| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.99867197875166, | |
| "eval_steps": 94, | |
| "global_step": 94, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010624169986719787, | |
| "grad_norm": 2.473472145582703, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.4101, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010624169986719787, | |
| "eval_loss": 1.6489976644515991, | |
| "eval_runtime": 38.1546, | |
| "eval_samples_per_second": 63.033, | |
| "eval_steps_per_second": 1.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021248339973439574, | |
| "grad_norm": 2.473600838217233, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4273, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03187250996015936, | |
| "grad_norm": 2.5043053838666367, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.4244, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04249667994687915, | |
| "grad_norm": 2.4185276106954317, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4166, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05312084993359894, | |
| "grad_norm": 2.101313294150849, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.3973, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "grad_norm": 2.32474051391718, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.364, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07436918990703852, | |
| "grad_norm": 2.1736886206661663, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.3353, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0849933598937583, | |
| "grad_norm": 1.7213633107027813, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3195, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09561752988047809, | |
| "grad_norm": 3.2596713587035007, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.3083, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10624169986719788, | |
| "grad_norm": 7.208305473873824, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3097, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11686586985391766, | |
| "grad_norm": 2.0792264874760193, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.2968, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12749003984063745, | |
| "grad_norm": 7.712252689421062, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2859, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13811420982735723, | |
| "grad_norm": 0.9497642120720764, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.2974, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14873837981407703, | |
| "grad_norm": 0.9147721663929693, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.2803, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1593625498007968, | |
| "grad_norm": 0.4984711347806819, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.2721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1699867197875166, | |
| "grad_norm": 0.471047244087332, | |
| "learning_rate": 4e-05, | |
| "loss": 0.262, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1806108897742364, | |
| "grad_norm": 0.472154205638306, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.2638, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19123505976095617, | |
| "grad_norm": 0.4625092675068189, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.2591, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20185922974767595, | |
| "grad_norm": 0.4996392904070069, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.2571, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.21248339973439576, | |
| "grad_norm": 1.0428146077253466, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2487, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22310756972111553, | |
| "grad_norm": 0.45426198900774195, | |
| "learning_rate": 4.9809160305343514e-05, | |
| "loss": 0.2523, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2337317397078353, | |
| "grad_norm": 0.3580171632863205, | |
| "learning_rate": 4.9618320610687025e-05, | |
| "loss": 0.2435, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24435590969455512, | |
| "grad_norm": 0.3537567495590767, | |
| "learning_rate": 4.9427480916030536e-05, | |
| "loss": 0.2411, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2549800796812749, | |
| "grad_norm": 0.3233498171110322, | |
| "learning_rate": 4.923664122137405e-05, | |
| "loss": 0.2319, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2656042496679947, | |
| "grad_norm": 0.26847478370421396, | |
| "learning_rate": 4.904580152671756e-05, | |
| "loss": 0.2401, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27622841965471445, | |
| "grad_norm": 0.22622668691998796, | |
| "learning_rate": 4.885496183206107e-05, | |
| "loss": 0.2339, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2868525896414343, | |
| "grad_norm": 0.17447662466704217, | |
| "learning_rate": 4.866412213740458e-05, | |
| "loss": 0.2334, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.29747675962815406, | |
| "grad_norm": 0.1406444973947631, | |
| "learning_rate": 4.847328244274809e-05, | |
| "loss": 0.2325, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.30810092961487384, | |
| "grad_norm": 0.15551008923115225, | |
| "learning_rate": 4.82824427480916e-05, | |
| "loss": 0.2312, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3187250996015936, | |
| "grad_norm": 0.1363375689910322, | |
| "learning_rate": 4.809160305343512e-05, | |
| "loss": 0.231, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3293492695883134, | |
| "grad_norm": 0.1701602959944274, | |
| "learning_rate": 4.7900763358778626e-05, | |
| "loss": 0.2293, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3399734395750332, | |
| "grad_norm": 0.13622900372630573, | |
| "learning_rate": 4.7709923664122144e-05, | |
| "loss": 0.2248, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.350597609561753, | |
| "grad_norm": 0.15128152543667112, | |
| "learning_rate": 4.751908396946565e-05, | |
| "loss": 0.2306, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3612217795484728, | |
| "grad_norm": 0.15811875642520323, | |
| "learning_rate": 4.7328244274809166e-05, | |
| "loss": 0.2321, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.37184594953519257, | |
| "grad_norm": 0.12645178389747586, | |
| "learning_rate": 4.713740458015267e-05, | |
| "loss": 0.2208, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.38247011952191234, | |
| "grad_norm": 0.12862564367197982, | |
| "learning_rate": 4.694656488549619e-05, | |
| "loss": 0.223, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3930942895086321, | |
| "grad_norm": 0.1369002410151976, | |
| "learning_rate": 4.675572519083969e-05, | |
| "loss": 0.2271, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4037184594953519, | |
| "grad_norm": 0.14767255168536392, | |
| "learning_rate": 4.656488549618321e-05, | |
| "loss": 0.2252, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.41434262948207173, | |
| "grad_norm": 0.13483775474592635, | |
| "learning_rate": 4.637404580152672e-05, | |
| "loss": 0.2256, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4249667994687915, | |
| "grad_norm": 0.14826458237724738, | |
| "learning_rate": 4.618320610687023e-05, | |
| "loss": 0.2191, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4355909694555113, | |
| "grad_norm": 0.12640771132223902, | |
| "learning_rate": 4.5992366412213745e-05, | |
| "loss": 0.2222, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.44621513944223107, | |
| "grad_norm": 0.12735423736878446, | |
| "learning_rate": 4.5801526717557256e-05, | |
| "loss": 0.215, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.45683930942895085, | |
| "grad_norm": 0.12856119123995918, | |
| "learning_rate": 4.561068702290077e-05, | |
| "loss": 0.2229, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4674634794156706, | |
| "grad_norm": 0.10294046565924951, | |
| "learning_rate": 4.541984732824428e-05, | |
| "loss": 0.2176, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.47808764940239046, | |
| "grad_norm": 0.15050659721187953, | |
| "learning_rate": 4.522900763358779e-05, | |
| "loss": 0.221, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.48871181938911024, | |
| "grad_norm": 0.11127436955612696, | |
| "learning_rate": 4.5038167938931294e-05, | |
| "loss": 0.2202, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.49933598937583, | |
| "grad_norm": 0.1369522376895646, | |
| "learning_rate": 4.484732824427481e-05, | |
| "loss": 0.2133, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5099601593625498, | |
| "grad_norm": 0.13836598803647265, | |
| "learning_rate": 4.465648854961832e-05, | |
| "loss": 0.2155, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5205843293492696, | |
| "grad_norm": 0.11643639323464662, | |
| "learning_rate": 4.4465648854961834e-05, | |
| "loss": 0.2152, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5312084993359893, | |
| "grad_norm": 0.13132395588523518, | |
| "learning_rate": 4.4274809160305345e-05, | |
| "loss": 0.2107, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5418326693227091, | |
| "grad_norm": 0.11238359379346577, | |
| "learning_rate": 4.408396946564886e-05, | |
| "loss": 0.2137, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5524568393094289, | |
| "grad_norm": 0.17138814733946134, | |
| "learning_rate": 4.389312977099237e-05, | |
| "loss": 0.2154, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5630810092961488, | |
| "grad_norm": 0.1092235798281431, | |
| "learning_rate": 4.370229007633588e-05, | |
| "loss": 0.2112, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.5737051792828686, | |
| "grad_norm": 0.11289137255732332, | |
| "learning_rate": 4.351145038167939e-05, | |
| "loss": 0.2122, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.5843293492695883, | |
| "grad_norm": 0.1025053581338601, | |
| "learning_rate": 4.332061068702291e-05, | |
| "loss": 0.2168, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5949535192563081, | |
| "grad_norm": 0.11102992105384238, | |
| "learning_rate": 4.312977099236641e-05, | |
| "loss": 0.2135, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6055776892430279, | |
| "grad_norm": 0.12567758664033069, | |
| "learning_rate": 4.293893129770993e-05, | |
| "loss": 0.211, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6162018592297477, | |
| "grad_norm": 0.11349920644602123, | |
| "learning_rate": 4.2748091603053435e-05, | |
| "loss": 0.2115, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6268260292164675, | |
| "grad_norm": 0.12916314836096926, | |
| "learning_rate": 4.255725190839695e-05, | |
| "loss": 0.2208, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6374501992031872, | |
| "grad_norm": 0.09752976352934666, | |
| "learning_rate": 4.236641221374046e-05, | |
| "loss": 0.2082, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.648074369189907, | |
| "grad_norm": 0.13511089875393836, | |
| "learning_rate": 4.2175572519083975e-05, | |
| "loss": 0.2081, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6586985391766268, | |
| "grad_norm": 0.10709804722840903, | |
| "learning_rate": 4.198473282442748e-05, | |
| "loss": 0.2089, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.6693227091633466, | |
| "grad_norm": 0.11164046629150956, | |
| "learning_rate": 4.1793893129771e-05, | |
| "loss": 0.212, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.6799468791500664, | |
| "grad_norm": 0.11504623760720377, | |
| "learning_rate": 4.160305343511451e-05, | |
| "loss": 0.2104, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.6905710491367862, | |
| "grad_norm": 0.1056951553011598, | |
| "learning_rate": 4.1412213740458014e-05, | |
| "loss": 0.2095, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.701195219123506, | |
| "grad_norm": 0.11902910166095262, | |
| "learning_rate": 4.122137404580153e-05, | |
| "loss": 0.21, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7118193891102258, | |
| "grad_norm": 0.11888528499779406, | |
| "learning_rate": 4.1030534351145036e-05, | |
| "loss": 0.2074, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7224435590969456, | |
| "grad_norm": 0.11792907862935477, | |
| "learning_rate": 4.0839694656488554e-05, | |
| "loss": 0.2074, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7330677290836654, | |
| "grad_norm": 0.12123246786138824, | |
| "learning_rate": 4.064885496183206e-05, | |
| "loss": 0.2117, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7436918990703851, | |
| "grad_norm": 0.11548221744093704, | |
| "learning_rate": 4.0458015267175576e-05, | |
| "loss": 0.2152, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7543160690571049, | |
| "grad_norm": 0.11744546618963372, | |
| "learning_rate": 4.026717557251908e-05, | |
| "loss": 0.2102, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.7649402390438247, | |
| "grad_norm": 0.1129425013506569, | |
| "learning_rate": 4.00763358778626e-05, | |
| "loss": 0.2084, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.7755644090305445, | |
| "grad_norm": 0.11061564445479172, | |
| "learning_rate": 3.988549618320611e-05, | |
| "loss": 0.2077, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.7861885790172642, | |
| "grad_norm": 0.12747716190819824, | |
| "learning_rate": 3.969465648854962e-05, | |
| "loss": 0.2065, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.796812749003984, | |
| "grad_norm": 0.11144908828621163, | |
| "learning_rate": 3.950381679389313e-05, | |
| "loss": 0.2106, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8074369189907038, | |
| "grad_norm": 0.10477648755637319, | |
| "learning_rate": 3.9312977099236644e-05, | |
| "loss": 0.2126, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8180610889774237, | |
| "grad_norm": 0.12819412448665685, | |
| "learning_rate": 3.9122137404580155e-05, | |
| "loss": 0.2079, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8286852589641435, | |
| "grad_norm": 0.11200327130647701, | |
| "learning_rate": 3.8931297709923666e-05, | |
| "loss": 0.2092, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8393094289508632, | |
| "grad_norm": 0.10297552490298816, | |
| "learning_rate": 3.874045801526718e-05, | |
| "loss": 0.2024, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.849933598937583, | |
| "grad_norm": 0.11622087800076612, | |
| "learning_rate": 3.854961832061069e-05, | |
| "loss": 0.2041, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8605577689243028, | |
| "grad_norm": 0.12063464037416519, | |
| "learning_rate": 3.83587786259542e-05, | |
| "loss": 0.2139, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.8711819389110226, | |
| "grad_norm": 0.10545414252113708, | |
| "learning_rate": 3.816793893129771e-05, | |
| "loss": 0.207, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.8818061088977424, | |
| "grad_norm": 0.11873399276296229, | |
| "learning_rate": 3.797709923664122e-05, | |
| "loss": 0.2114, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.8924302788844621, | |
| "grad_norm": 0.12163297981289363, | |
| "learning_rate": 3.778625954198473e-05, | |
| "loss": 0.2088, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9030544488711819, | |
| "grad_norm": 0.11583886378919572, | |
| "learning_rate": 3.7595419847328244e-05, | |
| "loss": 0.2097, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9136786188579017, | |
| "grad_norm": 0.11870676027662425, | |
| "learning_rate": 3.7404580152671756e-05, | |
| "loss": 0.1982, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9243027888446215, | |
| "grad_norm": 0.1188545663258694, | |
| "learning_rate": 3.721374045801527e-05, | |
| "loss": 0.2006, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9349269588313412, | |
| "grad_norm": 0.11078800000682179, | |
| "learning_rate": 3.702290076335878e-05, | |
| "loss": 0.2011, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.9455511288180611, | |
| "grad_norm": 0.11154286597122227, | |
| "learning_rate": 3.683206106870229e-05, | |
| "loss": 0.2011, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.9561752988047809, | |
| "grad_norm": 0.10658131888410093, | |
| "learning_rate": 3.66412213740458e-05, | |
| "loss": 0.2048, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.9667994687915007, | |
| "grad_norm": 0.09993801688648761, | |
| "learning_rate": 3.645038167938932e-05, | |
| "loss": 0.2049, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.9774236387782205, | |
| "grad_norm": 0.11005954464067705, | |
| "learning_rate": 3.625954198473282e-05, | |
| "loss": 0.208, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.9880478087649402, | |
| "grad_norm": 0.10245543326903217, | |
| "learning_rate": 3.606870229007634e-05, | |
| "loss": 0.204, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.99867197875166, | |
| "grad_norm": 0.1163495155338574, | |
| "learning_rate": 3.5877862595419845e-05, | |
| "loss": 0.2037, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.99867197875166, | |
| "eval_loss": 1.6727522611618042, | |
| "eval_runtime": 38.3479, | |
| "eval_samples_per_second": 62.715, | |
| "eval_steps_per_second": 1.982, | |
| "step": 94 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 282, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 94, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8221787935132877e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |