| { | |
| "best_metric": 0.6317539484621779, | |
| "best_model_checkpoint": "./experiment/train_0503_sparc_no_coref_only_dependency/checkpoint-1344", | |
| "epoch": 149.3221476510067, | |
| "global_step": 1344, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6153, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5839, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5896, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.352, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2808, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2175, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1583, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.13, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1486, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_exact_match": 0.48960931005818786, | |
| "eval_exec": 0.542809642560266, | |
| "eval_loss": 0.17051339149475098, | |
| "eval_runtime": 473.2311, | |
| "eval_samples_per_second": 3.434, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1015, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0976, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0801, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0797, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0718, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.061, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0583, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0491, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "eval_exact_match": 0.5403158769742311, | |
| "eval_exec": 0.6201163757273483, | |
| "eval_loss": 0.17214366793632507, | |
| "eval_runtime": 803.5727, | |
| "eval_samples_per_second": 2.022, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.048, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.039, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0393, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0423, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0375, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0439, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.026, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.024, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "eval_exact_match": 0.5502909393183707, | |
| "eval_exec": 0.6084788029925187, | |
| "eval_loss": 0.19952385127544403, | |
| "eval_runtime": 654.4546, | |
| "eval_samples_per_second": 2.483, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 22.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0227, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.02, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0175, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0161, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0136, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0135, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.013, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "eval_exact_match": 0.5694098088113051, | |
| "eval_exec": 0.6325852036575229, | |
| "eval_loss": 0.23655764758586884, | |
| "eval_runtime": 762.1152, | |
| "eval_samples_per_second": 2.132, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0123, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0133, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 31.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0094, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0166, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0154, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 34.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0109, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0077, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "eval_exact_match": 0.5901911886949294, | |
| "eval_exec": 0.6408977556109726, | |
| "eval_loss": 0.259878933429718, | |
| "eval_runtime": 661.2927, | |
| "eval_samples_per_second": 2.457, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0072, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0066, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 38.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0064, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.007, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 39.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0165, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 40.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0063, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 41.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0052, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "eval_exact_match": 0.5926849542809642, | |
| "eval_exec": 0.6525353283458022, | |
| "eval_loss": 0.2874293625354767, | |
| "eval_runtime": 686.186, | |
| "eval_samples_per_second": 2.368, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 43.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.006, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 44.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 46.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0041, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 47.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0043, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 47.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 48.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 49.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0036, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 49.75, | |
| "eval_exact_match": 0.6026600166251039, | |
| "eval_exec": 0.657522859517872, | |
| "eval_loss": 0.2975001633167267, | |
| "eval_runtime": 636.4635, | |
| "eval_samples_per_second": 2.553, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 50.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 51.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 52.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 53.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 54.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 56.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 56.86, | |
| "eval_exact_match": 0.6109725685785536, | |
| "eval_exec": 0.6583541147132169, | |
| "eval_loss": 0.32981422543525696, | |
| "eval_runtime": 627.5266, | |
| "eval_samples_per_second": 2.59, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 57.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 58.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.005, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 59.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0204, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 61.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 62.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 63.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "eval_exact_match": 0.6134663341645885, | |
| "eval_exec": 0.6658354114713217, | |
| "eval_loss": 0.3227553963661194, | |
| "eval_runtime": 689.9491, | |
| "eval_samples_per_second": 2.355, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 64.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 65.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 66.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 67.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 68.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 69.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 70.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "eval_exact_match": 0.600166251039069, | |
| "eval_exec": 0.6583541147132169, | |
| "eval_loss": 0.3371490240097046, | |
| "eval_runtime": 633.7926, | |
| "eval_samples_per_second": 2.564, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 71.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 72.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 73.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 74.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0082, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 75.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 76.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 77.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 78.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 78.21, | |
| "eval_exact_match": 0.6034912718204489, | |
| "eval_exec": 0.6533665835411472, | |
| "eval_loss": 0.33176735043525696, | |
| "eval_runtime": 625.8717, | |
| "eval_samples_per_second": 2.596, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 79.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 79.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 80.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 81.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 82.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 83.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 84.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 85.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 85.32, | |
| "eval_exact_match": 0.6234413965087282, | |
| "eval_exec": 0.6716541978387365, | |
| "eval_loss": 0.285192608833313, | |
| "eval_runtime": 642.1565, | |
| "eval_samples_per_second": 2.531, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 86.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 87.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 87.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 88.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 89.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0046, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 90.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 91.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 92.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 92.43, | |
| "eval_exact_match": 0.5344970906068163, | |
| "eval_exec": 0.5802161263507897, | |
| "eval_loss": 0.37689846754074097, | |
| "eval_runtime": 614.899, | |
| "eval_samples_per_second": 2.643, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 93.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0083, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 94.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 95.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 95.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 96.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 97.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 98.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0132, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 99.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 99.54, | |
| "eval_exact_match": 0.6126350789692435, | |
| "eval_exec": 0.6724854530340815, | |
| "eval_loss": 0.3111036419868469, | |
| "eval_runtime": 624.8082, | |
| "eval_samples_per_second": 2.601, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 100.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 101.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 102.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 103.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 103.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 104.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 105.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 106.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0114, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 106.64, | |
| "eval_exact_match": 0.6151288445552785, | |
| "eval_exec": 0.6774729842061513, | |
| "eval_loss": 0.3059256076812744, | |
| "eval_runtime": 709.1272, | |
| "eval_samples_per_second": 2.292, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 107.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 108.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 109.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 110.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 111.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 111.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 112.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 113.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 113.75, | |
| "eval_exact_match": 0.6176226101413134, | |
| "eval_exec": 0.6724854530340815, | |
| "eval_loss": 0.35855236649513245, | |
| "eval_runtime": 647.1974, | |
| "eval_samples_per_second": 2.511, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 114.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 115.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 116.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 117.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 118.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 119.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 119.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 120.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 120.86, | |
| "eval_exact_match": 0.6118038237738986, | |
| "eval_exec": 0.6766417290108063, | |
| "eval_loss": 0.34494832158088684, | |
| "eval_runtime": 1089.7361, | |
| "eval_samples_per_second": 1.491, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 121.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 122.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 123.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 124.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 125.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 126.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 127.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 127.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 127.97, | |
| "eval_exact_match": 0.6234413965087282, | |
| "eval_exec": 0.6724854530340815, | |
| "eval_loss": 0.352324515581131, | |
| "eval_runtime": 627.1111, | |
| "eval_samples_per_second": 2.591, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 128.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 129.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 130.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 131.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 132.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 133.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 134.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0052, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 135.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 135.11, | |
| "eval_exact_match": 0.6101413133832086, | |
| "eval_exec": 0.6608478802992519, | |
| "eval_loss": 0.34119850397109985, | |
| "eval_runtime": 683.7196, | |
| "eval_samples_per_second": 2.377, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 135.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 136.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 137.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 138.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 139.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 140.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 141.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 142.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 142.21, | |
| "eval_exact_match": 0.6300914380714879, | |
| "eval_exec": 0.6658354114713217, | |
| "eval_loss": 0.36506175994873047, | |
| "eval_runtime": 628.8834, | |
| "eval_samples_per_second": 2.584, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 143.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 143.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 144.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0029, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 145.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 146.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 147.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 148.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 149.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 149.32, | |
| "eval_exact_match": 0.6317539484621779, | |
| "eval_exec": 0.6874480465502909, | |
| "eval_loss": 0.37579649686813354, | |
| "eval_runtime": 605.7302, | |
| "eval_samples_per_second": 2.683, | |
| "step": 1344 | |
| } | |
| ], | |
| "max_steps": 27648, | |
| "num_train_epochs": 3072, | |
| "total_flos": 1.0258011267411214e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |