| { | |
| "best_metric": 0.6417290108063175, | |
| "best_model_checkpoint": "./experiment/train_0429_sparc_add_coref/checkpoint-2432", | |
| "epoch": 270.2147651006711, | |
| "global_step": 2432, | |
| "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": 3.5405, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3105, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1917, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.57, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3591, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2618, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2122, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1584, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1421, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "eval_exact_match": 0.39068994181213634, | |
| "eval_exec": 0.457190357439734, | |
| "eval_loss": 0.1790621280670166, | |
| "eval_runtime": 891.1645, | |
| "eval_samples_per_second": 1.823, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1129, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1136, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.102, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 10.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0846, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 11.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0752, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0681, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 13.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0655, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0551, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 14.21, | |
| "eval_exact_match": 0.5586034912718204, | |
| "eval_exec": 0.6226101413133832, | |
| "eval_loss": 0.16853797435760498, | |
| "eval_runtime": 623.0506, | |
| "eval_samples_per_second": 2.608, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0499, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0572, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0459, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0386, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 18.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0342, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 19.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0315, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 20.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0282, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.027, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 21.32, | |
| "eval_exact_match": 0.5810473815461347, | |
| "eval_exec": 0.6342477140482128, | |
| "eval_loss": 0.21147404611110687, | |
| "eval_runtime": 655.5734, | |
| "eval_samples_per_second": 2.479, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 22.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0233, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0231, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 23.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0431, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0212, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0153, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0144, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0156, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 28.43, | |
| "eval_exact_match": 0.5818786367414797, | |
| "eval_exec": 0.6408977556109726, | |
| "eval_loss": 0.23599478602409363, | |
| "eval_runtime": 661.7445, | |
| "eval_samples_per_second": 2.456, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 29.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0141, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 30.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0115, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 31.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0113, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0107, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 33.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0096, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 34.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.01, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 35.54, | |
| "eval_exact_match": 0.5985037406483791, | |
| "eval_exec": 0.655860349127182, | |
| "eval_loss": 0.26971787214279175, | |
| "eval_runtime": 691.9565, | |
| "eval_samples_per_second": 2.348, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 36.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0084, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 37.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0098, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 38.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0206, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0071, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 39.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0061, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 40.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0061, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 41.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0059, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0099, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 42.64, | |
| "eval_exact_match": 0.5901911886949294, | |
| "eval_exec": 0.6367414796342478, | |
| "eval_loss": 0.2628422975540161, | |
| "eval_runtime": 655.666, | |
| "eval_samples_per_second": 2.478, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 43.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0055, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 44.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0052, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 45.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 46.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.005, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 47.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0048, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 47.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0042, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 48.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0049, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 49.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 49.75, | |
| "eval_exact_match": 0.5985037406483791, | |
| "eval_exec": 0.6517040731504572, | |
| "eval_loss": 0.3072524070739746, | |
| "eval_runtime": 692.7017, | |
| "eval_samples_per_second": 2.346, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 50.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0047, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 51.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0039, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 52.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 53.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0037, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 54.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0034, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 55.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 55.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.003, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 56.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 56.86, | |
| "eval_exact_match": 0.5993349958437241, | |
| "eval_exec": 0.6492103075644223, | |
| "eval_loss": 0.3246177136898041, | |
| "eval_runtime": 716.2484, | |
| "eval_samples_per_second": 2.269, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 57.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 58.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 59.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0031, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 60.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 61.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.004, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 62.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0033, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 63.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 63.97, | |
| "eval_exact_match": 0.5935162094763092, | |
| "eval_exec": 0.6433915211970075, | |
| "eval_loss": 0.31884506344795227, | |
| "eval_runtime": 835.1344, | |
| "eval_samples_per_second": 1.946, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 64.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 65.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 66.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 67.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 68.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0026, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 69.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 70.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0024, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 71.11, | |
| "eval_exact_match": 0.6018287614297589, | |
| "eval_exec": 0.6583541147132169, | |
| "eval_loss": 0.3463212847709656, | |
| "eval_runtime": 682.2964, | |
| "eval_samples_per_second": 2.382, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 71.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 72.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 73.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 74.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 75.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 76.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 77.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 78.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 78.21, | |
| "eval_exact_match": 0.6043225270157938, | |
| "eval_exec": 0.6583541147132169, | |
| "eval_loss": 0.34072062373161316, | |
| "eval_runtime": 645.8928, | |
| "eval_samples_per_second": 2.516, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 79.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 79.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 80.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0028, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 81.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0199, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 82.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 83.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0019, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 84.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 85.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.002, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 85.32, | |
| "eval_exact_match": 0.5968412302576891, | |
| "eval_exec": 0.6517040731504572, | |
| "eval_loss": 0.34500738978385925, | |
| "eval_runtime": 667.4413, | |
| "eval_samples_per_second": 2.435, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 86.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 87.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 87.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 88.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 89.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 90.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 91.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 92.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 92.43, | |
| "eval_exact_match": 0.5985037406483791, | |
| "eval_exec": 0.656691604322527, | |
| "eval_loss": 0.35779085755348206, | |
| "eval_runtime": 620.7719, | |
| "eval_samples_per_second": 2.618, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 93.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 94.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 95.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 95.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 96.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 97.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 98.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 99.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 99.54, | |
| "eval_exact_match": 0.6051537822111388, | |
| "eval_exec": 0.6508728179551122, | |
| "eval_loss": 0.37539783120155334, | |
| "eval_runtime": 640.8712, | |
| "eval_samples_per_second": 2.536, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 100.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 101.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 102.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 103.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 103.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 104.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 105.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 106.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 106.64, | |
| "eval_exact_match": 0.6101413133832086, | |
| "eval_exec": 0.6550290939318371, | |
| "eval_loss": 0.37180858850479126, | |
| "eval_runtime": 660.4887, | |
| "eval_samples_per_second": 2.46, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 107.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0025, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 108.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0022, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 109.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 110.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 111.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 111.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 112.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 113.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 113.75, | |
| "eval_exact_match": 0.5943474646716542, | |
| "eval_exec": 0.6458852867830424, | |
| "eval_loss": 0.37901195883750916, | |
| "eval_runtime": 727.9232, | |
| "eval_samples_per_second": 2.232, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 114.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 115.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 116.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 117.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 118.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 119.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 119.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 120.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 120.86, | |
| "eval_exact_match": 0.6126350789692435, | |
| "eval_exec": 0.6600166251039069, | |
| "eval_loss": 0.3471900224685669, | |
| "eval_runtime": 623.9447, | |
| "eval_samples_per_second": 2.604, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 121.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 122.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0141, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 123.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0032, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 124.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 125.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 126.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 127.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0061, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 127.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0017, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 127.97, | |
| "eval_exact_match": 0.6126350789692435, | |
| "eval_exec": 0.6517040731504572, | |
| "eval_loss": 0.3467860519886017, | |
| "eval_runtime": 618.228, | |
| "eval_samples_per_second": 2.628, | |
| "step": 1152 | |
| }, | |
| { | |
| "epoch": 128.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.011, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 129.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1168 | |
| }, | |
| { | |
| "epoch": 130.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 131.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 1184 | |
| }, | |
| { | |
| "epoch": 132.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 1192 | |
| }, | |
| { | |
| "epoch": 133.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0053, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 134.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1208 | |
| }, | |
| { | |
| "epoch": 135.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 135.11, | |
| "eval_exact_match": 0.6201163757273483, | |
| "eval_exec": 0.6583541147132169, | |
| "eval_loss": 0.3528030216693878, | |
| "eval_runtime": 653.8235, | |
| "eval_samples_per_second": 2.485, | |
| "step": 1216 | |
| }, | |
| { | |
| "epoch": 135.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 136.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 137.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 138.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 139.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1256 | |
| }, | |
| { | |
| "epoch": 140.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1264 | |
| }, | |
| { | |
| "epoch": 141.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1272 | |
| }, | |
| { | |
| "epoch": 142.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 142.21, | |
| "eval_exact_match": 0.6201163757273483, | |
| "eval_exec": 0.6625103906899418, | |
| "eval_loss": 0.38731279969215393, | |
| "eval_runtime": 657.4977, | |
| "eval_samples_per_second": 2.471, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 143.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 143.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1296 | |
| }, | |
| { | |
| "epoch": 144.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1304 | |
| }, | |
| { | |
| "epoch": 145.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 146.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 147.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1328 | |
| }, | |
| { | |
| "epoch": 148.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1336 | |
| }, | |
| { | |
| "epoch": 149.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 149.32, | |
| "eval_exact_match": 0.6118038237738986, | |
| "eval_exec": 0.6541978387364921, | |
| "eval_loss": 0.38289570808410645, | |
| "eval_runtime": 654.6029, | |
| "eval_samples_per_second": 2.482, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 150.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0018, | |
| "step": 1352 | |
| }, | |
| { | |
| "epoch": 151.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 151.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1368 | |
| }, | |
| { | |
| "epoch": 152.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0021, | |
| "step": 1376 | |
| }, | |
| { | |
| "epoch": 153.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 154.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1392 | |
| }, | |
| { | |
| "epoch": 155.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 156.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 156.43, | |
| "eval_exact_match": 0.6068162926018288, | |
| "eval_exec": 0.6525353283458022, | |
| "eval_loss": 0.386453777551651, | |
| "eval_runtime": 661.6138, | |
| "eval_samples_per_second": 2.456, | |
| "step": 1408 | |
| }, | |
| { | |
| "epoch": 157.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1416 | |
| }, | |
| { | |
| "epoch": 158.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1424 | |
| }, | |
| { | |
| "epoch": 159.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1432 | |
| }, | |
| { | |
| "epoch": 159.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 160.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1448 | |
| }, | |
| { | |
| "epoch": 161.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 162.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 163.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 163.54, | |
| "eval_exact_match": 0.6059850374064838, | |
| "eval_exec": 0.6533665835411472, | |
| "eval_loss": 0.36874809861183167, | |
| "eval_runtime": 690.7636, | |
| "eval_samples_per_second": 2.352, | |
| "step": 1472 | |
| }, | |
| { | |
| "epoch": 164.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 165.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1488 | |
| }, | |
| { | |
| "epoch": 166.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0023, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 167.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0027, | |
| "step": 1504 | |
| }, | |
| { | |
| "epoch": 167.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1512 | |
| }, | |
| { | |
| "epoch": 168.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 169.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1528 | |
| }, | |
| { | |
| "epoch": 170.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 170.64, | |
| "eval_exact_match": 0.6134663341645885, | |
| "eval_exec": 0.6591853699085619, | |
| "eval_loss": 0.3634226620197296, | |
| "eval_runtime": 651.3159, | |
| "eval_samples_per_second": 2.495, | |
| "step": 1536 | |
| }, | |
| { | |
| "epoch": 171.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1544 | |
| }, | |
| { | |
| "epoch": 172.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1552 | |
| }, | |
| { | |
| "epoch": 173.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 174.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1568 | |
| }, | |
| { | |
| "epoch": 175.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1576 | |
| }, | |
| { | |
| "epoch": 175.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 176.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0016, | |
| "step": 1592 | |
| }, | |
| { | |
| "epoch": 177.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 177.75, | |
| "eval_exact_match": 0.6084788029925187, | |
| "eval_exec": 0.6541978387364921, | |
| "eval_loss": 0.36969253420829773, | |
| "eval_runtime": 616.1266, | |
| "eval_samples_per_second": 2.637, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 178.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1608 | |
| }, | |
| { | |
| "epoch": 179.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1616 | |
| }, | |
| { | |
| "epoch": 180.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1624 | |
| }, | |
| { | |
| "epoch": 181.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 182.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 183.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1648 | |
| }, | |
| { | |
| "epoch": 183.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0035, | |
| "step": 1656 | |
| }, | |
| { | |
| "epoch": 184.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 184.86, | |
| "eval_exact_match": 0.6109725685785536, | |
| "eval_exec": 0.6658354114713217, | |
| "eval_loss": 0.34515219926834106, | |
| "eval_runtime": 645.9688, | |
| "eval_samples_per_second": 2.516, | |
| "step": 1664 | |
| }, | |
| { | |
| "epoch": 185.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1672 | |
| }, | |
| { | |
| "epoch": 186.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 187.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1688 | |
| }, | |
| { | |
| "epoch": 188.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1696 | |
| }, | |
| { | |
| "epoch": 189.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0154, | |
| "step": 1704 | |
| }, | |
| { | |
| "epoch": 190.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0011, | |
| "step": 1712 | |
| }, | |
| { | |
| "epoch": 191.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0069, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 191.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 191.97, | |
| "eval_exact_match": 0.6109725685785536, | |
| "eval_exec": 0.6616791354945969, | |
| "eval_loss": 0.35217443108558655, | |
| "eval_runtime": 638.0561, | |
| "eval_samples_per_second": 2.547, | |
| "step": 1728 | |
| }, | |
| { | |
| "epoch": 192.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1736 | |
| }, | |
| { | |
| "epoch": 193.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1744 | |
| }, | |
| { | |
| "epoch": 194.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1752 | |
| }, | |
| { | |
| "epoch": 195.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 196.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 197.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1776 | |
| }, | |
| { | |
| "epoch": 198.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1784 | |
| }, | |
| { | |
| "epoch": 199.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 199.11, | |
| "eval_exact_match": 0.6076475477971738, | |
| "eval_exec": 0.655860349127182, | |
| "eval_loss": 0.38836565613746643, | |
| "eval_runtime": 698.9686, | |
| "eval_samples_per_second": 2.325, | |
| "step": 1792 | |
| }, | |
| { | |
| "epoch": 199.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 200.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1808 | |
| }, | |
| { | |
| "epoch": 201.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 1816 | |
| }, | |
| { | |
| "epoch": 202.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0098, | |
| "step": 1824 | |
| }, | |
| { | |
| "epoch": 203.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1832 | |
| }, | |
| { | |
| "epoch": 204.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 205.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1848 | |
| }, | |
| { | |
| "epoch": 206.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 206.21, | |
| "eval_exact_match": 0.6192851205320034, | |
| "eval_exec": 0.6650041562759768, | |
| "eval_loss": 0.3801758289337158, | |
| "eval_runtime": 619.6713, | |
| "eval_samples_per_second": 2.622, | |
| "step": 1856 | |
| }, | |
| { | |
| "epoch": 207.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1864 | |
| }, | |
| { | |
| "epoch": 207.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 1872 | |
| }, | |
| { | |
| "epoch": 208.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 209.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1888 | |
| }, | |
| { | |
| "epoch": 210.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1896 | |
| }, | |
| { | |
| "epoch": 211.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 212.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1912 | |
| }, | |
| { | |
| "epoch": 213.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 213.32, | |
| "eval_exact_match": 0.6134663341645885, | |
| "eval_exec": 0.6633416458852868, | |
| "eval_loss": 0.39502447843551636, | |
| "eval_runtime": 693.1979, | |
| "eval_samples_per_second": 2.344, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 214.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 1928 | |
| }, | |
| { | |
| "epoch": 215.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 1936 | |
| }, | |
| { | |
| "epoch": 215.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1944 | |
| }, | |
| { | |
| "epoch": 216.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1952 | |
| }, | |
| { | |
| "epoch": 217.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 218.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 1968 | |
| }, | |
| { | |
| "epoch": 219.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1976 | |
| }, | |
| { | |
| "epoch": 220.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 220.43, | |
| "eval_exact_match": 0.6192851205320034, | |
| "eval_exec": 0.6600166251039069, | |
| "eval_loss": 0.3968105614185333, | |
| "eval_runtime": 631.3521, | |
| "eval_samples_per_second": 2.574, | |
| "step": 1984 | |
| }, | |
| { | |
| "epoch": 221.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 1992 | |
| }, | |
| { | |
| "epoch": 222.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 223.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2008 | |
| }, | |
| { | |
| "epoch": 223.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2016 | |
| }, | |
| { | |
| "epoch": 224.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2024 | |
| }, | |
| { | |
| "epoch": 225.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 2032 | |
| }, | |
| { | |
| "epoch": 226.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0012, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 227.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0014, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 227.54, | |
| "eval_exact_match": 0.6084788029925187, | |
| "eval_exec": 0.6591853699085619, | |
| "eval_loss": 0.3648475110530853, | |
| "eval_runtime": 1018.7111, | |
| "eval_samples_per_second": 1.595, | |
| "step": 2048 | |
| }, | |
| { | |
| "epoch": 228.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 2056 | |
| }, | |
| { | |
| "epoch": 229.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2064 | |
| }, | |
| { | |
| "epoch": 230.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 2072 | |
| }, | |
| { | |
| "epoch": 231.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 231.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2088 | |
| }, | |
| { | |
| "epoch": 232.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 2096 | |
| }, | |
| { | |
| "epoch": 233.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2104 | |
| }, | |
| { | |
| "epoch": 234.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 234.64, | |
| "eval_exact_match": 0.6126350789692435, | |
| "eval_exec": 0.6633416458852868, | |
| "eval_loss": 0.39520663022994995, | |
| "eval_runtime": 677.2313, | |
| "eval_samples_per_second": 2.399, | |
| "step": 2112 | |
| }, | |
| { | |
| "epoch": 235.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 236.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2128 | |
| }, | |
| { | |
| "epoch": 237.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2136 | |
| }, | |
| { | |
| "epoch": 238.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2144 | |
| }, | |
| { | |
| "epoch": 239.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2152 | |
| }, | |
| { | |
| "epoch": 239.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 240.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2168 | |
| }, | |
| { | |
| "epoch": 241.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2176 | |
| }, | |
| { | |
| "epoch": 241.75, | |
| "eval_exact_match": 0.6234413965087282, | |
| "eval_exec": 0.6683291770573566, | |
| "eval_loss": 0.40271905064582825, | |
| "eval_runtime": 654.7779, | |
| "eval_samples_per_second": 2.482, | |
| "step": 2176 | |
| }, | |
| { | |
| "epoch": 242.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 243.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2192 | |
| }, | |
| { | |
| "epoch": 244.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 245.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2208 | |
| }, | |
| { | |
| "epoch": 246.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 2216 | |
| }, | |
| { | |
| "epoch": 247.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2224 | |
| }, | |
| { | |
| "epoch": 247.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2232 | |
| }, | |
| { | |
| "epoch": 248.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 248.86, | |
| "eval_exact_match": 0.6184538653366584, | |
| "eval_exec": 0.6641729010806318, | |
| "eval_loss": 0.3742313086986542, | |
| "eval_runtime": 577.1527, | |
| "eval_samples_per_second": 2.816, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 249.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2248 | |
| }, | |
| { | |
| "epoch": 250.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2256 | |
| }, | |
| { | |
| "epoch": 251.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2264 | |
| }, | |
| { | |
| "epoch": 252.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 2272 | |
| }, | |
| { | |
| "epoch": 253.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 254.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 2288 | |
| }, | |
| { | |
| "epoch": 255.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 2296 | |
| }, | |
| { | |
| "epoch": 255.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0009, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 255.97, | |
| "eval_exact_match": 0.6109725685785536, | |
| "eval_exec": 0.6450540315876975, | |
| "eval_loss": 0.3888351619243622, | |
| "eval_runtime": 585.9503, | |
| "eval_samples_per_second": 2.773, | |
| "step": 2304 | |
| }, | |
| { | |
| "epoch": 256.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0038, | |
| "step": 2312 | |
| }, | |
| { | |
| "epoch": 257.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 258.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0015, | |
| "step": 2328 | |
| }, | |
| { | |
| "epoch": 259.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.001, | |
| "step": 2336 | |
| }, | |
| { | |
| "epoch": 260.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2344 | |
| }, | |
| { | |
| "epoch": 261.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2352 | |
| }, | |
| { | |
| "epoch": 262.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 263.11, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2368 | |
| }, | |
| { | |
| "epoch": 263.11, | |
| "eval_exact_match": 0.6300914380714879, | |
| "eval_exec": 0.6741479634247715, | |
| "eval_loss": 0.38216930627822876, | |
| "eval_runtime": 619.0871, | |
| "eval_samples_per_second": 2.625, | |
| "step": 2368 | |
| }, | |
| { | |
| "epoch": 263.97, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0008, | |
| "step": 2376 | |
| }, | |
| { | |
| "epoch": 264.86, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2384 | |
| }, | |
| { | |
| "epoch": 265.75, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0007, | |
| "step": 2392 | |
| }, | |
| { | |
| "epoch": 266.64, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0013, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 267.54, | |
| "learning_rate": 0.0001, | |
| "loss": 0.009, | |
| "step": 2408 | |
| }, | |
| { | |
| "epoch": 268.43, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2416 | |
| }, | |
| { | |
| "epoch": 269.32, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2424 | |
| }, | |
| { | |
| "epoch": 270.21, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0006, | |
| "step": 2432 | |
| }, | |
| { | |
| "epoch": 270.21, | |
| "eval_exact_match": 0.6417290108063175, | |
| "eval_exec": 0.6816292601828762, | |
| "eval_loss": 0.385798841714859, | |
| "eval_runtime": 1200.0927, | |
| "eval_samples_per_second": 1.354, | |
| "step": 2432 | |
| } | |
| ], | |
| "max_steps": 27648, | |
| "num_train_epochs": 3072, | |
| "total_flos": 1.8557441383975617e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |