| { | |
| "best_metric": 0.5253227408142999, | |
| "best_model_checkpoint": "/experiments/cosql/1ccc8b19-d4cc-42ca-b70f-7d796303d2e5/checkpoint-1856", | |
| "epoch": 231.9922480620155, | |
| "global_step": 1856, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2224, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1652, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8035, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.642, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.537, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4739, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4251, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3945, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.352, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3245, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2948, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.287, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2686, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2745, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2495, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2298, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "eval_exact_match": 0.3644488579940417, | |
| "eval_exec": 0.3902681231380338, | |
| "eval_loss": 0.23653237521648407, | |
| "eval_runtime": 724.5845, | |
| "eval_samples_per_second": 1.794, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2242, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.205, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1932, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1937, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1978, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1747, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1669, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 11.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1734, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1615, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1551, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1519, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1476, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1483, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1478, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1292, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1285, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "eval_exact_match": 0.4170804369414101, | |
| "eval_exec": 0.45878848063555117, | |
| "eval_loss": 0.20163151621818542, | |
| "eval_runtime": 846.5253, | |
| "eval_samples_per_second": 1.536, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1407, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1228, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1324, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 17.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1214, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1224, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1128, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1016, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 19.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.107, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 20.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1116, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0997, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 21.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1025, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 21.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0973, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0996, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0917, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 23.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0899, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 23.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0896, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 23.99, | |
| "eval_exact_match": 0.4816285998013903, | |
| "eval_exec": 0.5104270109235353, | |
| "eval_loss": 0.19154271483421326, | |
| "eval_runtime": 788.1761, | |
| "eval_samples_per_second": 1.649, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 24.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0909, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0867, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 25.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.089, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 25.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0888, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 26.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0946, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0803, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0769, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 27.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.078, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.084, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.07, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0727, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 29.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0719, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 30.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0727, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 30.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0759, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0708, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 31.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0674, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 31.99, | |
| "eval_exact_match": 0.5014895729890765, | |
| "eval_exec": 0.5382323733862959, | |
| "eval_loss": 0.19477179646492004, | |
| "eval_runtime": 786.6121, | |
| "eval_samples_per_second": 1.653, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0673, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 32.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0716, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 33.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0658, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 33.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0564, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 34.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0604, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 34.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0632, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 35.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0611, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 35.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0577, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 36.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0602, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 36.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0556, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0588, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 37.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0584, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 38.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0537, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 38.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0538, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 39.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0517, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0542, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 39.99, | |
| "eval_exact_match": 0.5173783515392254, | |
| "eval_exec": 0.5501489572989077, | |
| "eval_loss": 0.21476374566555023, | |
| "eval_runtime": 722.7734, | |
| "eval_samples_per_second": 1.799, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 40.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.052, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 40.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0552, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 41.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0474, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 41.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0456, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 42.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0517, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 42.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0484, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 43.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0432, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 43.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0446, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 44.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0443, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 44.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0425, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 45.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0452, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 45.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0429, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 46.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0471, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 46.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0433, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 47.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0416, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 47.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0397, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 47.99, | |
| "eval_exact_match": 0.5143992055610725, | |
| "eval_exec": 0.5491559086395233, | |
| "eval_loss": 0.22859126329421997, | |
| "eval_runtime": 751.9885, | |
| "eval_samples_per_second": 1.729, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 48.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0449, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 48.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0404, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 49.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0384, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 49.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0378, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 50.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0405, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 50.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0391, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 51.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0377, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 51.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0349, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 52.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0328, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 52.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0363, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 53.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0355, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 53.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0317, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 54.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0308, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 54.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0303, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 55.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0313, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 55.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0351, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 55.99, | |
| "eval_exact_match": 0.5243296921549155, | |
| "eval_exec": 0.5561072492552135, | |
| "eval_loss": 0.2355286180973053, | |
| "eval_runtime": 746.4078, | |
| "eval_samples_per_second": 1.742, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 56.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0307, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 56.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0296, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 57.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0295, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 57.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0316, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 58.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0283, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 58.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0321, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 59.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0296, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 59.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0262, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 60.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0259, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 60.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.027, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 61.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0263, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 61.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0259, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 62.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0275, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 62.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0262, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 63.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0252, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 63.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.025, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 63.99, | |
| "eval_exact_match": 0.5094339622641509, | |
| "eval_exec": 0.5422045680238332, | |
| "eval_loss": 0.2562254071235657, | |
| "eval_runtime": 720.3713, | |
| "eval_samples_per_second": 1.805, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 64.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0256, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 64.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0272, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 65.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0293, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 65.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0231, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 66.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0232, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 66.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0253, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 67.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0224, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 67.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.021, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 68.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0206, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 68.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0229, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 69.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0243, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 69.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0211, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 70.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0208, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 70.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0225, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 71.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0209, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 71.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0225, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 71.99, | |
| "eval_exact_match": 0.5173783515392254, | |
| "eval_exec": 0.5461767626613704, | |
| "eval_loss": 0.2805687189102173, | |
| "eval_runtime": 749.8642, | |
| "eval_samples_per_second": 1.734, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 72.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0188, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 72.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0209, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 73.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0193, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 73.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0221, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 74.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0193, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 74.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0184, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 75.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0169, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 75.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0177, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 76.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0189, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 76.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0185, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 77.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0166, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 77.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0167, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 78.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 78.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0162, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 79.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 79.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0172, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 79.99, | |
| "eval_exact_match": 0.5134061569016882, | |
| "eval_exec": 0.5431976166832175, | |
| "eval_loss": 0.2822588086128235, | |
| "eval_runtime": 735.1307, | |
| "eval_samples_per_second": 1.768, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 80.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.017, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 80.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0166, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 81.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0157, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 81.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0182, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 82.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 82.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 83.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 83.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0139, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 84.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0151, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 84.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 85.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 85.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0119, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 86.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0128, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 86.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0134, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 87.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0143, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 87.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0189, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 87.99, | |
| "eval_exact_match": 0.5134061569016882, | |
| "eval_exec": 0.5441906653426017, | |
| "eval_loss": 0.285916805267334, | |
| "eval_runtime": 740.5163, | |
| "eval_samples_per_second": 1.756, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 88.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 88.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0122, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 89.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0141, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 89.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0132, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 90.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0152, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 90.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 91.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0105, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 91.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0117, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 92.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0119, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 92.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0126, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 93.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 93.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0143, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 94.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0127, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 94.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0143, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 95.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0107, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 95.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0112, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 95.99, | |
| "eval_exact_match": 0.506454816285998, | |
| "eval_exec": 0.5461767626613704, | |
| "eval_loss": 0.3350318670272827, | |
| "eval_runtime": 791.2409, | |
| "eval_samples_per_second": 1.643, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 96.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0113, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 96.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0107, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 97.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0112, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 97.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.011, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 98.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 98.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0122, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 99.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0113, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 99.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0101, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 100.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0089, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 100.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.011, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 101.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0086, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 101.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0097, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 102.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.011, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 102.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0085, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 103.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0086, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 103.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0094, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 103.99, | |
| "eval_exact_match": 0.5183714001986097, | |
| "eval_exec": 0.5441906653426017, | |
| "eval_loss": 0.34131428599357605, | |
| "eval_runtime": 681.4487, | |
| "eval_samples_per_second": 1.908, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 104.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0111, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 104.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0095, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 105.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0083, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 105.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0083, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 106.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0085, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 106.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0086, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 107.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0085, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 107.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0088, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 108.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0094, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 108.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 109.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0075, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 109.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0093, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 110.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0091, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 110.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0088, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 111.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0083, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 111.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0086, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 111.99, | |
| "eval_exact_match": 0.5243296921549155, | |
| "eval_exec": 0.5521350546176763, | |
| "eval_loss": 0.3550397753715515, | |
| "eval_runtime": 717.3828, | |
| "eval_samples_per_second": 1.812, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 112.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0086, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 112.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0085, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 113.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0076, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 113.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0093, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 114.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0068, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 114.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0075, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 115.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0073, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 115.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0071, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 116.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0077, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 116.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.006, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 117.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0065, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 117.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.008, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 118.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0069, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 118.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0082, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 119.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0058, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 119.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0072, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 119.99, | |
| "eval_exact_match": 0.5104270109235353, | |
| "eval_exec": 0.5431976166832175, | |
| "eval_loss": 0.3599448800086975, | |
| "eval_runtime": 731.1991, | |
| "eval_samples_per_second": 1.778, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 120.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0062, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 120.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0066, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 121.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0054, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 121.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 122.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0054, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 122.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0066, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 123.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0068, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 123.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 124.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0065, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 124.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0067, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 125.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0061, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 125.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 126.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0056, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 126.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 127.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0062, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 127.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.006, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 127.99, | |
| "eval_exact_match": 0.5203574975173784, | |
| "eval_exec": 0.5501489572989077, | |
| "eval_loss": 0.39113467931747437, | |
| "eval_runtime": 888.0535, | |
| "eval_samples_per_second": 1.464, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 128.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0066, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 128.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0065, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 129.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 129.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.005, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 130.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 130.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 131.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 131.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0095, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 132.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0058, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 132.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 133.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0067, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 133.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0056, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 134.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 134.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 135.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 135.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0054, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 135.99, | |
| "eval_exact_match": 0.5084409136047666, | |
| "eval_exec": 0.535253227408143, | |
| "eval_loss": 0.3826310336589813, | |
| "eval_runtime": 944.2579, | |
| "eval_samples_per_second": 1.377, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 136.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 136.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 137.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 137.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 138.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0054, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 138.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 139.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 139.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 140.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0087, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 140.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 141.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 141.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 142.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 142.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 143.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0066, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 143.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0052, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 143.99, | |
| "eval_exact_match": 0.506454816285998, | |
| "eval_exec": 0.5402184707050646, | |
| "eval_loss": 0.39830923080444336, | |
| "eval_runtime": 975.7311, | |
| "eval_samples_per_second": 1.332, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 144.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 144.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 145.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 145.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 146.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 1172 | |
| }, | |
| { | |
| "epoch": 146.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 147.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 147.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 148.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 148.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 149.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1196 | |
| }, | |
| { | |
| "epoch": 149.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 150.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 150.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 151.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 1212 | |
| }, | |
| { | |
| "epoch": 151.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 151.99, | |
| "eval_exact_match": 0.44885799404170806, | |
| "eval_exec": 0.5014895729890765, | |
| "eval_loss": 0.34375911951065063, | |
| "eval_runtime": 974.1005, | |
| "eval_samples_per_second": 1.335, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 152.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0114, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 152.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0044, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 153.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 1228 | |
| }, | |
| { | |
| "epoch": 153.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0045, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 154.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 1236 | |
| }, | |
| { | |
| "epoch": 154.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 155.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 155.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 156.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 1252 | |
| }, | |
| { | |
| "epoch": 156.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 157.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 157.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 158.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 1268 | |
| }, | |
| { | |
| "epoch": 158.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 159.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 159.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 159.99, | |
| "eval_exact_match": 0.5153922542204568, | |
| "eval_exec": 0.5441906653426017, | |
| "eval_loss": 0.41516825556755066, | |
| "eval_runtime": 976.5716, | |
| "eval_samples_per_second": 1.331, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 160.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 160.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 161.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 161.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 162.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 162.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 163.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 163.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 164.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 164.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 165.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1324 | |
| }, | |
| { | |
| "epoch": 165.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 166.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 166.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 167.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0031, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 167.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 167.99, | |
| "eval_exact_match": 0.5143992055610725, | |
| "eval_exec": 0.5382323733862959, | |
| "eval_loss": 0.4463094472885132, | |
| "eval_runtime": 955.823, | |
| "eval_samples_per_second": 1.36, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 168.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 1348 | |
| }, | |
| { | |
| "epoch": 168.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 169.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 1356 | |
| }, | |
| { | |
| "epoch": 169.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 170.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1364 | |
| }, | |
| { | |
| "epoch": 170.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 171.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0031, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 171.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 172.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 172.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 173.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 1388 | |
| }, | |
| { | |
| "epoch": 173.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 174.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 174.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 175.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 1404 | |
| }, | |
| { | |
| "epoch": 175.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 175.99, | |
| "eval_exact_match": 0.5074478649453823, | |
| "eval_exec": 0.5342601787487586, | |
| "eval_loss": 0.4188894033432007, | |
| "eval_runtime": 941.4278, | |
| "eval_samples_per_second": 1.381, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 176.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 1412 | |
| }, | |
| { | |
| "epoch": 176.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 177.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 177.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 178.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 178.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 179.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0057, | |
| "step": 1436 | |
| }, | |
| { | |
| "epoch": 179.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 180.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1444 | |
| }, | |
| { | |
| "epoch": 180.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 181.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 181.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 182.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 182.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0051, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 183.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1468 | |
| }, | |
| { | |
| "epoch": 183.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0031, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 183.99, | |
| "eval_exact_match": 0.519364448857994, | |
| "eval_exec": 0.5441906653426017, | |
| "eval_loss": 0.422220915555954, | |
| "eval_runtime": 973.3607, | |
| "eval_samples_per_second": 1.336, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 184.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1476 | |
| }, | |
| { | |
| "epoch": 184.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 185.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 185.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 186.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 1492 | |
| }, | |
| { | |
| "epoch": 186.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 187.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 187.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 188.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1508 | |
| }, | |
| { | |
| "epoch": 188.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 189.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1516 | |
| }, | |
| { | |
| "epoch": 189.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 190.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1524 | |
| }, | |
| { | |
| "epoch": 190.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1528 | |
| }, | |
| { | |
| "epoch": 191.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 191.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 191.99, | |
| "eval_exact_match": 0.5203574975173784, | |
| "eval_exec": 0.5491559086395233, | |
| "eval_loss": 0.44573745131492615, | |
| "eval_runtime": 974.7523, | |
| "eval_samples_per_second": 1.334, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 192.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 192.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1544 | |
| }, | |
| { | |
| "epoch": 193.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 1548 | |
| }, | |
| { | |
| "epoch": 193.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 194.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1556 | |
| }, | |
| { | |
| "epoch": 194.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 195.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 195.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 196.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1572 | |
| }, | |
| { | |
| "epoch": 196.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1576 | |
| }, | |
| { | |
| "epoch": 197.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 197.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 198.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1588 | |
| }, | |
| { | |
| "epoch": 198.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 199.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1596 | |
| }, | |
| { | |
| "epoch": 199.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 199.99, | |
| "eval_exact_match": 0.5114200595829196, | |
| "eval_exec": 0.5521350546176763, | |
| "eval_loss": 0.4328438639640808, | |
| "eval_runtime": 959.4133, | |
| "eval_samples_per_second": 1.355, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 200.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1604 | |
| }, | |
| { | |
| "epoch": 200.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 201.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1612 | |
| }, | |
| { | |
| "epoch": 201.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1616 | |
| }, | |
| { | |
| "epoch": 202.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 202.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 203.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1628 | |
| }, | |
| { | |
| "epoch": 203.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 204.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1636 | |
| }, | |
| { | |
| "epoch": 204.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 205.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 205.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 206.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1652 | |
| }, | |
| { | |
| "epoch": 206.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 207.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 207.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 207.99, | |
| "eval_exact_match": 0.5153922542204568, | |
| "eval_exec": 0.5422045680238332, | |
| "eval_loss": 0.46325209736824036, | |
| "eval_runtime": 948.9363, | |
| "eval_samples_per_second": 1.37, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 208.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1668 | |
| }, | |
| { | |
| "epoch": 208.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 209.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1676 | |
| }, | |
| { | |
| "epoch": 209.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 210.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1684 | |
| }, | |
| { | |
| "epoch": 210.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 211.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1692 | |
| }, | |
| { | |
| "epoch": 211.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 212.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 212.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1704 | |
| }, | |
| { | |
| "epoch": 213.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 213.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1712 | |
| }, | |
| { | |
| "epoch": 214.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1716 | |
| }, | |
| { | |
| "epoch": 214.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 215.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 1724 | |
| }, | |
| { | |
| "epoch": 215.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 215.99, | |
| "eval_exact_match": 0.5134061569016882, | |
| "eval_exec": 0.551142005958292, | |
| "eval_loss": 0.4671519100666046, | |
| "eval_runtime": 968.39, | |
| "eval_samples_per_second": 1.342, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 216.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1732 | |
| }, | |
| { | |
| "epoch": 216.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 217.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 217.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 1744 | |
| }, | |
| { | |
| "epoch": 218.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1748 | |
| }, | |
| { | |
| "epoch": 218.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 219.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1756 | |
| }, | |
| { | |
| "epoch": 219.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 220.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 1764 | |
| }, | |
| { | |
| "epoch": 220.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 221.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1772 | |
| }, | |
| { | |
| "epoch": 221.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 222.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 222.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1784 | |
| }, | |
| { | |
| "epoch": 223.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1788 | |
| }, | |
| { | |
| "epoch": 223.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 223.99, | |
| "eval_exact_match": 0.5143992055610725, | |
| "eval_exec": 0.5402184707050646, | |
| "eval_loss": 0.4584057629108429, | |
| "eval_runtime": 959.2229, | |
| "eval_samples_per_second": 1.355, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 224.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 1796 | |
| }, | |
| { | |
| "epoch": 224.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 225.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 1804 | |
| }, | |
| { | |
| "epoch": 225.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 1808 | |
| }, | |
| { | |
| "epoch": 226.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 226.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1816 | |
| }, | |
| { | |
| "epoch": 227.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 227.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 228.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 1828 | |
| }, | |
| { | |
| "epoch": 228.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1832 | |
| }, | |
| { | |
| "epoch": 229.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 1836 | |
| }, | |
| { | |
| "epoch": 229.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 230.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 1844 | |
| }, | |
| { | |
| "epoch": 230.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 231.5, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 1852 | |
| }, | |
| { | |
| "epoch": 231.99, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 231.99, | |
| "eval_exact_match": 0.5253227408142999, | |
| "eval_exec": 0.5561072492552135, | |
| "eval_loss": 0.44773775339126587, | |
| "eval_runtime": 980.451, | |
| "eval_samples_per_second": 1.326, | |
| "step": 1856 | |
| } | |
| ], | |
| "max_steps": 24576, | |
| "num_train_epochs": 3072, | |
| "total_flos": 7.797838246859244e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |