| { | |
| "best_metric": 0.6431334622823984, | |
| "best_model_checkpoint": "/train/checkpoint-960", | |
| "epoch": 319.87857142857143, | |
| "global_step": 960, | |
| "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": 4.3334, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5151, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9333, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.752, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5448, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.462, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 9.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4756, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 10.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3546, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 11.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3301, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 13.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3248, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3018, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 15.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.259, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2618, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 18.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2293, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 19.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2112, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2184, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 21.29, | |
| "eval_exact_match": 0.41779497098646035, | |
| "eval_exec": 0.4632495164410058, | |
| "eval_loss": 0.20271794497966766, | |
| "eval_runtime": 484.5096, | |
| "eval_samples_per_second": 2.134, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 22.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1879, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 23.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1768, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 25.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1749, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 26.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1515, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 27.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1434, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 29.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1509, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 30.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1318, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 31.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1196, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 33.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1206, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 34.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1119, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 35.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1047, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 37.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1066, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 38.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0941, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 39.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.086, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 41.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0936, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.087, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 42.59, | |
| "eval_exact_match": 0.5309477756286267, | |
| "eval_exec": 0.558027079303675, | |
| "eval_loss": 0.1789044588804245, | |
| "eval_runtime": 379.4369, | |
| "eval_samples_per_second": 2.725, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 43.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0758, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 45.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0861, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 46.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0731, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 47.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0699, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 49.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0708, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 50.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0663, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 51.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0666, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 53.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0631, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 54.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0543, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 55.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0534, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 57.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0635, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 58.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.052, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 59.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0487, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 61.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0509, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 62.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.047, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 63.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0463, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 63.88, | |
| "eval_exact_match": 0.5880077369439072, | |
| "eval_exec": 0.6237911025145068, | |
| "eval_loss": 0.1990066021680832, | |
| "eval_runtime": 395.2147, | |
| "eval_samples_per_second": 2.616, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 65.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.044, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 66.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.044, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 67.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0364, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 69.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.039, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 70.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0354, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 71.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.034, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 73.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0367, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 74.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0317, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 75.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0305, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 77.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0366, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 78.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0265, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 79.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0261, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 81.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0296, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 82.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0269, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 83.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0289, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 85.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0248, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 85.29, | |
| "eval_exact_match": 0.597678916827853, | |
| "eval_exec": 0.632495164410058, | |
| "eval_loss": 0.22355332970619202, | |
| "eval_runtime": 439.8485, | |
| "eval_samples_per_second": 2.351, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 86.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0213, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 87.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0243, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 89.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0258, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 90.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0239, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 91.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0184, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 93.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0193, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 94.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 95.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0174, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 97.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0182, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 98.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0158, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 99.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0158, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 101.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0197, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 102.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0136, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 103.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0141, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 105.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 106.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0123, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 106.59, | |
| "eval_exact_match": 0.6054158607350096, | |
| "eval_exec": 0.6402321083172147, | |
| "eval_loss": 0.2540315091609955, | |
| "eval_runtime": 435.8233, | |
| "eval_samples_per_second": 2.373, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 107.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 109.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0131, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 110.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 111.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0116, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 113.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 114.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0102, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 115.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0099, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 117.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 118.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0185, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 119.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0203, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 121.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0096, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 122.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 123.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.009, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 125.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0234, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 126.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0079, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 127.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0078, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 127.88, | |
| "eval_exact_match": 0.6228239845261122, | |
| "eval_exec": 0.655705996131528, | |
| "eval_loss": 0.25919318199157715, | |
| "eval_runtime": 429.4397, | |
