| { | |
| "best_metric": 1.2822918891906738, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 1.7122507122507122, | |
| "eval_steps": 25, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011396011396011397, | |
| "grad_norm": 1.242348313331604, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.422, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011396011396011397, | |
| "eval_loss": 3.177332878112793, | |
| "eval_runtime": 3.7731, | |
| "eval_samples_per_second": 13.252, | |
| "eval_steps_per_second": 1.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 1.8322075605392456, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.5783, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 2.020585298538208, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.6564, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 2.5826776027679443, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.8498, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05698005698005698, | |
| "grad_norm": 2.6277267932891846, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 2.108013391494751, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.5327, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07977207977207977, | |
| "grad_norm": 1.871590495109558, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.6416, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 1.4747263193130493, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2568, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 1.4162403345108032, | |
| "learning_rate": 0.00027, | |
| "loss": 2.1993, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 1.840993881225586, | |
| "learning_rate": 0.0003, | |
| "loss": 2.2469, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12535612535612536, | |
| "grad_norm": 1.7273625135421753, | |
| "learning_rate": 0.0002999731384004606, | |
| "loss": 2.2418, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 1.926708459854126, | |
| "learning_rate": 0.0002998925632224497, | |
| "loss": 2.2026, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 1.9321305751800537, | |
| "learning_rate": 0.00029975830332434265, | |
| "loss": 1.9119, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 2.490229368209839, | |
| "learning_rate": 0.00029957040679194776, | |
| "loss": 2.0595, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 1.834265947341919, | |
| "learning_rate": 0.00029932894092128383, | |
| "loss": 1.7713, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 1.866288661956787, | |
| "learning_rate": 0.0002990339921944777, | |
| "loss": 1.788, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19373219373219372, | |
| "grad_norm": 2.058414936065674, | |
| "learning_rate": 0.00029868566624879054, | |
| "loss": 2.2457, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.0486984252929688, | |
| "learning_rate": 0.00029828408783878324, | |
| "loss": 1.6807, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21652421652421652, | |
| "grad_norm": 2.277202844619751, | |
| "learning_rate": 0.00029782940079163485, | |
| "loss": 1.3828, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 4.133257865905762, | |
| "learning_rate": 0.00029732176795563037, | |
| "loss": 1.7191, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 4.480098247528076, | |
| "learning_rate": 0.0002967613711418359, | |
| "loss": 2.2437, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 7.444812774658203, | |
| "learning_rate": 0.000296148411058982, | |
| "loss": 2.8992, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2621082621082621, | |
| "grad_norm": 4.207739353179932, | |
| "learning_rate": 0.00029548310724157904, | |
| "loss": 2.5165, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 3.196674108505249, | |
| "learning_rate": 0.0002947656979712899, | |
| "loss": 2.3562, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "grad_norm": 2.0648515224456787, | |
| "learning_rate": 0.0002939964401915884, | |
| "loss": 2.3079, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "eval_loss": 2.0342981815338135, | |
| "eval_runtime": 2.5329, | |
| "eval_samples_per_second": 19.74, | |
| "eval_steps_per_second": 2.764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 1.3079276084899902, | |
| "learning_rate": 0.0002931756094157332, | |
| "loss": 2.0207, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.369789958000183, | |
| "learning_rate": 0.0002923034996280924, | |
| "loss": 1.9252, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3190883190883191, | |
| "grad_norm": 1.2784935235977173, | |
| "learning_rate": 0.0002913804231788509, | |
| "loss": 2.0475, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.33048433048433046, | |
| "grad_norm": 1.2535200119018555, | |
| "learning_rate": 0.00029040671067214087, | |
| "loss": 1.721, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 1.2530908584594727, | |
| "learning_rate": 0.0002893827108476348, | |
| "loss": 1.7821, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35327635327635326, | |
| "grad_norm": 1.2298803329467773, | |
| "learning_rate": 0.000288308790455642, | |
| "loss": 1.8249, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3646723646723647, | |
| "grad_norm": 1.3265615701675415, | |
| "learning_rate": 0.00028718533412575606, | |
| "loss": 1.6928, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.37606837606837606, | |
| "grad_norm": 1.251693606376648, | |
| "learning_rate": 0.00028601274422909733, | |
| "loss": 1.6522, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38746438746438744, | |
| "grad_norm": 1.5398131608963013, | |
| "learning_rate": 0.00028479144073420234, | |
| "loss": 1.6683, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39886039886039887, | |
| "grad_norm": 1.4659887552261353, | |
| "learning_rate": 0.0002835218610566095, | |
| "loss": 1.8089, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 1.523636817932129, | |
| "learning_rate": 0.0002822044599021973, | |
| "loss": 1.5808, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42165242165242167, | |
| "grad_norm": 1.5644186735153198, | |
| "learning_rate": 0.0002808397091043291, | |
| "loss": 1.5013, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.43304843304843305, | |
| "grad_norm": 1.8397467136383057, | |
| "learning_rate": 0.00027942809745486343, | |
| "loss": 1.6593, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.4349550008773804, | |
| "learning_rate": 0.0002779701305290915, | |
| "loss": 1.1733, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45584045584045585, | |
| "grad_norm": 1.55949068069458, | |
| "learning_rate": 0.00027646633050466265, | |
| "loss": 1.2653, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4672364672364672, | |
| "grad_norm": 2.077700614929199, | |
| "learning_rate": 0.0002749172359745641, | |
| "loss": 1.3511, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47863247863247865, | |
| "grad_norm": 4.83554744720459, | |
| "learning_rate": 0.0002733234017542215, | |
| "loss": 2.2896, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.49002849002849, | |
| "grad_norm": 4.110280513763428, | |
| "learning_rate": 0.0002716853986827888, | |
| "loss": 2.4133, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5014245014245015, | |
| "grad_norm": 2.6813883781433105, | |
| "learning_rate": 0.0002700038134187002, | |
| "loss": 2.3927, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 2.2160282135009766, | |
| "learning_rate": 0.00026827924822955487, | |
| "loss": 2.1391, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5242165242165242, | |
| "grad_norm": 1.5930802822113037, | |
| "learning_rate": 0.0002665123207764128, | |
| "loss": 1.9937, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5356125356125356, | |
| "grad_norm": 1.3064656257629395, | |
| "learning_rate": 0.00026470366389257614, | |
| "loss": 1.7019, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5470085470085471, | |
| "grad_norm": 1.0493654012680054, | |
| "learning_rate": 0.0002628539253569372, | |
| "loss": 1.976, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5584045584045584, | |
| "grad_norm": 1.2099847793579102, | |
| "learning_rate": 0.00026096376766197307, | |
| "loss": 1.9622, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "grad_norm": 1.1180739402770996, | |
| "learning_rate": 0.00025903386777647154, | |
| "loss": 1.8666, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5698005698005698, | |
| "eval_loss": 1.7883830070495605, | |
| "eval_runtime": 2.5361, | |
| "eval_samples_per_second": 19.716, | |
| "eval_steps_per_second": 2.76, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5811965811965812, | |
| "grad_norm": 1.0719735622406006, | |
| "learning_rate": 0.0002570649169030708, | |
| "loss": 1.8955, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.078503966331482, | |
| "learning_rate": 0.0002550576202307026, | |
| "loss": 1.5589, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.603988603988604, | |
| "grad_norm": 1.1071960926055908, | |
| "learning_rate": 0.00025301269668202516, | |
| "loss": 1.546, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.0681451559066772, | |
| "learning_rate": 0.0002509308786559378, | |
| "loss": 1.5604, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6267806267806267, | |
| "grad_norm": 1.173900842666626, | |
| "learning_rate": 0.00024881291176526903, | |
| "loss": 1.4711, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6381766381766382, | |
| "grad_norm": 1.070963740348816, | |
| "learning_rate": 0.00024665955456973154, | |
| "loss": 1.3633, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6495726495726496, | |
| "grad_norm": 1.2699030637741089, | |
| "learning_rate": 0.00024447157830424066, | |
| "loss": 1.4303, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6609686609686609, | |
| "grad_norm": 5.538363933563232, | |
| "learning_rate": 0.00024224976660269302, | |
| "loss": 1.7974, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6723646723646723, | |
| "grad_norm": 1.8669769763946533, | |
| "learning_rate": 0.0002399949152173043, | |
| "loss": 1.3754, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 1.68172287940979, | |
| "learning_rate": 0.00023770783173360704, | |
| "loss": 1.3149, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6951566951566952, | |
| "grad_norm": 1.3897011280059814, | |
| "learning_rate": 0.00023538933528120988, | |
| "loss": 1.0742, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7065527065527065, | |
| "grad_norm": 1.9569456577301025, | |
| "learning_rate": 0.00023304025624042263, | |
| "loss": 1.2155, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 3.3312759399414062, | |
| "learning_rate": 0.00023066143594485178, | |
| "loss": 2.1298, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7293447293447294, | |
| "grad_norm": 1.547868013381958, | |
| "learning_rate": 0.00022825372638007267, | |
| "loss": 2.2686, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.5944535732269287, | |
| "learning_rate": 0.0002258179898784871, | |
| "loss": 2.1082, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7521367521367521, | |
| "grad_norm": 1.5516560077667236, | |
| "learning_rate": 0.00022335509881047497, | |
| "loss": 2.0809, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7635327635327636, | |
| "grad_norm": 1.4995073080062866, | |
| "learning_rate": 0.00022086593527195062, | |
| "loss": 2.0216, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7749287749287749, | |
| "grad_norm": 1.274309754371643, | |
| "learning_rate": 0.00021835139076843623, | |
| "loss": 1.8188, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7863247863247863, | |
| "grad_norm": 0.9307559132575989, | |
| "learning_rate": 0.00021581236589576476, | |
| "loss": 1.6062, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7977207977207977, | |
| "grad_norm": 1.0454336404800415, | |
| "learning_rate": 0.00021324977001752757, | |
| "loss": 1.5165, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8091168091168092, | |
| "grad_norm": 0.9848281145095825, | |
| "learning_rate": 0.00021066452093938153, | |
| "loss": 1.5541, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 1.0764801502227783, | |
| "learning_rate": 0.0002080575445803326, | |
| "loss": 1.511, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8319088319088319, | |
| "grad_norm": 1.072153091430664, | |
| "learning_rate": 0.00020542977464111352, | |
| "loss": 1.6469, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8433048433048433, | |
| "grad_norm": 1.0326112508773804, | |
| "learning_rate": 0.00020278215226977493, | |
| "loss": 1.5988, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 1.093682050704956, | |
| "learning_rate": 0.0002001156257246085, | |
| "loss": 1.5237, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "eval_loss": 1.6302566528320312, | |
| "eval_runtime": 2.5336, | |
| "eval_samples_per_second": 19.735, | |
| "eval_steps_per_second": 2.763, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8660968660968661, | |
| "grad_norm": 1.018373727798462, | |
| "learning_rate": 0.00019743115003452357, | |
| "loss": 1.3891, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8774928774928775, | |
| "grad_norm": 1.1713063716888428, | |
| "learning_rate": 0.0001947296866569998, | |
| "loss": 1.0838, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.148584246635437, | |
| "learning_rate": 0.00019201220313373607, | |
| "loss": 1.4356, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.9002849002849003, | |
| "grad_norm": 1.1051701307296753, | |
| "learning_rate": 0.00018927967274412098, | |
| "loss": 1.1822, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.9116809116809117, | |
| "grad_norm": 1.3948734998703003, | |
| "learning_rate": 0.00018653307415664877, | |
| "loss": 1.2418, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.060866355895996, | |
| "learning_rate": 0.00018377339107840412, | |
| "loss": 0.9866, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.9344729344729344, | |
| "grad_norm": 1.3267959356307983, | |
| "learning_rate": 0.0001810016119027429, | |
| "loss": 1.2331, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9458689458689459, | |
| "grad_norm": 1.868615984916687, | |
| "learning_rate": 0.00017821872935529505, | |
| "loss": 1.0533, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9572649572649573, | |
| "grad_norm": 3.270871639251709, | |
| "learning_rate": 0.0001754257401384145, | |
| "loss": 1.6908, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9686609686609686, | |
| "grad_norm": 1.1830881834030151, | |
| "learning_rate": 0.00017262364457420608, | |
| "loss": 1.861, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.98005698005698, | |
| "grad_norm": 1.3552889823913574, | |
| "learning_rate": 0.00016981344624625536, | |
| "loss": 1.6788, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9914529914529915, | |
| "grad_norm": 1.6340991258621216, | |
| "learning_rate": 0.0001669961516401905, | |
| "loss": 1.0865, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.0056980056980056, | |
| "grad_norm": 2.1923134326934814, | |
| "learning_rate": 0.00016417276978320468, | |
| "loss": 2.0869, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.017094017094017, | |
| "grad_norm": 1.1427710056304932, | |
| "learning_rate": 0.00016134431188266851, | |
| "loss": 1.9375, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.0284900284900285, | |
| "grad_norm": 1.0332353115081787, | |
| "learning_rate": 0.00015851179096396112, | |
| "loss": 1.8373, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.03988603988604, | |
| "grad_norm": 1.0836644172668457, | |
| "learning_rate": 0.00015567622150765057, | |
| "loss": 1.8318, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.0512820512820513, | |
| "grad_norm": 0.9457873702049255, | |
| "learning_rate": 0.00015283861908615284, | |
| "loss": 1.4851, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.0626780626780628, | |
| "grad_norm": 0.8754853010177612, | |
| "learning_rate": 0.00015, | |
| "loss": 1.3744, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.074074074074074, | |
| "grad_norm": 0.7847860455513, | |
| "learning_rate": 0.00014716138091384716, | |
| "loss": 1.3702, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.0854700854700854, | |
| "grad_norm": 0.8638334274291992, | |
| "learning_rate": 0.00014432377849234946, | |
| "loss": 1.4673, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0968660968660968, | |
| "grad_norm": 0.8940455913543701, | |
| "learning_rate": 0.00014148820903603888, | |
| "loss": 1.2493, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.1082621082621082, | |
| "grad_norm": 0.8780096769332886, | |
| "learning_rate": 0.00013865568811733151, | |
| "loss": 1.3118, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.1196581196581197, | |
| "grad_norm": 0.9429007172584534, | |
| "learning_rate": 0.00013582723021679532, | |
| "loss": 1.255, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.131054131054131, | |
| "grad_norm": 1.0075204372406006, | |
| "learning_rate": 0.0001330038483598095, | |
| "loss": 1.112, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.1424501424501425, | |
| "grad_norm": 1.133158564567566, | |
| "learning_rate": 0.00013018655375374467, | |
| "loss": 1.175, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1424501424501425, | |
| "eval_loss": 1.5009154081344604, | |
| "eval_runtime": 2.8313, | |
| "eval_samples_per_second": 17.66, | |
| "eval_steps_per_second": 2.472, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 1.0093574523925781, | |
| "learning_rate": 0.00012737635542579392, | |
| "loss": 0.9741, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.1652421652421652, | |
| "grad_norm": 1.1475558280944824, | |
| "learning_rate": 0.00012457425986158547, | |
| "loss": 1.1514, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.1766381766381766, | |
| "grad_norm": 1.0175673961639404, | |
| "learning_rate": 0.00012178127064470495, | |
| "loss": 0.892, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.188034188034188, | |
| "grad_norm": 1.1485775709152222, | |
| "learning_rate": 0.00011899838809725704, | |
| "loss": 0.9361, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.1994301994301995, | |
| "grad_norm": 1.1438003778457642, | |
| "learning_rate": 0.00011622660892159588, | |
| "loss": 1.0521, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.210826210826211, | |
| "grad_norm": 1.055317997932434, | |
| "learning_rate": 0.0001134669258433512, | |
| "loss": 0.7935, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 1.357569932937622, | |
| "learning_rate": 0.00011072032725587898, | |
| "loss": 0.7351, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.2336182336182335, | |
| "grad_norm": 2.4943761825561523, | |
| "learning_rate": 0.00010798779686626394, | |
| "loss": 1.2773, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.245014245014245, | |
| "grad_norm": 1.9703893661499023, | |
| "learning_rate": 0.0001052703133430002, | |
| "loss": 1.7024, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.2564102564102564, | |
| "grad_norm": 1.2065763473510742, | |
| "learning_rate": 0.00010256884996547639, | |
| "loss": 1.7203, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.2678062678062678, | |
| "grad_norm": 1.4649949073791504, | |
| "learning_rate": 9.988437427539152e-05, | |
| "loss": 1.7926, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.2792022792022792, | |
| "grad_norm": 1.2466754913330078, | |
| "learning_rate": 9.721784773022504e-05, | |
| "loss": 1.805, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.2905982905982907, | |
| "grad_norm": 1.2706060409545898, | |
| "learning_rate": 9.457022535888646e-05, | |
| "loss": 1.4421, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.301994301994302, | |
| "grad_norm": 1.3075103759765625, | |
| "learning_rate": 9.194245541966741e-05, | |
| "loss": 1.3973, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.3133903133903133, | |
| "grad_norm": 1.1189782619476318, | |
| "learning_rate": 8.933547906061846e-05, | |
| "loss": 1.4012, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3247863247863247, | |
| "grad_norm": 1.4372056722640991, | |
| "learning_rate": 8.675022998247239e-05, | |
| "loss": 1.4232, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.3361823361823362, | |
| "grad_norm": 1.2321964502334595, | |
| "learning_rate": 8.418763410423521e-05, | |
| "loss": 1.1983, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.3475783475783476, | |
| "grad_norm": 1.393195390701294, | |
| "learning_rate": 8.164860923156377e-05, | |
| "loss": 1.1489, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.358974358974359, | |
| "grad_norm": 1.1735514402389526, | |
| "learning_rate": 7.913406472804938e-05, | |
| "loss": 1.1197, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.3703703703703702, | |
| "grad_norm": 1.2319945096969604, | |
| "learning_rate": 7.664490118952502e-05, | |
| "loss": 1.2014, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.381766381766382, | |
| "grad_norm": 1.0852819681167603, | |
| "learning_rate": 7.418201012151291e-05, | |
| "loss": 0.957, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.393162393162393, | |
| "grad_norm": 1.0578720569610596, | |
| "learning_rate": 7.174627361992732e-05, | |
| "loss": 0.9002, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.4045584045584045, | |
| "grad_norm": 1.19394052028656, | |
| "learning_rate": 6.933856405514818e-05, | |
| "loss": 0.869, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.415954415954416, | |
| "grad_norm": 1.4179712533950806, | |
| "learning_rate": 6.695974375957732e-05, | |
| "loss": 0.8395, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.4273504273504274, | |
| "grad_norm": 1.5434173345565796, | |
| "learning_rate": 6.461066471879014e-05, | |
| "loss": 0.9276, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4273504273504274, | |
| "eval_loss": 1.3488426208496094, | |
| "eval_runtime": 2.8312, | |
| "eval_samples_per_second": 17.661, | |
| "eval_steps_per_second": 2.472, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.4387464387464388, | |
| "grad_norm": 1.3119511604309082, | |
| "learning_rate": 6.229216826639293e-05, | |
| "loss": 0.864, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.45014245014245, | |
| "grad_norm": 1.39320707321167, | |
| "learning_rate": 6.000508478269568e-05, | |
| "loss": 0.8115, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 1.4658546447753906, | |
| "learning_rate": 5.775023339730696e-05, | |
| "loss": 0.7579, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.4729344729344729, | |
| "grad_norm": 2.2543859481811523, | |
| "learning_rate": 5.552842169575929e-05, | |
| "loss": 0.8667, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.4843304843304843, | |
| "grad_norm": 1.626423716545105, | |
| "learning_rate": 5.3340445430268436e-05, | |
| "loss": 1.4114, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.4957264957264957, | |
| "grad_norm": 1.1121342182159424, | |
| "learning_rate": 5.118708823473095e-05, | |
| "loss": 1.5799, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.5071225071225072, | |
| "grad_norm": 1.16105318069458, | |
| "learning_rate": 4.906912134406216e-05, | |
| "loss": 1.4849, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.5185185185185186, | |
| "grad_norm": 1.185447335243225, | |
| "learning_rate": 4.6987303317974865e-05, | |
| "loss": 1.4004, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.5299145299145298, | |
| "grad_norm": 1.2638546228408813, | |
| "learning_rate": 4.4942379769297414e-05, | |
| "loss": 1.3315, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.5413105413105415, | |
| "grad_norm": 1.316292405128479, | |
| "learning_rate": 4.293508309692913e-05, | |
| "loss": 1.3905, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.5527065527065527, | |
| "grad_norm": 1.37898850440979, | |
| "learning_rate": 4.096613222352843e-05, | |
| "loss": 1.2715, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.564102564102564, | |
| "grad_norm": 1.1590007543563843, | |
| "learning_rate": 3.90362323380269e-05, | |
| "loss": 1.0867, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.5754985754985755, | |
| "grad_norm": 1.10092031955719, | |
| "learning_rate": 3.714607464306281e-05, | |
| "loss": 1.0965, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.5868945868945867, | |
| "grad_norm": 2.0354859828948975, | |
| "learning_rate": 3.529633610742382e-05, | |
| "loss": 0.9744, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.5982905982905984, | |
| "grad_norm": 1.2980939149856567, | |
| "learning_rate": 3.348767922358719e-05, | |
| "loss": 1.0778, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.6096866096866096, | |
| "grad_norm": 1.143785834312439, | |
| "learning_rate": 3.172075177044513e-05, | |
| "loss": 1.0259, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.6210826210826212, | |
| "grad_norm": 1.204784870147705, | |
| "learning_rate": 2.9996186581299824e-05, | |
| "loss": 0.9, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.6324786324786325, | |
| "grad_norm": 1.0703641176223755, | |
| "learning_rate": 2.831460131721116e-05, | |
| "loss": 0.8159, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.6438746438746439, | |
| "grad_norm": 1.161806583404541, | |
| "learning_rate": 2.6676598245778498e-05, | |
| "loss": 0.9118, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.6552706552706553, | |
| "grad_norm": 1.3269273042678833, | |
| "learning_rate": 2.5082764025435865e-05, | |
| "loss": 1.0347, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.4473638534545898, | |
| "learning_rate": 2.353366949533736e-05, | |
| "loss": 1.0452, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.6780626780626782, | |
| "grad_norm": 1.5314830541610718, | |
| "learning_rate": 2.20298694709085e-05, | |
| "loss": 0.888, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.6894586894586894, | |
| "grad_norm": 1.3223233222961426, | |
| "learning_rate": 2.0571902545136565e-05, | |
| "loss": 0.7846, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.7008547008547008, | |
| "grad_norm": 1.436808705329895, | |
| "learning_rate": 1.9160290895670937e-05, | |
| "loss": 0.6303, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.7122507122507122, | |
| "grad_norm": 2.25252103805542, | |
| "learning_rate": 1.7795540097802668e-05, | |
| "loss": 1.0496, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7122507122507122, | |
| "eval_loss": 1.2822918891906738, | |
| "eval_runtime": 2.5321, | |
| "eval_samples_per_second": 19.747, | |
| "eval_steps_per_second": 2.765, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 176, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.669377994561946e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |