| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004995254508217193, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.9952545082171936e-05, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.990509016434387e-05, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0001498576352465158, | |
| "grad_norm": 1.078125, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7756, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00019981018032868775, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6268, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002497627254108597, | |
| "grad_norm": 0.97265625, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3838, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002997152704930316, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003496678155752036, | |
| "grad_norm": 0.625, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0735, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003996203606573755, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.969, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004495729057395474, | |
| "grad_norm": 0.427734375, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0166, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004995254508217194, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9446, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005494779959038913, | |
| "grad_norm": 0.31640625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.975, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0005994305409860632, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9867, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006493830860682351, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9101, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0006993356311504072, | |
| "grad_norm": 0.2109375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9296, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0007492881762325791, | |
| "grad_norm": 0.2158203125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9783, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000799240721314751, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9612, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008491932663969229, | |
| "grad_norm": 0.2138671875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9648, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0008991458114790948, | |
| "grad_norm": 0.197265625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9303, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009490983565612668, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9416, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0009990509016434388, | |
| "grad_norm": 0.1904296875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9454, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010490034467256107, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9603, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0010989559918077826, | |
| "grad_norm": 0.171875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9216, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0011489085368899545, | |
| "grad_norm": 0.2255859375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9503, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0011988610819721264, | |
| "grad_norm": 0.1572265625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9421, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012488136270542983, | |
| "grad_norm": 0.1591796875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9211, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0012987661721364703, | |
| "grad_norm": 0.1611328125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9854, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0013487187172186424, | |
| "grad_norm": 0.1455078125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9081, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0013986712623008143, | |
| "grad_norm": 0.15625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9687, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0014486238073829862, | |
| "grad_norm": 0.1494140625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9339, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0014985763524651581, | |
| "grad_norm": 0.1484375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00154852889754733, | |
| "grad_norm": 0.138671875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9222, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.001598481442629502, | |
| "grad_norm": 0.158203125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.937, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0016484339877116739, | |
| "grad_norm": 0.1455078125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9536, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0016983865327938458, | |
| "grad_norm": 0.13671875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9108, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0017483390778760177, | |
| "grad_norm": 0.1376953125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9168, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017982916229581896, | |
| "grad_norm": 0.1435546875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9554, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0018482441680403618, | |
| "grad_norm": 0.1396484375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9365, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0018981967131225337, | |
| "grad_norm": 0.130859375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9047, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0019481492582047056, | |
| "grad_norm": 0.138671875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.953, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0019981018032868775, | |
| "grad_norm": 0.146484375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9552, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020480543483690494, | |
| "grad_norm": 0.140625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9421, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0020980068934512213, | |
| "grad_norm": 0.134765625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9078, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0021479594385333933, | |
| "grad_norm": 0.1669921875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9458, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002197911983615565, | |
| "grad_norm": 0.1357421875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9172, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.002247864528697737, | |
| "grad_norm": 0.1396484375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8999, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002297817073779909, | |
| "grad_norm": 0.1435546875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9224, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.002347769618862081, | |
| "grad_norm": 0.18359375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9183, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.002397722163944253, | |
| "grad_norm": 0.1630859375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9258, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0024476747090264248, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9046, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0024976272541085967, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9506, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0025475797991907686, | |
| "grad_norm": 0.171875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9396, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0025975323442729405, | |
| "grad_norm": 0.1552734375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9131, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.002647484889355113, | |
| "grad_norm": 0.1591796875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8852, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0026974374344372848, | |
| "grad_norm": 0.154296875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9306, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0027473899795194567, | |
| "grad_norm": 0.14453125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8989, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0027973425246016286, | |
| "grad_norm": 0.154296875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9273, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0028472950696838005, | |
| "grad_norm": 0.16015625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9314, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0028972476147659724, | |
| "grad_norm": 0.1474609375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9098, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0029472001598481443, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8778, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.0029971527049303163, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8856, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.003047105250012488, | |
| "grad_norm": 0.21484375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8735, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.00309705779509466, | |
| "grad_norm": 0.154296875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9047, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.003147010340176832, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9401, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003196962885259004, | |
| "grad_norm": 0.1826171875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9593, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.003246915430341176, | |
| "grad_norm": 0.1494140625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8762, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0032968679754233478, | |
| "grad_norm": 0.1943359375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9102, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0033468205205055197, | |
| "grad_norm": 0.203125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8891, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0033967730655876916, | |
| "grad_norm": 0.1748046875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.89, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0034467256106698635, | |
| "grad_norm": 0.1591796875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9058, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0034966781557520354, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.921, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0035466307008342073, | |
| "grad_norm": 0.169921875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9024, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0035965832459163793, | |
| "grad_norm": 0.201171875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.888, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003646535790998551, | |
| "grad_norm": 0.1923828125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9482, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0036964883360807235, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9083, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0037464408811628954, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8941, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0037963934262450674, | |
| "grad_norm": 0.1875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8182, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0038463459713272393, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8851, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.003896298516409411, | |
| "grad_norm": 0.1806640625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8908, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.003946251061491583, | |
| "grad_norm": 0.17578125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.865, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.003996203606573755, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8739, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.004046156151655927, | |
| "grad_norm": 0.2001953125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8663, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.004096108696738099, | |
| "grad_norm": 0.1708984375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8611, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.004146061241820271, | |
| "grad_norm": 0.19921875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9407, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.004196013786902443, | |
| "grad_norm": 0.177734375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8856, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.004245966331984615, | |
| "grad_norm": 0.193359375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8824, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0042959188770667865, | |
| "grad_norm": 0.1787109375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8966, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.004345871422148958, | |
| "grad_norm": 0.19140625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.889, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.00439582396723113, | |
| "grad_norm": 0.1884765625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8558, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.004445776512313302, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8981, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.004495729057395474, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8875, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004545681602477646, | |
| "grad_norm": 0.248046875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9172, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.004595634147559818, | |
| "grad_norm": 0.189453125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8927, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.00464558669264199, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8491, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.004695539237724162, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9081, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.004745491782806334, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8536, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.004795444327888506, | |
| "grad_norm": 0.2080078125, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8619, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.004845396872970678, | |
| "grad_norm": 0.216796875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8592, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0048953494180528495, | |
| "grad_norm": 0.2119140625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8504, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.004945301963135021, | |
| "grad_norm": 0.2177734375, | |
| "learning_rate": 0.0002, | |
| "loss": 1.851, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.004995254508217193, | |
| "grad_norm": 0.1982421875, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8595, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 12011400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 600, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2021802943447040.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |