spider_relation_t5_3b-3392 / trainer_state.json
Jiexing's picture
commit for jxqi spider-max-em-model
9043147
{
"best_metric": 0.7214700193423598,
"best_model_checkpoint": "./experiment/train_0407_3b_db_use_init_10770/checkpoint-3392",
"epoch": 1130.581818181818,
"global_step": 3392,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.0524,
"step": 1
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.0135,
"step": 3
},
{
"epoch": 1.87,
"learning_rate": 0.0001,
"loss": 0.0271,
"step": 6
},
{
"epoch": 2.87,
"learning_rate": 0.0001,
"loss": 0.0032,
"step": 9
},
{
"epoch": 3.87,
"learning_rate": 0.0001,
"loss": 0.0041,
"step": 12
},
{
"epoch": 4.87,
"learning_rate": 0.0001,
"loss": 0.0117,
"step": 15
},
{
"epoch": 5.87,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 18
},
{
"epoch": 6.87,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 21
},
{
"epoch": 7.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 24
},
{
"epoch": 8.87,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 27
},
{
"epoch": 9.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 30
},
{
"epoch": 10.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 33
},
{
"epoch": 11.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 36
},
{
"epoch": 12.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 39
},
{
"epoch": 13.87,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 42
},
{
"epoch": 14.87,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 45
},
{
"epoch": 15.87,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 48
},
{
"epoch": 16.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 51
},
{
"epoch": 17.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 54
},
{
"epoch": 18.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 57
},
{
"epoch": 19.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 60
},
{
"epoch": 20.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 63
},
{
"epoch": 21.29,
"eval_exact_match": 0.6711798839458414,
"eval_exec": 0.7263056092843327,
"eval_loss": 0.31857267022132874,
"eval_runtime": 1456.357,
"eval_samples_per_second": 0.71,
"step": 64
},
{
"epoch": 21.87,
"learning_rate": 0.0001,
"loss": 0.0063,
"step": 66
},
{
"epoch": 22.87,
"learning_rate": 0.0001,
"loss": 0.0066,
"step": 69
},
{
"epoch": 23.87,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 72
},
{
"epoch": 24.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 75
},
{
"epoch": 25.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 78
},
{
"epoch": 26.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 81
},
{
"epoch": 27.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 84
},
{
"epoch": 28.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 87
},
{
"epoch": 29.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 90
},
{
"epoch": 30.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 93
},
{
"epoch": 31.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 96
},
{
"epoch": 32.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 99
},
{
"epoch": 33.87,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 102
},
{
"epoch": 34.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 105
},
{
"epoch": 35.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 108
},
{
"epoch": 36.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 111
},
{
"epoch": 37.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 114
},
{
"epoch": 38.87,
"learning_rate": 0.0001,
"loss": 0.0062,
"step": 117
},
{
"epoch": 39.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 120
},
{
"epoch": 40.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 123
},
{
"epoch": 41.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 126
},
{
"epoch": 42.58,
"eval_exact_match": 0.660541586073501,
"eval_exec": 0.7030947775628626,
"eval_loss": 0.3405461311340332,
"eval_runtime": 549.64,
"eval_samples_per_second": 1.881,
"step": 128
},
{
"epoch": 42.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 129
},
{
"epoch": 43.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 132
},
{
"epoch": 44.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 135
},
{
"epoch": 45.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 138
},
{
"epoch": 46.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 141
},
{
"epoch": 47.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 144
},
{
"epoch": 48.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 147
},
{
"epoch": 49.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 150
},
{
"epoch": 50.87,
"learning_rate": 0.0001,
"loss": 0.0098,
"step": 153
},
{
"epoch": 51.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 156
},
{
"epoch": 52.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 159
},
{
"epoch": 53.87,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 162
},
{
"epoch": 54.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 165
},
{
"epoch": 55.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 168
},
{
"epoch": 56.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 171
},
{
"epoch": 57.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 174
},
{
"epoch": 58.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 177
},
{
"epoch": 59.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 180
},
{
"epoch": 60.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 183
},
{
"epoch": 61.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 186
},
{
"epoch": 62.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 189
},
{
"epoch": 63.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 192
},
{
"epoch": 63.87,
"eval_exact_match": 0.683752417794971,
"eval_exec": 0.7137330754352031,
"eval_loss": 0.36411476135253906,
"eval_runtime": 516.7586,
"eval_samples_per_second": 2.001,
"step": 192
},
{
"epoch": 64.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 195
},
{
"epoch": 65.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 198
},
{
"epoch": 66.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 201
},
{
"epoch": 67.87,
"learning_rate": 0.0001,
"loss": 0.0062,
"step": 204
},
{
"epoch": 68.87,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 207
},
{
"epoch": 69.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 210
},
{
"epoch": 70.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 213
},
{
"epoch": 71.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 216
},
{
"epoch": 72.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 219
},
{
"epoch": 73.87,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 222
},
{
"epoch": 74.87,
"learning_rate": 0.0001,
"loss": 0.0051,
"step": 225
},
{
"epoch": 75.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 228
},
{
"epoch": 76.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 231
},
{
"epoch": 77.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 234
},
{
"epoch": 78.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 237
},
{
"epoch": 79.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 240
},
{
"epoch": 80.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 243
},
{
"epoch": 81.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 246
},
{
"epoch": 82.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 249
},
{
"epoch": 83.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 252
},
{
"epoch": 84.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 255
},
{
"epoch": 85.29,
"eval_exact_match": 0.6876208897485493,
"eval_exec": 0.7156673114119922,
"eval_loss": 0.3546766936779022,
"eval_runtime": 519.3296,
"eval_samples_per_second": 1.991,
"step": 256
},
{
"epoch": 85.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 258
},
{
"epoch": 86.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 261
},
{
"epoch": 87.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 264
},
{
"epoch": 88.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 267
},
{
"epoch": 89.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 270
},
{
"epoch": 90.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 273
},
{
"epoch": 91.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 276
},
{
"epoch": 92.87,
"learning_rate": 0.0001,
"loss": 0.0126,
"step": 279
},
{
"epoch": 93.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 282
},
{
"epoch": 94.87,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 285
},
{
"epoch": 95.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 288
},
{
"epoch": 96.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 291
},
{
"epoch": 97.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 294
},
{
"epoch": 98.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 297
},
{
"epoch": 99.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 300
},
{
"epoch": 100.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 303
},
{
"epoch": 101.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 306
},
{
"epoch": 102.87,
"learning_rate": 0.0001,
"loss": 0.0119,
"step": 309
},
{
"epoch": 103.87,
"learning_rate": 0.0001,
"loss": 0.0156,
"step": 312
},
{
"epoch": 104.87,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 315
},
{
"epoch": 105.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 318
},
{
"epoch": 106.58,
"eval_exact_match": 0.6769825918762089,
"eval_exec": 0.718568665377176,
"eval_loss": 0.30316162109375,
"eval_runtime": 480.1138,
"eval_samples_per_second": 2.154,
"step": 320
},
{
"epoch": 106.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 321
},
{
"epoch": 107.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 324
},
{
"epoch": 108.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 327
},
{
"epoch": 109.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 330
},
{
"epoch": 110.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 333
},
{
"epoch": 111.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 336
},
{
"epoch": 112.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 339
},
{
"epoch": 113.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 342
},
{
"epoch": 114.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 345
},
{
"epoch": 115.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 348
},
{
"epoch": 116.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 351
},
{
"epoch": 117.87,
"learning_rate": 0.0001,
"loss": 0.002,
"step": 354
},
{
"epoch": 118.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 357
},
{
"epoch": 119.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 360
},
{
"epoch": 120.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 363
},
{
"epoch": 121.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 366
},
{
"epoch": 122.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 369
},
{
"epoch": 123.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 372
},
{
"epoch": 124.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 375
},
{
"epoch": 125.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 378
},
{
"epoch": 126.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 381
},
{
"epoch": 127.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 384
},
{
"epoch": 127.87,
"eval_exact_match": 0.6866537717601547,
"eval_exec": 0.7272727272727273,
"eval_loss": 0.3592199981212616,
"eval_runtime": 499.5116,
"eval_samples_per_second": 2.07,
"step": 384
},
{
"epoch": 128.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 387
},
{
"epoch": 129.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 390
},
{
"epoch": 130.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 393
},
{
"epoch": 131.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 396
},
{
"epoch": 132.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 399
},
{
"epoch": 133.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 402
},
{
"epoch": 134.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 405
},
{
"epoch": 135.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 408
},
{
"epoch": 136.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 411
},
{
"epoch": 137.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 414
},
{
"epoch": 138.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 417
},
{
"epoch": 139.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 420
},
{
"epoch": 140.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 423
},
{
"epoch": 141.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 426
},
{
"epoch": 142.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 429
},
{
"epoch": 143.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 432
},
{
"epoch": 144.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 435
},
{
"epoch": 145.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 438
},
{
"epoch": 146.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 441
},
{
"epoch": 147.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 444
},
{
"epoch": 148.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 447
},
{
"epoch": 149.29,
"eval_exact_match": 0.683752417794971,
"eval_exec": 0.7263056092843327,
"eval_loss": 0.37971413135528564,
"eval_runtime": 539.1731,
"eval_samples_per_second": 1.918,
"step": 448
},
{
"epoch": 149.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 450
},
{
"epoch": 150.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 453
},
{
"epoch": 151.87,
"learning_rate": 0.0001,
"loss": 0.0079,
"step": 456
},
{
"epoch": 152.87,
"learning_rate": 0.0001,
"loss": 0.0039,
"step": 459
},
{
"epoch": 153.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 462
},
{
"epoch": 154.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 465
},
{
"epoch": 155.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 468
},
{
"epoch": 156.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 471
},
{
"epoch": 157.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 474
},
{
"epoch": 158.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 477
},
{
"epoch": 159.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 480
},
{
"epoch": 160.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 483
},
{
"epoch": 161.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 486
},
{
"epoch": 162.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 489
},
{
"epoch": 163.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 492
},
{
"epoch": 164.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 495
},
{
"epoch": 165.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 498
},
{
"epoch": 166.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 501
},
{
"epoch": 167.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 504
},
{
"epoch": 168.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 507
},
{
"epoch": 169.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 510
},
{
"epoch": 170.58,
"eval_exact_match": 0.690522243713733,
"eval_exec": 0.7263056092843327,
"eval_loss": 0.3713047504425049,
"eval_runtime": 487.523,
"eval_samples_per_second": 2.121,
"step": 512
},
{
"epoch": 170.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 513
},
{
"epoch": 171.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 516
},
{
"epoch": 172.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 519
},
{
"epoch": 173.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 522
},
{
"epoch": 174.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 525
},
{
"epoch": 175.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 528
},
{
"epoch": 176.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 531
},
{
"epoch": 177.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 534
},
{
"epoch": 178.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 537
},
{
"epoch": 179.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 540
},
{
"epoch": 180.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 543
},
{
"epoch": 181.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 546
},
{
"epoch": 182.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 549
},
{
"epoch": 183.87,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 552
},
{
"epoch": 184.87,
"learning_rate": 0.0001,
"loss": 0.0104,
"step": 555
},
{
"epoch": 185.87,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 558
},
{
"epoch": 186.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 561
},
{
"epoch": 187.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 564
},
{
"epoch": 188.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 567
},
{
"epoch": 189.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 570
},
{
"epoch": 190.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 573
},
{
"epoch": 191.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 576
},
{
"epoch": 191.87,
"eval_exact_match": 0.6982591876208898,
"eval_exec": 0.7398452611218569,
"eval_loss": 0.35731402039527893,
"eval_runtime": 515.4072,
"eval_samples_per_second": 2.006,
"step": 576
},
{
"epoch": 192.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 579
},
{
"epoch": 193.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 582
},
{
"epoch": 194.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 585
},
{
"epoch": 195.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 588
},
{
"epoch": 196.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 591
},
{
"epoch": 197.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 594
},
{
"epoch": 198.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 597
},
{
"epoch": 199.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 600
},
{
"epoch": 200.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 603
},
{
"epoch": 201.87,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 606
},
{
"epoch": 202.87,
"learning_rate": 0.0001,
"loss": 0.0022,
"step": 609
},
{
"epoch": 203.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 612
},
{
"epoch": 204.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 615
},
{
"epoch": 205.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 618
},
{
"epoch": 206.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 621
},
{
"epoch": 207.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 624
},
{
"epoch": 208.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 627
},
{
"epoch": 209.87,
"learning_rate": 0.0001,
"loss": 0.0061,
"step": 630
},
{
"epoch": 210.87,
"learning_rate": 0.0001,
"loss": 0.0214,
"step": 633
},
{
"epoch": 211.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 636
},
{
"epoch": 212.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 639
},
{
"epoch": 213.29,
"eval_exact_match": 0.7059961315280464,
"eval_exec": 0.7350096711798839,
"eval_loss": 0.3407991826534271,
"eval_runtime": 507.7063,
"eval_samples_per_second": 2.037,
"step": 640
},
{
"epoch": 213.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 642
},
{
"epoch": 214.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 645
},
{
"epoch": 215.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 648
},
{
"epoch": 216.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 651
},
{
"epoch": 217.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 654
},
{
"epoch": 218.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 657
},
{
"epoch": 219.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 660
},
{
"epoch": 220.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 663
},
{
"epoch": 221.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 666
},
{
"epoch": 222.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 669
},
{
"epoch": 223.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 672
},
{
"epoch": 224.87,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 675
},
{
"epoch": 225.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 678
},
{
"epoch": 226.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 681
},
{
"epoch": 227.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 684
},
{
"epoch": 228.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 687
},
{
"epoch": 229.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 690
},
{
"epoch": 230.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 693
},
{
"epoch": 231.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 696
},
{
"epoch": 232.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 699
},
{
"epoch": 233.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 702
},
{
"epoch": 234.58,
"eval_exact_match": 0.6992263056092843,
"eval_exec": 0.7272727272727273,
"eval_loss": 0.3767277002334595,
"eval_runtime": 545.434,
"eval_samples_per_second": 1.896,
"step": 704
},
{
"epoch": 234.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 705
},
{
"epoch": 235.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 708
},
{
"epoch": 236.87,
"learning_rate": 0.0001,
"loss": 0.0116,
"step": 711
},
{
"epoch": 237.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 714
},
{
"epoch": 238.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 717
},
{
"epoch": 239.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 720
},
{
"epoch": 240.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 723
},
{
"epoch": 241.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 726
},
{
"epoch": 242.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 729
},
{
"epoch": 243.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 732
},
{
"epoch": 244.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 735
},
{
"epoch": 245.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 738
},
{
"epoch": 246.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 741
},
{
"epoch": 247.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 744
},
{
"epoch": 248.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 747
},
{
"epoch": 249.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 750
},
{
"epoch": 250.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 753
},
{
"epoch": 251.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 756
},
{
"epoch": 252.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 759
},
{
"epoch": 253.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 762
},
{
"epoch": 254.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 765
},
{
"epoch": 255.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 768
},
{
"epoch": 255.87,
"eval_exact_match": 0.6943907156673114,
"eval_exec": 0.7282398452611218,
"eval_loss": 0.3885338008403778,
"eval_runtime": 546.3768,
"eval_samples_per_second": 1.892,
"step": 768
},
{
"epoch": 256.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 771
},
{
"epoch": 257.87,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 774
},
{
"epoch": 258.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 777
},
{
"epoch": 259.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 780
},
{
"epoch": 260.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 783
},
{
"epoch": 261.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 786
},
{
"epoch": 262.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 789
},
{
"epoch": 263.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 792
},
{
"epoch": 264.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 795
},
{
"epoch": 265.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 798
},
{
"epoch": 266.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 801
},
{
"epoch": 267.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 804
},
{
"epoch": 268.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 807
},
{
"epoch": 269.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 810
},
{
"epoch": 270.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 813
},
{
"epoch": 271.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 816
},
{
"epoch": 272.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 819
},
{
"epoch": 273.87,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 822
},
{
"epoch": 274.87,
"learning_rate": 0.0001,
"loss": 0.0059,
"step": 825
},
{
"epoch": 275.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 828
},
{
"epoch": 276.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 831
},
{
"epoch": 277.29,
"eval_exact_match": 0.695357833655706,
"eval_exec": 0.7321083172147002,
"eval_loss": 0.35210856795310974,
"eval_runtime": 608.3162,
"eval_samples_per_second": 1.7,
"step": 832
},
{
"epoch": 277.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 834
},
{
"epoch": 278.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 837
},
{
"epoch": 279.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 840
},
{
"epoch": 280.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 843
},
{
"epoch": 281.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 846
},
{
"epoch": 282.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 849
},
{
"epoch": 283.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 852
},
{
"epoch": 284.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 855
},
{
"epoch": 285.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 858
},
{
"epoch": 286.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 861
},
{
"epoch": 287.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 864
},
{
"epoch": 288.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 867
},
{
"epoch": 289.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 870
},
{
"epoch": 290.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 873
},
{
"epoch": 291.87,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 876
},
{
"epoch": 292.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 879
},
{
"epoch": 293.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 882
},
{
"epoch": 294.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 885
},
{
"epoch": 295.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 888
},
{
"epoch": 296.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 891
},
{
"epoch": 297.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 894
},
{
"epoch": 298.58,
"eval_exact_match": 0.688588007736944,
"eval_exec": 0.7214700193423598,
"eval_loss": 0.3566940426826477,
"eval_runtime": 584.9721,
"eval_samples_per_second": 1.768,
"step": 896
},
{
"epoch": 298.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 897
},
{
"epoch": 299.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 900
},
{
"epoch": 300.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 903
},
{
"epoch": 301.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 906
},
{
"epoch": 302.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 909
},
{
"epoch": 303.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 912
},
{
"epoch": 304.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 915
},
{
"epoch": 305.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 918
},
{
"epoch": 306.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 921
},
{
"epoch": 307.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 924
},
{
"epoch": 308.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 927
},
{
"epoch": 309.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 930
},
{
"epoch": 310.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 933
},
{
"epoch": 311.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 936
},
{
"epoch": 312.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 939
},
{
"epoch": 313.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 942
},
{
"epoch": 314.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 945
},
{
"epoch": 315.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 948
},
{
"epoch": 316.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 951
},
{
"epoch": 317.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 954
},
{
"epoch": 318.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 957
},
{
"epoch": 319.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 960
},
{
"epoch": 319.87,
"eval_exact_match": 0.6963249516441006,
"eval_exec": 0.730174081237911,
"eval_loss": 0.37420669198036194,
"eval_runtime": 518.4361,
"eval_samples_per_second": 1.994,
"step": 960
},
{
"epoch": 320.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 963
},
{
"epoch": 321.87,
"learning_rate": 0.0001,
"loss": 0.0024,
"step": 966
},
{
"epoch": 322.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 969
},
{
"epoch": 323.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 972
},
{
"epoch": 324.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 975
},
{
"epoch": 325.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 978
},
{
"epoch": 326.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 981
},
{
"epoch": 327.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 984
},
{
"epoch": 328.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 987
},
{
"epoch": 329.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 990
},
{
"epoch": 330.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 993
},
{
"epoch": 331.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 996
},
{
"epoch": 332.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 999
},
{
"epoch": 333.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1002
},
{
"epoch": 334.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1005
},
{
"epoch": 335.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1008
},
{
"epoch": 336.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1011
},
{
"epoch": 337.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1014
},
{
"epoch": 338.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1017
},
{
"epoch": 339.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1020
},
{
"epoch": 340.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1023
},
{
"epoch": 341.29,
"eval_exact_match": 0.6924564796905223,
"eval_exec": 0.7359767891682786,
"eval_loss": 0.39109551906585693,
"eval_runtime": 1517.7959,
"eval_samples_per_second": 0.681,
"step": 1024
},
{
"epoch": 341.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1026
},
{
"epoch": 342.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1029
},
{
"epoch": 343.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1032
},
{
"epoch": 344.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1035
},
{
"epoch": 345.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1038
},
{
"epoch": 346.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1041
},
{
"epoch": 347.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1044
},
{
"epoch": 348.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1047
},
{
"epoch": 349.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1050
},
{
"epoch": 350.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1053
},
{
"epoch": 351.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1056
},
{
"epoch": 352.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1059
},
{
"epoch": 353.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1062
},
{
"epoch": 354.87,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1065
},
{
"epoch": 355.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1068
},
{
"epoch": 356.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1071
},
{
"epoch": 357.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1074
},
{
"epoch": 358.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1077
},
{
"epoch": 359.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1080
},
{
"epoch": 360.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1083
},
{
"epoch": 361.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1086
},
{
"epoch": 362.58,
"eval_exact_match": 0.6760154738878144,
"eval_exec": 0.7156673114119922,
"eval_loss": 0.37218964099884033,
"eval_runtime": 526.428,
"eval_samples_per_second": 1.964,
"step": 1088
},
{
"epoch": 362.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1089
},
{
"epoch": 363.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1092
},
{
"epoch": 364.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1095
},
{
"epoch": 365.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1098
},
{
"epoch": 366.87,
"learning_rate": 0.0001,
"loss": 0.0019,
"step": 1101
},
{
"epoch": 367.87,
"learning_rate": 0.0001,
"loss": 0.01,
"step": 1104
},
{
"epoch": 368.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1107
},
{
"epoch": 369.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1110
},
{
"epoch": 370.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1113
},
{
"epoch": 371.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1116
},
{
"epoch": 372.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1119
},
{
"epoch": 373.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1122
},
{
"epoch": 374.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1125
},
{
"epoch": 375.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1128
},
{
"epoch": 376.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1131
},
{
"epoch": 377.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1134
},
{
"epoch": 378.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1137
},
{
"epoch": 379.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1140
},
{
"epoch": 380.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1143
},
{
"epoch": 381.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1146
},
{
"epoch": 382.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1149
},
{
"epoch": 383.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1152
},
{
"epoch": 383.87,
"eval_exact_match": 0.6934235976789168,
"eval_exec": 0.7408123791102514,
"eval_loss": 0.3976551294326782,
"eval_runtime": 484.9481,
"eval_samples_per_second": 2.132,
"step": 1152
},
{
"epoch": 384.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1155
},
{
"epoch": 385.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1158
},
{
"epoch": 386.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1161
},
{
"epoch": 387.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1164
},
{
"epoch": 388.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1167
},
{
"epoch": 389.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1170
},
{
"epoch": 390.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1173
},
{
"epoch": 391.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1176
},
{
"epoch": 392.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1179
},
{
"epoch": 393.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1182
},
{
"epoch": 394.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1185
},
{
"epoch": 395.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1188
},
{
"epoch": 396.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1191
},
{
"epoch": 397.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1194
},
{
"epoch": 398.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1197
},
{
"epoch": 399.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1200
},
{
"epoch": 400.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1203
},
{
"epoch": 401.87,
"learning_rate": 0.0001,
"loss": 0.0043,
"step": 1206
},
{
"epoch": 402.87,
"learning_rate": 0.0001,
"loss": 0.0078,
"step": 1209
},
{
"epoch": 403.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1212
},
{
"epoch": 404.87,
"learning_rate": 0.0001,
"loss": 0.0034,
"step": 1215
},
{
"epoch": 405.29,
"eval_exact_match": 0.6779497098646035,
"eval_exec": 0.7263056092843327,
"eval_loss": 0.32186877727508545,
"eval_runtime": 460.174,
"eval_samples_per_second": 2.247,
"step": 1216
},
{
"epoch": 405.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 1218
},
{
"epoch": 406.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1221
},
{
"epoch": 407.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1224
},
{
"epoch": 408.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1227
},
{
"epoch": 409.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1230
},
{
"epoch": 410.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1233
},
{
"epoch": 411.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1236
},
{
"epoch": 412.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1239
},
{
"epoch": 413.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1242
},
{
"epoch": 414.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1245
},
{
"epoch": 415.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1248
},
{
"epoch": 416.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1251
},
{
"epoch": 417.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1254
},
{
"epoch": 418.87,
"learning_rate": 0.0001,
"loss": 0.0015,
"step": 1257
},
{
"epoch": 419.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1260
},
{
"epoch": 420.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1263
},
{
"epoch": 421.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1266
},
{
"epoch": 422.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1269
},
{
"epoch": 423.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1272
},
{
"epoch": 424.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1275
},
{
"epoch": 425.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1278
