418,
"step": 528
},
{
"epoch": 66.5,
"learning_rate": 0.0001,
"loss": 0.038,
"step": 532
},
{
"epoch": 66.99,
"learning_rate": 0.0001,
"loss": 0.0388,
"step": 536
},
{
"epoch": 67.5,
"learning_rate": 0.0001,
"loss": 0.0383,
"step": 540
},
{
"epoch": 67.99,
"learning_rate": 0.0001,
"loss": 0.0384,
"step": 544
},
{
"epoch": 68.5,
"learning_rate": 0.0001,
"loss": 0.039,
"step": 548
},
{
"epoch": 68.99,
"learning_rate": 0.0001,
"loss": 0.0366,
"step": 552
},
{
"epoch": 69.5,
"learning_rate": 0.0001,
"loss": 0.0364,
"step": 556
},
{
"epoch": 69.99,
"learning_rate": 0.0001,
"loss": 0.0363,
"step": 560
},
{
"epoch": 70.5,
"learning_rate": 0.0001,
"loss": 0.036,
"step": 564
},
{
"epoch": 70.99,
"learning_rate": 0.0001,
"loss": 0.0358,
"step": 568
},
{
"epoch": 71.5,
"learning_rate": 0.0001,
"loss": 0.0339,
"step": 572
},
{
"epoch": 71.99,
"learning_rate": 0.0001,
"loss": 0.0374,
"step": 576
},
{
"epoch": 71.99,
"eval_exact_match": 0.435948361469712,
"eval_exec": 0.4766633565044687,
"eval_loss": 0.3480900824069977,
"eval_runtime": 174.2765,
"eval_samples_per_second": 7.459,
"step": 576
},
{
"epoch": 72.5,
"learning_rate": 0.0001,
"loss": 0.0376,
"step": 580
},
{
"epoch": 72.99,
"learning_rate": 0.0001,
"loss": 0.0341,
"step": 584
},
{
"epoch": 73.5,
"learning_rate": 0.0001,
"loss": 0.0329,
"step": 588
},
{
"epoch": 73.99,
"learning_rate": 0.0001,
"loss": 0.0329,
"step": 592
},
{
"epoch": 74.5,
"learning_rate": 0.0001,
"loss": 0.0334,
"step": 596
},
{
"epoch": 74.99,
"learning_rate": 0.0001,
"loss": 0.0334,
"step": 600
},
{
"epoch": 75.5,
"learning_rate": 0.0001,
"loss": 0.0327,
"step": 604
},
{
"epoch": 75.99,
"learning_rate": 0.0001,
"loss": 0.0328,
"step": 608
},
{
"epoch": 76.5,
"learning_rate": 0.0001,
"loss": 0.0321,
"step": 612
},
{
"epoch": 76.99,
"learning_rate": 0.0001,
"loss": 0.0327,
"step": 616
},
{
"epoch": 77.5,
"learning_rate": 0.0001,
"loss": 0.0321,
"step": 620
},
{
"epoch": 77.99,
"learning_rate": 0.0001,
"loss": 0.03,
"step": 624
},
{
"epoch": 78.5,
"learning_rate": 0.0001,
"loss": 0.0313,
"step": 628
},
{
"epoch": 78.99,
"learning_rate": 0.0001,
"loss": 0.0335,
"step": 632
},
{
"epoch": 79.5,
"learning_rate": 0.0001,
"loss": 0.0297,
"step": 636
},
{
"epoch": 79.99,
"learning_rate": 0.0001,
"loss": 0.0293,
"step": 640
},
{
"epoch": 79.99,
"eval_exact_match": 0.42899702085402186,
"eval_exec": 0.46871896722939427,
"eval_loss": 0.3477668762207031,
"eval_runtime": 228.958,
"eval_samples_per_second": 5.678,
"step": 640
},
{
"epoch": 80.5,
"learning_rate": 0.0001,
"loss": 0.0284,
"step": 644
},
{
"epoch": 80.99,
"learning_rate": 0.0001,
"loss": 0.028,
"step": 648
},
{
"epoch": 81.5,
"learning_rate": 0.0001,
"loss": 0.0311,
"step": 652
},
{
"epoch": 81.99,
"learning_rate": 0.0001,
"loss": 0.0286,
"step": 656
},
{
"epoch": 82.5,
"learning_rate": 0.0001,
"loss": 0.0299,
"step": 660
},
{
"epoch": 82.99,
"learning_rate": 0.0001,
"loss": 0.0294,
"step": 664
},
{
"epoch": 83.5,
"learning_rate": 0.0001,
"loss": 0.0265,
"step": 668
},
{
"epoch": 83.99,
"learning_rate": 0.0001,
"loss": 0.0269,
"step": 672
},
{
"epoch": 84.5,
"learning_rate": 0.0001,
"loss": 0.0267,
"step": 676
},
{
"epoch": 84.99,
"learning_rate": 0.0001,
"loss": 0.0269,
"step": 680
},
{
"epoch": 85.5,
"learning_rate": 0.0001,
"loss": 0.027,
"step": 684
},
{
"epoch": 85.99,
"learning_rate": 0.0001,
"loss": 0.0269,
"step": 688
},
{
"epoch": 86.5,
"learning_rate": 0.0001,
"loss": 0.026,
"step": 692
},
{
"epoch": 86.99,
"learning_rate": 0.0001,
"loss": 0.0259,
"step": 696
},
{
"epoch": 87.5,
"learning_rate": 0.0001,
"loss": 0.0251,
"step": 700
},
{
"epoch": 87.99,
"learning_rate": 0.0001,
"loss": 0.0253,
"step": 704
},
{
"epoch": 87.99,
"eval_exact_match": 0.423038728897716,
"eval_exec": 0.46971201588877853,
"eval_loss": 0.36298030614852905,
"eval_runtime": 237.4093,
"eval_samples_per_second": 5.476,
"step": 704
},
{
"epoch": 88.5,
"learning_rate": 0.0001,
"loss": 0.0252,
"step": 708
},
{
"epoch": 88.99,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 712
},
{
"epoch": 89.5,
"learning_rate": 0.0001,
"loss": 0.0262,
"step": 716
},
{
"epoch": 89.99,
"learning_rate": 0.0001,
"loss": 0.0261,
"step": 720
},
{
"epoch": 90.5,
"learning_rate": 0.0001,
"loss": 0.0236,
"step": 724
},
{
"epoch": 90.99,
"learning_rate": 0.0001,
"loss": 0.024,
"step": 728
},
{
"epoch": 91.5,
"learning_rate": 0.0001,
"loss": 0.0231,
"step": 732
},
{
"epoch": 91.99,
"learning_rate": 0.0001,
"loss": 0.0241,
"step": 736
},
{
"epoch": 92.5,
"learning_rate": 0.0001,
"loss": 0.0244,
"step": 740
},
{
"epoch": 92.99,
"learning_rate": 0.0001,
"loss": 0.0242,
"step": 744
},
{
"epoch": 93.5,
"learning_rate": 0.0001,
"loss": 0.023,
"step": 748
},
{
"epoch": 93.99,
"learning_rate": 0.0001,
"loss": 0.025,
"step": 752
},
{
"epoch": 94.5,
"learning_rate": 0.0001,
"loss": 0.0236,
"step": 756
},
{
"epoch": 94.99,
"learning_rate": 0.0001,
"loss": 0.022,
"step": 760
},
{
"epoch": 95.5,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 764
},
{
"epoch": 95.99,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 768
},
{
"epoch": 95.99,
"eval_exact_match": 0.4329692154915591,
"eval_exec": 0.46871896722939427,
"eval_loss": 0.3830316960811615,
"eval_runtime": 229.6043,
"eval_samples_per_second": 5.662,
"step": 768
},
{
"epoch": 96.5,
"learning_rate": 0.0001,
"loss": 0.0226,
"step": 772
},
{
"epoch": 96.99,
"learning_rate": 0.0001,
"loss": 0.0215,
"step": 776
},
{
"epoch": 97.5,
"learning_rate": 0.0001,
"loss": 0.0213,
"step": 780
},
{
"epoch": 97.99,
"learning_rate": 0.0001,
"loss": 0.0209,
"step": 784
},
{
"epoch": 98.5,
"learning_rate": 0.0001,
"loss": 0.0199,
"step": 788
},
{
"epoch": 98.99,
"learning_rate": 0.0001,
"loss": 0.0208,
"step": 792
},
{
"epoch": 99.5,
"learning_rate": 0.0001,
"loss": 0.0205,
"step": 796
},
{
"epoch": 99.99,
"learning_rate": 0.0001,
"loss": 0.0209,
"step": 800
},
{
"epoch": 100.5,
"learning_rate": 0.0001,
"loss": 0.0217,
"step": 804
},
{
"epoch": 100.99,
"learning_rate": 0.0001,
"loss": 0.02,
"step": 808
},
{
"epoch": 101.5,
"learning_rate": 0.0001,
"loss": 0.0192,
"step": 812
},
{
"epoch": 101.99,
"learning_rate": 0.0001,
"loss": 0.0195,
"step": 816
},
{
"epoch": 102.5,
"learning_rate": 0.0001,
"loss": 0.0194,
"step": 820
},
{
"epoch": 102.99,
"learning_rate": 0.0001,
"loss": 0.0193,
"step": 824
},
{
"epoch": 103.5,
"learning_rate": 0.0001,
"loss": 0.0212,
"step": 828
},
{
"epoch": 103.99,
"learning_rate": 0.0001,
"loss": 0.0195,
"step": 832
},
{
"epoch": 103.99,
"eval_exact_match": 0.41807348560079444,
"eval_exec": 0.4667328699106256,
"eval_loss": 0.388680100440979,
"eval_runtime": 220.6138,
"eval_samples_per_second": 5.893,
"step": 832
},
{
"epoch": 104.5,
"learning_rate": 0.0001,
"loss": 0.018,
"step": 836
},
{
"epoch": 104.99,
"learning_rate": 0.0001,
"loss": 0.0185,
"step": 840
},
{
"epoch": 105.5,
"learning_rate": 0.0001,
"loss": 0.0195,
"step": 844
},
{
"epoch": 105.99,
"learning_rate": 0.0001,
"loss": 0.0196,
"step": 848
},
{
"epoch": 106.5,
"learning_rate": 0.0001,
"loss": 0.0189,
"step": 852
},
{
"epoch": 106.99,
"learning_rate": 0.0001,
"loss": 0.0182,
"step": 856
},
{
"epoch": 107.5,
"learning_rate": 0.0001,
"loss": 0.0168,
"step": 860
},
{
"epoch": 107.99,
"learning_rate": 0.0001,
"loss": 0.018,
"step": 864
},
{
"epoch": 108.5,
"learning_rate": 0.0001,
"loss": 0.0181,
"step": 868
},
{
"epoch": 108.99,
"learning_rate": 0.0001,
"loss": 0.0179,
"step": 872
},
{
"epoch": 109.5,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 876
},
{
"epoch": 109.99,
"learning_rate": 0.0001,
"loss": 0.0187,
"step": 880
},
{
"epoch": 110.5,
"learning_rate": 0.0001,
"loss": 0.0178,
"step": 884
},
{
"epoch": 110.99,
"learning_rate": 0.0001,
"loss": 0.0161,
"step": 888
},
{
"epoch": 111.5,
"learning_rate": 0.0001,
"loss": 0.0164,
"step": 892
},
{
"epoch": 111.99,
"learning_rate": 0.0001,
"loss": 0.0164,
"step": 896
},
{
"epoch": 111.99,
"eval_exact_match": 0.41012909632572,
"eval_exec": 0.464746772591857,
"eval_loss": 0.3992396891117096,
"eval_runtime": 240.1288,
"eval_samples_per_second": 5.414,
"step": 896
},
{
"epoch": 112.5,
"learning_rate": 0.0001,
"loss": 0.0172,
"step": 900
},
{
"epoch": 112.99,
"learning_rate": 0.0001,
"loss": 0.0173,
"step": 904
},
{
"epoch": 113.5,
"learning_rate": 0.0001,
"loss": 0.0163,
"step": 908
},
{
"epoch": 113.99,
"learning_rate": 0.0001,
"loss": 0.0153,
"step": 912
},
{
"epoch": 114.5,
"learning_rate": 0.0001,
"loss": 0.0157,
"step": 916
},
{
"epoch": 114.99,
"learning_rate": 0.0001,
"loss": 0.0159,
"step": 920
},
{
"epoch": 115.5,
"learning_rate": 0.0001,
"loss": 0.016,
"step": 924
},
{
"epoch": 115.99,
"learning_rate": 0.0001,
"loss": 0.0152,
"step": 928
},
{
"epoch": 116.5,
"learning_rate": 0.0001,
"loss": 0.0159,
"step": 932
},
{
"epoch": 116.99,
"learning_rate": 0.0001,
"loss": 0.0161,
"step": 936
},
{
"epoch": 117.5,
"learning_rate": 0.0001,
"loss": 0.0152,
"step": 940
},
{
"epoch": 117.99,
"learning_rate": 0.0001,
"loss": 0.0149,
"step": 944
},
{
"epoch": 118.5,
"learning_rate": 0.0001,
"loss": 0.0145,
"step": 948
},
{
"epoch": 118.99,
"learning_rate": 0.0001,
"loss": 0.0151,
"step": 952
},
{
"epoch": 119.5,
"learning_rate": 0.0001,
"loss": 0.0165,
"step": 956
},
{
"epoch": 119.99,
"learning_rate": 0.0001,
"loss": 0.0179,
"step": 960
},
{
"epoch": 119.99,
"eval_exact_match": 0.4329692154915591,
"eval_exec": 0.4746772591857001,
"eval_loss": 0.42190492153167725,
"eval_runtime": 202.7706,
"eval_samples_per_second": 6.411,
"step": 960
},
{
"epoch": 120.5,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 964
},
{
"epoch": 120.99,
"learning_rate": 0.0001,
"loss": 0.014,
"step": 968
},
{
"epoch": 121.5,
"learning_rate": 0.0001,
"loss": 0.0144,
"step": 972
},
{
"epoch": 121.99,
"learning_rate": 0.0001,
"loss": 0.0141,
"step": 976
},
{
"epoch": 122.5,
"learning_rate": 0.0001,
"loss": 0.0137,
"step": 980
},
{
"epoch": 122.99,
"learning_rate": 0.0001,
"loss": 0.0143,
"step": 984
},
{
"epoch": 123.5,
"learning_rate": 0.0001,
"loss": 0.015,
"step": 988
},
{
"epoch": 123.99,
"learning_rate": 0.0001,
"loss": 0.0157,
"step": 992
},
{
"epoch": 124.5,
"learning_rate": 0.0001,
"loss": 0.0137,
"step": 996
},
{
"epoch": 124.99,
"learning_rate": 0.0001,
"loss": 0.0131,
"step": 1000
},
{
"epoch": 125.5,
"learning_rate": 0.0001,
"loss": 0.0135,
"step": 1004
},
{
"epoch": 125.99,
"learning_rate": 0.0001,
"loss": 0.0133,
"step": 1008
},
{
"epoch": 126.5,
"learning_rate": 0.0001,
"loss": 0.0128,
"step": 1012
},
{
"epoch": 126.99,
"learning_rate": 0.0001,
"loss": 0.0134,
"step": 1016
},
{
"epoch": 127.5,
"learning_rate": 0.0001,
"loss": 0.0125,
"step": 1020
},
{
"epoch": 127.99,
"learning_rate": 0.0001,
"loss": 0.012,
"step": 1024
},
{
"epoch": 127.99,
"eval_exact_match": 0.43892750744786496,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.4193364083766937,
"eval_runtime": 203.6399,
"eval_samples_per_second": 6.384,
"step": 1024
},
{
"epoch": 128.5,
"learning_rate": 0.0001,
"loss": 0.012,
"step": 1028
},
{
"epoch": 128.99,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 1032
},
{
"epoch": 129.5,
"learning_rate": 0.0001,
"loss": 0.0136,
"step": 1036
},
{
"epoch": 129.99,
"learning_rate": 0.0001,
"loss": 0.0123,
"step": 1040
},
{
"epoch": 130.5,
"learning_rate": 0.0001,
"loss": 0.0122,
"step": 1044
},
{
"epoch": 130.99,
"learning_rate": 0.0001,
"loss": 0.0126,
"step": 1048
},
{
"epoch": 131.5,
"learning_rate": 0.0001,
"loss": 0.0111,
"step": 1052
},
{
"epoch": 131.99,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 1056
},
{
"epoch": 132.5,
"learning_rate": 0.0001,
"loss": 0.0135,
"step": 1060
},
{
"epoch": 132.99,
"learning_rate": 0.0001,
"loss": 0.012,
"step": 1064
},
{
"epoch": 133.5,
"learning_rate": 0.0001,
"loss": 0.0119,
"step": 1068
},
{
"epoch": 133.99,
"learning_rate": 0.0001,
"loss": 0.0115,
"step": 1072
},
{
"epoch": 134.5,
"learning_rate": 0.0001,
"loss": 0.0113,
"step": 1076
},
{
"epoch": 134.99,
"learning_rate": 0.0001,
"loss": 0.0131,
"step": 1080
},
{
"epoch": 135.5,
"learning_rate": 0.0001,
"loss": 0.0126,
"step": 1084
},
{
"epoch": 135.99,
"learning_rate": 0.0001,
"loss": 0.0114,
"step": 1088
},
{
"epoch": 135.99,
"eval_exact_match": 0.4240317775571003,
"eval_exec": 0.4726911618669315,
"eval_loss": 0.4311941862106323,
"eval_runtime": 209.696,
"eval_samples_per_second": 6.199,
"step": 1088
},
{
"epoch": 136.5,
"learning_rate": 0.0001,
"loss": 0.0111,
"step": 1092
},
{
"epoch": 136.99,
"learning_rate": 0.0001,
"loss": 0.0109,
"step": 1096
},
{
"epoch": 137.5,
"learning_rate": 0.0001,
"loss": 0.0105,
"step": 1100
},
{
"epoch": 137.99,
"learning_rate": 0.0001,
"loss": 0.0108,
"step": 1104
},
{
"epoch": 138.5,
"learning_rate": 0.0001,
"loss": 0.0106,
"step": 1108
},
{
"epoch": 138.99,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 1112
},
{
"epoch": 139.5,
"learning_rate": 0.0001,
"loss": 0.0115,
"step": 1116
},
{
"epoch": 139.99,
"learning_rate": 0.0001,
"loss": 0.0111,
"step": 1120
},
{
"epoch": 140.5,
"learning_rate": 0.0001,
"loss": 0.0105,
"step": 1124
},
{
"epoch": 140.99,
"learning_rate": 0.0001,
"loss": 0.0101,
"step": 1128
},
{
"epoch": 141.5,
"learning_rate": 0.0001,
"loss": 0.0099,
"step": 1132
},
{
"epoch": 141.99,
"learning_rate": 0.0001,
"loss": 0.0099,
"step": 1136
},
{
"epoch": 142.5,
"learning_rate": 0.0001,
"loss": 0.0104,
"step": 1140
},
{
"epoch": 142.99,
"learning_rate": 0.0001,
"loss": 0.0111,
"step": 1144
},
{
"epoch": 143.5,
"learning_rate": 0.0001,
"loss": 0.011,
"step": 1148
},
{
"epoch": 143.99,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 1152
},
{
"epoch": 143.99,
"eval_exact_match": 0.42105263157894735,
"eval_exec": 0.47070506454816285,
"eval_loss": 0.4453062117099762,
"eval_runtime": 205.5286,
"eval_samples_per_second": 6.325,
"step": 1152
},
{
"epoch": 144.5,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 1156
},
{
"epoch": 144.99,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 1160
},
{
"epoch": 145.5,
"learning_rate": 0.0001,
"loss": 0.0096,
"step": 1164
},
{
"epoch": 145.99,
"learning_rate": 0.0001,
"loss": 0.0101,
"step": 1168
},
{
"epoch": 146.5,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 1172
},
{
"epoch": 146.99,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 1176
},
{
"epoch": 147.5,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 1180
},
{
"epoch": 147.99,
"learning_rate": 0.0001,
"loss": 0.0103,
"step": 1184
},
{
"epoch": 148.5,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 1188
},
{
"epoch": 148.99,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 1192
},
{
"epoch": 149.5,
"learning_rate": 0.0001,
"loss": 0.0093,
"step": 1196
},
{
"epoch": 149.99,
"learning_rate": 0.0001,
"loss": 0.0092,
"step": 1200
},
{
"epoch": 150.5,
"learning_rate": 0.0001,
"loss": 0.0087,
"step": 1204
},
{
"epoch": 150.99,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 1208
},
{
"epoch": 151.5,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 1212
},
{
"epoch": 151.99,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 1216
},
{
"epoch": 151.99,
"eval_exact_match": 0.43892750744786496,
"eval_exec": 0.47765640516385305,
"eval_loss": 0.45582684874534607,
"eval_runtime": 213.7344,
"eval_samples_per_second": 6.082,
"step": 1216
},
{
"epoch": 152.5,
"learning_rate": 0.0001,
"loss": 0.0092,
"step": 1220
},
{
"epoch": 152.99,
"learning_rate": 0.0001,
"loss": 0.009,
"step": 1224
},
{
"epoch": 153.5,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 1228
},
{
"epoch": 153.99,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 1232
},
{
"epoch": 154.5,
"learning_rate": 0.0001,
"loss": 0.0089,
"step": 1236
},
{
"epoch": 154.99,
"learning_rate": 0.0001,
"loss": 0.009,
"step": 1240
},
{
"epoch": 155.5,
"learning_rate": 0.0001,
"loss": 0.0084,
"step": 1244
},
{
"epoch": 155.99,
"learning_rate": 0.0001,
"loss": 0.0088,
"step": 1248
},
{
"epoch": 156.5,
"learning_rate": 0.0001,
"loss": 0.0084,
"step": 1252
},
{
"epoch": 156.99,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 1256
},
{
"epoch": 157.5,
"learning_rate": 0.0001,
"loss": 0.0087,
"step": 1260
},
{
"epoch": 157.99,
"learning_rate": 0.0001,
"loss": 0.0084,
"step": 1264
},
{
"epoch": 158.5,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 1268
},
{
"epoch": 158.99,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 1272
},
{
"epoch": 159.5,
"learning_rate": 0.0001,
"loss": 0.0082,
"step": 1276
},
{
"epoch": 159.99,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 1280
},
{
"epoch": 159.99,
"eval_exact_match": 0.4200595829195631,
"eval_exec": 0.47070506454816285,
"eval_loss": 0.45270583033561707,
"eval_runtime": 204.4816,
"eval_samples_per_second": 6.358,
"step": 1280
},
{
"epoch": 160.5,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 1284
},
{
"epoch": 160.99,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 1288
},
{
"epoch": 161.5,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 1292
},
{
"epoch": 161.99,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 1296
},
{
"epoch": 162.5,
"learning_rate": 0.0001,
"loss": 0.0082,
"step": 1300
},
{
"epoch": 162.99,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 1304
},
{
"epoch": 163.5,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 1308
},
{
"epoch": 163.99,
"learning_rate": 0.0001,
"loss": 0.0076,
"step": 1312
},
{
"epoch": 164.5,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 1316
},
{
"epoch": 164.99,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 1320
},
{
"epoch": 165.5,
"learning_rate": 0.0001,
"loss": 0.0081,
"step": 1324
},
{
"epoch": 165.99,
"learning_rate": 0.0001,
"loss": 0.008,
"step": 1328
},
{
"epoch": 166.5,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 1332
},
{
"epoch": 166.99,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 1336
},
{
"epoch": 167.5,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 1340
},
{
"epoch": 167.99,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 1344
},
{
"epoch": 167.99,
"eval_exact_match": 0.42502482621648463,
"eval_exec": 0.4766633565044687,
"eval_loss": 0.46810275316238403,
"eval_runtime": 209.333,
"eval_samples_per_second": 6.21,
"step": 1344
},
{
"epoch": 168.5,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 1348
},
{
"epoch": 168.99,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1352
},
{
"epoch": 169.5,
"learning_rate": 0.0001,
"loss": 0.0074,
"step": 1356
},
{
"epoch": 169.99,
"learning_rate": 0.0001,
"loss": 0.0073,
"step": 1360
},
{
"epoch": 170.5,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1364
},
{
"epoch": 170.99,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 1368
},
{
"epoch": 171.5,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 1372
},
{
"epoch": 171.99,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1376
},
{
"epoch": 172.5,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 1380
},
{
"epoch": 172.99,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1384
},
{
"epoch": 173.5,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 1388
},
{
"epoch": 173.99,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1392
},
{
"epoch": 174.5,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 1396
},
{
"epoch": 174.99,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 1400
},
{
"epoch": 175.5,
"learning_rate": 0.0001,
"loss": 0.0067,
"step": 1404
},
{
"epoch": 175.99,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1408
},
{
"epoch": 175.99,
"eval_exact_match": 0.423038728897716,
"eval_exec": 0.47070506454816285,
"eval_loss": 0.48861581087112427,
"eval_runtime": 209.5612,
"eval_samples_per_second": 6.203,
"step": 1408
},
{
"epoch": 176.5,
"learning_rate": 0.0001,
"loss": 0.0068,
"step": 1412
},
{
"epoch": 176.99,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 1416
},
{
"epoch": 177.5,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 1420
},
{
"epoch": 177.99,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 1424
},
{
"epoch": 178.5,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 1428
},
{
"epoch": 178.99,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 1432
},
{
"epoch": 179.5,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 1436
},
{
"epoch": 179.99,
"learning_rate": 0.0001,
"loss": 0.0062,
"step": 1440
},
{
"epoch": 180.5,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 1444
},
{
"epoch": 180.99,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 1448
},
{
"epoch": 181.5,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 1452
},
{
"epoch": 181.99,
"learning_rate": 0.0001,
"loss": 0.0058,
"step": 1456
},
{
"epoch": 182.5,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 1460
},
{
"epoch": 182.99,
"learning_rate": 0.0001,
"loss": 0.0074,
"step": 1464
},
{
"epoch": 183.5,
"learning_rate": 0.0001,
"loss": 0.0083,
"step": 1468
},
{
"epoch": 183.99,
"learning_rate": 0.0001,
"loss": 0.0075,
"step": 1472
},
{
"epoch": 183.99,
"eval_exact_match": 0.4399205561072492,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.46796470880508423,
"eval_runtime": 198.2198,
"eval_samples_per_second": 6.558,
"step": 1472
},
{
"epoch": 184.5,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 1476
},
{
"epoch": 184.99,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 1480
},
{
"epoch": 185.5,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 1484
},
{
"epoch": 185.99,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 1488
},
{
"epoch": 186.5,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 1492
},
{
"epoch": 186.99,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 1496
},
{
"epoch": 187.5,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 1500
},
{
"epoch": 187.99,
"learning_rate": 0.0001,
"loss": 0.0062,
"step": 1504
},
{
"epoch": 188.5,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 1508
},
{
"epoch": 188.99,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 1512
},
{
"epoch": 189.5,
"learning_rate": 0.0001,
"loss": 0.0062,
"step": 1516
},
{
"epoch": 189.99,
"learning_rate": 0.0001,
"loss": 0.007,
"step": 1520
},
{
"epoch": 190.5,
"learning_rate": 0.0001,
"loss": 0.0077,
"step": 1524
},
{
"epoch": 190.99,
"learning_rate": 0.0001,
"loss": 0.0057,
"step": 1528
},
{
"epoch": 191.5,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 1532
},
{
"epoch": 191.99,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 1536
},
{
"epoch": 191.99,
"eval_exact_match": 0.43197616683217477,
"eval_exec": 0.4746772591857001,
"eval_loss": 0.4912528097629547,
"eval_runtime": 222.179,
"eval_samples_per_second": 5.851,
"step": 1536
},
{
"epoch": 192.5,
"learning_rate": 0.0001,
"loss": 0.006,
"step": 1540
},
{
"epoch": 192.99,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 1544
},
{
"epoch": 193.5,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 1548
},
{
"epoch": 193.99,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 1552
},
{
"epoch": 194.5,
"learning_rate": 0.0001,
"loss": 0.0056,
"step": 1556
},
{
"epoch": 194.99,
"learning_rate": 0.0001,
"loss": 0.0055,
"step": 1560
},
{
"epoch": 195.5,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 1564
},
{
"epoch": 195.99,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 1568
},
{
"epoch": 196.5,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 1572
},
{
"epoch": 196.99,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 1576
},
{
"epoch": 197.5,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1580
},
{
"epoch": 197.99,
"learning_rate": 0.0001,
"loss": 0.0053,
"step": 1584
},
{
"epoch": 198.5,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1588
},
{
"epoch": 198.99,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 1592
},
{
"epoch": 199.5,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 1596
},
{
"epoch": 199.99,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1600
},
{
"epoch": 199.99,
"eval_exact_match": 0.4329692154915591,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.4948062002658844,
"eval_runtime": 223.792,
"eval_samples_per_second": 5.809,
"step": 1600
},
{
"epoch": 200.5,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1604
},
{
"epoch": 200.99,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1608
},
{
"epoch": 201.5,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1612
},
{
"epoch": 201.99,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1616
},
{
"epoch": 202.5,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1620
},
{
"epoch": 202.99,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 1624
},
{
"epoch": 203.5,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 1628
},
{
"epoch": 203.99,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1632
},
{
"epoch": 204.5,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 1636
},
{
"epoch": 204.99,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1640
},
{
"epoch": 205.5,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1644
},
{
"epoch": 205.99,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1648
},
{
"epoch": 206.5,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 1652
},
{
"epoch": 206.99,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 1656
},
{
"epoch": 207.5,
"learning_rate": 0.0001,
"loss": 0.0048,
"step": 1660
},
{
"epoch": 207.99,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1664
},
{
"epoch": 207.99,
"eval_exact_match": 0.42502482621648463,
"eval_exec": 0.48063555114200596,
"eval_loss": 0.4956875443458557,
"eval_runtime": 203.094,
"eval_samples_per_second": 6.401,
"step": 1664
},
{
"epoch": 208.5,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1668
},
{
"epoch": 208.99,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 1672
},
{
"epoch": 209.5,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1676
},
{
"epoch": 209.99,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1680
},
{
"epoch": 210.5,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1684
},
{
"epoch": 210.99,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1688
},
{
"epoch": 211.5,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 1692
},
{
"epoch": 211.99,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1696
},
{
"epoch": 212.5,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 1700
},
{
"epoch": 212.99,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 1704
},
{
"epoch": 213.5,
"learning_rate": 0.0001,
"loss": 0.0044,
"step": 1708
},
{
"epoch": 213.99,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 1712
},
{
"epoch": 214.5,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1716
},
{
"epoch": 214.99,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1720
},
{
"epoch": 215.5,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1724
},
{
"epoch": 215.99,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 1728
},
{
"epoch": 215.99,
"eval_exact_match": 0.4339622641509434,
"eval_exec": 0.4726911618669315,
"eval_loss": 0.4982646703720093,
"eval_runtime": 200.9709,
"eval_samples_per_second": 6.469,
"step": 1728
},
{
"epoch": 216.5,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 1732
},
{
"epoch": 216.99,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1736
},
{
"epoch": 217.5,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1740
},
{
"epoch": 217.99,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1744
},
{
"epoch": 218.5,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1748
},
{
"epoch": 218.99,
"learning_rate": 0.0001,
"loss": 0.0045,
"step": 1752
},
{
"epoch": 219.5,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1756
},
{
"epoch": 219.99,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1760
},
{
"epoch": 220.5,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1764
},
{
"epoch": 220.99,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1768
},
{
"epoch": 221.5,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1772
},
{
"epoch": 221.99,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1776
},
{
"epoch": 222.5,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1780
},
{
"epoch": 222.99,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1784
},
{
"epoch": 223.5,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1788
},
{
"epoch": 223.99,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1792
},
{
"epoch": 223.99,
"eval_exact_match": 0.43793445878848064,
"eval_exec": 0.4756703078450844,
"eval_loss": 0.5064935088157654,
"eval_runtime": 200.6112,
"eval_samples_per_second": 6.48,
"step": 1792
},
{
"epoch": 224.5,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1796
},
{
"epoch": 224.99,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1800
},
{
"epoch": 225.5,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1804
},
{
"epoch": 225.99,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1808
},
{
"epoch": 226.5,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1812
},
{
"epoch": 226.99,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1816
},
{
"epoch": 227.5,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1820
},
{
"epoch": 227.99,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1824
},
{
"epoch": 228.5,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1828
},
{
"epoch": 228.99,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1832
},
{
"epoch": 229.5,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1836
},
{
"epoch": 229.99,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1840
},
{
"epoch": 230.5,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1844
},
{
"epoch": 230.99,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1848
},
{
"epoch": 231.5,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1852
},
{
"epoch": 231.99,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1856
},
{
"epoch": 231.99,
"eval_exact_match": 0.43793445878848064,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.5247978568077087,
"eval_runtime": 207.1906,
"eval_samples_per_second": 6.274,
"step": 1856
},
{
"epoch": 232.5,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1860
},
{
"epoch": 232.99,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1864
},
{
"epoch": 233.5,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 1868
},
{
"epoch": 233.99,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1872
},
{
"epoch": 234.5,
"learning_rate": 0.0001,
"loss": 0.0042,
"step": 1876
},
{
"epoch": 234.99,
"learning_rate": 0.0001,
"loss": 0.004,
"step": 1880
},
{
"epoch": 235.5,
"learning_rate": 0.0001,
"loss": 0.0047,
"step": 1884
},
{
"epoch": 235.99,
"learning_rate": 0.0001,
"loss": 0.0065,
"step": 1888
},
{
"epoch": 236.5,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1892
},
{
"epoch": 236.99,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1896
},
{
"epoch": 237.5,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1900
},
{
"epoch": 237.99,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 1904
},
{
"epoch": 238.5,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1908
},
{
"epoch": 238.99,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1912
},
{
"epoch": 239.5,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1916
},
{
"epoch": 239.99,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1920
},
{
"epoch": 239.99,
"eval_exact_match": 0.43892750744786496,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.5224528908729553,
"eval_runtime": 194.9847,
"eval_samples_per_second": 6.667,
"step": 1920
},
{
"epoch": 240.5,
"learning_rate": 0.0001,
"loss": 0.0074,
"step": 1924
},
{
"epoch": 240.99,
"learning_rate": 0.0001,
"loss": 0.0054,
"step": 1928
},
{
"epoch": 241.5,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1932
},
{
"epoch": 241.99,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1936
},
{
"epoch": 242.5,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1940
},
{
"epoch": 242.99,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 1944
},
{
"epoch": 243.5,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1948
},
{
"epoch": 243.99,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1952
},
{
"epoch": 244.5,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1956
},
{
"epoch": 244.99,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1960
},
{
"epoch": 245.5,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1964
},
{
"epoch": 245.99,
"learning_rate": 0.0001,
"loss": 0.0036,
"step": 1968
},
{
"epoch": 246.5,
"learning_rate": 0.0001,
"loss": 0.0038,
"step": 1972
},
{
"epoch": 246.99,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1976
},
{
"epoch": 247.5,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1980
},
{
"epoch": 247.99,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1984
},
{
"epoch": 247.99,
"eval_exact_match": 0.4299900695134062,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.521920382976532,
"eval_runtime": 197.9426,
"eval_samples_per_second": 6.568,
"step": 1984
},
{
"epoch": 248.5,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1988
},
{
"epoch": 248.99,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 1992
},
{
"epoch": 249.5,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1996
},
{
"epoch": 249.99,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2000
},
{
"epoch": 250.5,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2004
},
{
"epoch": 250.99,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2008
},
{
"epoch": 251.5,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 2012
},
{
"epoch": 251.99,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2016
},
{
"epoch": 252.5,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2020
},
{
"epoch": 252.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2024
},
{
"epoch": 253.5,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2028
},
{
"epoch": 253.99,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2032
},
{
"epoch": 254.5,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 2036
},
{
"epoch": 254.99,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 2040
},
{
"epoch": 255.5,
"learning_rate": 0.0001,
"loss": 0.0064,
"step": 2044
},
{
"epoch": 255.99,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 2048
},
{
"epoch": 255.99,
"eval_exact_match": 0.4399205561072492,
"eval_exec": 0.49056603773584906,
"eval_loss": 0.516386091709137,
"eval_runtime": 193.5596,
"eval_samples_per_second": 6.716,
"step": 2048
},
{
"epoch": 256.5,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2052
},
{
"epoch": 256.99,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 2056
},
{
"epoch": 257.5,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2060
},
{
"epoch": 257.99,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2064
},
{
"epoch": 258.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2068
},
{
"epoch": 258.99,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2072
},
{
"epoch": 259.5,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2076
},
{
"epoch": 259.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2080
},
{
"epoch": 260.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2084
},
{
"epoch": 260.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2088
},
{
"epoch": 261.5,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2092
},
{
"epoch": 261.99,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 2096
},
{
"epoch": 262.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2100
},
{
"epoch": 262.99,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2104
},
{
"epoch": 263.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2108
},
{
"epoch": 263.99,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2112
},
{
"epoch": 263.99,
"eval_exact_match": 0.43793445878848064,
"eval_exec": 0.48758689175769615,
"eval_loss": 0.5402066707611084,
"eval_runtime": 203.0032,
"eval_samples_per_second": 6.404,
"step": 2112
},
{
"epoch": 264.5,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2116
},
{
"epoch": 264.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2120
},
{
"epoch": 265.5,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2124
},
{
"epoch": 265.99,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2128
},
{
"epoch": 266.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2132
},
{
"epoch": 266.99,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2136
},
{
"epoch": 267.5,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2140
},
{
"epoch": 267.99,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2144
},
{
"epoch": 268.5,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2148
},
{
"epoch": 268.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2152
},
{
"epoch": 269.5,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 2156
},
{
"epoch": 269.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2160
},
{
"epoch": 270.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2164
},
{
"epoch": 270.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2168
},
{
"epoch": 271.5,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2172
},
{
"epoch": 271.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2176
},
{
"epoch": 271.99,
"eval_exact_match": 0.43495531281032773,
"eval_exec": 0.4816285998013903,
"eval_loss": 0.5360086560249329,
"eval_runtime": 197.8829,
"eval_samples_per_second": 6.57,
"step": 2176
},
{
"epoch": 272.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2180
},
{
"epoch": 272.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2184
},
{
"epoch": 273.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2188
},
{
"epoch": 273.99,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2192
},
{
"epoch": 274.5,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2196
},
{
"epoch": 274.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2200
},
{
"epoch": 275.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2204
},
{
"epoch": 275.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2208
},
{
"epoch": 276.5,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2212
},
{
"epoch": 276.99,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2216
},
{
"epoch": 277.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2220
},
{
"epoch": 277.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2224
},
{
"epoch": 278.5,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2228
},
{
"epoch": 278.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2232
},
{
"epoch": 279.5,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2236
},
{
"epoch": 279.99,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2240
},
{
"epoch": 279.99,
"eval_exact_match": 0.4369414101290963,
"eval_exec": 0.48063555114200596,
"eval_loss": 0.5520691871643066,
"eval_runtime": 204.4424,
"eval_samples_per_second": 6.359,
"step": 2240
},
{
"epoch": 280.5,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2244
},
{
"epoch": 280.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2248
},
{
"epoch": 281.5,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2252
},
{
"epoch": 281.99,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2256
},
{
"epoch": 282.5,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2260
},
{
"epoch": 282.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2264
},
{
"epoch": 283.5,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2268
},
{
"epoch": 283.99,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2272
},
{
"epoch": 284.5,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2276
},
{
"epoch": 284.99,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2280
},
{
"epoch": 285.5,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2284
},
{
"epoch": 285.99,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2288
},
{
"epoch": 286.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2292
},
{
"epoch": 286.99,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2296
},
{
"epoch": 287.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2300
},
{
"epoch": 287.99,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2304
},
{
"epoch": 287.99,
"eval_exact_match": 0.4438927507447865,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.5534113645553589,
"eval_runtime": 202.8208,
"eval_samples_per_second": 6.41,
"step": 2304
},
{
"epoch": 288.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2308
},
{
"epoch": 288.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2312
},
{
"epoch": 289.5,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2316
},
{
"epoch": 289.99,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2320
},
{
"epoch": 290.5,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2324
},
{
"epoch": 290.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2328
},
{
"epoch": 291.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2332
},
{
"epoch": 291.99,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2336
},
{
"epoch": 292.5,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2340
},
{
"epoch": 292.99,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2344
},
{
"epoch": 293.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2348
},
{
"epoch": 293.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2352
},
{
"epoch": 294.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2356
},
{
"epoch": 294.99,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2360
},
{
"epoch": 295.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2364
},
{
"epoch": 295.99,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2368
},
{
"epoch": 295.99,
"eval_exact_match": 0.4428997020854022,
"eval_exec": 0.4816285998013903,
"eval_loss": 0.557854413986206,
"eval_runtime": 203.9919,
"eval_samples_per_second": 6.373,
"step": 2368
},
{
"epoch": 296.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2372
},
{
"epoch": 296.99,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2376
},
{
"epoch": 297.5,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2380
},
{
"epoch": 297.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2384
},
{
"epoch": 298.5,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2388
},
{
"epoch": 298.99,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2392
},
{
"epoch": 299.5,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2396
},
{
"epoch": 299.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2400
},
{
"epoch": 300.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2404
},
{
"epoch": 300.99,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2408
},
{
"epoch": 301.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2412
},
{
"epoch": 301.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2416
},
{
"epoch": 302.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2420
},
{
"epoch": 302.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2424
},
{
"epoch": 303.5,
"learning_rate": 0.0001,
"loss": 0.0028,
"step": 2428
},
{
"epoch": 303.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 2432
},
{
"epoch": 303.99,
"eval_exact_match": 0.44985104270109233,
"eval_exec": 0.49056603773584906,
"eval_loss": 0.5580935478210449,
"eval_runtime": 200.2593,
"eval_samples_per_second": 6.492,
"step": 2432
},
{
"epoch": 304.5,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2436
},
{
"epoch": 304.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2440
},
{
"epoch": 305.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2444
},
{
"epoch": 305.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2448
},
{
"epoch": 306.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2452
},
{
"epoch": 306.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2456
},
{
"epoch": 307.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2460
},
{
"epoch": 307.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2464
},
{
"epoch": 308.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2468
},
{
"epoch": 308.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2472
},
{
"epoch": 309.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2476
},
{
"epoch": 309.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2480
},
{
"epoch": 310.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2484
},
{
"epoch": 310.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2488
},
{
"epoch": 311.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2492
},
{
"epoch": 311.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2496
},
{
"epoch": 311.99,
"eval_exact_match": 0.4200595829195631,
"eval_exec": 0.47070506454816285,
"eval_loss": 0.560897946357727,
"eval_runtime": 202.502,
"eval_samples_per_second": 6.42,
"step": 2496
},
{
"epoch": 312.5,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2500
},
{
"epoch": 312.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2504
},
{
"epoch": 313.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2508
},
{
"epoch": 313.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2512
},
{
"epoch": 314.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2516
},
{
"epoch": 314.99,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 2520
},
{
"epoch": 315.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2524
},
{
"epoch": 315.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2528
},
{
"epoch": 316.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2532
},
{
"epoch": 316.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2536
},
{
"epoch": 317.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2540
},
{
"epoch": 317.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2544
},
{
"epoch": 318.5,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2548
},
{
"epoch": 318.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2552
},
{
"epoch": 319.5,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2556
},
{
"epoch": 319.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2560
},
{
"epoch": 319.99,
"eval_exact_match": 0.42800397219463754,
"eval_exec": 0.46971201588877853,
"eval_loss": 0.5524822473526001,
"eval_runtime": 204.4122,
"eval_samples_per_second": 6.36,
"step": 2560
},
{
"epoch": 320.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2564
},
{
"epoch": 320.99,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 2568
},
{
"epoch": 321.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2572
},
{
"epoch": 321.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2576
},
{
"epoch": 322.5,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2580
},
{
"epoch": 322.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2584
},
{
"epoch": 323.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2588
},
{
"epoch": 323.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2592
},
{
"epoch": 324.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2596
},
{
"epoch": 324.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2600
},
{
"epoch": 325.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2604
},
{
"epoch": 325.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2608
},
{
"epoch": 326.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2612
},
{
"epoch": 326.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2616
},
{
"epoch": 327.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2620
},
{
"epoch": 327.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2624
},
{
"epoch": 327.99,
"eval_exact_match": 0.4260178748758689,
"eval_exec": 0.48361469712015887,
"eval_loss": 0.5746508240699768,
"eval_runtime": 194.402,
"eval_samples_per_second": 6.687,
"step": 2624
},
{
"epoch": 328.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2628
},
{
"epoch": 328.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2632
},
{
"epoch": 329.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2636
},
{
"epoch": 329.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2640
},
{
"epoch": 330.5,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 2644
},
{
"epoch": 330.99,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2648
},
{
"epoch": 331.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2652
},
{
"epoch": 331.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2656
},
{
"epoch": 332.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2660
},
{
"epoch": 332.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2664
},
{
"epoch": 333.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2668
},
{
"epoch": 333.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2672
},
{
"epoch": 334.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2676
},
{
"epoch": 334.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2680
},
{
"epoch": 335.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2684
},
{
"epoch": 335.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2688
},
{
"epoch": 335.99,
"eval_exact_match": 0.4369414101290963,
"eval_exec": 0.4786494538232373,
"eval_loss": 0.5734978914260864,
"eval_runtime": 199.4394,
"eval_samples_per_second": 6.518,
"step": 2688
},
{
"epoch": 336.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2692
},
{
"epoch": 336.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2696
},
{
"epoch": 337.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2700
},
{
"epoch": 337.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2704
},
{
"epoch": 338.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2708
},
{
"epoch": 338.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2712
},
{
"epoch": 339.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2716
},
{
"epoch": 339.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2720
},
{
"epoch": 340.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2724
},
{
"epoch": 340.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2728
},
{
"epoch": 341.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2732
},
{
"epoch": 341.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 2736
},
{
"epoch": 342.5,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 2740
},
{
"epoch": 342.99,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 2744
},
{
"epoch": 343.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2748
},
{
"epoch": 343.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2752
},
{
"epoch": 343.99,
"eval_exact_match": 0.4369414101290963,
"eval_exec": 0.48063555114200596,
"eval_loss": 0.5549472570419312,
"eval_runtime": 209.2028,
"eval_samples_per_second": 6.214,
"step": 2752
},
{
"epoch": 344.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2756
},
{
"epoch": 344.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2760
},
{
"epoch": 345.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2764
},
{
"epoch": 345.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2768
},
{
"epoch": 346.5,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 2772
},
{
"epoch": 346.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2776
},
{
"epoch": 347.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2780
},
{
"epoch": 347.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2784
},
{
"epoch": 348.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2788
},
{
"epoch": 348.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2792
},
{
"epoch": 349.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2796
},
{
"epoch": 349.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2800
},
{
"epoch": 350.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2804
},
{
"epoch": 350.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2808
},
{
"epoch": 351.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2812
},
{
"epoch": 351.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2816
},
{
"epoch": 351.99,
"eval_exact_match": 0.4448857994041708,
"eval_exec": 0.48758689175769615,
"eval_loss": 0.5706749558448792,
"eval_runtime": 208.8886,
"eval_samples_per_second": 6.223,
"step": 2816
},
{
"epoch": 352.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2820
},
{
"epoch": 352.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2824
},
{
"epoch": 353.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2828
},
{
"epoch": 353.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2832
},
{
"epoch": 354.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2836
},
{
"epoch": 354.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2840
},
{
"epoch": 355.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2844
},
{
"epoch": 355.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2848
},
{
"epoch": 356.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2852
},
{
"epoch": 356.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2856
},
{
"epoch": 357.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2860
},
{
"epoch": 357.99,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2864
},
{
"epoch": 358.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2868
},
{
"epoch": 358.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2872
},
{
"epoch": 359.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2876
},
{
"epoch": 359.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2880
},
{
"epoch": 359.99,
"eval_exact_match": 0.4468718967229394,
"eval_exec": 0.48957298907646474,
"eval_loss": 0.5861152410507202,
"eval_runtime": 206.5997,
"eval_samples_per_second": 6.292,
"step": 2880
},
{
"epoch": 360.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2884
},
{
"epoch": 360.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2888
},
{
"epoch": 361.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2892
},
{
"epoch": 361.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2896
},
{
"epoch": 362.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2900
},
{
"epoch": 362.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2904
},
{
"epoch": 363.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 2908
},
{
"epoch": 363.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2912
},
{
"epoch": 364.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2916
},
{
"epoch": 364.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2920
},
{
"epoch": 365.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2924
},
{
"epoch": 365.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2928
},
{
"epoch": 366.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2932
},
{
"epoch": 366.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2936
},
{
"epoch": 367.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2940
},
{
"epoch": 367.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2944
},
{
"epoch": 367.99,
"eval_exact_match": 0.44786494538232374,
"eval_exec": 0.4955312810327706,
"eval_loss": 0.5812374949455261,
"eval_runtime": 213.3063,
"eval_samples_per_second": 6.095,
"step": 2944
},
{
"epoch": 368.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2948
},
{
"epoch": 368.99,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 2952
},
{
"epoch": 369.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2956
},
{
"epoch": 369.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2960
},
{
"epoch": 370.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2964
},
{
"epoch": 370.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2968
},
{
"epoch": 371.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2972
},
{
"epoch": 371.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2976
},
{
"epoch": 372.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 2980
},
{
"epoch": 372.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2984
},
{
"epoch": 373.5,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 2988
},
{
"epoch": 373.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2992
},
{
"epoch": 374.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 2996
},
{
"epoch": 374.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3000
},
{
"epoch": 375.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3004
},
{
"epoch": 375.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 3008
},
{
"epoch": 375.99,
"eval_exact_match": 0.4438927507447865,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.5652831792831421,
"eval_runtime": 210.776,
"eval_samples_per_second": 6.168,
"step": 3008
},
{
"epoch": 376.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 3012
},
{
"epoch": 376.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 3016
},
{
"epoch": 377.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3020
},
{
"epoch": 377.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3024
},
{
"epoch": 378.5,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 3028
},
{
"epoch": 378.99,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 3032
},
{
"epoch": 379.5,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 3036
},
{
"epoch": 379.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3040
},
{
"epoch": 380.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3044
},
{
"epoch": 380.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3048
},
{
"epoch": 381.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3052
},
{
"epoch": 381.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3056
},
{
"epoch": 382.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 3060
},
{
"epoch": 382.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3064
},
{
"epoch": 383.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3068
},
{
"epoch": 383.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3072
},
{
"epoch": 383.99,
"eval_exact_match": 0.44985104270109233,
"eval_exec": 0.4915590863952334,
"eval_loss": 0.5784198641777039,
"eval_runtime": 204.8823,
"eval_samples_per_second": 6.345,
"step": 3072
},
{
"epoch": 384.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3076
},
{
"epoch": 384.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3080
},
{
"epoch": 385.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3084
},
{
"epoch": 385.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3088
},
{
"epoch": 386.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3092
},
{
"epoch": 386.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 3096
},
{
"epoch": 387.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3100
},
{
"epoch": 387.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 3104
},
{
"epoch": 388.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3108
},
{
"epoch": 388.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3112
},
{
"epoch": 389.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3116
},
{
"epoch": 389.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3120
},
{
"epoch": 390.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3124
},
{
"epoch": 390.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3128
},
{
"epoch": 391.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3132
},
{
"epoch": 391.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3136
},
{
"epoch": 391.99,
"eval_exact_match": 0.4528301886792453,
"eval_exec": 0.4925521350546177,
"eval_loss": 0.5775428414344788,
"eval_runtime": 211.2569,
"eval_samples_per_second": 6.154,
"step": 3136
},
{
"epoch": 392.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3140
},
{
"epoch": 392.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3144
},
{
"epoch": 393.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3148
},
{
"epoch": 393.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3152
},
{
"epoch": 394.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3156
},
{
"epoch": 394.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3160
},
{
"epoch": 395.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3164
},
{
"epoch": 395.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3168
},
{
"epoch": 396.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3172
},
{
"epoch": 396.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3176
},
{
"epoch": 397.5,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 3180
},
{
"epoch": 397.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3184
},
{
"epoch": 398.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3188
},
{
"epoch": 398.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3192
},
{
"epoch": 399.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3196
},
{
"epoch": 399.99,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 3200
},
{
"epoch": 399.99,
"eval_exact_match": 0.4538232373386296,
"eval_exec": 0.49751737835153925,
"eval_loss": 0.5791714191436768,
"eval_runtime": 202.6045,
"eval_samples_per_second": 6.416,
"step": 3200
},
{
"epoch": 400.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3204
},
{
"epoch": 400.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3208
},
{
"epoch": 401.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3212
},
{
"epoch": 401.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3216
},
{
"epoch": 402.5,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3220
},
{
"epoch": 402.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3224
},
{
"epoch": 403.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3228
},
{
"epoch": 403.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3232
},
{
"epoch": 404.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3236
},
{
"epoch": 404.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3240
},
{
"epoch": 405.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3244
},
{
"epoch": 405.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3248
},
{
"epoch": 406.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3252
},
{
"epoch": 406.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3256
},
{
"epoch": 407.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3260
},
{
"epoch": 407.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3264
},
{
"epoch": 407.99,
"eval_exact_match": 0.44190665342601787,
"eval_exec": 0.48361469712015887,
"eval_loss": 0.58585524559021,
"eval_runtime": 208.6202,
"eval_samples_per_second": 6.231,
"step": 3264
},
{
"epoch": 408.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3268
},
{
"epoch": 408.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3272
},
{
"epoch": 409.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3276
},
{
"epoch": 409.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3280
},
{
"epoch": 410.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3284
},
{
"epoch": 410.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3288
},
{
"epoch": 411.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3292
},
{
"epoch": 411.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3296
},
{
"epoch": 412.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3300
},
{
"epoch": 412.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3304
},
{
"epoch": 413.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3308
},
{
"epoch": 413.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3312
},
{
"epoch": 414.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3316
},
{
"epoch": 414.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3320
},
{
"epoch": 415.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3324
},
{
"epoch": 415.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3328
},
{
"epoch": 415.99,
"eval_exact_match": 0.44786494538232374,
"eval_exec": 0.48361469712015887,
"eval_loss": 0.5857390761375427,
"eval_runtime": 199.7986,
"eval_samples_per_second": 6.507,
"step": 3328
},
{
"epoch": 416.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3332
},
{
"epoch": 416.99,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 3336
},
{
"epoch": 417.5,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 3340
},
{
"epoch": 417.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3344
},
{
"epoch": 418.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3348
},
{
"epoch": 418.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3352
},
{
"epoch": 419.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3356
},
{
"epoch": 419.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3360
},
{
"epoch": 420.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3364
},
{
"epoch": 420.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3368
},
{
"epoch": 421.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3372
},
{
"epoch": 421.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3376
},
{
"epoch": 422.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3380
},
{
"epoch": 422.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3384
},
{
"epoch": 423.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3388
},
{
"epoch": 423.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3392
},
{
"epoch": 423.99,
"eval_exact_match": 0.4468718967229394,
"eval_exec": 0.48758689175769615,
"eval_loss": 0.5896801948547363,
"eval_runtime": 211.8567,
"eval_samples_per_second": 6.136,
"step": 3392
},
{
"epoch": 424.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3396
},
{
"epoch": 424.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3400
},
{
"epoch": 425.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3404
},
{
"epoch": 425.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3408
},
{
"epoch": 426.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3412
},
{
"epoch": 426.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3416
},
{
"epoch": 427.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3420
},
{
"epoch": 427.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3424
},
{
"epoch": 428.5,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3428
},
{
"epoch": 428.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3432
},
{
"epoch": 429.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3436
},
{
"epoch": 429.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3440
},
{
"epoch": 430.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3444
},
{
"epoch": 430.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3448
},
{
"epoch": 431.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3452
},
{
"epoch": 431.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3456
},
{
"epoch": 431.99,
"eval_exact_match": 0.44885799404170806,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.5921575427055359,
"eval_runtime": 197.9512,
"eval_samples_per_second": 6.567,
"step": 3456
},
{
"epoch": 432.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3460
},
{
"epoch": 432.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3464
},
{
"epoch": 433.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3468
},
{
"epoch": 433.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3472
},
{
"epoch": 434.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3476
},
{
"epoch": 434.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3480
},
{
"epoch": 435.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3484
},
{
"epoch": 435.99,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 3488
},
{
"epoch": 436.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3492
},
{
"epoch": 436.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3496
},
{
"epoch": 437.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3500
},
{
"epoch": 437.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3504
},
{
"epoch": 438.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3508
},
{
"epoch": 438.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3512
},
{
"epoch": 439.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3516
},
{
"epoch": 439.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3520
},
{
"epoch": 439.99,
"eval_exact_match": 0.4428997020854022,
"eval_exec": 0.49056603773584906,
"eval_loss": 0.5778002142906189,
"eval_runtime": 200.4589,
"eval_samples_per_second": 6.485,
"step": 3520
},
{
"epoch": 440.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3524
},
{
"epoch": 440.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3528
},
{
"epoch": 441.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3532
},
{
"epoch": 441.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3536
},
{
"epoch": 442.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3540
},
{
"epoch": 442.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3544
},
{
"epoch": 443.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3548
},
{
"epoch": 443.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3552
},
{
"epoch": 444.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3556
},
{
"epoch": 444.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3560
},
{
"epoch": 445.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3564
},
{
"epoch": 445.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3568
},
{
"epoch": 446.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3572
},
{
"epoch": 446.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3576
},
{
"epoch": 447.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3580
},
{
"epoch": 447.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3584
},
{
"epoch": 447.99,
"eval_exact_match": 0.4438927507447865,
"eval_exec": 0.47765640516385305,
"eval_loss": 0.584464967250824,
"eval_runtime": 195.0196,
"eval_samples_per_second": 6.666,
"step": 3584
},
{
"epoch": 448.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3588
},
{
"epoch": 448.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3592
},
{
"epoch": 449.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3596
},
{
"epoch": 449.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3600
},
{
"epoch": 450.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3604
},
{
"epoch": 450.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3608
},
{
"epoch": 451.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3612
},
{
"epoch": 451.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3616
},
{
"epoch": 452.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3620
},
{
"epoch": 452.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3624
},
{
"epoch": 453.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3628
},
{
"epoch": 453.99,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 3632
},
{
"epoch": 454.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3636
},
{
"epoch": 454.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3640
},
{
"epoch": 455.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3644
},
{
"epoch": 455.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3648
},
{
"epoch": 455.99,
"eval_exact_match": 0.4438927507447865,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.6006260514259338,
"eval_runtime": 207.0142,
"eval_samples_per_second": 6.28,
"step": 3648
},
{
"epoch": 456.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3652
},
{
"epoch": 456.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3656
},
{
"epoch": 457.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3660
},
{
"epoch": 457.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3664
},
{
"epoch": 458.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3668
},
{
"epoch": 458.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3672
},
{
"epoch": 459.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3676
},
{
"epoch": 459.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3680
},
{
"epoch": 460.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3684
},
{
"epoch": 460.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3688
},
{
"epoch": 461.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3692
},
{
"epoch": 461.99,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3696
},
{
"epoch": 462.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3700
},
{
"epoch": 462.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3704
},
{
"epoch": 463.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3708
},
{
"epoch": 463.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3712
},
{
"epoch": 463.99,
"eval_exact_match": 0.4448857994041708,
"eval_exec": 0.47765640516385305,
"eval_loss": 0.6055679321289062,
"eval_runtime": 203.8538,
"eval_samples_per_second": 6.377,
"step": 3712
},
{
"epoch": 464.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3716
},
{
"epoch": 464.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3720
},
{
"epoch": 465.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3724
},
{
"epoch": 465.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3728
},
{
"epoch": 466.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3732
},
{
"epoch": 466.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3736
},
{
"epoch": 467.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3740
},
{
"epoch": 467.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3744
},
{
"epoch": 468.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3748
},
{
"epoch": 468.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3752
},
{
"epoch": 469.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3756
},
{
"epoch": 469.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3760
},
{
"epoch": 470.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3764
},
{
"epoch": 470.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3768
},
{
"epoch": 471.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3772
},
{
"epoch": 471.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3776
},
{
"epoch": 471.99,
"eval_exact_match": 0.44190665342601787,
"eval_exec": 0.47368421052631576,
"eval_loss": 0.6094422340393066,
"eval_runtime": 200.6337,
"eval_samples_per_second": 6.479,
"step": 3776
},
{
"epoch": 472.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3780
},
{
"epoch": 472.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 3784
},
{
"epoch": 473.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3788
},
{
"epoch": 473.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3792
},
{
"epoch": 474.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3796
},
{
"epoch": 474.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3800
},
{
"epoch": 475.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 3804
},
{
"epoch": 475.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3808
},
{
"epoch": 476.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3812
},
{
"epoch": 476.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3816
},
{
"epoch": 477.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3820
},
{
"epoch": 477.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3824
},
{
"epoch": 478.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3828
},
{
"epoch": 478.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3832
},
{
"epoch": 479.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3836
},
{
"epoch": 479.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3840
},
{
"epoch": 479.99,
"eval_exact_match": 0.4458788480635551,
"eval_exec": 0.49354518371400197,
"eval_loss": 0.6145819425582886,
"eval_runtime": 190.4305,
"eval_samples_per_second": 6.827,
"step": 3840
},
{
"epoch": 480.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3844
},
{
"epoch": 480.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3848
},
{
"epoch": 481.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3852
},
{
"epoch": 481.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3856
},
{
"epoch": 482.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3860
},
{
"epoch": 482.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3864
},
{
"epoch": 483.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3868
},
{
"epoch": 483.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3872
},
{
"epoch": 484.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3876
},
{
"epoch": 484.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 3880
},
{
"epoch": 485.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3884
},
{
"epoch": 485.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3888
},
{
"epoch": 486.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3892
},
{
"epoch": 486.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 3896
},
{
"epoch": 487.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3900
},
{
"epoch": 487.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3904
},
{
"epoch": 487.99,
"eval_exact_match": 0.44190665342601787,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.6196692585945129,
"eval_runtime": 197.0844,
"eval_samples_per_second": 6.596,
"step": 3904
},
{
"epoch": 488.5,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 3908
},
{
"epoch": 488.99,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3912
},
{
"epoch": 489.5,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 3916
},
{
"epoch": 489.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3920
},
{
"epoch": 490.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3924
},
{
"epoch": 490.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3928
},
{
"epoch": 491.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3932
},
{
"epoch": 491.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3936
},
{
"epoch": 492.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3940
},
{
"epoch": 492.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3944
},
{
"epoch": 493.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3948
},
{
"epoch": 493.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3952
},
{
"epoch": 494.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3956
},
{
"epoch": 494.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3960
},
{
"epoch": 495.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3964
},
{
"epoch": 495.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3968
},
{
"epoch": 495.99,
"eval_exact_match": 0.4339622641509434,
"eval_exec": 0.4756703078450844,
"eval_loss": 0.6161912679672241,
"eval_runtime": 201.1763,
"eval_samples_per_second": 6.462,
"step": 3968
},
{
"epoch": 496.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3972
},
{
"epoch": 496.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3976
},
{
"epoch": 497.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3980
},
{
"epoch": 497.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 3984
},
{
"epoch": 498.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3988
},
{
"epoch": 498.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 3992
},
{
"epoch": 499.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 3996
},
{
"epoch": 499.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4000
},
{
"epoch": 500.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4004
},
{
"epoch": 500.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4008
},
{
"epoch": 501.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4012
},
{
"epoch": 501.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4016
},
{
"epoch": 502.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 4020
},
{
"epoch": 502.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4024
},
{
"epoch": 503.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4028
},
{
"epoch": 503.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4032
},
{
"epoch": 503.99,
"eval_exact_match": 0.4399205561072492,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.6102380156517029,
"eval_runtime": 199.2958,
"eval_samples_per_second": 6.523,
"step": 4032
},
{
"epoch": 504.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4036
},
{
"epoch": 504.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4040
},
{
"epoch": 505.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4044
},
{
"epoch": 505.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4048
},
{
"epoch": 506.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4052
},
{
"epoch": 506.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4056
},
{
"epoch": 507.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4060
},
{
"epoch": 507.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4064
},
{
"epoch": 508.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4068
},
{
"epoch": 508.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4072
},
{
"epoch": 509.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4076
},
{
"epoch": 509.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4080
},
{
"epoch": 510.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4084
},
{
"epoch": 510.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4088
},
{
"epoch": 511.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4092
},
{
"epoch": 511.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4096
},
{
"epoch": 511.99,
"eval_exact_match": 0.4399205561072492,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.619750440120697,
"eval_runtime": 211.0292,
"eval_samples_per_second": 6.16,
"step": 4096
},
{
"epoch": 512.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4100
},
{
"epoch": 512.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4104
},
{
"epoch": 513.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4108
},
{
"epoch": 513.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4112
},
{
"epoch": 514.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4116
},
{
"epoch": 514.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4120
},
{
"epoch": 515.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4124
},
{
"epoch": 515.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4128
},
{
"epoch": 516.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4132
},
{
"epoch": 516.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4136
},
{
"epoch": 517.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4140
},
{
"epoch": 517.99,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 4144
},
{
"epoch": 518.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4148
},
{
"epoch": 518.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4152
},
{
"epoch": 519.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4156
},
{
"epoch": 519.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4160
},
{
"epoch": 519.99,
"eval_exact_match": 0.4428997020854022,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.6127471327781677,
"eval_runtime": 203.9094,
"eval_samples_per_second": 6.375,
"step": 4160
},
{
"epoch": 520.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4164
},
{
"epoch": 520.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4168
},
{
"epoch": 521.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4172
},
{
"epoch": 521.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4176
},
{
"epoch": 522.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4180
},
{
"epoch": 522.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4184
},
{
"epoch": 523.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4188
},
{
"epoch": 523.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4192
},
{
"epoch": 524.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4196
},
{
"epoch": 524.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4200
},
{
"epoch": 525.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4204
},
{
"epoch": 525.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4208
},
{
"epoch": 526.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4212
},
{
"epoch": 526.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4216
},
{
"epoch": 527.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4220
},
{
"epoch": 527.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4224
},
{
"epoch": 527.99,
"eval_exact_match": 0.4458788480635551,
"eval_exec": 0.48758689175769615,
"eval_loss": 0.6248003244400024,
"eval_runtime": 204.1177,
"eval_samples_per_second": 6.369,
"step": 4224
},
{
"epoch": 528.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4228
},
{
"epoch": 528.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4232
},
{
"epoch": 529.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4236
},
{
"epoch": 529.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4240
},
{
"epoch": 530.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4244
},
{
"epoch": 530.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4248
},
{
"epoch": 531.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4252
},
{
"epoch": 531.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4256
},
{
"epoch": 532.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4260
},
{
"epoch": 532.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4264
},
{
"epoch": 533.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4268
},
{
"epoch": 533.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4272
},
{
"epoch": 534.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4276
},
{
"epoch": 534.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4280
},
{
"epoch": 535.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4284
},
{
"epoch": 535.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4288
},
{
"epoch": 535.99,
"eval_exact_match": 0.4468718967229394,
"eval_exec": 0.48063555114200596,
"eval_loss": 0.6122114658355713,
"eval_runtime": 196.9407,
"eval_samples_per_second": 6.601,
"step": 4288
},
{
"epoch": 536.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4292
},
{
"epoch": 536.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4296
},
{
"epoch": 537.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4300
},
{
"epoch": 537.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4304
},
{
"epoch": 538.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 4308
},
{
"epoch": 538.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4312
},
{
"epoch": 539.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4316
},
{
"epoch": 539.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4320
},
{
"epoch": 540.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4324
},
{
"epoch": 540.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4328
},
{
"epoch": 541.5,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 4332
},
{
"epoch": 541.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4336
},
{
"epoch": 542.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4340
},
{
"epoch": 542.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4344
},
{
"epoch": 543.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4348
},
{
"epoch": 543.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4352
},
{
"epoch": 543.99,
"eval_exact_match": 0.43495531281032773,
"eval_exec": 0.4816285998013903,
"eval_loss": 0.605417013168335,
"eval_runtime": 200.1247,
"eval_samples_per_second": 6.496,
"step": 4352
},
{
"epoch": 544.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4356
},
{
"epoch": 544.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4360
},
{
"epoch": 545.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4364
},
{
"epoch": 545.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4368
},
{
"epoch": 546.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4372
},
{
"epoch": 546.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4376
},
{
"epoch": 547.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4380
},
{
"epoch": 547.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4384
},
{
"epoch": 548.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4388
},
{
"epoch": 548.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4392
},
{
"epoch": 549.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4396
},
{
"epoch": 549.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4400
},
{
"epoch": 550.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4404
},
{
"epoch": 550.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4408
},
{
"epoch": 551.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4412
},
{
"epoch": 551.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4416
},
{
"epoch": 551.99,
"eval_exact_match": 0.4369414101290963,
"eval_exec": 0.4746772591857001,
"eval_loss": 0.6194772124290466,
"eval_runtime": 195.0605,
"eval_samples_per_second": 6.665,
"step": 4416
},
{
"epoch": 552.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4420
},
{
"epoch": 552.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4424
},
{
"epoch": 553.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4428
},
{
"epoch": 553.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4432
},
{
"epoch": 554.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4436
},
{
"epoch": 554.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4440
},
{
"epoch": 555.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4444
},
{
"epoch": 555.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4448
},
{
"epoch": 556.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4452
},
{
"epoch": 556.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4456
},
{
"epoch": 557.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4460
},
{
"epoch": 557.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4464
},
{
"epoch": 558.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4468
},
{
"epoch": 558.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4472
},
{
"epoch": 559.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4476
},
{
"epoch": 559.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4480
},
{
"epoch": 559.99,
"eval_exact_match": 0.44885799404170806,
"eval_exec": 0.4925521350546177,
"eval_loss": 0.6179357767105103,
"eval_runtime": 194.9028,
"eval_samples_per_second": 6.67,
"step": 4480
},
{
"epoch": 560.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4484
},
{
"epoch": 560.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4488
},
{
"epoch": 561.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4492
},
{
"epoch": 561.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4496
},
{
"epoch": 562.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4500
},
{
"epoch": 562.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4504
},
{
"epoch": 563.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4508
},
{
"epoch": 563.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4512
},
{
"epoch": 564.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4516
},
{
"epoch": 564.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4520
},
{
"epoch": 565.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4524
},
{
"epoch": 565.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4528
},
{
"epoch": 566.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4532
},
{
"epoch": 566.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4536
},
{
"epoch": 567.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4540
},
{
"epoch": 567.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4544
},
{
"epoch": 567.99,
"eval_exact_match": 0.45084409136047665,
"eval_exec": 0.4915590863952334,
"eval_loss": 0.6036345958709717,
"eval_runtime": 196.9122,
"eval_samples_per_second": 6.602,
"step": 4544
},
{
"epoch": 568.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4548
},
{
"epoch": 568.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4552
},
{
"epoch": 569.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4556
},
{
"epoch": 569.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4560
},
{
"epoch": 570.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4564
},
{
"epoch": 570.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4568
},
{
"epoch": 571.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4572
},
{
"epoch": 571.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4576
},
{
"epoch": 572.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4580
},
{
"epoch": 572.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4584
},
{
"epoch": 573.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4588
},
{
"epoch": 573.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4592
},
{
"epoch": 574.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4596
},
{
"epoch": 574.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4600
},
{
"epoch": 575.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4604
},
{
"epoch": 575.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4608
},
{
"epoch": 575.99,
"eval_exact_match": 0.45183714001986097,
"eval_exec": 0.49354518371400197,
"eval_loss": 0.6121585369110107,
"eval_runtime": 216.7301,
"eval_samples_per_second": 5.998,
"step": 4608
},
{
"epoch": 576.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4612
},
{
"epoch": 576.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4616
},
{
"epoch": 577.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4620
},
{
"epoch": 577.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4624
},
{
"epoch": 578.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4628
},
{
"epoch": 578.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4632
},
{
"epoch": 579.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4636
},
{
"epoch": 579.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4640
},
{
"epoch": 580.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4644
},
{
"epoch": 580.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4648
},
{
"epoch": 581.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4652
},
{
"epoch": 581.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4656
},
{
"epoch": 582.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4660
},
{
"epoch": 582.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4664
},
{
"epoch": 583.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4668
},
{
"epoch": 583.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4672
},
{
"epoch": 583.99,
"eval_exact_match": 0.4438927507447865,
"eval_exec": 0.48063555114200596,
"eval_loss": 0.6172407269477844,
"eval_runtime": 196.291,
"eval_samples_per_second": 6.623,
"step": 4672
},
{
"epoch": 584.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4676
},
{
"epoch": 584.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4680
},
{
"epoch": 585.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4684
},
{
"epoch": 585.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4688
},
{
"epoch": 586.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4692
},
{
"epoch": 586.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4696
},
{
"epoch": 587.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4700
},
{
"epoch": 587.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4704
},
{
"epoch": 588.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4708
},
{
"epoch": 588.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4712
},
{
"epoch": 589.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4716
},
{
"epoch": 589.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4720
},
{
"epoch": 590.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4724
},
{
"epoch": 590.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4728
},
{
"epoch": 591.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4732
},
{
"epoch": 591.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4736
},
{
"epoch": 591.99,
"eval_exact_match": 0.43793445878848064,
"eval_exec": 0.4766633565044687,
"eval_loss": 0.6108298301696777,
"eval_runtime": 203.2897,
"eval_samples_per_second": 6.395,
"step": 4736
},
{
"epoch": 592.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4740
},
{
"epoch": 592.99,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4744
},
{
"epoch": 593.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4748
},
{
"epoch": 593.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4752
},
{
"epoch": 594.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 4756
},
{
"epoch": 594.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4760
},
{
"epoch": 595.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4764
},
{
"epoch": 595.99,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 4768
},
{
"epoch": 596.5,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 4772
},
{
"epoch": 596.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4776
},
{
"epoch": 597.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4780
},
{
"epoch": 597.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4784
},
{
"epoch": 598.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4788
},
{
"epoch": 598.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4792
},
{
"epoch": 599.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4796
},
{
"epoch": 599.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4800
},
{
"epoch": 599.99,
"eval_exact_match": 0.4369414101290963,
"eval_exec": 0.4746772591857001,
"eval_loss": 0.6420004367828369,
"eval_runtime": 195.6774,
"eval_samples_per_second": 6.644,
"step": 4800
},
{
"epoch": 600.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4804
},
{
"epoch": 600.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4808
},
{
"epoch": 601.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4812
},
{
"epoch": 601.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4816
},
{
"epoch": 602.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4820
},
{
"epoch": 602.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4824
},
{
"epoch": 603.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4828
},
{
"epoch": 603.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4832
},
{
"epoch": 604.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4836
},
{
"epoch": 604.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4840
},
{
"epoch": 605.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4844
},
{
"epoch": 605.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4848
},
{
"epoch": 606.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4852
},
{
"epoch": 606.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4856
},
{
"epoch": 607.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4860
},
{
"epoch": 607.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4864
},
{
"epoch": 607.99,
"eval_exact_match": 0.4438927507447865,
"eval_exec": 0.4726911618669315,
"eval_loss": 0.6424113512039185,
"eval_runtime": 202.6801,
"eval_samples_per_second": 6.414,
"step": 4864
},
{
"epoch": 608.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4868
},
{
"epoch": 608.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4872
},
{
"epoch": 609.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4876
},
{
"epoch": 609.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4880
},
{
"epoch": 610.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 4884
},
{
"epoch": 610.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4888
},
{
"epoch": 611.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4892
},
{
"epoch": 611.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4896
},
{
"epoch": 612.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4900
},
{
"epoch": 612.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4904
},
{
"epoch": 613.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4908
},
{
"epoch": 613.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4912
},
{
"epoch": 614.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4916
},
{
"epoch": 614.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4920
},
{
"epoch": 615.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4924
},
{
"epoch": 615.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4928
},
{
"epoch": 615.99,
"eval_exact_match": 0.4339622641509434,
"eval_exec": 0.46871896722939427,
"eval_loss": 0.630379319190979,
"eval_runtime": 198.8917,
"eval_samples_per_second": 6.536,
"step": 4928
},
{
"epoch": 616.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4932
},
{
"epoch": 616.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4936
},
{
"epoch": 617.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4940
},
{
"epoch": 617.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4944
},
{
"epoch": 618.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4948
},
{
"epoch": 618.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4952
},
{
"epoch": 619.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4956
},
{
"epoch": 619.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4960
},
{
"epoch": 620.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4964
},
{
"epoch": 620.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4968
},
{
"epoch": 621.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 4972
},
{
"epoch": 621.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4976
},
{
"epoch": 622.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4980
},
{
"epoch": 622.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4984
},
{
"epoch": 623.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4988
},
{
"epoch": 623.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 4992
},
{
"epoch": 623.99,
"eval_exact_match": 0.44190665342601787,
"eval_exec": 0.48361469712015887,
"eval_loss": 0.6309102177619934,
"eval_runtime": 191.856,
"eval_samples_per_second": 6.776,
"step": 4992
},
{
"epoch": 624.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 4996
},
{
"epoch": 624.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5000
},
{
"epoch": 625.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 5004
},
{
"epoch": 625.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5008
},
{
"epoch": 626.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5012
},
{
"epoch": 626.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5016
},
{
"epoch": 627.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5020
},
{
"epoch": 627.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5024
},
{
"epoch": 628.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5028
},
{
"epoch": 628.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5032
},
{
"epoch": 629.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5036
},
{
"epoch": 629.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5040
},
{
"epoch": 630.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5044
},
{
"epoch": 630.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5048
},
{
"epoch": 631.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5052
},
{
"epoch": 631.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5056
},
{
"epoch": 631.99,
"eval_exact_match": 0.4369414101290963,
"eval_exec": 0.46772591857000995,
"eval_loss": 0.6289202570915222,
"eval_runtime": 198.0458,
"eval_samples_per_second": 6.564,
"step": 5056
},
{
"epoch": 632.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5060
},
{
"epoch": 632.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5064
},
{
"epoch": 633.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5068
},
{
"epoch": 633.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5072
},
{
"epoch": 634.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5076
},
{
"epoch": 634.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5080
},
{
"epoch": 635.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5084
},
{
"epoch": 635.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5088
},
{
"epoch": 636.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5092
},
{
"epoch": 636.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5096
},
{
"epoch": 637.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5100
},
{
"epoch": 637.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5104
},
{
"epoch": 638.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5108
},
{
"epoch": 638.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5112
},
{
"epoch": 639.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5116
},
{
"epoch": 639.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5120
},
{
"epoch": 639.99,
"eval_exact_match": 0.44985104270109233,
"eval_exec": 0.4885799404170804,
"eval_loss": 0.6289829015731812,
"eval_runtime": 208.2718,
"eval_samples_per_second": 6.242,
"step": 5120
},
{
"epoch": 640.5,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 5124
},
{
"epoch": 640.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5128
},
{
"epoch": 641.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5132
},
{
"epoch": 641.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5136
},
{
"epoch": 642.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5140
},
{
"epoch": 642.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5144
},
{
"epoch": 643.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5148
},
{
"epoch": 643.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5152
},
{
"epoch": 644.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5156
},
{
"epoch": 644.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5160
},
{
"epoch": 645.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5164
},
{
"epoch": 645.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5168
},
{
"epoch": 646.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5172
},
{
"epoch": 646.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5176
},
{
"epoch": 647.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5180
},
{
"epoch": 647.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5184
},
{
"epoch": 647.99,
"eval_exact_match": 0.45084409136047665,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.6306817531585693,
"eval_runtime": 212.6718,
"eval_samples_per_second": 6.113,
"step": 5184
},
{
"epoch": 648.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5188
},
{
"epoch": 648.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5192
},
{
"epoch": 649.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5196
},
{
"epoch": 649.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5200
},
{
"epoch": 650.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5204
},
{
"epoch": 650.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5208
},
{
"epoch": 651.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5212
},
{
"epoch": 651.99,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 5216
},
{
"epoch": 652.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5220
},
{
"epoch": 652.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5224
},
{
"epoch": 653.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5228
},
{
"epoch": 653.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5232
},
{
"epoch": 654.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5236
},
{
"epoch": 654.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5240
},
{
"epoch": 655.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5244
},
{
"epoch": 655.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5248
},
{
"epoch": 655.99,
"eval_exact_match": 0.43495531281032773,
"eval_exec": 0.4746772591857001,
"eval_loss": 0.6379679441452026,
"eval_runtime": 203.8275,
"eval_samples_per_second": 6.378,
"step": 5248
},
{
"epoch": 656.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5252
},
{
"epoch": 656.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5256
},
{
"epoch": 657.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5260
},
{
"epoch": 657.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5264
},
{
"epoch": 658.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5268
},
{
"epoch": 658.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5272
},
{
"epoch": 659.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5276
},
{
"epoch": 659.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5280
},
{
"epoch": 660.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5284
},
{
"epoch": 660.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5288
},
{
"epoch": 661.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5292
},
{
"epoch": 661.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5296
},
{
"epoch": 662.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5300
},
{
"epoch": 662.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5304
},
{
"epoch": 663.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5308
},
{
"epoch": 663.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5312
},
{
"epoch": 663.99,
"eval_exact_match": 0.43793445878848064,
"eval_exec": 0.4766633565044687,
"eval_loss": 0.6149209141731262,
"eval_runtime": 205.2947,
"eval_samples_per_second": 6.332,
"step": 5312
},
{
"epoch": 664.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5316
},
{
"epoch": 664.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5320
},
{
"epoch": 665.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5324
},
{
"epoch": 665.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5328
},
{
"epoch": 666.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5332
},
{
"epoch": 666.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5336
},
{
"epoch": 667.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5340
},
{
"epoch": 667.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5344
},
{
"epoch": 668.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5348
},
{
"epoch": 668.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5352
},
{
"epoch": 669.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5356
},
{
"epoch": 669.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5360
},
{
"epoch": 670.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5364
},
{
"epoch": 670.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5368
},
{
"epoch": 671.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5372
},
{
"epoch": 671.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5376
},
{
"epoch": 671.99,
"eval_exact_match": 0.4458788480635551,
"eval_exec": 0.47765640516385305,
"eval_loss": 0.6341748237609863,
"eval_runtime": 200.2501,
"eval_samples_per_second": 6.492,
"step": 5376
},
{
"epoch": 672.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5380
},
{
"epoch": 672.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5384
},
{
"epoch": 673.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5388
},
{
"epoch": 673.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5392
},
{
"epoch": 674.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5396
},
{
"epoch": 674.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5400
},
{
"epoch": 675.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5404
},
{
"epoch": 675.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5408
},
{
"epoch": 676.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5412
},
{
"epoch": 676.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5416
},
{
"epoch": 677.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5420
},
{
"epoch": 677.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5424
},
{
"epoch": 678.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5428
},
{
"epoch": 678.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5432
},
{
"epoch": 679.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5436
},
{
"epoch": 679.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5440
},
{
"epoch": 679.99,
"eval_exact_match": 0.43892750744786496,
"eval_exec": 0.4766633565044687,
"eval_loss": 0.6424917578697205,
"eval_runtime": 214.8147,
"eval_samples_per_second": 6.052,
"step": 5440
},
{
"epoch": 680.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5444
},
{
"epoch": 680.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5448
},
{
"epoch": 681.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5452
},
{
"epoch": 681.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5456
},
{
"epoch": 682.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5460
},
{
"epoch": 682.99,
"learning_rate": 0.0001,
"loss": 0.0029,
"step": 5464
},
{
"epoch": 683.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5468
},
{
"epoch": 683.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5472
},
{
"epoch": 684.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5476
},
{
"epoch": 684.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5480
},
{
"epoch": 685.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5484
},
{
"epoch": 685.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5488
},
{
"epoch": 686.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5492
},
{
"epoch": 686.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5496
},
{
"epoch": 687.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5500
},
{
"epoch": 687.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5504
},
{
"epoch": 687.99,
"eval_exact_match": 0.44786494538232374,
"eval_exec": 0.4826216484607746,
"eval_loss": 0.6195693612098694,
"eval_runtime": 205.7504,
"eval_samples_per_second": 6.318,
"step": 5504
},
{
"epoch": 688.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5508
},
{
"epoch": 688.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5512
},
{
"epoch": 689.5,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5516
},
{
"epoch": 689.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5520
},
{
"epoch": 690.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5524
},
{
"epoch": 690.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5528
},
{
"epoch": 691.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5532
},
{
"epoch": 691.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5536
},
{
"epoch": 692.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5540
},
{
"epoch": 692.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5544
},
{
"epoch": 693.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5548
},
{
"epoch": 693.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5552
},
{
"epoch": 694.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5556
},
{
"epoch": 694.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5560
},
{
"epoch": 695.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5564
},
{
"epoch": 695.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5568
},
{
"epoch": 695.99,
"eval_exact_match": 0.4448857994041708,
"eval_exec": 0.48361469712015887,
"eval_loss": 0.6261533498764038,
"eval_runtime": 213.1489,
"eval_samples_per_second": 6.099,
"step": 5568
},
{
"epoch": 696.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5572
},
{
"epoch": 696.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5576
},
{
"epoch": 697.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5580
},
{
"epoch": 697.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5584
},
{
"epoch": 698.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5588
},
{
"epoch": 698.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5592
},
{
"epoch": 699.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5596
},
{
"epoch": 699.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5600
},
{
"epoch": 700.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5604
},
{
"epoch": 700.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5608
},
{
"epoch": 701.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5612
},
{
"epoch": 701.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5616
},
{
"epoch": 702.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5620
},
{
"epoch": 702.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5624
},
{
"epoch": 703.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5628
},
{
"epoch": 703.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5632
},
{
"epoch": 703.99,
"eval_exact_match": 0.43892750744786496,
"eval_exec": 0.4756703078450844,
"eval_loss": 0.6435733437538147,
"eval_runtime": 208.5122,
"eval_samples_per_second": 6.235,
"step": 5632
},
{
"epoch": 704.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5636
},
{
"epoch": 704.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5640
},
{
"epoch": 705.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5644
},
{
"epoch": 705.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5648
},
{
"epoch": 706.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5652
},
{
"epoch": 706.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5656
},
{
"epoch": 707.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5660
},
{
"epoch": 707.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5664
},
{
"epoch": 708.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5668
},
{
"epoch": 708.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5672
},
{
"epoch": 709.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5676
},
{
"epoch": 709.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5680
},
{
"epoch": 710.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5684
},
{
"epoch": 710.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5688
},
{
"epoch": 711.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5692
},
{
"epoch": 711.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5696
},
{
"epoch": 711.99,
"eval_exact_match": 0.44985104270109233,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.6287506818771362,
"eval_runtime": 206.1374,
"eval_samples_per_second": 6.306,
"step": 5696
},
{
"epoch": 712.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5700
},
{
"epoch": 712.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5704
},
{
"epoch": 713.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5708
},
{
"epoch": 713.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5712
},
{
"epoch": 714.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5716
},
{
"epoch": 714.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5720
},
{
"epoch": 715.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5724
},
{
"epoch": 715.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5728
},
{
"epoch": 716.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5732
},
{
"epoch": 716.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5736
},
{
"epoch": 717.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5740
},
{
"epoch": 717.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5744
},
{
"epoch": 718.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5748
},
{
"epoch": 718.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5752
},
{
"epoch": 719.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5756
},
{
"epoch": 719.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5760
},
{
"epoch": 719.99,
"eval_exact_match": 0.4448857994041708,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.641159176826477,
"eval_runtime": 206.6444,
"eval_samples_per_second": 6.291,
"step": 5760
},
{
"epoch": 720.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5764
},
{
"epoch": 720.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5768
},
{
"epoch": 721.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5772
},
{
"epoch": 721.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5776
},
{
"epoch": 722.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5780
},
{
"epoch": 722.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5784
},
{
"epoch": 723.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5788
},
{
"epoch": 723.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 5792
},
{
"epoch": 724.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5796
},
{
"epoch": 724.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5800
},
{
"epoch": 725.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5804
},
{
"epoch": 725.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5808
},
{
"epoch": 726.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5812
},
{
"epoch": 726.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5816
},
{
"epoch": 727.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5820
},
{
"epoch": 727.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5824
},
{
"epoch": 727.99,
"eval_exact_match": 0.4458788480635551,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.647663414478302,
"eval_runtime": 211.128,
"eval_samples_per_second": 6.157,
"step": 5824
},
{
"epoch": 728.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5828
},
{
"epoch": 728.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5832
},
{
"epoch": 729.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5836
},
{
"epoch": 729.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5840
},
{
"epoch": 730.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5844
},
{
"epoch": 730.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5848
},
{
"epoch": 731.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 5852
},
{
"epoch": 731.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5856
},
{
"epoch": 732.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5860
},
{
"epoch": 732.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5864
},
{
"epoch": 733.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 5868
},
{
"epoch": 733.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5872
},
{
"epoch": 734.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5876
},
{
"epoch": 734.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5880
},
{
"epoch": 735.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5884
},
{
"epoch": 735.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5888
},
{
"epoch": 735.99,
"eval_exact_match": 0.4448857994041708,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.6436724662780762,
"eval_runtime": 200.2646,
"eval_samples_per_second": 6.491,
"step": 5888
},
{
"epoch": 736.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5892
},
{
"epoch": 736.99,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5896
},
{
"epoch": 737.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5900
},
{
"epoch": 737.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5904
},
{
"epoch": 738.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5908
},
{
"epoch": 738.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5912
},
{
"epoch": 739.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5916
},
{
"epoch": 739.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5920
},
{
"epoch": 740.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5924
},
{
"epoch": 740.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5928
},
{
"epoch": 741.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5932
},
{
"epoch": 741.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5936
},
{
"epoch": 742.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 5940
},
{
"epoch": 742.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 5944
},
{
"epoch": 743.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 5948
},
{
"epoch": 743.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5952
},
{
"epoch": 743.99,
"eval_exact_match": 0.44786494538232374,
"eval_exec": 0.4826216484607746,
"eval_loss": 0.648475706577301,
"eval_runtime": 203.6491,
"eval_samples_per_second": 6.384,
"step": 5952
},
{
"epoch": 744.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5956
},
{
"epoch": 744.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5960
},
{
"epoch": 745.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5964
},
{
"epoch": 745.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 5968
},
{
"epoch": 746.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 5972
},
{
"epoch": 746.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5976
},
{
"epoch": 747.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5980
},
{
"epoch": 747.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5984
},
{
"epoch": 748.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5988
},
{
"epoch": 748.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 5992
},
{
"epoch": 749.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 5996
},
{
"epoch": 749.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6000
},
{
"epoch": 750.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6004
},
{
"epoch": 750.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6008
},
{
"epoch": 751.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6012
},
{
"epoch": 751.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6016
},
{
"epoch": 751.99,
"eval_exact_match": 0.4468718967229394,
"eval_exec": 0.48063555114200596,
"eval_loss": 0.6662933826446533,
"eval_runtime": 196.1389,
"eval_samples_per_second": 6.628,
"step": 6016
},
{
"epoch": 752.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6020
},
{
"epoch": 752.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6024
},
{
"epoch": 753.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6028
},
{
"epoch": 753.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6032
},
{
"epoch": 754.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6036
},
{
"epoch": 754.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6040
},
{
"epoch": 755.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6044
},
{
"epoch": 755.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6048
},
{
"epoch": 756.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6052
},
{
"epoch": 756.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6056
},
{
"epoch": 757.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6060
},
{
"epoch": 757.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6064
},
{
"epoch": 758.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6068
},
{
"epoch": 758.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6072
},
{
"epoch": 759.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6076
},
{
"epoch": 759.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6080
},
{
"epoch": 759.99,
"eval_exact_match": 0.43793445878848064,
"eval_exec": 0.46971201588877853,
"eval_loss": 0.6573625206947327,
"eval_runtime": 203.6771,
"eval_samples_per_second": 6.383,
"step": 6080
},
{
"epoch": 760.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6084
},
{
"epoch": 760.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6088
},
{
"epoch": 761.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6092
},
{
"epoch": 761.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6096
},
{
"epoch": 762.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6100
},
{
"epoch": 762.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6104
},
{
"epoch": 763.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6108
},
{
"epoch": 763.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6112
},
{
"epoch": 764.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6116
},
{
"epoch": 764.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6120
},
{
"epoch": 765.5,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 6124
},
{
"epoch": 765.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6128
},
{
"epoch": 766.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6132
},
{
"epoch": 766.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6136
},
{
"epoch": 767.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6140
},
{
"epoch": 767.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6144
},
{
"epoch": 767.99,
"eval_exact_match": 0.45183714001986097,
"eval_exec": 0.48957298907646474,
"eval_loss": 0.6423913240432739,
"eval_runtime": 196.8271,
"eval_samples_per_second": 6.605,
"step": 6144
},
{
"epoch": 768.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6148
},
{
"epoch": 768.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6152
},
{
"epoch": 769.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6156
},
{
"epoch": 769.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6160
},
{
"epoch": 770.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6164
},
{
"epoch": 770.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6168
},
{
"epoch": 771.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6172
},
{
"epoch": 771.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6176
},
{
"epoch": 772.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6180
},
{
"epoch": 772.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6184
},
{
"epoch": 773.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6188
},
{
"epoch": 773.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6192
},
{
"epoch": 774.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6196
},
{
"epoch": 774.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6200
},
{
"epoch": 775.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6204
},
{
"epoch": 775.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6208
},
{
"epoch": 775.99,
"eval_exact_match": 0.4558093346573982,
"eval_exec": 0.49652432969215493,
"eval_loss": 0.6396003365516663,
"eval_runtime": 214.4091,
"eval_samples_per_second": 6.063,
"step": 6208
},
{
"epoch": 776.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6212
},
{
"epoch": 776.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6216
},
{
"epoch": 777.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6220
},
{
"epoch": 777.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6224
},
{
"epoch": 778.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6228
},
{
"epoch": 778.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6232
},
{
"epoch": 779.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6236
},
{
"epoch": 779.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6240
},
{
"epoch": 780.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6244
},
{
"epoch": 780.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6248
},
{
"epoch": 781.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6252
},
{
"epoch": 781.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6256
},
{
"epoch": 782.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6260
},
{
"epoch": 782.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6264
},
{
"epoch": 783.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6268
},
{
"epoch": 783.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6272
},
{
"epoch": 783.99,
"eval_exact_match": 0.43892750744786496,
"eval_exec": 0.4856007944389275,
"eval_loss": 0.6399450898170471,
"eval_runtime": 226.2412,
"eval_samples_per_second": 5.746,
"step": 6272
},
{
"epoch": 784.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6276
},
{
"epoch": 784.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6280
},
{
"epoch": 785.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6284
},
{
"epoch": 785.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6288
},
{
"epoch": 786.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6292
},
{
"epoch": 786.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6296
},
{
"epoch": 787.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6300
},
{
"epoch": 787.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6304
},
{
"epoch": 788.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6308
},
{
"epoch": 788.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6312
},
{
"epoch": 789.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6316
},
{
"epoch": 789.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6320
},
{
"epoch": 790.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6324
},
{
"epoch": 790.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6328
},
{
"epoch": 791.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6332
},
{
"epoch": 791.99,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 6336
},
{
"epoch": 791.99,
"eval_exact_match": 0.44091360476663355,
"eval_exec": 0.47964250248262164,
"eval_loss": 0.6275960803031921,
"eval_runtime": 209.1576,
"eval_samples_per_second": 6.215,
"step": 6336
},
{
"epoch": 792.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6340
},
{
"epoch": 792.99,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 6344
},
{
"epoch": 793.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6348
},
{
"epoch": 793.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6352
},
{
"epoch": 794.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6356
},
{
"epoch": 794.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6360
},
{
"epoch": 795.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6364
},
{
"epoch": 795.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6368
},
{
"epoch": 796.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6372
},
{
"epoch": 796.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6376
},
{
"epoch": 797.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6380
},
{
"epoch": 797.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6384
},
{
"epoch": 798.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6388
},
{
"epoch": 798.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6392
},
{
"epoch": 799.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6396
},
{
"epoch": 799.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6400
},
{
"epoch": 799.99,
"eval_exact_match": 0.4468718967229394,
"eval_exec": 0.48659384309831183,
"eval_loss": 0.641415536403656,
"eval_runtime": 208.4431,
"eval_samples_per_second": 6.237,
"step": 6400
},
{
"epoch": 800.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6404
},
{
"epoch": 800.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6408
},
{
"epoch": 801.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6412
},
{
"epoch": 801.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6416
},
{
"epoch": 802.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6420
},
{
"epoch": 802.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6424
},
{
"epoch": 803.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6428
},
{
"epoch": 803.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6432
},
{
"epoch": 804.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6436
},
{
"epoch": 804.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6440
},
{
"epoch": 805.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6444
},
{
"epoch": 805.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6448
},
{
"epoch": 806.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6452
},
{
"epoch": 806.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6456
},
{
"epoch": 807.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6460
},
{
"epoch": 807.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6464
},
{
"epoch": 807.99,
"eval_exact_match": 0.44786494538232374,
"eval_exec": 0.4846077457795432,
"eval_loss": 0.6324633359909058,
"eval_runtime": 216.057,
"eval_samples_per_second": 6.017,
"step": 6464
},
{
"epoch": 808.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6468
},
{
"epoch": 808.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6472
},
{
"epoch": 809.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6476
},
{
"epoch": 809.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6480
},
{
"epoch": 810.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6484
},
{
"epoch": 810.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6488
},
{
"epoch": 811.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6492
},
{
"epoch": 811.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6496
},
{
"epoch": 812.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6500
},
{
"epoch": 812.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6504
},
{
"epoch": 813.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6508
},
{
"epoch": 813.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6512
},
{
"epoch": 814.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6516
},
{
"epoch": 814.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6520
},
{
"epoch": 815.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6524
},
{
"epoch": 815.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6528
},
{
"epoch": 815.99,
"eval_exact_match": 0.44190665342601787,
"eval_exec": 0.4885799404170804,
"eval_loss": 0.6281804442405701,
"eval_runtime": 213.8722,
"eval_samples_per_second": 6.078,
"step": 6528
},
{
"epoch": 816.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6532
},
{
"epoch": 816.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6536
},
{
"epoch": 817.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6540
},
{
"epoch": 817.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6544
},
{
"epoch": 818.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6548
},
{
"epoch": 818.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6552
},
{
"epoch": 819.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6556
},
{
"epoch": 819.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6560
},
{
"epoch": 820.5,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 6564
},
{
"epoch": 820.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6568
},
{
"epoch": 821.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6572
},
{
"epoch": 821.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6576
},
{
"epoch": 822.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6580
},
{
"epoch": 822.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6584
},
{
"epoch": 823.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6588
},
{
"epoch": 823.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6592
},
{
"epoch": 823.99,
"eval_exact_match": 0.45779543197616684,
"eval_exec": 0.4915590863952334,
"eval_loss": 0.6452751159667969,
"eval_runtime": 223.4105,
"eval_samples_per_second": 5.819,
"step": 6592
},
{
"epoch": 824.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6596
},
{
"epoch": 824.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6600
},
{
"epoch": 825.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6604
},
{
"epoch": 825.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6608
},
{
"epoch": 826.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6612
},
{
"epoch": 826.99,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 6616
},
{
"epoch": 827.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6620
},
{
"epoch": 827.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6624
},
{
"epoch": 828.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6628
},
{
"epoch": 828.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6632
},
{
"epoch": 829.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6636
},
{
"epoch": 829.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6640
},
{
"epoch": 830.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6644
},
{
"epoch": 830.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6648
},
{
"epoch": 831.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6652
},
{
"epoch": 831.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6656
},
{
"epoch": 831.99,
"eval_exact_match": 0.4637537239324727,
"eval_exec": 0.49751737835153925,
"eval_loss": 0.6585542559623718,
"eval_runtime": 209.9114,
"eval_samples_per_second": 6.193,
"step": 6656
},
{
"epoch": 832.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6660
},
{
"epoch": 832.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6664
},
{
"epoch": 833.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6668
},
{
"epoch": 833.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6672
},
{
"epoch": 834.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6676
},
{
"epoch": 834.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6680
},
{
"epoch": 835.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6684
},
{
"epoch": 835.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6688
},
{
"epoch": 836.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6692
},
{
"epoch": 836.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6696
},
{
"epoch": 837.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6700
},
{
"epoch": 837.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6704
},
{
"epoch": 838.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6708
},
{
"epoch": 838.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6712
},
{
"epoch": 839.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6716
},
{
"epoch": 839.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6720
},
{
"epoch": 839.99,
"eval_exact_match": 0.45978152929493543,
"eval_exec": 0.4945382323733863,
"eval_loss": 0.660439670085907,
"eval_runtime": 216.7543,
"eval_samples_per_second": 5.998,
"step": 6720
},
{
"epoch": 840.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6724
},
{
"epoch": 840.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6728
},
{
"epoch": 841.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6732
},
{
"epoch": 841.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6736
},
{
"epoch": 842.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6740
},
{
"epoch": 842.99,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 6744
},
{
"epoch": 843.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6748
},
{
"epoch": 843.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6752
},
{
"epoch": 844.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6756
},
{
"epoch": 844.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6760
},
{
"epoch": 845.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6764
},
{
"epoch": 845.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6768
},
{
"epoch": 846.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6772
},
{
"epoch": 846.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6776
},
{
"epoch": 847.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6780
},
{
"epoch": 847.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6784
},
{
"epoch": 847.99,
"eval_exact_match": 0.4468718967229394,
"eval_exec": 0.4885799404170804,
"eval_loss": 0.6388683319091797,
"eval_runtime": 225.744,
"eval_samples_per_second": 5.759,
"step": 6784
},
{
"epoch": 848.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6788
},
{
"epoch": 848.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6792
},
{
"epoch": 849.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6796
},
{
"epoch": 849.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6800
},
{
"epoch": 850.5,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6804
},
{
"epoch": 850.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6808
},
{
"epoch": 851.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6812
},
{
"epoch": 851.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6816
},
{
"epoch": 852.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6820
},
{
"epoch": 852.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6824
},
{
"epoch": 853.5,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6828
},
{
"epoch": 853.99,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 6832
},
{
"epoch": 854.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6836
},
{
"epoch": 854.99,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 6840
},
{
"epoch": 855.5,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6844
},
{
"epoch": 855.99,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 6848
},
{
"epoch": 855.99,
"eval_exact_match": 0.4657398212512413,
"eval_exec": 0.4925521350546177,
"eval_loss": 0.6665723323822021,
"eval_runtime": 199.9726,
"eval_samples_per_second": 6.501,
"step": 6848
}
],
"max_steps": 24576,
"num_train_epochs": 3072,
"total_flos": 7.45169724254251e+18,
"trial_name": null,
"trial_params": null
}