|
{ |
|
"best_metric": 0.6441005802707931, |
|
"best_model_checkpoint": "/train/checkpoint-1344", |
|
"epoch": 447.87857142857143, |
|
"global_step": 1344, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0001, |
|
"loss": 4.3257, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0001, |
|
"loss": 2.9741, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.59, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6232, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.951, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.7842, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 6.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.5481, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 7.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4986, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 9.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.4439, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 10.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3802, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 11.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3228, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 13.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.3209, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 14.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2883, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 15.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2424, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 17.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2485, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 18.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2291, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 19.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2096, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 21.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.2204, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 21.29, |
|
"eval_exact_match": 0.4090909090909091, |
|
"eval_exec": 0.44777562862669246, |
|
"eval_loss": 0.21543213725090027, |
|
"eval_runtime": 371.8333, |
|
"eval_samples_per_second": 2.781, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 22.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1867, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 23.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1716, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 25.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1708, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 26.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1475, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 27.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1406, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 29.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1382, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 30.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1211, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 31.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1082, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 33.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1139, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 34.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1048, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 35.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.097, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 37.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1101, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 38.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0946, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 39.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0852, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 41.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0923, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 42.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0736, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 42.59, |
|
"eval_exact_match": 0.5386847195357833, |
|
"eval_exec": 0.5725338491295938, |
|
"eval_loss": 0.1859811693429947, |
|
"eval_runtime": 369.8509, |
|
"eval_samples_per_second": 2.796, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 43.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0688, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 45.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0807, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 46.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0676, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 47.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0673, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 49.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0663, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 50.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0575, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 51.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0599, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 53.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.059, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 54.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0509, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 55.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0485, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 57.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0536, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 58.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0504, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 59.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0445, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 61.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0426, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 62.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0495, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 63.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0442, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 63.88, |
|
"eval_exact_match": 0.574468085106383, |
|
"eval_exec": 0.597678916827853, |
|
"eval_loss": 0.20976035296916962, |
|
"eval_runtime": 436.2256, |
|
"eval_samples_per_second": 2.37, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 65.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0421, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 66.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0411, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 67.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.036, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 69.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0346, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 70.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0294, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 71.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0323, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 73.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0367, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 74.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0277, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 75.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0281, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 77.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.026, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 78.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0242, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 79.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0245, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 81.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0264, |
|
"step": 244 |
|
}, |
|
{ |
|
"epoch": 82.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0264, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 83.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0248, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 85.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0254, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 85.29, |
|
"eval_exact_match": 0.59284332688588, |
|
"eval_exec": 0.6150870406189555, |
|
"eval_loss": 0.24511948227882385, |
|
"eval_runtime": 397.4948, |
|
"eval_samples_per_second": 2.601, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 86.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0192, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 87.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0181, |
|
"step": 264 |
|
}, |
|
{ |
|
"epoch": 89.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0195, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 90.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0184, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 91.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0162, |
|
"step": 276 |
|
}, |
|
{ |
|
"epoch": 93.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0167, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 94.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0163, |
|
"step": 284 |
|
}, |
|
{ |
|
"epoch": 95.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0164, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 97.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.016, |
|
"step": 292 |
|
}, |
|
{ |
|
"epoch": 98.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0136, |
|
"step": 296 |
|
}, |
|
{ |
|
"epoch": 99.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0182, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 101.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0205, |
|
"step": 304 |
|
}, |
|
{ |
|
"epoch": 102.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0136, |
|
"step": 308 |
|
}, |
|
{ |
|
"epoch": 103.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0136, |
|
"step": 312 |
|
}, |
|
{ |
|
"epoch": 105.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0117, |
|
"step": 316 |
|
}, |
|
{ |
|
"epoch": 106.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0103, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 106.59, |
|
"eval_exact_match": 0.5967117988394585, |
|
"eval_exec": 0.6179883945841392, |
|
"eval_loss": 0.29194486141204834, |
|
"eval_runtime": 428.7156, |
|
"eval_samples_per_second": 2.412, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 107.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0112, |
|
"step": 324 |
|
}, |
|
{ |
|
"epoch": 109.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.016, |
|
"step": 328 |
|
}, |
|
{ |
|
"epoch": 110.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0092, |
|
"step": 332 |
|
}, |
|
{ |
|
"epoch": 111.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0095, |
|
"step": 336 |
|
}, |
|
{ |
|
"epoch": 113.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.01, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 114.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0095, |
|
"step": 344 |
|
}, |
|
{ |
|
"epoch": 115.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0094, |
|
"step": 348 |
|
}, |
|
{ |
|
"epoch": 117.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0091, |
|
"step": 352 |
|
}, |
|
{ |
|
"epoch": 118.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0079, |
|
"step": 356 |
|
}, |
|
{ |
|
"epoch": 119.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0081, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 121.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0089, |
|
"step": 364 |
|
}, |
|
{ |
|
"epoch": 122.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0071, |
|
"step": 368 |
|
}, |
|
{ |
|
"epoch": 123.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0073, |
|
"step": 372 |
|
}, |
|
{ |
|
"epoch": 125.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0079, |
|
"step": 376 |
|
}, |
|
{ |
|
"epoch": 126.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0088, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 127.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0073, |
|
"step": 384 |
|
}, |
|
{ |
|
"epoch": 127.88, |
|
"eval_exact_match": 0.5957446808510638, |
|
"eval_exec": 0.6170212765957447, |
|
"eval_loss": 0.30737635493278503, |
|
"eval_runtime": 453.1803, |
|
"eval_samples_per_second": 2.282, |
|
"step": 384 |
|
}, |
|
{ |
|
"epoch": 129.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.007, |
|
"step": 388 |
|
}, |
|
{ |
|
"epoch": 130.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.006, |
|
"step": 392 |
|
}, |
|
{ |
|
"epoch": 131.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0065, |
|
"step": 396 |
|
}, |
|
{ |
|
"epoch": 133.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.006, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 134.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0054, |
|
"step": 404 |
|
}, |
|
{ |
|
"epoch": 135.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0059, |
|
"step": 408 |
|
}, |
|
{ |
|
"epoch": 137.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.017, |
|
"step": 412 |
|
}, |
|
{ |
|
"epoch": 138.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0096, |
|
"step": 416 |
|
}, |
|
{ |
|
"epoch": 139.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.006, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 141.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0061, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 142.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0048, |
|
"step": 428 |
|
}, |
|
{ |
|
"epoch": 143.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.005, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 145.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0133, |
|
"step": 436 |
|
}, |
|
{ |
|
"epoch": 146.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.005, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 147.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0043, |
|
"step": 444 |
|
}, |
|
{ |
|
"epoch": 149.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.004, |
|
"step": 448 |
|
}, |
|
{ |
|
"epoch": 149.29, |
|
"eval_exact_match": 0.6160541586073501, |
|
"eval_exec": 0.6286266924564797, |
|
"eval_loss": 0.3122102916240692, |
|
"eval_runtime": 446.9159, |
|
"eval_samples_per_second": 2.314, |
|
"step": 448 |
|
}, |
|
{ |
|
"epoch": 150.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.004, |
|
"step": 452 |
|
}, |
|
{ |
|
"epoch": 151.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0038, |
|
"step": 456 |
|
}, |
|
{ |
|
"epoch": 153.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0043, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 154.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0046, |
|
"step": 464 |
|
}, |
|
{ |
|
"epoch": 155.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0043, |
|
"step": 468 |
|
}, |
|
{ |
|
"epoch": 157.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0043, |
|
"step": 472 |
|
}, |
|
{ |
|
"epoch": 158.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.003, |
|
"step": 476 |
|
}, |
|
{ |
|
"epoch": 159.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0033, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 161.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0038, |
|
"step": 484 |
|
}, |
|
{ |
|
"epoch": 162.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0032, |
|
"step": 488 |
|
}, |
|
{ |
|
"epoch": 163.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0033, |
|
"step": 492 |
|
}, |
|
{ |
|
"epoch": 165.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0033, |
|
"step": 496 |
|
}, |
|
{ |
|
"epoch": 166.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.003, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 167.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0029, |
|
"step": 504 |
|
}, |
|
{ |
|
"epoch": 169.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.003, |
|
"step": 508 |
|
}, |
|
{ |
|
"epoch": 170.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0026, |
|
"step": 512 |
|
}, |
|
{ |
|
"epoch": 170.59, |
|
"eval_exact_match": 0.6092843326885881, |
|
"eval_exec": 0.6286266924564797, |
|
"eval_loss": 0.329732745885849, |
|
"eval_runtime": 461.0101, |
|
"eval_samples_per_second": 2.243, |
|
"step": 512 |
|
}, |
|
{ |
|
"epoch": 171.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0029, |
|
"step": 516 |
|
}, |
|
{ |
|
"epoch": 173.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.003, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 174.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0025, |
|
"step": 524 |
|
}, |
|
{ |
|
"epoch": 175.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0031, |
|
"step": 528 |
|
}, |
|
{ |
|
"epoch": 177.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0031, |
|
"step": 532 |
|
}, |
|
{ |
|
"epoch": 178.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0025, |
|
"step": 536 |
|
}, |
|
{ |
|
"epoch": 179.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0026, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 181.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0027, |
|
"step": 544 |
|
}, |
|
{ |
|
"epoch": 182.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0028, |
|
"step": 548 |
|
}, |
|
{ |
|
"epoch": 183.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0023, |
|
"step": 552 |
|
}, |
|
{ |
|
"epoch": 185.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0025, |
|
"step": 556 |
|
}, |
|
{ |
|
"epoch": 186.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0057, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 187.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.013, |
|
"step": 564 |
|
}, |
|
{ |
|
"epoch": 189.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0033, |
|
"step": 568 |
|
}, |
|
{ |
|
"epoch": 190.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0042, |
|
"step": 572 |
|
}, |
|
{ |
|
"epoch": 191.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0326, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 191.88, |
|
"eval_exact_match": 0.6199226305609284, |
|
"eval_exec": 0.6441005802707931, |
|
"eval_loss": 0.28043264150619507, |
|
"eval_runtime": 434.1831, |
|
"eval_samples_per_second": 2.381, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 193.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0029, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 194.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0021, |
|
"step": 584 |
|
}, |
|
{ |
|
"epoch": 195.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.002, |
|
"step": 588 |
|
}, |
|
{ |
|
"epoch": 197.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0021, |
|
"step": 592 |
|
}, |
|
{ |
|
"epoch": 198.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.002, |
|
"step": 596 |
|
}, |
|
{ |
|
"epoch": 199.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0017, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 201.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.002, |
|
"step": 604 |
|
}, |
|
{ |
|
"epoch": 202.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0016, |
|
"step": 608 |
|
}, |
|
{ |
|
"epoch": 203.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0018, |
|
"step": 612 |
|
}, |
|
{ |
|
"epoch": 205.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0021, |
|
"step": 616 |
|
}, |
|
{ |
|
"epoch": 206.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.002, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 207.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0018, |
|
"step": 624 |
|
}, |
|
{ |
|
"epoch": 209.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0026, |
|
"step": 628 |
|
}, |
|
{ |
|
"epoch": 210.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 632 |
|
}, |
|
{ |
|
"epoch": 211.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0018, |
|
"step": 636 |
|
}, |
|
{ |
|
"epoch": 213.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0054, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 213.29, |
|
"eval_exact_match": 0.5938104448742747, |
|
"eval_exec": 0.6160541586073501, |
|
"eval_loss": 0.34003064036369324, |
|
"eval_runtime": 454.3384, |
|
"eval_samples_per_second": 2.276, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 214.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0044, |
|
"step": 644 |
|
}, |
|
{ |
|
"epoch": 215.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0018, |
|
"step": 648 |
|
}, |
|
{ |
|
"epoch": 217.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0018, |
|
"step": 652 |
|
}, |
|
{ |
|
"epoch": 218.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 656 |
|
}, |
|
{ |
|
"epoch": 219.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0017, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 221.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0017, |
|
"step": 664 |
|
}, |
|
{ |
|
"epoch": 222.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 668 |
|
}, |
|
{ |
|
"epoch": 223.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 672 |
|
}, |
|
{ |
|
"epoch": 225.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 676 |
|
}, |
|
{ |
|
"epoch": 226.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0014, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 227.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0013, |
|
"step": 684 |
|
}, |
|
{ |
|
"epoch": 229.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 688 |
|
}, |
|
{ |
|
"epoch": 230.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0013, |
|
"step": 692 |
|
}, |
|
{ |
|
"epoch": 231.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 696 |
|
}, |
|
{ |
|
"epoch": 233.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0014, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 234.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0038, |
|
"step": 704 |
|
}, |
|
{ |
|
"epoch": 234.59, |
|
"eval_exact_match": 0.6305609284332688, |
|
"eval_exec": 0.648936170212766, |
|
"eval_loss": 0.3312581479549408, |
|
"eval_runtime": 454.3187, |
|
"eval_samples_per_second": 2.276, |
|
"step": 704 |
|
}, |
|
{ |
|
"epoch": 235.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0014, |
|
"step": 708 |
|
}, |
|
{ |
|
"epoch": 237.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0013, |
|
"step": 712 |
|
}, |
|
{ |
|
"epoch": 238.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 716 |
|
}, |
|
{ |
|
"epoch": 239.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 241.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0014, |
|
"step": 724 |
|
}, |
|
{ |
|
"epoch": 242.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0013, |
|
"step": 728 |
|
}, |
|
{ |
|
"epoch": 243.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 732 |
|
}, |
|
{ |
|
"epoch": 245.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 736 |
|
}, |
|
{ |
|
"epoch": 246.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 247.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 744 |
|
}, |
|
{ |
|
"epoch": 249.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 748 |
|
}, |
|
{ |
|
"epoch": 250.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 752 |
|
}, |
|
{ |
|
"epoch": 251.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 756 |
|
}, |
|
{ |
|
"epoch": 253.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 254.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 764 |
|
}, |
|
{ |
|
"epoch": 255.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 768 |
|
}, |
|
{ |
|
"epoch": 255.88, |
|
"eval_exact_match": 0.6141199226305609, |
|
"eval_exec": 0.6373307543520309, |
|
"eval_loss": 0.3713914155960083, |
|
"eval_runtime": 454.4742, |
|
"eval_samples_per_second": 2.275, |
|
"step": 768 |
|
}, |
|
{ |
|
"epoch": 257.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0014, |
|
"step": 772 |
|
}, |
|
{ |
|
"epoch": 258.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 776 |
|
}, |
|
{ |
|
"epoch": 259.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 261.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 784 |
|
}, |
|
{ |
|
"epoch": 262.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 788 |
|
}, |
|
{ |
|
"epoch": 263.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 792 |
|
}, |
|
{ |
|
"epoch": 265.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 796 |
|
}, |
|
{ |
|
"epoch": 266.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0013, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 267.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 804 |
|
}, |
|
{ |
|
"epoch": 269.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 808 |
|
}, |
|
{ |
|
"epoch": 270.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 812 |
|
}, |
|
{ |
|
"epoch": 271.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0104, |
|
"step": 816 |
|
}, |
|
{ |
|
"epoch": 273.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0057, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 274.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0013, |
|
"step": 824 |
|
}, |
|
{ |
|
"epoch": 275.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 828 |
|
}, |
|
{ |
|
"epoch": 277.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 832 |
|
}, |
|
{ |
|
"epoch": 277.29, |
|
"eval_exact_match": 0.6228239845261122, |
|
"eval_exec": 0.6450676982591876, |
|
"eval_loss": 0.3546225130558014, |
|
"eval_runtime": 443.6147, |
|
"eval_samples_per_second": 2.331, |
|
"step": 832 |
|
}, |
|
{ |
|
"epoch": 278.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0012, |
|
"step": 836 |
|
}, |
|
{ |
|
"epoch": 279.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0025, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 281.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0031, |
|
"step": 844 |
|
}, |
|
{ |
|
"epoch": 282.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 848 |
|
}, |
|
{ |
|
"epoch": 283.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 852 |
|
}, |
|
{ |
|
"epoch": 285.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 856 |
|
}, |
|
{ |
|
"epoch": 286.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 287.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0029, |
|
"step": 864 |
|
}, |
|
{ |
|
"epoch": 289.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0039, |
|
"step": 868 |
|
}, |
|
{ |
|
"epoch": 290.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 872 |
|
}, |
|
{ |
|
"epoch": 291.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 876 |
|
}, |
|
{ |
|
"epoch": 293.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 294.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 884 |
|
}, |
|
{ |
|
"epoch": 295.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 888 |
|
}, |
|
{ |
|
"epoch": 297.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 892 |
|
}, |
|
{ |
|
"epoch": 298.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 896 |
|
}, |
|
{ |
|
"epoch": 298.59, |
|
"eval_exact_match": 0.620889748549323, |
|
"eval_exec": 0.6450676982591876, |
|
"eval_loss": 0.3728490173816681, |
|
"eval_runtime": 458.092, |
|
"eval_samples_per_second": 2.257, |
|
"step": 896 |
|
}, |
|
{ |
|
"epoch": 299.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 301.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 904 |
|
}, |
|
{ |
|
"epoch": 302.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 908 |
|
}, |
|
{ |
|
"epoch": 303.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 912 |
|
}, |
|
{ |
|
"epoch": 305.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 916 |
|
}, |
|
{ |
|
"epoch": 306.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 307.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 924 |
|
}, |
|
{ |
|
"epoch": 309.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 928 |
|
}, |
|
{ |
|
"epoch": 310.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 932 |
|
}, |
|
{ |
|
"epoch": 311.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 936 |
|
}, |
|
{ |
|
"epoch": 313.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 314.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 944 |
|
}, |
|
{ |
|
"epoch": 315.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 948 |
|
}, |
|
{ |
|
"epoch": 317.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 952 |
|
}, |
|
{ |
|
"epoch": 318.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 956 |
|
}, |
|
{ |
|
"epoch": 319.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 319.88, |
|
"eval_exact_match": 0.6286266924564797, |
|
"eval_exec": 0.648936170212766, |
|
"eval_loss": 0.3788833022117615, |
|
"eval_runtime": 456.1366, |
|
"eval_samples_per_second": 2.267, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 321.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 964 |
|
}, |
|
{ |
|
"epoch": 322.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 968 |
|
}, |
|
{ |
|
"epoch": 323.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 972 |
|
}, |
|
{ |
|
"epoch": 325.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 976 |
|
}, |
|
{ |
|
"epoch": 326.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 327.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 984 |
|
}, |
|
{ |
|
"epoch": 329.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 988 |
|
}, |
|
{ |
|
"epoch": 330.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 992 |
|
}, |
|
{ |
|
"epoch": 331.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 996 |
|
}, |
|
{ |
|
"epoch": 333.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 334.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0069, |
|
"step": 1004 |
|
}, |
|
{ |
|
"epoch": 335.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0039, |
|
"step": 1008 |
|
}, |
|
{ |
|
"epoch": 337.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 1012 |
|
}, |
|
{ |
|
"epoch": 338.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1016 |
|
}, |
|
{ |
|
"epoch": 339.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 341.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 1024 |
|
}, |
|
{ |
|
"epoch": 341.29, |
|
"eval_exact_match": 0.6141199226305609, |
|
"eval_exec": 0.6402321083172147, |
|
"eval_loss": 0.37917226552963257, |
|
"eval_runtime": 457.05, |
|
"eval_samples_per_second": 2.262, |
|
"step": 1024 |
|
}, |
|
{ |
|
"epoch": 342.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1028 |
|
}, |
|
{ |
|
"epoch": 343.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1032 |
|
}, |
|
{ |
|
"epoch": 345.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1036 |
|
}, |
|
{ |
|
"epoch": 346.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 347.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1044 |
|
}, |
|
{ |
|
"epoch": 349.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1048 |
|
}, |
|
{ |
|
"epoch": 350.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1052 |
|
}, |
|
{ |
|
"epoch": 351.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1056 |
|
}, |
|
{ |
|
"epoch": 353.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 354.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1064 |
|
}, |
|
{ |
|
"epoch": 355.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1068 |
|
}, |
|
{ |
|
"epoch": 357.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1072 |
|
}, |
|
{ |
|
"epoch": 358.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1076 |
|
}, |
|
{ |
|
"epoch": 359.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 361.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1084 |
|
}, |
|
{ |
|
"epoch": 362.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0011, |
|
"step": 1088 |
|
}, |
|
{ |
|
"epoch": 362.59, |
|
"eval_exact_match": 0.6199226305609284, |
|
"eval_exec": 0.648936170212766, |
|
"eval_loss": 0.38900309801101685, |
|
"eval_runtime": 443.2936, |
|
"eval_samples_per_second": 2.333, |
|
"step": 1088 |
|
}, |
|
{ |
|
"epoch": 363.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0015, |
|
"step": 1092 |
|
}, |
|
{ |
|
"epoch": 365.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1096 |
|
}, |
|
{ |
|
"epoch": 366.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 367.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 1104 |
|
}, |
|
{ |
|
"epoch": 369.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0009, |
|
"step": 1108 |
|
}, |
|
{ |
|
"epoch": 370.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1112 |
|
}, |
|
{ |
|
"epoch": 371.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1116 |
|
}, |
|
{ |
|
"epoch": 373.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 374.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1124 |
|
}, |
|
{ |
|
"epoch": 375.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1128 |
|
}, |
|
{ |
|
"epoch": 377.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1132 |
|
}, |
|
{ |
|
"epoch": 378.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1136 |
|
}, |
|
{ |
|
"epoch": 379.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 381.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1144 |
|
}, |
|
{ |
|
"epoch": 382.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0016, |
|
"step": 1148 |
|
}, |
|
{ |
|
"epoch": 383.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.004, |
|
"step": 1152 |
|
}, |
|
{ |
|
"epoch": 383.88, |
|
"eval_exact_match": 0.6295938104448743, |
|
"eval_exec": 0.6528046421663443, |
|
"eval_loss": 0.35109272599220276, |
|
"eval_runtime": 428.9118, |
|
"eval_samples_per_second": 2.411, |
|
"step": 1152 |
|
}, |
|
{ |
|
"epoch": 385.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 1156 |
|
}, |
|
{ |
|
"epoch": 386.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 387.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1164 |
|
}, |
|
{ |
|
"epoch": 389.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1168 |
|
}, |
|
{ |
|
"epoch": 390.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1172 |
|
}, |
|
{ |
|
"epoch": 391.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1176 |
|
}, |
|
{ |
|
"epoch": 393.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 394.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1184 |
|
}, |
|
{ |
|
"epoch": 395.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1188 |
|
}, |
|
{ |
|
"epoch": 397.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1192 |
|
}, |
|
{ |
|
"epoch": 398.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1196 |
|
}, |
|
{ |
|
"epoch": 399.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 401.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1204 |
|
}, |
|
{ |
|
"epoch": 402.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1208 |
|
}, |
|
{ |
|
"epoch": 403.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1212 |
|
}, |
|
{ |
|
"epoch": 405.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1216 |
|
}, |
|
{ |
|
"epoch": 405.29, |
|
"eval_exact_match": 0.6353965183752418, |
|
"eval_exec": 0.660541586073501, |
|
"eval_loss": 0.4038596451282501, |
|
"eval_runtime": 442.9132, |
|
"eval_samples_per_second": 2.335, |
|
"step": 1216 |
|
}, |
|
{ |
|
"epoch": 406.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 407.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1224 |
|
}, |
|
{ |
|
"epoch": 409.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1228 |
|
}, |
|
{ |
|
"epoch": 410.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1232 |
|
}, |
|
{ |
|
"epoch": 411.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1236 |
|
}, |
|
{ |
|
"epoch": 413.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0059, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 414.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0007, |
|
"step": 1244 |
|
}, |
|
{ |
|
"epoch": 415.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1248 |
|
}, |
|
{ |
|
"epoch": 417.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1252 |
|
}, |
|
{ |
|
"epoch": 418.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1256 |
|
}, |
|
{ |
|
"epoch": 419.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 421.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1264 |
|
}, |
|
{ |
|
"epoch": 422.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1268 |
|
}, |
|
{ |
|
"epoch": 423.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1272 |
|
}, |
|
{ |
|
"epoch": 425.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1276 |
|
}, |
|
{ |
|
"epoch": 426.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 426.59, |
|
"eval_exact_match": 0.6295938104448743, |
|
"eval_exec": 0.6499032882011605, |
|
"eval_loss": 0.4094041585922241, |
|
"eval_runtime": 442.2153, |
|
"eval_samples_per_second": 2.338, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 427.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.001, |
|
"step": 1284 |
|
}, |
|
{ |
|
"epoch": 429.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1288 |
|
}, |
|
{ |
|
"epoch": 430.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1292 |
|
}, |
|
{ |
|
"epoch": 431.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1296 |
|
}, |
|
{ |
|
"epoch": 433.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 434.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1304 |
|
}, |
|
{ |
|
"epoch": 435.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0004, |
|
"step": 1308 |
|
}, |
|
{ |
|
"epoch": 437.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1312 |
|
}, |
|
{ |
|
"epoch": 438.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1316 |
|
}, |
|
{ |
|
"epoch": 439.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 441.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1324 |
|
}, |
|
{ |
|
"epoch": 442.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1328 |
|
}, |
|
{ |
|
"epoch": 443.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1332 |
|
}, |
|
{ |
|
"epoch": 445.29, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0005, |
|
"step": 1336 |
|
}, |
|
{ |
|
"epoch": 446.59, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0006, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 447.88, |
|
"learning_rate": 0.0001, |
|
"loss": 0.0008, |
|
"step": 1344 |
|
}, |
|
{ |
|
"epoch": 447.88, |
|
"eval_exact_match": 0.6441005802707931, |
|
"eval_exec": 0.6624758220502901, |
|
"eval_loss": 0.3987429440021515, |
|
"eval_runtime": 448.6509, |
|
"eval_samples_per_second": 2.305, |
|
"step": 1344 |
|
} |
|
], |
|
"max_steps": 9216, |
|
"num_train_epochs": 3072, |
|
"total_flos": 7.71745071522816e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|