},
{
"epoch": 426.58,
"eval_exact_match": 0.6895551257253385,
"eval_exec": 0.730174081237911,
"eval_loss": 0.37865036725997925,
"eval_runtime": 491.4423,
"eval_samples_per_second": 2.104,
"step": 1280
},
{
"epoch": 426.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1281
},
{
"epoch": 427.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1284
},
{
"epoch": 428.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1287
},
{
"epoch": 429.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1290
},
{
"epoch": 430.87,
"learning_rate": 0.0001,
"loss": 0.0025,
"step": 1293
},
{
"epoch": 431.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1296
},
{
"epoch": 432.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1299
},
{
"epoch": 433.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1302
},
{
"epoch": 434.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1305
},
{
"epoch": 435.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1308
},
{
"epoch": 436.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1311
},
{
"epoch": 437.87,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 1314
},
{
"epoch": 438.87,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1317
},
{
"epoch": 439.87,
"learning_rate": 0.0001,
"loss": 0.0016,
"step": 1320
},
{
"epoch": 440.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1323
},
{
"epoch": 441.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1326
},
{
"epoch": 442.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1329
},
{
"epoch": 443.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1332
},
{
"epoch": 444.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1335
},
{
"epoch": 445.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1338
},
{
"epoch": 446.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1341
},
{
"epoch": 447.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1344
},
{
"epoch": 447.87,
"eval_exact_match": 0.6934235976789168,
"eval_exec": 0.7282398452611218,
"eval_loss": 0.35363292694091797,
"eval_runtime": 532.2521,
"eval_samples_per_second": 1.943,
"step": 1344
},
{
"epoch": 448.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1347
},
{
"epoch": 449.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1350
},
{
"epoch": 450.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1353
},
{
"epoch": 451.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1356
},
{
"epoch": 452.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1359
},
{
"epoch": 453.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1362
},
{
"epoch": 454.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1365
},
{
"epoch": 455.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1368
},
{
"epoch": 456.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1371
},
{
"epoch": 457.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1374
},
{
"epoch": 458.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1377
},
{
"epoch": 459.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1380
},
{
"epoch": 460.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1383
},
{
"epoch": 461.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1386
},
{
"epoch": 462.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1389
},
{
"epoch": 463.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1392
},
{
"epoch": 464.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1395
},
{
"epoch": 465.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1398
},
{
"epoch": 466.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1401
},
{
"epoch": 467.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1404
},
{
"epoch": 468.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1407
},
{
"epoch": 469.29,
"eval_exact_match": 0.6895551257253385,
"eval_exec": 0.7263056092843327,
"eval_loss": 0.3940747082233429,
"eval_runtime": 480.6861,
"eval_samples_per_second": 2.151,
"step": 1408
},
{
"epoch": 469.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1410
},
{
"epoch": 470.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1413
},
{
"epoch": 471.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1416
},
{
"epoch": 472.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1419
},
{
"epoch": 473.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1422
},
{
"epoch": 474.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1425
},
{
"epoch": 475.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1428
},
{
"epoch": 476.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1431
},
{
"epoch": 477.87,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 1434
},
{
"epoch": 478.87,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 1437
},
{
"epoch": 479.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1440
},
{
"epoch": 480.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1443
},
{
"epoch": 481.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1446
},
{
"epoch": 482.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1449
},
{
"epoch": 483.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1452
},
{
"epoch": 484.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1455
},
{
"epoch": 485.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1458
},
{
"epoch": 486.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1461
},
{
"epoch": 487.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1464
},
{
"epoch": 488.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1467
},
{
"epoch": 489.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1470
},
{
"epoch": 490.58,
"eval_exact_match": 0.6895551257253385,
"eval_exec": 0.723404255319149,
"eval_loss": 0.39211201667785645,
"eval_runtime": 483.703,
"eval_samples_per_second": 2.138,
"step": 1472
},
{
"epoch": 490.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1473
},
{
"epoch": 491.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1476
},
{
"epoch": 492.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1479
},
{
"epoch": 493.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1482
},
{
"epoch": 494.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1485
},
{
"epoch": 495.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1488
},
{
"epoch": 496.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1491
},
{
"epoch": 497.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1494
},
{
"epoch": 498.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1497
},
{
"epoch": 499.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1500
},
{
"epoch": 500.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1503
},
{
"epoch": 501.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1506
},
{
"epoch": 502.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1509
},
{
"epoch": 503.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1512
},
{
"epoch": 504.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1515
},
{
"epoch": 505.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1518
},
{
"epoch": 506.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1521
},
{
"epoch": 507.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1524
},
{
"epoch": 508.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1527
},
{
"epoch": 509.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1530
},
{
"epoch": 510.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1533
},
{
"epoch": 511.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1536
},
{
"epoch": 511.87,
"eval_exact_match": 0.6972920696324951,
"eval_exec": 0.7330754352030948,
"eval_loss": 0.38117140531539917,
"eval_runtime": 463.195,
"eval_samples_per_second": 2.232,
"step": 1536
},
{
"epoch": 512.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 1539
},
{
"epoch": 513.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1542
},
{
"epoch": 514.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1545
},
{
"epoch": 515.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1548
},
{
"epoch": 516.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1551
},
{
"epoch": 517.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1554
},
{
"epoch": 518.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1557
},
{
"epoch": 519.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1560
},
{
"epoch": 520.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1563
},
{
"epoch": 521.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1566
},
{
"epoch": 522.87,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 1569
},
{
"epoch": 523.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1572
},
{
"epoch": 524.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1575
},
{
"epoch": 525.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1578
},
{
"epoch": 526.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1581
},
{
"epoch": 527.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1584
},
{
"epoch": 528.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1587
},
{
"epoch": 529.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1590
},
{
"epoch": 530.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1593
},
{
"epoch": 531.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1596
},
{
"epoch": 532.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1599
},
{
"epoch": 533.29,
"eval_exact_match": 0.7021276595744681,
"eval_exec": 0.7369439071566731,
"eval_loss": 0.3867366313934326,
"eval_runtime": 480.8888,
"eval_samples_per_second": 2.15,
"step": 1600
},
{
"epoch": 533.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1602
},
{
"epoch": 534.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1605
},
{
"epoch": 535.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1608
},
{
"epoch": 536.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1611
},
{
"epoch": 537.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1614
},
{
"epoch": 538.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1617
},
{
"epoch": 539.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1620
},
{
"epoch": 540.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1623
},
{
"epoch": 541.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1626
},
{
"epoch": 542.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1629
},
{
"epoch": 543.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1632
},
{
"epoch": 544.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1635
},
{
"epoch": 545.87,
"learning_rate": 0.0001,
"loss": 0.0118,
"step": 1638
},
{
"epoch": 546.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1641
},
{
"epoch": 547.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1644
},
{
"epoch": 548.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1647
},
{
"epoch": 549.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1650
},
{
"epoch": 550.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1653
},
{
"epoch": 551.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1656
},
{
"epoch": 552.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1659
},
{
"epoch": 553.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1662
},
{
"epoch": 554.58,
"eval_exact_match": 0.695357833655706,
"eval_exec": 0.7388781431334622,
"eval_loss": 0.36511388421058655,
"eval_runtime": 507.0372,
"eval_samples_per_second": 2.039,
"step": 1664
},
{
"epoch": 554.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1665
},
{
"epoch": 555.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1668
},
{
"epoch": 556.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1671
},
{
"epoch": 557.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1674
},
{
"epoch": 558.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1677
},
{
"epoch": 559.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1680
},
{
"epoch": 560.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1683
},
{
"epoch": 561.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1686
},
{
"epoch": 562.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1689
},
{
"epoch": 563.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1692
},
{
"epoch": 564.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1695
},
{
"epoch": 565.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1698
},
{
"epoch": 566.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1701
},
{
"epoch": 567.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1704
},
{
"epoch": 568.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1707
},
{
"epoch": 569.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1710
},
{
"epoch": 570.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1713
},
{
"epoch": 571.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1716
},
{
"epoch": 572.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1719
},
{
"epoch": 573.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1722
},
{
"epoch": 574.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1725
},
{
"epoch": 575.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1728
},
{
"epoch": 575.87,
"eval_exact_match": 0.6943907156673114,
"eval_exec": 0.7330754352030948,
"eval_loss": 0.38700243830680847,
"eval_runtime": 510.5436,
"eval_samples_per_second": 2.025,
"step": 1728
},
{
"epoch": 576.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 1731
},
{
"epoch": 577.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 1734
},
{
"epoch": 578.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1737
},
{
"epoch": 579.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1740
},
{
"epoch": 580.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1743
},
{
"epoch": 581.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1746
},
{
"epoch": 582.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1749
},
{
"epoch": 583.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1752
},
{
"epoch": 584.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1755
},
{
"epoch": 585.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1758
},
{
"epoch": 586.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 1761
},
{
"epoch": 587.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1764
},
{
"epoch": 588.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1767
},
{
"epoch": 589.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1770
},
{
"epoch": 590.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1773
},
{
"epoch": 591.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1776
},
{
"epoch": 592.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1779
},
{
"epoch": 593.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1782
},
{
"epoch": 594.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1785
},
{
"epoch": 595.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1788
},
{
"epoch": 596.87,
"learning_rate": 0.0001,
"loss": 0.0021,
"step": 1791
},
{
"epoch": 597.29,
"eval_exact_match": 0.6682785299806576,
"eval_exec": 0.7040618955512572,
"eval_loss": 0.37455007433891296,
"eval_runtime": 480.6892,
"eval_samples_per_second": 2.151,
"step": 1792
},
{
"epoch": 597.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1794
},
{
"epoch": 598.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1797
},
{
"epoch": 599.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1800
},
{
"epoch": 600.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1803
},
{
"epoch": 601.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1806
},
{
"epoch": 602.87,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1809
},
{
"epoch": 603.87,
"learning_rate": 0.0001,
"loss": 0.0035,
"step": 1812
},
{
"epoch": 604.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1815
},
{
"epoch": 605.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1818
},
{
"epoch": 606.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1821
},
{
"epoch": 607.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1824
},
{
"epoch": 608.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1827
},
{
"epoch": 609.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1830
},
{
"epoch": 610.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1833
},
{
"epoch": 611.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1836
},
{
"epoch": 612.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1839
},
{
"epoch": 613.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1842
},
{
"epoch": 614.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1845
},
{
"epoch": 615.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1848
},
{
"epoch": 616.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1851
},
{
"epoch": 617.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1854
},
{
"epoch": 618.58,
"eval_exact_match": 0.688588007736944,
"eval_exec": 0.7195357833655706,
"eval_loss": 0.37960970401763916,
"eval_runtime": 478.0693,
"eval_samples_per_second": 2.163,
"step": 1856
},
{
"epoch": 618.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1857
},
{
"epoch": 619.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1860
},
{
"epoch": 620.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1863
},
{
"epoch": 621.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1866
},
{
"epoch": 622.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1869
},
{
"epoch": 623.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1872
},
{
"epoch": 624.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1875
},
{
"epoch": 625.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1878
},
{
"epoch": 626.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1881
},
{
"epoch": 627.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 1884
},
{
"epoch": 628.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1887
},
{
"epoch": 629.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1890
},
{
"epoch": 630.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1893
},
{
"epoch": 631.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1896
},
{
"epoch": 632.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1899
},
{
"epoch": 633.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1902
},
{
"epoch": 634.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1905
},
{
"epoch": 635.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1908
},
{
"epoch": 636.87,
"learning_rate": 0.0001,
"loss": 0.0026,
"step": 1911
},
{
"epoch": 637.87,
"learning_rate": 0.0001,
"loss": 0.0046,
"step": 1914
},
{
"epoch": 638.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 1917
},
{
"epoch": 639.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1920
},
{
"epoch": 639.87,
"eval_exact_match": 0.6847195357833655,
"eval_exec": 0.723404255319149,
"eval_loss": 0.3337988555431366,
"eval_runtime": 469.6103,
"eval_samples_per_second": 2.202,
"step": 1920
},
{
"epoch": 640.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1923
},
{
"epoch": 641.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1926
},
{
"epoch": 642.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1929
},
{
"epoch": 643.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1932
},
{
"epoch": 644.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1935
},
{
"epoch": 645.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1938
},
{
"epoch": 646.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1941
},
{
"epoch": 647.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1944
},
{
"epoch": 648.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1947
},
{
"epoch": 649.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1950
},
{
"epoch": 650.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1953
},
{
"epoch": 651.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1956
},
{
"epoch": 652.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1959
},
{
"epoch": 653.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1962
},
{
"epoch": 654.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 1965
},
{
"epoch": 655.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1968
},
{
"epoch": 656.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1971
},
{
"epoch": 657.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1974
},
{
"epoch": 658.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 1977
},
{
"epoch": 659.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1980
},
{
"epoch": 660.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1983
},
{
"epoch": 661.29,
"eval_exact_match": 0.6731141199226306,
"eval_exec": 0.7127659574468085,
"eval_loss": 0.384302020072937,
"eval_runtime": 462.6516,
"eval_samples_per_second": 2.235,
"step": 1984
},
{
"epoch": 661.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1986
},
{
"epoch": 662.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1989
},
{
"epoch": 663.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 1992
},
{
"epoch": 664.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1995
},
{
"epoch": 665.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 1998
},
{
"epoch": 666.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2001
},
{
"epoch": 667.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2004
},
{
"epoch": 668.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2007
},
{
"epoch": 669.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2010
},
{
"epoch": 670.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2013
},
{
"epoch": 671.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2016
},
{
"epoch": 672.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2019
},
{
"epoch": 673.87,
"learning_rate": 0.0001,
"loss": 0.003,
"step": 2022
},
{
"epoch": 674.87,
"learning_rate": 0.0001,
"loss": 0.0014,
"step": 2025
},
{
"epoch": 675.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2028
},
{
"epoch": 676.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2031
},
{
"epoch": 677.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2034
},
{
"epoch": 678.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2037
},
{
"epoch": 679.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2040
},
{
"epoch": 680.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2043
},
{
"epoch": 681.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2046
},
{
"epoch": 682.58,
"eval_exact_match": 0.6924564796905223,
"eval_exec": 0.7311411992263056,
"eval_loss": 0.3901544213294983,
"eval_runtime": 510.2096,
"eval_samples_per_second": 2.027,
"step": 2048
},
{
"epoch": 682.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2049
},
{
"epoch": 683.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2052
},
{
"epoch": 684.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2055
},
{
"epoch": 685.87,
"learning_rate": 0.0001,
"loss": 0.005,
"step": 2058
},
{
"epoch": 686.87,
"learning_rate": 0.0001,
"loss": 0.0075,
"step": 2061
},
{
"epoch": 687.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2064
},
{
"epoch": 688.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2067
},
{
"epoch": 689.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2070
},
{
"epoch": 690.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2073
},
{
"epoch": 691.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2076
},
{
"epoch": 692.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2079
},
{
"epoch": 693.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2082
},
{
"epoch": 694.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2085
},
{
"epoch": 695.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2088
},
{
"epoch": 696.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2091
},
{
"epoch": 697.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2094
},
{
"epoch": 698.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2097
},
{
"epoch": 699.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2100
},
{
"epoch": 700.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2103
},
{
"epoch": 701.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2106
},
{
"epoch": 702.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2109
},
{
"epoch": 703.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2112
},
{
"epoch": 703.87,
"eval_exact_match": 0.690522243713733,
"eval_exec": 0.7272727272727273,
"eval_loss": 0.3928453326225281,
"eval_runtime": 466.0396,
"eval_samples_per_second": 2.219,
"step": 2112
},
{
"epoch": 704.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2115
},
{
"epoch": 705.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2118
},
{
"epoch": 706.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2121
},
{
"epoch": 707.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2124
},
{
"epoch": 708.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2127
},
{
"epoch": 709.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2130
},
{
"epoch": 710.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2133
},
{
"epoch": 711.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2136
},
{
"epoch": 712.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2139
},
{
"epoch": 713.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2142
},
{
"epoch": 714.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2145
},
{
"epoch": 715.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2148
},
{
"epoch": 716.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2151
},
{
"epoch": 717.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2154
},
{
"epoch": 718.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2157
},
{
"epoch": 719.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2160
},
{
"epoch": 720.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2163
},
{
"epoch": 721.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2166
},
{
"epoch": 722.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2169
},
{
"epoch": 723.87,
"learning_rate": 0.0001,
"loss": 0.0017,
"step": 2172
},
{
"epoch": 724.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2175
},
{
"epoch": 725.29,
"eval_exact_match": 0.7011605415860735,
"eval_exec": 0.7408123791102514,
"eval_loss": 0.3595825433731079,
"eval_runtime": 483.3909,
"eval_samples_per_second": 2.139,
"step": 2176
},
{
"epoch": 725.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2178
},
{
"epoch": 726.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2181
},
{
"epoch": 727.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2184
},
{
"epoch": 728.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 2187
},
{
"epoch": 729.87,
"learning_rate": 0.0001,
"loss": 0.0033,
"step": 2190
},
{
"epoch": 730.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2193
},
{
"epoch": 731.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2196
},
{
"epoch": 732.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2199
},
{
"epoch": 733.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2202
},
{
"epoch": 734.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2205
},
{
"epoch": 735.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2208
},
{
"epoch": 736.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2211
},
{
"epoch": 737.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2214
},
{
"epoch": 738.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2217
},
{
"epoch": 739.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2220
},
{
"epoch": 740.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2223
},
{
"epoch": 741.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2226
},
{
"epoch": 742.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2229
},
{
"epoch": 743.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2232
},
{
"epoch": 744.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2235
},
{
"epoch": 745.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2238
},
{
"epoch": 746.58,
"eval_exact_match": 0.690522243713733,
"eval_exec": 0.7350096711798839,
"eval_loss": 0.3938235640525818,
"eval_runtime": 476.497,
"eval_samples_per_second": 2.17,
"step": 2240
},
{
"epoch": 746.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2241
},
{
"epoch": 747.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2244
},
{
"epoch": 748.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2247
},
{
"epoch": 749.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2250
},
{
"epoch": 750.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2253
},
{
"epoch": 751.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2256
},
{
"epoch": 752.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2259
},
{
"epoch": 753.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2262
},
{
"epoch": 754.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2265
},
{
"epoch": 755.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2268
},
{
"epoch": 756.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2271
},
{
"epoch": 757.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2274
},
{
"epoch": 758.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2277
},
{
"epoch": 759.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2280
},
{
"epoch": 760.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2283
},
{
"epoch": 761.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2286
},
{
"epoch": 762.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2289
},
{
"epoch": 763.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2292
},
{
"epoch": 764.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2295
},
{
"epoch": 765.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2298
},
{
"epoch": 766.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2301
},
{
"epoch": 767.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2304
},
{
"epoch": 767.87,
"eval_exact_match": 0.7030947775628626,
"eval_exec": 0.7485493230174082,
"eval_loss": 0.41635680198669434,
"eval_runtime": 468.9737,
"eval_samples_per_second": 2.205,
"step": 2304
},
{
"epoch": 768.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2307
},
{
"epoch": 769.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2310
},
{
"epoch": 770.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2313
},
{
"epoch": 771.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2316
},
{
"epoch": 772.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2319
},
{
"epoch": 773.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2322
},
{
"epoch": 774.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2325
},
{
"epoch": 775.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2328
},
{
"epoch": 776.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2331
},
{
"epoch": 777.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2334
},
{
"epoch": 778.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2337
},
{
"epoch": 779.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2340
},
{
"epoch": 780.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2343
},
{
"epoch": 781.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2346
},
{
"epoch": 782.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2349
},
{
"epoch": 783.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2352
},
{
"epoch": 784.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2355
},
{
"epoch": 785.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2358
},
{
"epoch": 786.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2361
},
{
"epoch": 787.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2364
},
{
"epoch": 788.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2367
},
{
"epoch": 789.29,
"eval_exact_match": 0.7030947775628626,
"eval_exec": 0.7456479690522244,
"eval_loss": 0.4018816649913788,
"eval_runtime": 554.0201,
"eval_samples_per_second": 1.866,
"step": 2368
},
{
"epoch": 789.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2370
},
{
"epoch": 790.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2373
},
{
"epoch": 791.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2376
},
{
"epoch": 792.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2379
},
{
"epoch": 793.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2382
},
{
"epoch": 794.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2385
},
{
"epoch": 795.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2388
},
{
"epoch": 796.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2391
},
{
"epoch": 797.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2394
},
{
"epoch": 798.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2397
},
{
"epoch": 799.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2400
},
{
"epoch": 800.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2403
},
{
"epoch": 801.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2406
},
{
"epoch": 802.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2409
},
{
"epoch": 803.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2412
},
{
"epoch": 804.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2415
},
{
"epoch": 805.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2418
},
{
"epoch": 806.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2421
},
{
"epoch": 807.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2424
},
{
"epoch": 808.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2427
},
{
"epoch": 809.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2430
},
{
"epoch": 810.58,
"eval_exact_match": 0.7040618955512572,
"eval_exec": 0.7495164410058027,
"eval_loss": 0.37046629190444946,
"eval_runtime": 545.4486,
"eval_samples_per_second": 1.896,
"step": 2432
},
{
"epoch": 810.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2433
},
{
"epoch": 811.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2436
},
{
"epoch": 812.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2439
},
{
"epoch": 813.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2442
},
{
"epoch": 814.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2445
},
{
"epoch": 815.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2448
},
{
"epoch": 816.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2451
},
{
"epoch": 817.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2454
},
{
"epoch": 818.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2457
},
{
"epoch": 819.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2460
},
{
"epoch": 820.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2463
},
{
"epoch": 821.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2466
},
{
"epoch": 822.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2469
},
{
"epoch": 823.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2472
},
{
"epoch": 824.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2475
},
{
"epoch": 825.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2478
},
{
"epoch": 826.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2481
},
{
"epoch": 827.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2484
},
{
"epoch": 828.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2487
},
{
"epoch": 829.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2490
},
{
"epoch": 830.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2493
},
{
"epoch": 831.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2496
},
{
"epoch": 831.87,
"eval_exact_match": 0.7011605415860735,
"eval_exec": 0.7408123791102514,
"eval_loss": 0.4019996225833893,
"eval_runtime": 517.5919,
"eval_samples_per_second": 1.998,
"step": 2496
},
{
"epoch": 832.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2499
},
{
"epoch": 833.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2502
},
{
"epoch": 834.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2505
},
{
"epoch": 835.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2508
},
{
"epoch": 836.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2511
},
{
"epoch": 837.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2514
},
{
"epoch": 838.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2517
},
{
"epoch": 839.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2520
},
{
"epoch": 840.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2523
},
{
"epoch": 841.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2526
},
{
"epoch": 842.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2529
},
{
"epoch": 843.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2532
},
{
"epoch": 844.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2535
},
{
"epoch": 845.87,
"learning_rate": 0.0001,
"loss": 0.0013,
"step": 2538
},
{
"epoch": 846.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2541
},
{
"epoch": 847.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2544
},
{
"epoch": 848.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2547
},
{
"epoch": 849.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2550
},
{
"epoch": 850.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2553
},
{
"epoch": 851.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2556
},
{
"epoch": 852.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2559
},
{
"epoch": 853.29,
"eval_exact_match": 0.7030947775628626,
"eval_exec": 0.7475822050290135,
"eval_loss": 0.36097148060798645,
"eval_runtime": 463.1991,
"eval_samples_per_second": 2.232,
"step": 2560
},
{
"epoch": 853.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2562
},
{
"epoch": 854.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2565
},
{
"epoch": 855.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2568
},
{
"epoch": 856.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2571
},
{
"epoch": 857.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2574
},
{
"epoch": 858.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2577
},
{
"epoch": 859.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2580
},
{
"epoch": 860.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2583
},
{
"epoch": 861.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2586
},
{
"epoch": 862.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2589
},
{
"epoch": 863.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2592
},
{
"epoch": 864.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2595
},
{
"epoch": 865.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2598
},
{
"epoch": 866.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 2601
},
{
"epoch": 867.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2604
},
{
"epoch": 868.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2607
},
{
"epoch": 869.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2610
},
{
"epoch": 870.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2613
},
{
"epoch": 871.87,
"learning_rate": 0.0001,
"loss": 0.0027,
"step": 2616
},
{
"epoch": 872.87,
"learning_rate": 0.0001,
"loss": 0.0008,
"step": 2619
},
{
"epoch": 873.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2622
},
{
"epoch": 874.58,
"eval_exact_match": 0.7195357833655706,
"eval_exec": 0.7659574468085106,
"eval_loss": 0.33834004402160645,
"eval_runtime": 494.2046,
"eval_samples_per_second": 2.092,
"step": 2624
},
{
"epoch": 874.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2625
},
{
"epoch": 875.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2628
},
{
"epoch": 876.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2631
},
{
"epoch": 877.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2634
},
{
"epoch": 878.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2637
},
{
"epoch": 879.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2640
},
{
"epoch": 880.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2643
},
{
"epoch": 881.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2646
},
{
"epoch": 882.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2649
},
{
"epoch": 883.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2652
},
{
"epoch": 884.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2655
},
{
"epoch": 885.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2658
},
{
"epoch": 886.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2661
},
{
"epoch": 887.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2664
},
{
"epoch": 888.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2667
},
{
"epoch": 889.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 2670
},
{
"epoch": 890.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2673
},
{
"epoch": 891.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2676
},
{
"epoch": 892.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2679
},
{
"epoch": 893.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2682
},
{
"epoch": 894.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2685
},
{
"epoch": 895.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2688
},
{
"epoch": 895.87,
"eval_exact_match": 0.7079303675048356,
"eval_exec": 0.753384912959381,
"eval_loss": 0.36499086022377014,
"eval_runtime": 549.4813,
"eval_samples_per_second": 1.882,
"step": 2688
},
{
"epoch": 896.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2691
},
{
"epoch": 897.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2694
},
{
"epoch": 898.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2697
},
{
"epoch": 899.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2700
},
{
"epoch": 900.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2703
},
{
"epoch": 901.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2706
},
{
"epoch": 902.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2709
},
{
"epoch": 903.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2712
},
{
"epoch": 904.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2715
},
{
"epoch": 905.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2718
},
{
"epoch": 906.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2721
},
{
"epoch": 907.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2724
},
{
"epoch": 908.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2727
},
{
"epoch": 909.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2730
},
{
"epoch": 910.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2733
},
{
"epoch": 911.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2736
},
{
"epoch": 912.87,
"learning_rate": 0.0001,
"loss": 0.0052,
"step": 2739
},
{
"epoch": 913.87,
"learning_rate": 0.0001,
"loss": 0.0085,
"step": 2742
},
{
"epoch": 914.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2745
},
{
"epoch": 915.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2748
},
{
"epoch": 916.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2751
},
{
"epoch": 917.29,
"eval_exact_match": 0.7176015473887815,
"eval_exec": 0.758220502901354,
"eval_loss": 0.35287681221961975,
"eval_runtime": 527.4463,
"eval_samples_per_second": 1.96,
"step": 2752
},
{
"epoch": 917.87,
"learning_rate": 0.0001,
"loss": 0.001,
"step": 2754
},
{
"epoch": 918.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 2757
},
{
"epoch": 919.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2760
},
{
"epoch": 920.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2763
},
{
"epoch": 921.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2766
},
{
"epoch": 922.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2769
},
{
"epoch": 923.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2772
},
{
"epoch": 924.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2775
},
{
"epoch": 925.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2778
},
{
"epoch": 926.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2781
},
{
"epoch": 927.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2784
},
{
"epoch": 928.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2787
},
{
"epoch": 929.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2790
},
{
"epoch": 930.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2793
},
{
"epoch": 931.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2796
},
{
"epoch": 932.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2799
},
{
"epoch": 933.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2802
},
{
"epoch": 934.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2805
},
{
"epoch": 935.87,
"learning_rate": 0.0001,
"loss": 0.0031,
"step": 2808
},
{
"epoch": 936.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 2811
},
{
"epoch": 937.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2814
},
{
"epoch": 938.58,
"eval_exact_match": 0.7040618955512572,
"eval_exec": 0.7543520309477756,
"eval_loss": 0.3663797676563263,
"eval_runtime": 481.0364,
"eval_samples_per_second": 2.15,
"step": 2816
},
{
"epoch": 938.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2817
},
{
"epoch": 939.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2820
},
{
"epoch": 940.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2823
},
{
"epoch": 941.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2826
},
{
"epoch": 942.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2829
},
{
"epoch": 943.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2832
},
{
"epoch": 944.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2835
},
{
"epoch": 945.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2838
},
{
"epoch": 946.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2841
},
{
"epoch": 947.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2844
},
{
"epoch": 948.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2847
},
{
"epoch": 949.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2850
},
{
"epoch": 950.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2853
},
{
"epoch": 951.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2856
},
{
"epoch": 952.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2859
},
{
"epoch": 953.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2862
},
{
"epoch": 954.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2865
},
{
"epoch": 955.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2868
},
{
"epoch": 956.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2871
},
{
"epoch": 957.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2874
},
{
"epoch": 958.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2877
},
{
"epoch": 959.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2880
},
{
"epoch": 959.87,
"eval_exact_match": 0.7040618955512572,
"eval_exec": 0.7456479690522244,
"eval_loss": 0.3911956250667572,
"eval_runtime": 473.5193,
"eval_samples_per_second": 2.184,
"step": 2880
},
{
"epoch": 960.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2883
},
{
"epoch": 961.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2886
},
{
"epoch": 962.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2889
},
{
"epoch": 963.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2892
},
{
"epoch": 964.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2895
},
{
"epoch": 965.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2898
},
{
"epoch": 966.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2901
},
{
"epoch": 967.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2904
},
{
"epoch": 968.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2907
},
{
"epoch": 969.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2910
},
{
"epoch": 970.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2913
},
{
"epoch": 971.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2916
},
{
"epoch": 972.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2919
},
{
"epoch": 973.87,
"learning_rate": 0.0001,
"loss": 0.0037,
"step": 2922
},
{
"epoch": 974.87,
"learning_rate": 0.0001,
"loss": 0.0012,
"step": 2925
},
{
"epoch": 975.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2928
},
{
"epoch": 976.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2931
},
{
"epoch": 977.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2934
},
{
"epoch": 978.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2937
},
{
"epoch": 979.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2940
},
{
"epoch": 980.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2943
},
{
"epoch": 981.29,
"eval_exact_match": 0.7195357833655706,
"eval_exec": 0.7485493230174082,
"eval_loss": 0.3832685053348541,
"eval_runtime": 501.8416,
"eval_samples_per_second": 2.06,
"step": 2944
},
{
"epoch": 981.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2946
},
{
"epoch": 982.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2949
},
{
"epoch": 983.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2952
},
{
"epoch": 984.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2955
},
{
"epoch": 985.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2958
},
{
"epoch": 986.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2961
},
{
"epoch": 987.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2964
},
{
"epoch": 988.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2967
},
{
"epoch": 989.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2970
},
{
"epoch": 990.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2973
},
{
"epoch": 991.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2976
},
{
"epoch": 992.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 2979
},
{
"epoch": 993.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2982
},
{
"epoch": 994.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 2985
},
{
"epoch": 995.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 2988
},
{
"epoch": 996.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2991
},
{
"epoch": 997.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 2994
},
{
"epoch": 998.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 2997
},
{
"epoch": 999.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3000
},
{
"epoch": 1000.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3003
},
{
"epoch": 1001.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3006
},
{
"epoch": 1002.58,
"eval_exact_match": 0.7156673114119922,
"eval_exec": 0.7427466150870407,
"eval_loss": 0.3957798480987549,
"eval_runtime": 491.7076,
"eval_samples_per_second": 2.103,
"step": 3008
},
{
"epoch": 1002.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3009
},
{
"epoch": 1003.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3012
},
{
"epoch": 1004.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3015
},
{
"epoch": 1005.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3018
},
{
"epoch": 1006.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3021
},
{
"epoch": 1007.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 3024
},
{
"epoch": 1008.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3027
},
{
"epoch": 1009.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3030
},
{
"epoch": 1010.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3033
},
{
"epoch": 1011.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3036
},
{
"epoch": 1012.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3039
},
{
"epoch": 1013.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3042
},
{
"epoch": 1014.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3045
},
{
"epoch": 1015.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 3048
},
{
"epoch": 1016.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 3051
},
{
"epoch": 1017.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3054
},
{
"epoch": 1018.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3057
},
{
"epoch": 1019.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3060
},
{
"epoch": 1020.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3063
},
{
"epoch": 1021.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3066
},
{
"epoch": 1022.87,
"learning_rate": 0.0001,
"loss": 0.0006,
"step": 3069
},
{
"epoch": 1023.87,
"learning_rate": 0.0001,
"loss": 0.0018,
"step": 3072
},
{
"epoch": 1023.87,
"eval_exact_match": 0.690522243713733,
"eval_exec": 0.7253384912959381,
"eval_loss": 0.3460274934768677,
"eval_runtime": 479.4016,
"eval_samples_per_second": 2.157,
"step": 3072
},
{
"epoch": 1024.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3075
},
{
"epoch": 1025.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3078
},
{
"epoch": 1026.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3081
},
{
"epoch": 1027.87,
"learning_rate": 0.0001,
"loss": 0.0011,
"step": 3084
},
{
"epoch": 1028.87,
"learning_rate": 0.0001,
"loss": 0.0023,
"step": 3087
},
{
"epoch": 1029.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 3090
},
{
"epoch": 1030.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3093
},
{
"epoch": 1031.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3096
},
{
"epoch": 1032.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3099
},
{
"epoch": 1033.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3102
},
{
"epoch": 1034.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3105
},
{
"epoch": 1035.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3108
},
{
"epoch": 1036.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3111
},
{
"epoch": 1037.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3114
},
{
"epoch": 1038.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 3117
},
{
"epoch": 1039.87,
"learning_rate": 0.0001,
"loss": 0.0049,
"step": 3120
},
{
"epoch": 1040.87,
"learning_rate": 0.0001,
"loss": 0.0003,
"step": 3123
},
{
"epoch": 1041.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 3126
},
{
"epoch": 1042.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 3129
},
{
"epoch": 1043.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 3132
},
{
"epoch": 1044.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3135
},
{
"epoch": 1045.29,
"eval_exact_match": 0.7001934235976789,
"eval_exec": 0.7427466150870407,
"eval_loss": 0.355153888463974,
"eval_runtime": 451.6545,
"eval_samples_per_second": 2.289,
"step": 3136
},
{
"epoch": 1045.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3138
},
{
"epoch": 1046.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3141
},
{
"epoch": 1047.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3144
},
{
"epoch": 1048.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3147
},
{
"epoch": 1049.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3150
},
{
"epoch": 1050.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3153
},
{
"epoch": 1051.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3156
},
{
"epoch": 1052.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3159
},
{
"epoch": 1053.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3162
},
{
"epoch": 1054.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3165
},
{
"epoch": 1055.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 3168
},
{
"epoch": 1056.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3171
},
{
"epoch": 1057.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3174
},
{
"epoch": 1058.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3177
},
{
"epoch": 1059.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3180
},
{
"epoch": 1060.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3183
},
{
"epoch": 1061.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3186
},
{
"epoch": 1062.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3189
},
{
"epoch": 1063.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3192
},
{
"epoch": 1064.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3195
},
{
"epoch": 1065.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 3198
},
{
"epoch": 1066.58,
"eval_exact_match": 0.7127659574468085,
"eval_exec": 0.7543520309477756,
"eval_loss": 0.4037820100784302,
"eval_runtime": 464.6921,
"eval_samples_per_second": 2.225,
"step": 3200
},
{
"epoch": 1066.87,
"learning_rate": 0.0001,
"loss": 0.0004,
"step": 3201
},
{
"epoch": 1067.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3204
},
{
"epoch": 1068.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3207
},
{
"epoch": 1069.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3210
},
{
"epoch": 1070.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3213
},
{
"epoch": 1071.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3216
},
{
"epoch": 1072.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3219
},
{
"epoch": 1073.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3222
},
{
"epoch": 1074.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3225
},
{
"epoch": 1075.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3228
},
{
"epoch": 1076.87,
"learning_rate": 0.0001,
"loss": 0.0002,
"step": 3231
},
{
"epoch": 1077.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 3234
},
{
"epoch": 1078.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3237
},
{
"epoch": 1079.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3240
},
{
"epoch": 1080.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3243
},
{
"epoch": 1081.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3246
},
{
"epoch": 1082.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3249
},
{
"epoch": 1083.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3252
},
{
"epoch": 1084.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3255
},
{
"epoch": 1085.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3258
},
{
"epoch": 1086.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3261
},
{
"epoch": 1087.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3264
},
{
"epoch": 1087.87,
"eval_exact_match": 0.7117988394584139,
"eval_exec": 0.7485493230174082,
"eval_loss": 0.4036550521850586,
"eval_runtime": 486.4323,
"eval_samples_per_second": 2.126,
"step": 3264
},
{
"epoch": 1088.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3267
},
{
"epoch": 1089.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3270
},
{
"epoch": 1090.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3273
},
{
"epoch": 1091.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3276
},
{
"epoch": 1092.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3279
},
{
"epoch": 1093.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3282
},
{
"epoch": 1094.87,
"learning_rate": 0.0001,
"loss": 0.0007,
"step": 3285
},
{
"epoch": 1095.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3288
},
{
"epoch": 1096.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3291
},
{
"epoch": 1097.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3294
},
{
"epoch": 1098.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3297
},
{
"epoch": 1099.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3300
},
{
"epoch": 1100.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3303
},
{
"epoch": 1101.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3306
},
{
"epoch": 1102.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3309
},
{
"epoch": 1103.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3312
},
{
"epoch": 1104.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3315
},
{
"epoch": 1105.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3318
},
{
"epoch": 1106.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3321
},
{
"epoch": 1107.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3324
},
{
"epoch": 1108.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3327
},
{
"epoch": 1109.29,
"eval_exact_match": 0.7021276595744681,
"eval_exec": 0.7408123791102514,
"eval_loss": 0.4005126953125,
"eval_runtime": 524.1199,
"eval_samples_per_second": 1.973,
"step": 3328
},
{
"epoch": 1109.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3330
},
{
"epoch": 1110.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3333
},
{
"epoch": 1111.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3336
},
{
"epoch": 1112.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3339
},
{
"epoch": 1113.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3342
},
{
"epoch": 1114.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3345
},
{
"epoch": 1115.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3348
},
{
"epoch": 1116.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3351
},
{
"epoch": 1117.87,
"learning_rate": 0.0001,
"loss": 0.0001,
"step": 3354
},
{
"epoch": 1118.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3357
},
{
"epoch": 1119.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3360
},
{
"epoch": 1120.87,
"learning_rate": 0.0001,
"loss": 0.0005,
"step": 3363
},
{
"epoch": 1121.87,
"learning_rate": 0.0001,
"loss": 0.0009,
"step": 3366
},
{
"epoch": 1122.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3369
},
{
"epoch": 1123.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3372
},
{
"epoch": 1124.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3375
},
{
"epoch": 1125.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3378
},
{
"epoch": 1126.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3381
},
{
"epoch": 1127.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3384
},
{
"epoch": 1128.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3387
},
{
"epoch": 1129.87,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 3390
},
{
"epoch": 1130.58,
"eval_exact_match": 0.7214700193423598,
"eval_exec": 0.7562862669245648,
"eval_loss": 0.41660553216934204,
"eval_runtime": 517.542,
"eval_samples_per_second": 1.998,
"step": 3392
}
],
"max_steps": 9216,
"num_train_epochs": 3072,
"total_flos": 2.960191905890671e+19,
"trial_name": null,
"trial_params": null
}