| "eval_samples_per_second": 2.408, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 129.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0082, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 130.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0081, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 131.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0076, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 133.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0073, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 134.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0062, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 135.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0061, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 137.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 138.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 139.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.007, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 141.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0064, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 142.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0052, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 143.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 145.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 146.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 147.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0056, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 149.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 149.29, | |
| "eval_exact_match": 0.6286266924564797, | |
| "eval_exec": 0.6595744680851063, | |
| "eval_loss": 0.29107969999313354, | |
| "eval_runtime": 414.8613, | |
| "eval_samples_per_second": 2.492, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 150.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 151.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 153.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 154.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 155.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0044, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 157.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 158.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 159.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 161.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 162.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 163.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 165.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 166.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 167.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 169.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 170.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0031, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 170.59, | |
| "eval_exact_match": 0.6189555125725339, | |
| "eval_exec": 0.6547388781431335, | |
| "eval_loss": 0.30714040994644165, | |
| "eval_runtime": 432.9287, | |
| "eval_samples_per_second": 2.388, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 171.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 173.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 174.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0119, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 175.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 177.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 178.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 179.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 181.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 182.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 183.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 185.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 186.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 187.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 189.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 190.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 191.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 191.88, | |
| "eval_exact_match": 0.6295938104448743, | |
| "eval_exec": 0.6634429400386848, | |
| "eval_loss": 0.3123248815536499, | |
| "eval_runtime": 427.6812, | |
| "eval_samples_per_second": 2.418, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 193.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 194.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 195.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 197.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 198.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 199.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 201.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 202.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 203.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 205.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 206.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 207.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 209.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 210.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 211.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 213.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 213.29, | |
| "eval_exact_match": 0.6286266924564797, | |
| "eval_exec": 0.655705996131528, | |
| "eval_loss": 0.3154772222042084, | |
| "eval_runtime": 416.5624, | |
| "eval_samples_per_second": 2.482, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 214.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 215.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 217.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 218.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 219.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 221.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 222.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 223.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 225.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 226.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 227.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 229.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 230.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 231.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 233.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0121, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 234.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 234.59, | |
| "eval_exact_match": 0.6373307543520309, | |
| "eval_exec": 0.6721470019342359, | |
| "eval_loss": 0.31656521558761597, | |
| "eval_runtime": 424.2598, | |
| "eval_samples_per_second": 2.437, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 235.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 237.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 238.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 239.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 241.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 242.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 243.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 245.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 246.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 247.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 249.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 250.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 251.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 253.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 254.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 255.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 255.88, | |
| "eval_exact_match": 0.6295938104448743, | |
| "eval_exec": 0.6653771760154739, | |
| "eval_loss": 0.3407166302204132, | |
| "eval_runtime": 416.5111, | |
| "eval_samples_per_second": 2.483, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 257.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 258.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 259.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0081, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 261.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 262.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 263.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 265.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 266.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 267.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 269.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 270.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 271.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 273.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 274.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 275.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 277.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 277.29, | |
| "eval_exact_match": 0.6344294003868471, | |
| "eval_exec": 0.6653771760154739, | |
| "eval_loss": 0.3532732427120209, | |
| "eval_runtime": 444.5473, | |
| "eval_samples_per_second": 2.326, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 278.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 279.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 281.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 282.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 283.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 285.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 286.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 287.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 289.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 290.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 291.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 293.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 294.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 295.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 297.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 298.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 298.59, | |
| "eval_exact_match": 0.6373307543520309, | |
| "eval_exec": 0.6721470019342359, | |
| "eval_loss": 0.35602492094039917, | |
| "eval_runtime": 434.7668, | |
| "eval_samples_per_second": 2.378, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 299.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 301.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 302.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 303.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 305.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 306.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 307.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 309.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 310.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 311.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 313.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 314.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 315.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 317.29, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 318.59, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 319.88, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 319.88, | |
| "eval_exact_match": 0.6431334622823984, | |
| "eval_exec": 0.6750483558994197, | |
| "eval_loss": 0.33101460337638855, | |
| "eval_runtime": 445.7155, | |
| "eval_samples_per_second": 2.32, | |
| "step": 960 | |
| } | |
| ], | |
| "max_steps": 9216, | |
| "num_train_epochs": 3072, | |
| "total_flos": 4.564030172352e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |