diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,5255 +1,6662 @@ { - "best_global_step": 744, - "best_metric": 0.9021978021978022, - "best_model_checkpoint": "./albert_multilabel_base\\checkpoint-744", + "best_global_step": 945, + "best_metric": 0.9067245119305856, + "best_model_checkpoint": "./albert_multilabel_base\\checkpoint-945", "epoch": 3.0, "eval_steps": 500, - "global_step": 744, + "global_step": 945, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { - "epoch": 0.004032258064516129, - "grad_norm": 4.463273525238037, - "learning_rate": 1.9973118279569895e-05, - "loss": 0.6697, + "epoch": 0.0031746031746031746, + "grad_norm": 5.873334884643555, + "learning_rate": 1.9978835978835978e-05, + "loss": 0.7415, "step": 1 }, { - "epoch": 0.008064516129032258, - "grad_norm": 4.188074111938477, - "learning_rate": 1.9946236559139788e-05, - "loss": 0.618, + "epoch": 0.006349206349206349, + "grad_norm": 3.8492350578308105, + "learning_rate": 1.995767195767196e-05, + "loss": 0.641, "step": 2 }, { - "epoch": 0.012096774193548387, - "grad_norm": 4.5477166175842285, - "learning_rate": 1.9919354838709678e-05, - "loss": 0.5686, + "epoch": 0.009523809523809525, + "grad_norm": 5.353137969970703, + "learning_rate": 1.9936507936507938e-05, + "loss": 0.6094, "step": 3 }, { - "epoch": 0.016129032258064516, - "grad_norm": 3.3298499584198, - "learning_rate": 1.989247311827957e-05, - "loss": 0.5691, + "epoch": 0.012698412698412698, + "grad_norm": 5.4316205978393555, + "learning_rate": 1.9915343915343918e-05, + "loss": 0.5962, "step": 4 }, { - "epoch": 0.020161290322580645, - "grad_norm": 3.3022494316101074, - "learning_rate": 1.9865591397849465e-05, - "loss": 0.5157, + "epoch": 0.015873015873015872, + "grad_norm": 5.829203128814697, + "learning_rate": 1.9894179894179895e-05, + "loss": 0.5501, "step": 5 }, { - "epoch": 0.024193548387096774, - "grad_norm": 3.095808744430542, - "learning_rate": 1.9838709677419358e-05, - "loss": 0.4709, + "epoch": 0.01904761904761905, + "grad_norm": 4.358727931976318, + "learning_rate": 1.9873015873015875e-05, + "loss": 0.545, "step": 6 }, { - "epoch": 0.028225806451612902, - "grad_norm": 2.8690195083618164, - "learning_rate": 1.9811827956989248e-05, - "loss": 0.4679, + "epoch": 0.022222222222222223, + "grad_norm": 4.357857704162598, + "learning_rate": 1.9851851851851855e-05, + "loss": 0.5061, "step": 7 }, { - "epoch": 0.03225806451612903, - "grad_norm": 2.376504898071289, - "learning_rate": 1.978494623655914e-05, - "loss": 0.4801, + "epoch": 0.025396825396825397, + "grad_norm": 4.403970718383789, + "learning_rate": 1.983068783068783e-05, + "loss": 0.5087, "step": 8 }, { - "epoch": 0.036290322580645164, - "grad_norm": 2.947565793991089, - "learning_rate": 1.9758064516129035e-05, - "loss": 0.4196, + "epoch": 0.02857142857142857, + "grad_norm": 3.005472183227539, + "learning_rate": 1.980952380952381e-05, + "loss": 0.4843, "step": 9 }, { - "epoch": 0.04032258064516129, - "grad_norm": 2.624013662338257, - "learning_rate": 1.9731182795698928e-05, - "loss": 0.3948, + "epoch": 0.031746031746031744, + "grad_norm": 3.458085536956787, + "learning_rate": 1.978835978835979e-05, + "loss": 0.4531, "step": 10 }, { - "epoch": 0.04435483870967742, - "grad_norm": 2.218142032623291, - "learning_rate": 1.9704301075268818e-05, - "loss": 0.3588, + "epoch": 0.03492063492063492, + "grad_norm": 2.9909160137176514, + "learning_rate": 1.9767195767195768e-05, + "loss": 0.4446, "step": 11 }, { - "epoch": 0.04838709677419355, - "grad_norm": 2.0879335403442383, - "learning_rate": 1.967741935483871e-05, - "loss": 0.3732, + "epoch": 0.0380952380952381, + "grad_norm": 2.683769702911377, + "learning_rate": 1.9746031746031748e-05, + "loss": 0.4209, "step": 12 }, { - "epoch": 0.05241935483870968, - "grad_norm": 1.8436014652252197, - "learning_rate": 1.9650537634408605e-05, - "loss": 0.3549, + "epoch": 0.04126984126984127, + "grad_norm": 2.373673677444458, + "learning_rate": 1.9724867724867728e-05, + "loss": 0.4255, "step": 13 }, { - "epoch": 0.056451612903225805, - "grad_norm": 2.7105393409729004, - "learning_rate": 1.9623655913978498e-05, - "loss": 0.3588, + "epoch": 0.044444444444444446, + "grad_norm": 2.1575582027435303, + "learning_rate": 1.9703703703703704e-05, + "loss": 0.4167, "step": 14 }, { - "epoch": 0.06048387096774194, - "grad_norm": 2.038672685623169, - "learning_rate": 1.9596774193548388e-05, - "loss": 0.3431, + "epoch": 0.047619047619047616, + "grad_norm": 2.3038744926452637, + "learning_rate": 1.9682539682539684e-05, + "loss": 0.4381, "step": 15 }, { - "epoch": 0.06451612903225806, - "grad_norm": 1.9189316034317017, - "learning_rate": 1.956989247311828e-05, - "loss": 0.3334, + "epoch": 0.050793650793650794, + "grad_norm": 1.905539631843567, + "learning_rate": 1.9661375661375664e-05, + "loss": 0.3931, "step": 16 }, { - "epoch": 0.06854838709677419, - "grad_norm": 1.5137898921966553, - "learning_rate": 1.9543010752688174e-05, - "loss": 0.3142, + "epoch": 0.05396825396825397, + "grad_norm": 2.117608070373535, + "learning_rate": 1.964021164021164e-05, + "loss": 0.4157, "step": 17 }, { - "epoch": 0.07258064516129033, - "grad_norm": 1.6630574464797974, - "learning_rate": 1.9516129032258068e-05, - "loss": 0.3702, + "epoch": 0.05714285714285714, + "grad_norm": 2.0442044734954834, + "learning_rate": 1.961904761904762e-05, + "loss": 0.3664, "step": 18 }, { - "epoch": 0.07661290322580645, - "grad_norm": 1.7377407550811768, - "learning_rate": 1.9489247311827958e-05, - "loss": 0.3059, + "epoch": 0.06031746031746032, + "grad_norm": 2.372775077819824, + "learning_rate": 1.95978835978836e-05, + "loss": 0.3694, "step": 19 }, { - "epoch": 0.08064516129032258, - "grad_norm": 1.9414572715759277, - "learning_rate": 1.946236559139785e-05, - "loss": 0.3146, + "epoch": 0.06349206349206349, + "grad_norm": 1.7043017148971558, + "learning_rate": 1.9576719576719577e-05, + "loss": 0.4054, "step": 20 }, { - "epoch": 0.0846774193548387, - "grad_norm": 1.5869086980819702, - "learning_rate": 1.9435483870967744e-05, - "loss": 0.3053, + "epoch": 0.06666666666666667, + "grad_norm": 2.494601249694824, + "learning_rate": 1.9555555555555557e-05, + "loss": 0.3136, "step": 21 }, { - "epoch": 0.08870967741935484, - "grad_norm": 1.5989874601364136, - "learning_rate": 1.9408602150537638e-05, - "loss": 0.3022, + "epoch": 0.06984126984126984, + "grad_norm": 1.9976402521133423, + "learning_rate": 1.9534391534391537e-05, + "loss": 0.3434, "step": 22 }, { - "epoch": 0.09274193548387097, - "grad_norm": 2.2120656967163086, - "learning_rate": 1.9381720430107528e-05, - "loss": 0.3372, + "epoch": 0.07301587301587302, + "grad_norm": 2.0567805767059326, + "learning_rate": 1.9513227513227514e-05, + "loss": 0.3314, "step": 23 }, { - "epoch": 0.0967741935483871, - "grad_norm": 1.8420207500457764, - "learning_rate": 1.935483870967742e-05, - "loss": 0.2947, + "epoch": 0.0761904761904762, + "grad_norm": 3.78642201423645, + "learning_rate": 1.9492063492063494e-05, + "loss": 0.3232, "step": 24 }, { - "epoch": 0.10080645161290322, - "grad_norm": 1.324240803718567, - "learning_rate": 1.9327956989247314e-05, - "loss": 0.3117, + "epoch": 0.07936507936507936, + "grad_norm": 3.212415933609009, + "learning_rate": 1.947089947089947e-05, + "loss": 0.3604, "step": 25 }, { - "epoch": 0.10483870967741936, - "grad_norm": 1.3763035535812378, - "learning_rate": 1.9301075268817207e-05, - "loss": 0.3097, + "epoch": 0.08253968253968254, + "grad_norm": 1.7311122417449951, + "learning_rate": 1.944973544973545e-05, + "loss": 0.3974, "step": 26 }, { - "epoch": 0.10887096774193548, - "grad_norm": 1.13789963722229, - "learning_rate": 1.9274193548387097e-05, - "loss": 0.3073, + "epoch": 0.08571428571428572, + "grad_norm": 2.760939359664917, + "learning_rate": 1.942857142857143e-05, + "loss": 0.3272, "step": 27 }, { - "epoch": 0.11290322580645161, - "grad_norm": 1.8375061750411987, - "learning_rate": 1.924731182795699e-05, - "loss": 0.2729, + "epoch": 0.08888888888888889, + "grad_norm": 2.228309154510498, + "learning_rate": 1.9407407407407407e-05, + "loss": 0.2956, "step": 28 }, { - "epoch": 0.11693548387096774, - "grad_norm": 1.4714664220809937, - "learning_rate": 1.9220430107526884e-05, - "loss": 0.2884, + "epoch": 0.09206349206349207, + "grad_norm": 1.7933294773101807, + "learning_rate": 1.9386243386243387e-05, + "loss": 0.3595, "step": 29 }, { - "epoch": 0.12096774193548387, - "grad_norm": 1.7859275341033936, - "learning_rate": 1.9193548387096777e-05, - "loss": 0.2921, + "epoch": 0.09523809523809523, + "grad_norm": 1.4846535921096802, + "learning_rate": 1.9365079365079367e-05, + "loss": 0.3192, "step": 30 }, { - "epoch": 0.125, - "grad_norm": 1.1975992918014526, - "learning_rate": 1.916666666666667e-05, - "loss": 0.2999, + "epoch": 0.09841269841269841, + "grad_norm": 2.0749635696411133, + "learning_rate": 1.9343915343915343e-05, + "loss": 0.3091, "step": 31 }, { - "epoch": 0.12903225806451613, - "grad_norm": 1.1491625308990479, - "learning_rate": 1.913978494623656e-05, - "loss": 0.3037, + "epoch": 0.10158730158730159, + "grad_norm": 1.6887636184692383, + "learning_rate": 1.9322751322751327e-05, + "loss": 0.3104, "step": 32 }, { - "epoch": 0.13306451612903225, - "grad_norm": 1.7719403505325317, - "learning_rate": 1.9112903225806454e-05, - "loss": 0.3097, + "epoch": 0.10476190476190476, + "grad_norm": 2.527775764465332, + "learning_rate": 1.9301587301587303e-05, + "loss": 0.3251, "step": 33 }, { - "epoch": 0.13709677419354838, - "grad_norm": 2.003831148147583, - "learning_rate": 1.9086021505376347e-05, - "loss": 0.3419, + "epoch": 0.10793650793650794, + "grad_norm": 1.630950689315796, + "learning_rate": 1.928042328042328e-05, + "loss": 0.227, "step": 34 }, { - "epoch": 0.14112903225806453, - "grad_norm": 1.2528795003890991, - "learning_rate": 1.905913978494624e-05, - "loss": 0.3104, + "epoch": 0.1111111111111111, + "grad_norm": 1.3698337078094482, + "learning_rate": 1.925925925925926e-05, + "loss": 0.2475, "step": 35 }, { - "epoch": 0.14516129032258066, - "grad_norm": 1.9549521207809448, - "learning_rate": 1.903225806451613e-05, - "loss": 0.2948, + "epoch": 0.11428571428571428, + "grad_norm": 1.7205814123153687, + "learning_rate": 1.923809523809524e-05, + "loss": 0.3325, "step": 36 }, { - "epoch": 0.14919354838709678, - "grad_norm": 3.2783548831939697, - "learning_rate": 1.9005376344086024e-05, - "loss": 0.2442, + "epoch": 0.11746031746031746, + "grad_norm": 1.7424278259277344, + "learning_rate": 1.921693121693122e-05, + "loss": 0.3464, "step": 37 }, { - "epoch": 0.1532258064516129, - "grad_norm": 2.185920476913452, - "learning_rate": 1.8978494623655917e-05, - "loss": 0.2714, + "epoch": 0.12063492063492064, + "grad_norm": 2.311513900756836, + "learning_rate": 1.9195767195767196e-05, + "loss": 0.3085, "step": 38 }, { - "epoch": 0.15725806451612903, - "grad_norm": 1.0794386863708496, - "learning_rate": 1.895161290322581e-05, - "loss": 0.27, + "epoch": 0.12380952380952381, + "grad_norm": 1.5352858304977417, + "learning_rate": 1.9174603174603176e-05, + "loss": 0.2555, "step": 39 }, { - "epoch": 0.16129032258064516, - "grad_norm": 1.1620965003967285, - "learning_rate": 1.89247311827957e-05, - "loss": 0.2259, + "epoch": 0.12698412698412698, + "grad_norm": 1.770841360092163, + "learning_rate": 1.9153439153439156e-05, + "loss": 0.227, "step": 40 }, { - "epoch": 0.16532258064516128, - "grad_norm": 1.599996566772461, - "learning_rate": 1.8897849462365594e-05, - "loss": 0.2035, + "epoch": 0.13015873015873017, + "grad_norm": 1.5325216054916382, + "learning_rate": 1.9132275132275133e-05, + "loss": 0.3112, "step": 41 }, { - "epoch": 0.1693548387096774, - "grad_norm": 1.2780784368515015, - "learning_rate": 1.8870967741935487e-05, - "loss": 0.22, + "epoch": 0.13333333333333333, + "grad_norm": 2.6165037155151367, + "learning_rate": 1.9111111111111113e-05, + "loss": 0.2583, "step": 42 }, { - "epoch": 0.17338709677419356, - "grad_norm": 1.4363526105880737, - "learning_rate": 1.884408602150538e-05, - "loss": 0.2368, + "epoch": 0.1365079365079365, + "grad_norm": 3.5023488998413086, + "learning_rate": 1.9089947089947093e-05, + "loss": 0.2517, "step": 43 }, { - "epoch": 0.1774193548387097, - "grad_norm": 2.520078420639038, - "learning_rate": 1.881720430107527e-05, - "loss": 0.1892, + "epoch": 0.13968253968253969, + "grad_norm": 5.8022541999816895, + "learning_rate": 1.906878306878307e-05, + "loss": 0.224, "step": 44 }, { - "epoch": 0.1814516129032258, - "grad_norm": 1.2548242807388306, - "learning_rate": 1.8790322580645163e-05, - "loss": 0.2666, + "epoch": 0.14285714285714285, + "grad_norm": 4.037482261657715, + "learning_rate": 1.904761904761905e-05, + "loss": 0.3183, "step": 45 }, { - "epoch": 0.18548387096774194, - "grad_norm": 3.150402545928955, - "learning_rate": 1.8763440860215057e-05, - "loss": 0.2119, + "epoch": 0.14603174603174604, + "grad_norm": 4.820381164550781, + "learning_rate": 1.902645502645503e-05, + "loss": 0.3127, "step": 46 }, { - "epoch": 0.18951612903225806, - "grad_norm": 2.226469039916992, - "learning_rate": 1.8736559139784947e-05, - "loss": 0.2952, + "epoch": 0.1492063492063492, + "grad_norm": 31.217069625854492, + "learning_rate": 1.9005291005291006e-05, + "loss": 0.2682, "step": 47 }, { - "epoch": 0.1935483870967742, - "grad_norm": 2.2046310901641846, - "learning_rate": 1.870967741935484e-05, - "loss": 0.2089, + "epoch": 0.1523809523809524, + "grad_norm": 5.381537914276123, + "learning_rate": 1.8984126984126986e-05, + "loss": 0.2201, "step": 48 }, { - "epoch": 0.1975806451612903, - "grad_norm": 2.4914636611938477, - "learning_rate": 1.8682795698924733e-05, - "loss": 0.2622, + "epoch": 0.15555555555555556, + "grad_norm": 2.7507314682006836, + "learning_rate": 1.8962962962962966e-05, + "loss": 0.2608, "step": 49 }, { - "epoch": 0.20161290322580644, - "grad_norm": 1.6519418954849243, - "learning_rate": 1.8655913978494623e-05, - "loss": 0.2268, + "epoch": 0.15873015873015872, + "grad_norm": 1.940741777420044, + "learning_rate": 1.8941798941798943e-05, + "loss": 0.2613, "step": 50 }, { - "epoch": 0.2056451612903226, - "grad_norm": 2.803372383117676, - "learning_rate": 1.8629032258064517e-05, - "loss": 0.2628, + "epoch": 0.1619047619047619, + "grad_norm": 1.6945521831512451, + "learning_rate": 1.8920634920634923e-05, + "loss": 0.2661, "step": 51 }, { - "epoch": 0.20967741935483872, - "grad_norm": 1.6514664888381958, - "learning_rate": 1.860215053763441e-05, - "loss": 0.1742, + "epoch": 0.16507936507936508, + "grad_norm": 4.606514930725098, + "learning_rate": 1.8899470899470903e-05, + "loss": 0.2806, "step": 52 }, { - "epoch": 0.21370967741935484, - "grad_norm": 4.286014556884766, - "learning_rate": 1.8575268817204303e-05, - "loss": 0.3353, + "epoch": 0.16825396825396827, + "grad_norm": 1.9876173734664917, + "learning_rate": 1.887830687830688e-05, + "loss": 0.2937, "step": 53 }, { - "epoch": 0.21774193548387097, - "grad_norm": 1.3388841152191162, - "learning_rate": 1.8548387096774193e-05, - "loss": 0.193, + "epoch": 0.17142857142857143, + "grad_norm": 2.3264224529266357, + "learning_rate": 1.885714285714286e-05, + "loss": 0.2692, "step": 54 }, { - "epoch": 0.2217741935483871, - "grad_norm": 3.4638161659240723, - "learning_rate": 1.8521505376344086e-05, - "loss": 0.243, + "epoch": 0.1746031746031746, + "grad_norm": 1.6710952520370483, + "learning_rate": 1.8835978835978836e-05, + "loss": 0.2608, "step": 55 }, { - "epoch": 0.22580645161290322, - "grad_norm": 2.002242088317871, - "learning_rate": 1.849462365591398e-05, - "loss": 0.2098, + "epoch": 0.17777777777777778, + "grad_norm": 4.827817440032959, + "learning_rate": 1.8814814814814816e-05, + "loss": 0.237, "step": 56 }, { - "epoch": 0.22983870967741934, - "grad_norm": 2.865968942642212, - "learning_rate": 1.8467741935483873e-05, - "loss": 0.2875, + "epoch": 0.18095238095238095, + "grad_norm": 13.628049850463867, + "learning_rate": 1.8793650793650796e-05, + "loss": 0.2296, "step": 57 }, { - "epoch": 0.23387096774193547, - "grad_norm": 4.366675853729248, - "learning_rate": 1.8440860215053763e-05, - "loss": 0.1991, + "epoch": 0.18412698412698414, + "grad_norm": 2.3664677143096924, + "learning_rate": 1.8772486772486772e-05, + "loss": 0.261, "step": 58 }, { - "epoch": 0.23790322580645162, - "grad_norm": 3.3366456031799316, - "learning_rate": 1.8413978494623656e-05, - "loss": 0.2024, + "epoch": 0.1873015873015873, + "grad_norm": 3.718492031097412, + "learning_rate": 1.8751322751322752e-05, + "loss": 0.2448, "step": 59 }, { - "epoch": 0.24193548387096775, - "grad_norm": 3.0101261138916016, - "learning_rate": 1.838709677419355e-05, - "loss": 0.1529, + "epoch": 0.19047619047619047, + "grad_norm": 2.3620049953460693, + "learning_rate": 1.8730158730158732e-05, + "loss": 0.2308, "step": 60 }, { - "epoch": 0.24596774193548387, - "grad_norm": 1.7896872758865356, - "learning_rate": 1.8360215053763443e-05, - "loss": 0.1969, + "epoch": 0.19365079365079366, + "grad_norm": 4.279988765716553, + "learning_rate": 1.870899470899471e-05, + "loss": 0.282, "step": 61 }, { - "epoch": 0.25, - "grad_norm": 3.260681390762329, - "learning_rate": 1.8333333333333333e-05, - "loss": 0.2426, + "epoch": 0.19682539682539682, + "grad_norm": 4.543224334716797, + "learning_rate": 1.868783068783069e-05, + "loss": 0.2539, "step": 62 }, { - "epoch": 0.2540322580645161, - "grad_norm": 2.9987573623657227, - "learning_rate": 1.8306451612903226e-05, - "loss": 0.2763, + "epoch": 0.2, + "grad_norm": 3.09006929397583, + "learning_rate": 1.866666666666667e-05, + "loss": 0.3036, "step": 63 }, { - "epoch": 0.25806451612903225, - "grad_norm": 2.370321273803711, - "learning_rate": 1.827956989247312e-05, - "loss": 0.1721, + "epoch": 0.20317460317460317, + "grad_norm": 4.814393520355225, + "learning_rate": 1.8645502645502645e-05, + "loss": 0.3125, "step": 64 }, { - "epoch": 0.2620967741935484, - "grad_norm": 2.941296339035034, - "learning_rate": 1.8252688172043013e-05, - "loss": 0.2495, + "epoch": 0.20634920634920634, + "grad_norm": 4.603379726409912, + "learning_rate": 1.8624338624338625e-05, + "loss": 0.2309, "step": 65 }, { - "epoch": 0.2661290322580645, - "grad_norm": 2.7063724994659424, - "learning_rate": 1.8225806451612903e-05, - "loss": 0.1995, + "epoch": 0.20952380952380953, + "grad_norm": 3.806410789489746, + "learning_rate": 1.8603174603174605e-05, + "loss": 0.2269, "step": 66 }, { - "epoch": 0.2701612903225806, - "grad_norm": 2.6740007400512695, - "learning_rate": 1.8198924731182796e-05, - "loss": 0.1484, + "epoch": 0.2126984126984127, + "grad_norm": 3.9393911361694336, + "learning_rate": 1.8582010582010582e-05, + "loss": 0.2771, "step": 67 }, { - "epoch": 0.27419354838709675, - "grad_norm": 4.054372310638428, - "learning_rate": 1.817204301075269e-05, - "loss": 0.1958, + "epoch": 0.21587301587301588, + "grad_norm": 4.534191131591797, + "learning_rate": 1.8560846560846562e-05, + "loss": 0.1907, "step": 68 }, { - "epoch": 0.2782258064516129, - "grad_norm": 3.995595932006836, - "learning_rate": 1.8145161290322583e-05, - "loss": 0.1581, + "epoch": 0.21904761904761905, + "grad_norm": 1.9561638832092285, + "learning_rate": 1.853968253968254e-05, + "loss": 0.2155, "step": 69 }, { - "epoch": 0.28225806451612906, - "grad_norm": 4.279732704162598, - "learning_rate": 1.8118279569892473e-05, - "loss": 0.2051, + "epoch": 0.2222222222222222, + "grad_norm": 1.7607568502426147, + "learning_rate": 1.851851851851852e-05, + "loss": 0.261, "step": 70 }, { - "epoch": 0.2862903225806452, - "grad_norm": 2.194711446762085, - "learning_rate": 1.8091397849462366e-05, - "loss": 0.2699, + "epoch": 0.2253968253968254, + "grad_norm": 2.7111716270446777, + "learning_rate": 1.8497354497354498e-05, + "loss": 0.2359, "step": 71 }, { - "epoch": 0.2903225806451613, - "grad_norm": 2.1309289932250977, - "learning_rate": 1.806451612903226e-05, - "loss": 0.202, + "epoch": 0.22857142857142856, + "grad_norm": 2.541506290435791, + "learning_rate": 1.8476190476190478e-05, + "loss": 0.3044, "step": 72 }, { - "epoch": 0.29435483870967744, - "grad_norm": 4.026139259338379, - "learning_rate": 1.8037634408602153e-05, - "loss": 0.2346, + "epoch": 0.23174603174603176, + "grad_norm": 2.005059242248535, + "learning_rate": 1.8455026455026458e-05, + "loss": 0.2437, "step": 73 }, { - "epoch": 0.29838709677419356, - "grad_norm": 2.3642139434814453, - "learning_rate": 1.8010752688172042e-05, - "loss": 0.2095, + "epoch": 0.23492063492063492, + "grad_norm": 2.583658456802368, + "learning_rate": 1.8433862433862435e-05, + "loss": 0.2576, "step": 74 }, { - "epoch": 0.3024193548387097, - "grad_norm": 1.9105987548828125, - "learning_rate": 1.7983870967741936e-05, - "loss": 0.1839, + "epoch": 0.23809523809523808, + "grad_norm": 2.5794029235839844, + "learning_rate": 1.8412698412698415e-05, + "loss": 0.2768, "step": 75 }, { - "epoch": 0.3064516129032258, - "grad_norm": 1.926434874534607, - "learning_rate": 1.795698924731183e-05, - "loss": 0.1984, + "epoch": 0.24126984126984127, + "grad_norm": 3.1481902599334717, + "learning_rate": 1.8391534391534395e-05, + "loss": 0.2398, "step": 76 }, { - "epoch": 0.31048387096774194, - "grad_norm": 1.3975627422332764, - "learning_rate": 1.7930107526881722e-05, - "loss": 0.2008, + "epoch": 0.24444444444444444, + "grad_norm": 3.1876864433288574, + "learning_rate": 1.837037037037037e-05, + "loss": 0.2659, "step": 77 }, { - "epoch": 0.31451612903225806, - "grad_norm": 2.820605993270874, - "learning_rate": 1.7903225806451612e-05, - "loss": 0.1451, + "epoch": 0.24761904761904763, + "grad_norm": 2.9135754108428955, + "learning_rate": 1.834920634920635e-05, + "loss": 0.2196, "step": 78 }, { - "epoch": 0.3185483870967742, - "grad_norm": 2.23899245262146, - "learning_rate": 1.7876344086021506e-05, - "loss": 0.1839, + "epoch": 0.2507936507936508, + "grad_norm": 2.10673451423645, + "learning_rate": 1.832804232804233e-05, + "loss": 0.1785, "step": 79 }, { - "epoch": 0.3225806451612903, - "grad_norm": 1.4833577871322632, - "learning_rate": 1.78494623655914e-05, - "loss": 0.1874, + "epoch": 0.25396825396825395, + "grad_norm": 1.572043538093567, + "learning_rate": 1.8306878306878308e-05, + "loss": 0.2442, "step": 80 }, { - "epoch": 0.32661290322580644, - "grad_norm": 3.754470109939575, - "learning_rate": 1.7822580645161292e-05, - "loss": 0.2299, + "epoch": 0.2571428571428571, + "grad_norm": 3.0884344577789307, + "learning_rate": 1.8285714285714288e-05, + "loss": 0.2486, "step": 81 }, { - "epoch": 0.33064516129032256, - "grad_norm": 3.65791654586792, - "learning_rate": 1.7795698924731186e-05, - "loss": 0.2075, + "epoch": 0.26031746031746034, + "grad_norm": 1.2815704345703125, + "learning_rate": 1.8264550264550268e-05, + "loss": 0.2351, "step": 82 }, { - "epoch": 0.3346774193548387, - "grad_norm": 2.704558849334717, - "learning_rate": 1.7768817204301075e-05, - "loss": 0.1688, + "epoch": 0.2634920634920635, + "grad_norm": 2.322263240814209, + "learning_rate": 1.8243386243386244e-05, + "loss": 0.2458, "step": 83 }, { - "epoch": 0.3387096774193548, - "grad_norm": 1.7909516096115112, - "learning_rate": 1.774193548387097e-05, - "loss": 0.2472, + "epoch": 0.26666666666666666, + "grad_norm": 2.1008965969085693, + "learning_rate": 1.8222222222222224e-05, + "loss": 0.2297, "step": 84 }, { - "epoch": 0.34274193548387094, - "grad_norm": 1.412300705909729, - "learning_rate": 1.7715053763440862e-05, - "loss": 0.1858, + "epoch": 0.2698412698412698, + "grad_norm": 1.5457587242126465, + "learning_rate": 1.82010582010582e-05, + "loss": 0.1929, "step": 85 }, { - "epoch": 0.3467741935483871, - "grad_norm": 2.0086007118225098, - "learning_rate": 1.7688172043010755e-05, - "loss": 0.2088, + "epoch": 0.273015873015873, + "grad_norm": 1.5334382057189941, + "learning_rate": 1.817989417989418e-05, + "loss": 0.176, "step": 86 }, { - "epoch": 0.35080645161290325, - "grad_norm": 1.4397780895233154, - "learning_rate": 1.7661290322580645e-05, - "loss": 0.1816, + "epoch": 0.2761904761904762, + "grad_norm": 1.8110551834106445, + "learning_rate": 1.815873015873016e-05, + "loss": 0.1673, "step": 87 }, { - "epoch": 0.3548387096774194, - "grad_norm": 2.947721242904663, - "learning_rate": 1.763440860215054e-05, - "loss": 0.1629, + "epoch": 0.27936507936507937, + "grad_norm": 1.4845051765441895, + "learning_rate": 1.8137566137566137e-05, + "loss": 0.2548, "step": 88 }, { - "epoch": 0.3588709677419355, - "grad_norm": 1.9372519254684448, - "learning_rate": 1.7607526881720432e-05, - "loss": 0.1636, + "epoch": 0.28253968253968254, + "grad_norm": 2.435779094696045, + "learning_rate": 1.8116402116402117e-05, + "loss": 0.1582, "step": 89 }, { - "epoch": 0.3629032258064516, - "grad_norm": 1.4998315572738647, - "learning_rate": 1.7580645161290325e-05, - "loss": 0.2162, + "epoch": 0.2857142857142857, + "grad_norm": 2.4211058616638184, + "learning_rate": 1.8095238095238097e-05, + "loss": 0.1934, "step": 90 }, { - "epoch": 0.36693548387096775, - "grad_norm": 3.8654611110687256, - "learning_rate": 1.7553763440860215e-05, - "loss": 0.2311, + "epoch": 0.28888888888888886, + "grad_norm": 1.5612387657165527, + "learning_rate": 1.8074074074074074e-05, + "loss": 0.2069, "step": 91 }, { - "epoch": 0.3709677419354839, - "grad_norm": 2.416931390762329, - "learning_rate": 1.752688172043011e-05, - "loss": 0.161, + "epoch": 0.2920634920634921, + "grad_norm": 2.1465699672698975, + "learning_rate": 1.8052910052910054e-05, + "loss": 0.2309, "step": 92 }, { - "epoch": 0.375, - "grad_norm": 1.4065924882888794, - "learning_rate": 1.7500000000000002e-05, - "loss": 0.1919, + "epoch": 0.29523809523809524, + "grad_norm": 1.3713735342025757, + "learning_rate": 1.8031746031746034e-05, + "loss": 0.2265, "step": 93 }, { - "epoch": 0.3790322580645161, - "grad_norm": 3.5286269187927246, - "learning_rate": 1.7473118279569895e-05, - "loss": 0.2338, + "epoch": 0.2984126984126984, + "grad_norm": 3.7306222915649414, + "learning_rate": 1.801058201058201e-05, + "loss": 0.2364, "step": 94 }, { - "epoch": 0.38306451612903225, - "grad_norm": 3.0253779888153076, - "learning_rate": 1.7446236559139785e-05, - "loss": 0.1824, + "epoch": 0.30158730158730157, + "grad_norm": 3.276874542236328, + "learning_rate": 1.798941798941799e-05, + "loss": 0.26, "step": 95 }, { - "epoch": 0.3870967741935484, - "grad_norm": 1.31352961063385, - "learning_rate": 1.741935483870968e-05, - "loss": 0.1203, + "epoch": 0.3047619047619048, + "grad_norm": 2.0132765769958496, + "learning_rate": 1.796825396825397e-05, + "loss": 0.1905, "step": 96 }, { - "epoch": 0.3911290322580645, - "grad_norm": 2.3616368770599365, - "learning_rate": 1.7392473118279572e-05, - "loss": 0.2555, + "epoch": 0.30793650793650795, + "grad_norm": 1.992788314819336, + "learning_rate": 1.7947089947089947e-05, + "loss": 0.2202, "step": 97 }, { - "epoch": 0.3951612903225806, - "grad_norm": 1.9040699005126953, - "learning_rate": 1.7365591397849465e-05, - "loss": 0.1857, + "epoch": 0.3111111111111111, + "grad_norm": 1.4299159049987793, + "learning_rate": 1.7925925925925927e-05, + "loss": 0.1365, "step": 98 }, { - "epoch": 0.39919354838709675, - "grad_norm": 1.4389543533325195, - "learning_rate": 1.7338709677419355e-05, - "loss": 0.1379, + "epoch": 0.3142857142857143, + "grad_norm": 4.919161319732666, + "learning_rate": 1.7904761904761907e-05, + "loss": 0.1887, "step": 99 }, { - "epoch": 0.4032258064516129, - "grad_norm": 1.4597176313400269, - "learning_rate": 1.7311827956989248e-05, - "loss": 0.1258, + "epoch": 0.31746031746031744, + "grad_norm": 8.949520111083984, + "learning_rate": 1.7883597883597884e-05, + "loss": 0.2233, "step": 100 }, { - "epoch": 0.40725806451612906, - "grad_norm": 2.730079174041748, - "learning_rate": 1.728494623655914e-05, - "loss": 0.1936, + "epoch": 0.32063492063492066, + "grad_norm": 7.236527442932129, + "learning_rate": 1.7862433862433863e-05, + "loss": 0.1797, "step": 101 }, { - "epoch": 0.4112903225806452, - "grad_norm": 1.6900081634521484, - "learning_rate": 1.7258064516129035e-05, - "loss": 0.1782, + "epoch": 0.3238095238095238, + "grad_norm": 1.5892037153244019, + "learning_rate": 1.7841269841269843e-05, + "loss": 0.2002, "step": 102 }, { - "epoch": 0.4153225806451613, - "grad_norm": 3.9283804893493652, - "learning_rate": 1.7231182795698925e-05, - "loss": 0.1447, + "epoch": 0.326984126984127, + "grad_norm": 3.141767978668213, + "learning_rate": 1.7820105820105823e-05, + "loss": 0.1858, "step": 103 }, { - "epoch": 0.41935483870967744, - "grad_norm": 2.625030755996704, - "learning_rate": 1.7204301075268818e-05, - "loss": 0.1361, + "epoch": 0.33015873015873015, + "grad_norm": 4.194268703460693, + "learning_rate": 1.77989417989418e-05, + "loss": 0.281, "step": 104 }, { - "epoch": 0.42338709677419356, - "grad_norm": 6.293011665344238, - "learning_rate": 1.717741935483871e-05, - "loss": 0.2563, + "epoch": 0.3333333333333333, + "grad_norm": 1.9994726181030273, + "learning_rate": 1.7777777777777777e-05, + "loss": 0.2466, "step": 105 }, { - "epoch": 0.4274193548387097, - "grad_norm": 3.8414859771728516, - "learning_rate": 1.7150537634408605e-05, - "loss": 0.2118, + "epoch": 0.33650793650793653, + "grad_norm": 6.111693382263184, + "learning_rate": 1.775661375661376e-05, + "loss": 0.2222, "step": 106 }, { - "epoch": 0.4314516129032258, - "grad_norm": 1.7090542316436768, - "learning_rate": 1.7123655913978495e-05, - "loss": 0.2919, + "epoch": 0.3396825396825397, + "grad_norm": 4.901621341705322, + "learning_rate": 1.7735449735449737e-05, + "loss": 0.176, "step": 107 }, { - "epoch": 0.43548387096774194, - "grad_norm": 1.4093631505966187, - "learning_rate": 1.7096774193548388e-05, - "loss": 0.2151, + "epoch": 0.34285714285714286, + "grad_norm": 2.9189085960388184, + "learning_rate": 1.7714285714285717e-05, + "loss": 0.2822, "step": 108 }, { - "epoch": 0.43951612903225806, - "grad_norm": 1.6816186904907227, - "learning_rate": 1.706989247311828e-05, - "loss": 0.2001, + "epoch": 0.346031746031746, + "grad_norm": 2.6285767555236816, + "learning_rate": 1.7693121693121696e-05, + "loss": 0.1854, "step": 109 }, { - "epoch": 0.4435483870967742, - "grad_norm": 2.5388357639312744, - "learning_rate": 1.7043010752688175e-05, - "loss": 0.1839, + "epoch": 0.3492063492063492, + "grad_norm": 3.9845187664031982, + "learning_rate": 1.7671957671957673e-05, + "loss": 0.1497, "step": 110 }, { - "epoch": 0.4475806451612903, - "grad_norm": 4.355051040649414, - "learning_rate": 1.7016129032258068e-05, - "loss": 0.1517, + "epoch": 0.3523809523809524, + "grad_norm": 3.853863477706909, + "learning_rate": 1.7650793650793653e-05, + "loss": 0.2805, "step": 111 }, { - "epoch": 0.45161290322580644, - "grad_norm": 5.043978691101074, - "learning_rate": 1.6989247311827958e-05, - "loss": 0.1148, + "epoch": 0.35555555555555557, + "grad_norm": 2.910295248031616, + "learning_rate": 1.7629629629629633e-05, + "loss": 0.1216, "step": 112 }, { - "epoch": 0.45564516129032256, - "grad_norm": 4.623153209686279, - "learning_rate": 1.696236559139785e-05, - "loss": 0.2277, + "epoch": 0.35873015873015873, + "grad_norm": 2.9138343334198, + "learning_rate": 1.760846560846561e-05, + "loss": 0.2278, "step": 113 }, { - "epoch": 0.4596774193548387, - "grad_norm": 2.165748119354248, - "learning_rate": 1.6935483870967744e-05, - "loss": 0.175, + "epoch": 0.3619047619047619, + "grad_norm": 2.24206805229187, + "learning_rate": 1.758730158730159e-05, + "loss": 0.1538, "step": 114 }, { - "epoch": 0.4637096774193548, - "grad_norm": 2.074892520904541, - "learning_rate": 1.6908602150537638e-05, - "loss": 0.107, + "epoch": 0.36507936507936506, + "grad_norm": 2.591796398162842, + "learning_rate": 1.7566137566137566e-05, + "loss": 0.1831, "step": 115 }, { - "epoch": 0.46774193548387094, - "grad_norm": 4.597195625305176, - "learning_rate": 1.6881720430107528e-05, - "loss": 0.201, + "epoch": 0.3682539682539683, + "grad_norm": 1.7508796453475952, + "learning_rate": 1.7544973544973546e-05, + "loss": 0.191, "step": 116 }, { - "epoch": 0.4717741935483871, - "grad_norm": 1.589660406112671, - "learning_rate": 1.685483870967742e-05, - "loss": 0.1904, + "epoch": 0.37142857142857144, + "grad_norm": 2.6940598487854004, + "learning_rate": 1.7523809523809526e-05, + "loss": 0.2372, "step": 117 }, { - "epoch": 0.47580645161290325, - "grad_norm": 3.892699718475342, - "learning_rate": 1.6827956989247314e-05, - "loss": 0.1536, + "epoch": 0.3746031746031746, + "grad_norm": 2.82623553276062, + "learning_rate": 1.7502645502645503e-05, + "loss": 0.285, "step": 118 }, { - "epoch": 0.4798387096774194, - "grad_norm": 1.4085686206817627, - "learning_rate": 1.6801075268817208e-05, - "loss": 0.1762, + "epoch": 0.37777777777777777, + "grad_norm": 5.410754680633545, + "learning_rate": 1.7481481481481483e-05, + "loss": 0.2368, "step": 119 }, { - "epoch": 0.4838709677419355, - "grad_norm": 2.0159590244293213, - "learning_rate": 1.6774193548387098e-05, - "loss": 0.1433, + "epoch": 0.38095238095238093, + "grad_norm": 2.7831737995147705, + "learning_rate": 1.7460317460317463e-05, + "loss": 0.1801, "step": 120 }, { - "epoch": 0.4879032258064516, - "grad_norm": 3.211463451385498, - "learning_rate": 1.674731182795699e-05, - "loss": 0.2131, + "epoch": 0.38412698412698415, + "grad_norm": 3.9018654823303223, + "learning_rate": 1.743915343915344e-05, + "loss": 0.2322, "step": 121 }, { - "epoch": 0.49193548387096775, - "grad_norm": 1.9942578077316284, - "learning_rate": 1.6720430107526884e-05, - "loss": 0.1962, + "epoch": 0.3873015873015873, + "grad_norm": 4.209503173828125, + "learning_rate": 1.741798941798942e-05, + "loss": 0.1469, "step": 122 }, { - "epoch": 0.4959677419354839, - "grad_norm": 2.7773678302764893, - "learning_rate": 1.6693548387096778e-05, - "loss": 0.1516, + "epoch": 0.3904761904761905, + "grad_norm": 2.2420248985290527, + "learning_rate": 1.73968253968254e-05, + "loss": 0.2441, "step": 123 }, { - "epoch": 0.5, - "grad_norm": 4.387947082519531, - "learning_rate": 1.6666666666666667e-05, - "loss": 0.2402, + "epoch": 0.39365079365079364, + "grad_norm": 3.6898937225341797, + "learning_rate": 1.7375661375661376e-05, + "loss": 0.175, "step": 124 }, { - "epoch": 0.5040322580645161, - "grad_norm": 3.206733465194702, - "learning_rate": 1.663978494623656e-05, - "loss": 0.1615, + "epoch": 0.3968253968253968, + "grad_norm": 2.903392791748047, + "learning_rate": 1.7354497354497356e-05, + "loss": 0.2485, "step": 125 }, { - "epoch": 0.5080645161290323, - "grad_norm": 4.810270309448242, - "learning_rate": 1.6612903225806454e-05, - "loss": 0.1587, + "epoch": 0.4, + "grad_norm": 3.170260190963745, + "learning_rate": 1.7333333333333336e-05, + "loss": 0.2284, "step": 126 }, { - "epoch": 0.5120967741935484, - "grad_norm": 3.2066237926483154, - "learning_rate": 1.6586021505376347e-05, - "loss": 0.1747, + "epoch": 0.4031746031746032, + "grad_norm": 4.36612606048584, + "learning_rate": 1.7312169312169312e-05, + "loss": 0.1552, "step": 127 }, { - "epoch": 0.5161290322580645, - "grad_norm": 1.2533971071243286, - "learning_rate": 1.6559139784946237e-05, - "loss": 0.1662, + "epoch": 0.40634920634920635, + "grad_norm": 3.356701374053955, + "learning_rate": 1.7291005291005292e-05, + "loss": 0.1526, "step": 128 }, { - "epoch": 0.5201612903225806, - "grad_norm": 4.853026390075684, - "learning_rate": 1.653225806451613e-05, - "loss": 0.1895, + "epoch": 0.4095238095238095, + "grad_norm": 7.871209621429443, + "learning_rate": 1.7269841269841272e-05, + "loss": 0.292, "step": 129 }, { - "epoch": 0.5241935483870968, - "grad_norm": 1.5984219312667847, - "learning_rate": 1.6505376344086024e-05, - "loss": 0.1867, + "epoch": 0.4126984126984127, + "grad_norm": 3.702918529510498, + "learning_rate": 1.724867724867725e-05, + "loss": 0.285, "step": 130 }, { - "epoch": 0.5282258064516129, - "grad_norm": 1.9208190441131592, - "learning_rate": 1.6478494623655917e-05, - "loss": 0.1661, + "epoch": 0.4158730158730159, + "grad_norm": 3.1132378578186035, + "learning_rate": 1.722751322751323e-05, + "loss": 0.1566, "step": 131 }, { - "epoch": 0.532258064516129, - "grad_norm": 4.714879035949707, - "learning_rate": 1.6451612903225807e-05, - "loss": 0.1978, + "epoch": 0.41904761904761906, + "grad_norm": 1.5112287998199463, + "learning_rate": 1.720634920634921e-05, + "loss": 0.158, "step": 132 }, { - "epoch": 0.5362903225806451, - "grad_norm": 1.9932862520217896, - "learning_rate": 1.64247311827957e-05, - "loss": 0.1894, + "epoch": 0.4222222222222222, + "grad_norm": 1.7887698411941528, + "learning_rate": 1.7185185185185185e-05, + "loss": 0.2029, "step": 133 }, { - "epoch": 0.5403225806451613, - "grad_norm": 1.8594914674758911, - "learning_rate": 1.6397849462365594e-05, - "loss": 0.1819, + "epoch": 0.4253968253968254, + "grad_norm": 2.924344301223755, + "learning_rate": 1.7164021164021165e-05, + "loss": 0.1924, "step": 134 }, { - "epoch": 0.5443548387096774, - "grad_norm": 3.666376829147339, - "learning_rate": 1.6370967741935487e-05, - "loss": 0.1594, + "epoch": 0.42857142857142855, + "grad_norm": 1.2232037782669067, + "learning_rate": 1.7142857142857142e-05, + "loss": 0.1928, "step": 135 }, { - "epoch": 0.5483870967741935, - "grad_norm": 5.887596607208252, - "learning_rate": 1.6344086021505377e-05, - "loss": 0.1807, + "epoch": 0.43174603174603177, + "grad_norm": 1.825201153755188, + "learning_rate": 1.7121693121693125e-05, + "loss": 0.2007, "step": 136 }, { - "epoch": 0.5524193548387096, - "grad_norm": 1.3112871646881104, - "learning_rate": 1.631720430107527e-05, - "loss": 0.1411, + "epoch": 0.43492063492063493, + "grad_norm": 2.588146686553955, + "learning_rate": 1.7100529100529102e-05, + "loss": 0.2131, "step": 137 }, { - "epoch": 0.5564516129032258, - "grad_norm": 2.456446409225464, - "learning_rate": 1.6290322580645164e-05, - "loss": 0.1413, + "epoch": 0.4380952380952381, + "grad_norm": 2.4709854125976562, + "learning_rate": 1.707936507936508e-05, + "loss": 0.1792, "step": 138 }, { - "epoch": 0.5604838709677419, - "grad_norm": 4.192088603973389, - "learning_rate": 1.6263440860215057e-05, - "loss": 0.1422, + "epoch": 0.44126984126984126, + "grad_norm": 3.379082679748535, + "learning_rate": 1.7058201058201062e-05, + "loss": 0.1801, "step": 139 }, { - "epoch": 0.5645161290322581, - "grad_norm": 2.659003734588623, - "learning_rate": 1.6236559139784947e-05, - "loss": 0.1812, + "epoch": 0.4444444444444444, + "grad_norm": 2.428194999694824, + "learning_rate": 1.7037037037037038e-05, + "loss": 0.1374, "step": 140 }, { - "epoch": 0.5685483870967742, - "grad_norm": 1.699617624282837, - "learning_rate": 1.620967741935484e-05, - "loss": 0.1771, + "epoch": 0.44761904761904764, + "grad_norm": 1.5804234743118286, + "learning_rate": 1.7015873015873018e-05, + "loss": 0.1989, "step": 141 }, { - "epoch": 0.5725806451612904, - "grad_norm": 2.221937656402588, - "learning_rate": 1.618279569892473e-05, - "loss": 0.1815, + "epoch": 0.4507936507936508, + "grad_norm": 2.639671564102173, + "learning_rate": 1.6994708994708998e-05, + "loss": 0.1549, "step": 142 }, { - "epoch": 0.5766129032258065, - "grad_norm": 1.5366272926330566, - "learning_rate": 1.6155913978494623e-05, - "loss": 0.184, + "epoch": 0.45396825396825397, + "grad_norm": 2.976484775543213, + "learning_rate": 1.6973544973544975e-05, + "loss": 0.1205, "step": 143 }, { - "epoch": 0.5806451612903226, - "grad_norm": 2.0756564140319824, - "learning_rate": 1.6129032258064517e-05, - "loss": 0.145, + "epoch": 0.45714285714285713, + "grad_norm": 3.520148754119873, + "learning_rate": 1.6952380952380955e-05, + "loss": 0.1873, "step": 144 }, { - "epoch": 0.5846774193548387, - "grad_norm": 1.1063413619995117, - "learning_rate": 1.610215053763441e-05, - "loss": 0.0964, + "epoch": 0.4603174603174603, + "grad_norm": 1.7141591310501099, + "learning_rate": 1.693121693121693e-05, + "loss": 0.2201, "step": 145 }, { - "epoch": 0.5887096774193549, - "grad_norm": 1.9002684354782104, - "learning_rate": 1.60752688172043e-05, - "loss": 0.2313, + "epoch": 0.4634920634920635, + "grad_norm": 2.2544193267822266, + "learning_rate": 1.691005291005291e-05, + "loss": 0.2098, "step": 146 }, { - "epoch": 0.592741935483871, - "grad_norm": 3.5199642181396484, - "learning_rate": 1.6048387096774193e-05, - "loss": 0.1803, + "epoch": 0.4666666666666667, + "grad_norm": 2.9456677436828613, + "learning_rate": 1.688888888888889e-05, + "loss": 0.1637, "step": 147 }, { - "epoch": 0.5967741935483871, - "grad_norm": 2.263772487640381, - "learning_rate": 1.6021505376344087e-05, - "loss": 0.1661, + "epoch": 0.46984126984126984, + "grad_norm": 5.148157119750977, + "learning_rate": 1.6867724867724868e-05, + "loss": 0.369, "step": 148 }, { - "epoch": 0.6008064516129032, - "grad_norm": 3.434790849685669, - "learning_rate": 1.599462365591398e-05, - "loss": 0.1729, + "epoch": 0.473015873015873, + "grad_norm": 2.040313243865967, + "learning_rate": 1.6846560846560848e-05, + "loss": 0.1666, "step": 149 }, { - "epoch": 0.6048387096774194, - "grad_norm": 3.1659963130950928, - "learning_rate": 1.596774193548387e-05, - "loss": 0.2271, + "epoch": 0.47619047619047616, + "grad_norm": 1.5156350135803223, + "learning_rate": 1.6825396825396828e-05, + "loss": 0.1873, "step": 150 }, { - "epoch": 0.6088709677419355, - "grad_norm": 3.9298930168151855, - "learning_rate": 1.5940860215053763e-05, - "loss": 0.1787, + "epoch": 0.4793650793650794, + "grad_norm": 1.2989375591278076, + "learning_rate": 1.6804232804232804e-05, + "loss": 0.1661, "step": 151 }, { - "epoch": 0.6129032258064516, - "grad_norm": 5.221301078796387, - "learning_rate": 1.5913978494623657e-05, - "loss": 0.1432, + "epoch": 0.48253968253968255, + "grad_norm": 2.593242645263672, + "learning_rate": 1.6783068783068784e-05, + "loss": 0.1537, "step": 152 }, { - "epoch": 0.6169354838709677, - "grad_norm": 0.9517404437065125, - "learning_rate": 1.588709677419355e-05, - "loss": 0.143, + "epoch": 0.4857142857142857, + "grad_norm": 2.770364284515381, + "learning_rate": 1.6761904761904764e-05, + "loss": 0.2254, "step": 153 }, { - "epoch": 0.6209677419354839, - "grad_norm": 1.685404658317566, - "learning_rate": 1.586021505376344e-05, - "loss": 0.1446, + "epoch": 0.4888888888888889, + "grad_norm": 1.4074443578720093, + "learning_rate": 1.674074074074074e-05, + "loss": 0.1206, "step": 154 }, { - "epoch": 0.625, - "grad_norm": 4.428375720977783, - "learning_rate": 1.5833333333333333e-05, - "loss": 0.2276, + "epoch": 0.49206349206349204, + "grad_norm": 1.7672759294509888, + "learning_rate": 1.671957671957672e-05, + "loss": 0.1832, "step": 155 }, { - "epoch": 0.6290322580645161, - "grad_norm": 1.976226568222046, - "learning_rate": 1.5806451612903226e-05, - "loss": 0.1822, + "epoch": 0.49523809523809526, + "grad_norm": 2.1247332096099854, + "learning_rate": 1.66984126984127e-05, + "loss": 0.124, "step": 156 }, { - "epoch": 0.6330645161290323, - "grad_norm": 2.600104570388794, - "learning_rate": 1.577956989247312e-05, - "loss": 0.2352, + "epoch": 0.4984126984126984, + "grad_norm": 2.6754729747772217, + "learning_rate": 1.6677248677248677e-05, + "loss": 0.1887, "step": 157 }, { - "epoch": 0.6370967741935484, - "grad_norm": 2.413137197494507, - "learning_rate": 1.5752688172043013e-05, - "loss": 0.258, + "epoch": 0.5015873015873016, + "grad_norm": 2.6920604705810547, + "learning_rate": 1.6656084656084657e-05, + "loss": 0.1585, "step": 158 }, { - "epoch": 0.6411290322580645, - "grad_norm": 2.801959753036499, - "learning_rate": 1.5725806451612903e-05, - "loss": 0.1796, + "epoch": 0.5047619047619047, + "grad_norm": 1.7507778406143188, + "learning_rate": 1.6634920634920637e-05, + "loss": 0.168, "step": 159 }, { - "epoch": 0.6451612903225806, - "grad_norm": 2.2109487056732178, - "learning_rate": 1.5698924731182796e-05, - "loss": 0.1749, + "epoch": 0.5079365079365079, + "grad_norm": 2.0529165267944336, + "learning_rate": 1.6613756613756614e-05, + "loss": 0.2108, "step": 160 }, { - "epoch": 0.6491935483870968, - "grad_norm": 3.4560952186584473, - "learning_rate": 1.567204301075269e-05, - "loss": 0.1315, + "epoch": 0.5111111111111111, + "grad_norm": 1.1451058387756348, + "learning_rate": 1.6592592592592594e-05, + "loss": 0.1178, "step": 161 }, { - "epoch": 0.6532258064516129, - "grad_norm": 3.611140251159668, - "learning_rate": 1.5645161290322583e-05, - "loss": 0.2518, + "epoch": 0.5142857142857142, + "grad_norm": 6.2355756759643555, + "learning_rate": 1.6571428571428574e-05, + "loss": 0.2472, "step": 162 }, { - "epoch": 0.657258064516129, - "grad_norm": 3.5987987518310547, - "learning_rate": 1.5618279569892473e-05, - "loss": 0.2134, + "epoch": 0.5174603174603175, + "grad_norm": 1.53696870803833, + "learning_rate": 1.655026455026455e-05, + "loss": 0.1592, "step": 163 }, { - "epoch": 0.6612903225806451, - "grad_norm": 3.6609513759613037, - "learning_rate": 1.5591397849462366e-05, - "loss": 0.1134, + "epoch": 0.5206349206349207, + "grad_norm": 1.9149675369262695, + "learning_rate": 1.652910052910053e-05, + "loss": 0.2418, "step": 164 }, { - "epoch": 0.6653225806451613, - "grad_norm": 4.708600044250488, - "learning_rate": 1.556451612903226e-05, - "loss": 0.1581, + "epoch": 0.5238095238095238, + "grad_norm": 6.642933368682861, + "learning_rate": 1.6507936507936507e-05, + "loss": 0.1381, "step": 165 }, { - "epoch": 0.6693548387096774, - "grad_norm": 2.0652990341186523, - "learning_rate": 1.5537634408602153e-05, - "loss": 0.114, + "epoch": 0.526984126984127, + "grad_norm": 2.186159372329712, + "learning_rate": 1.648677248677249e-05, + "loss": 0.1464, "step": 166 }, { - "epoch": 0.6733870967741935, - "grad_norm": 2.3634023666381836, - "learning_rate": 1.5510752688172043e-05, - "loss": 0.1383, + "epoch": 0.5301587301587302, + "grad_norm": 2.2545220851898193, + "learning_rate": 1.6465608465608467e-05, + "loss": 0.1396, "step": 167 }, { - "epoch": 0.6774193548387096, - "grad_norm": 1.8686503171920776, - "learning_rate": 1.5483870967741936e-05, - "loss": 0.1071, + "epoch": 0.5333333333333333, + "grad_norm": 1.8454933166503906, + "learning_rate": 1.6444444444444444e-05, + "loss": 0.114, "step": 168 }, { - "epoch": 0.6814516129032258, - "grad_norm": 2.7749221324920654, - "learning_rate": 1.545698924731183e-05, - "loss": 0.1394, + "epoch": 0.5365079365079365, + "grad_norm": 2.3766286373138428, + "learning_rate": 1.6423280423280427e-05, + "loss": 0.1398, "step": 169 }, { - "epoch": 0.6854838709677419, - "grad_norm": 5.210952281951904, - "learning_rate": 1.5430107526881723e-05, - "loss": 0.1698, + "epoch": 0.5396825396825397, + "grad_norm": 3.3228402137756348, + "learning_rate": 1.6402116402116404e-05, + "loss": 0.1666, "step": 170 }, { - "epoch": 0.6895161290322581, - "grad_norm": 1.9079982042312622, - "learning_rate": 1.5403225806451613e-05, - "loss": 0.149, + "epoch": 0.5428571428571428, + "grad_norm": 1.8218978643417358, + "learning_rate": 1.6380952380952384e-05, + "loss": 0.2628, "step": 171 }, { - "epoch": 0.6935483870967742, - "grad_norm": 3.1015419960021973, - "learning_rate": 1.5376344086021506e-05, - "loss": 0.1821, + "epoch": 0.546031746031746, + "grad_norm": 3.25368595123291, + "learning_rate": 1.6359788359788363e-05, + "loss": 0.1462, "step": 172 }, { - "epoch": 0.6975806451612904, - "grad_norm": 2.9040095806121826, - "learning_rate": 1.53494623655914e-05, - "loss": 0.1624, + "epoch": 0.5492063492063493, + "grad_norm": 3.9840452671051025, + "learning_rate": 1.633862433862434e-05, + "loss": 0.2258, "step": 173 }, { - "epoch": 0.7016129032258065, - "grad_norm": 3.451782703399658, - "learning_rate": 1.5322580645161292e-05, - "loss": 0.2349, + "epoch": 0.5523809523809524, + "grad_norm": 3.3438644409179688, + "learning_rate": 1.631746031746032e-05, + "loss": 0.2644, "step": 174 }, { - "epoch": 0.7056451612903226, - "grad_norm": 2.0777103900909424, - "learning_rate": 1.5295698924731182e-05, - "loss": 0.1575, + "epoch": 0.5555555555555556, + "grad_norm": 3.3649120330810547, + "learning_rate": 1.6296296296296297e-05, + "loss": 0.1658, "step": 175 }, { - "epoch": 0.7096774193548387, - "grad_norm": 2.8455822467803955, - "learning_rate": 1.5268817204301076e-05, - "loss": 0.1402, + "epoch": 0.5587301587301587, + "grad_norm": 2.9229865074157715, + "learning_rate": 1.6275132275132277e-05, + "loss": 0.2054, "step": 176 }, { - "epoch": 0.7137096774193549, - "grad_norm": 2.1864373683929443, - "learning_rate": 1.5241935483870969e-05, - "loss": 0.2501, + "epoch": 0.5619047619047619, + "grad_norm": 3.2928781509399414, + "learning_rate": 1.6253968253968257e-05, + "loss": 0.1611, "step": 177 }, { - "epoch": 0.717741935483871, - "grad_norm": 2.945974349975586, - "learning_rate": 1.521505376344086e-05, - "loss": 0.1758, + "epoch": 0.5650793650793651, + "grad_norm": 1.7885255813598633, + "learning_rate": 1.6232804232804233e-05, + "loss": 0.1948, "step": 178 }, { - "epoch": 0.7217741935483871, - "grad_norm": 2.071998357772827, - "learning_rate": 1.5188172043010754e-05, - "loss": 0.1185, + "epoch": 0.5682539682539682, + "grad_norm": 3.2603516578674316, + "learning_rate": 1.6211640211640213e-05, + "loss": 0.165, "step": 179 }, { - "epoch": 0.7258064516129032, - "grad_norm": 2.1226487159729004, - "learning_rate": 1.5161290322580646e-05, - "loss": 0.1809, + "epoch": 0.5714285714285714, + "grad_norm": 1.4518803358078003, + "learning_rate": 1.6190476190476193e-05, + "loss": 0.2135, "step": 180 }, { - "epoch": 0.7298387096774194, - "grad_norm": 3.2159790992736816, - "learning_rate": 1.5134408602150539e-05, - "loss": 0.1583, + "epoch": 0.5746031746031746, + "grad_norm": 3.1771421432495117, + "learning_rate": 1.616931216931217e-05, + "loss": 0.2069, "step": 181 }, { - "epoch": 0.7338709677419355, - "grad_norm": 1.7255215644836426, - "learning_rate": 1.510752688172043e-05, - "loss": 0.1706, + "epoch": 0.5777777777777777, + "grad_norm": 3.5020251274108887, + "learning_rate": 1.614814814814815e-05, + "loss": 0.2018, "step": 182 }, { - "epoch": 0.7379032258064516, - "grad_norm": 1.9457521438598633, - "learning_rate": 1.5080645161290324e-05, - "loss": 0.1658, + "epoch": 0.580952380952381, + "grad_norm": 2.5956308841705322, + "learning_rate": 1.612698412698413e-05, + "loss": 0.1813, "step": 183 }, { - "epoch": 0.7419354838709677, - "grad_norm": 7.032689571380615, - "learning_rate": 1.5053763440860215e-05, - "loss": 0.173, + "epoch": 0.5841269841269842, + "grad_norm": 1.245976209640503, + "learning_rate": 1.6105820105820106e-05, + "loss": 0.1378, "step": 184 }, { - "epoch": 0.7459677419354839, - "grad_norm": 2.1762492656707764, - "learning_rate": 1.5026881720430109e-05, - "loss": 0.144, + "epoch": 0.5873015873015873, + "grad_norm": 2.6138696670532227, + "learning_rate": 1.6084656084656086e-05, + "loss": 0.2536, "step": 185 }, { - "epoch": 0.75, - "grad_norm": 3.8494467735290527, - "learning_rate": 1.5000000000000002e-05, - "loss": 0.1933, + "epoch": 0.5904761904761905, + "grad_norm": 1.3784005641937256, + "learning_rate": 1.6063492063492066e-05, + "loss": 0.1519, "step": 186 }, { - "epoch": 0.7540322580645161, - "grad_norm": 1.369672179222107, - "learning_rate": 1.4973118279569894e-05, - "loss": 0.1082, + "epoch": 0.5936507936507937, + "grad_norm": 2.212174654006958, + "learning_rate": 1.6042328042328043e-05, + "loss": 0.2144, "step": 187 }, { - "epoch": 0.7580645161290323, - "grad_norm": 2.0053024291992188, - "learning_rate": 1.4946236559139787e-05, - "loss": 0.1564, + "epoch": 0.5968253968253968, + "grad_norm": 2.8217222690582275, + "learning_rate": 1.6021164021164023e-05, + "loss": 0.2145, "step": 188 }, { - "epoch": 0.7620967741935484, - "grad_norm": 3.1830568313598633, - "learning_rate": 1.4919354838709679e-05, - "loss": 0.1956, + "epoch": 0.6, + "grad_norm": 2.7043497562408447, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.175, "step": 189 }, { - "epoch": 0.7661290322580645, - "grad_norm": 2.129666328430176, - "learning_rate": 1.4892473118279572e-05, - "loss": 0.2594, + "epoch": 0.6031746031746031, + "grad_norm": 2.9069631099700928, + "learning_rate": 1.597883597883598e-05, + "loss": 0.2267, "step": 190 }, { - "epoch": 0.7701612903225806, - "grad_norm": 2.121384859085083, - "learning_rate": 1.4865591397849464e-05, - "loss": 0.1363, + "epoch": 0.6063492063492063, + "grad_norm": 2.0674169063568115, + "learning_rate": 1.595767195767196e-05, + "loss": 0.1572, "step": 191 }, { - "epoch": 0.7741935483870968, - "grad_norm": 2.5438694953918457, - "learning_rate": 1.4838709677419357e-05, - "loss": 0.15, + "epoch": 0.6095238095238096, + "grad_norm": 1.8505525588989258, + "learning_rate": 1.5936507936507936e-05, + "loss": 0.1485, "step": 192 }, { - "epoch": 0.7782258064516129, - "grad_norm": 1.4790626764297485, - "learning_rate": 1.4811827956989248e-05, - "loss": 0.1677, + "epoch": 0.6126984126984127, + "grad_norm": 10.307085037231445, + "learning_rate": 1.5915343915343916e-05, + "loss": 0.1361, "step": 193 }, { - "epoch": 0.782258064516129, - "grad_norm": 5.348865985870361, - "learning_rate": 1.4784946236559142e-05, - "loss": 0.2535, + "epoch": 0.6158730158730159, + "grad_norm": 1.7781238555908203, + "learning_rate": 1.5894179894179896e-05, + "loss": 0.175, "step": 194 }, { - "epoch": 0.7862903225806451, - "grad_norm": 7.304387092590332, - "learning_rate": 1.4758064516129033e-05, - "loss": 0.2327, + "epoch": 0.6190476190476191, + "grad_norm": 1.8744263648986816, + "learning_rate": 1.5873015873015872e-05, + "loss": 0.15, "step": 195 }, { - "epoch": 0.7903225806451613, - "grad_norm": 1.6960372924804688, - "learning_rate": 1.4731182795698927e-05, - "loss": 0.1453, + "epoch": 0.6222222222222222, + "grad_norm": 5.24875020980835, + "learning_rate": 1.5851851851851852e-05, + "loss": 0.2107, "step": 196 }, { - "epoch": 0.7943548387096774, - "grad_norm": 5.402785301208496, - "learning_rate": 1.4704301075268818e-05, - "loss": 0.2091, + "epoch": 0.6253968253968254, + "grad_norm": 2.198106288909912, + "learning_rate": 1.5830687830687832e-05, + "loss": 0.1557, "step": 197 }, { - "epoch": 0.7983870967741935, - "grad_norm": 6.772708415985107, - "learning_rate": 1.4677419354838712e-05, - "loss": 0.1622, + "epoch": 0.6285714285714286, + "grad_norm": 1.5822123289108276, + "learning_rate": 1.580952380952381e-05, + "loss": 0.171, "step": 198 }, { - "epoch": 0.8024193548387096, - "grad_norm": 2.564171075820923, - "learning_rate": 1.4650537634408603e-05, - "loss": 0.2299, + "epoch": 0.6317460317460317, + "grad_norm": 1.3433043956756592, + "learning_rate": 1.5788359788359792e-05, + "loss": 0.1712, "step": 199 }, { - "epoch": 0.8064516129032258, - "grad_norm": 2.6038239002227783, - "learning_rate": 1.4623655913978497e-05, - "loss": 0.1725, + "epoch": 0.6349206349206349, + "grad_norm": 2.727231025695801, + "learning_rate": 1.576719576719577e-05, + "loss": 0.1521, "step": 200 }, { - "epoch": 0.8104838709677419, - "grad_norm": 2.527942180633545, - "learning_rate": 1.4596774193548388e-05, - "loss": 0.1359, + "epoch": 0.638095238095238, + "grad_norm": 1.4410356283187866, + "learning_rate": 1.5746031746031745e-05, + "loss": 0.1566, "step": 201 }, { - "epoch": 0.8145161290322581, - "grad_norm": 3.5944533348083496, - "learning_rate": 1.4569892473118282e-05, - "loss": 0.1268, + "epoch": 0.6412698412698413, + "grad_norm": 1.2949568033218384, + "learning_rate": 1.5724867724867725e-05, + "loss": 0.1549, "step": 202 }, { - "epoch": 0.8185483870967742, - "grad_norm": 3.4926414489746094, - "learning_rate": 1.4543010752688173e-05, - "loss": 0.1473, + "epoch": 0.6444444444444445, + "grad_norm": 2.1393208503723145, + "learning_rate": 1.5703703703703705e-05, + "loss": 0.219, "step": 203 }, { - "epoch": 0.8225806451612904, - "grad_norm": 5.071582794189453, - "learning_rate": 1.4516129032258066e-05, - "loss": 0.196, + "epoch": 0.6476190476190476, + "grad_norm": 1.4255844354629517, + "learning_rate": 1.5682539682539685e-05, + "loss": 0.1669, "step": 204 }, { - "epoch": 0.8266129032258065, - "grad_norm": 4.80251932144165, - "learning_rate": 1.4489247311827958e-05, - "loss": 0.19, + "epoch": 0.6507936507936508, + "grad_norm": 3.404088258743286, + "learning_rate": 1.5661375661375662e-05, + "loss": 0.0715, "step": 205 }, { - "epoch": 0.8306451612903226, - "grad_norm": 3.378063678741455, - "learning_rate": 1.4462365591397851e-05, - "loss": 0.1293, + "epoch": 0.653968253968254, + "grad_norm": 4.217573165893555, + "learning_rate": 1.5640211640211642e-05, + "loss": 0.1841, "step": 206 }, { - "epoch": 0.8346774193548387, - "grad_norm": 3.138362407684326, - "learning_rate": 1.4435483870967743e-05, - "loss": 0.1919, + "epoch": 0.6571428571428571, + "grad_norm": 3.1164944171905518, + "learning_rate": 1.5619047619047622e-05, + "loss": 0.1227, "step": 207 }, { - "epoch": 0.8387096774193549, - "grad_norm": 3.114121675491333, - "learning_rate": 1.4408602150537636e-05, - "loss": 0.3021, + "epoch": 0.6603174603174603, + "grad_norm": 2.8788647651672363, + "learning_rate": 1.55978835978836e-05, + "loss": 0.2173, "step": 208 }, { - "epoch": 0.842741935483871, - "grad_norm": 2.903273582458496, - "learning_rate": 1.4381720430107528e-05, - "loss": 0.1613, + "epoch": 0.6634920634920635, + "grad_norm": 2.5300145149230957, + "learning_rate": 1.557671957671958e-05, + "loss": 0.184, "step": 209 }, { - "epoch": 0.8467741935483871, - "grad_norm": 2.530947685241699, - "learning_rate": 1.4354838709677421e-05, - "loss": 0.2119, + "epoch": 0.6666666666666666, + "grad_norm": 1.4018241167068481, + "learning_rate": 1.555555555555556e-05, + "loss": 0.1847, "step": 210 }, { - "epoch": 0.8508064516129032, - "grad_norm": 1.9773578643798828, - "learning_rate": 1.4327956989247313e-05, - "loss": 0.1994, + "epoch": 0.6698412698412698, + "grad_norm": 2.571445941925049, + "learning_rate": 1.5534391534391535e-05, + "loss": 0.1471, "step": 211 }, { - "epoch": 0.8548387096774194, - "grad_norm": 3.0400474071502686, - "learning_rate": 1.4301075268817206e-05, - "loss": 0.1553, + "epoch": 0.6730158730158731, + "grad_norm": 1.2815457582473755, + "learning_rate": 1.5513227513227515e-05, + "loss": 0.1548, "step": 212 }, { - "epoch": 0.8588709677419355, - "grad_norm": 2.43621826171875, - "learning_rate": 1.4274193548387098e-05, - "loss": 0.1592, + "epoch": 0.6761904761904762, + "grad_norm": 1.678731083869934, + "learning_rate": 1.5492063492063495e-05, + "loss": 0.175, "step": 213 }, { - "epoch": 0.8629032258064516, - "grad_norm": 3.8775973320007324, - "learning_rate": 1.4247311827956991e-05, - "loss": 0.161, + "epoch": 0.6793650793650794, + "grad_norm": 2.5812015533447266, + "learning_rate": 1.547089947089947e-05, + "loss": 0.1326, "step": 214 }, { - "epoch": 0.8669354838709677, - "grad_norm": 2.805100202560425, - "learning_rate": 1.4220430107526883e-05, - "loss": 0.1363, + "epoch": 0.6825396825396826, + "grad_norm": 7.971780776977539, + "learning_rate": 1.544973544973545e-05, + "loss": 0.1369, "step": 215 }, { - "epoch": 0.8709677419354839, - "grad_norm": 5.203761577606201, - "learning_rate": 1.4193548387096776e-05, - "loss": 0.1403, + "epoch": 0.6857142857142857, + "grad_norm": 2.4395737648010254, + "learning_rate": 1.542857142857143e-05, + "loss": 0.197, "step": 216 }, { - "epoch": 0.875, - "grad_norm": 2.3190488815307617, - "learning_rate": 1.416666666666667e-05, - "loss": 0.2115, + "epoch": 0.6888888888888889, + "grad_norm": 5.476943016052246, + "learning_rate": 1.5407407407407408e-05, + "loss": 0.162, "step": 217 }, { - "epoch": 0.8790322580645161, - "grad_norm": 2.513376474380493, - "learning_rate": 1.4139784946236561e-05, - "loss": 0.227, + "epoch": 0.692063492063492, + "grad_norm": 3.184767484664917, + "learning_rate": 1.5386243386243388e-05, + "loss": 0.1606, "step": 218 }, { - "epoch": 0.8830645161290323, - "grad_norm": 3.1920270919799805, - "learning_rate": 1.4112903225806454e-05, - "loss": 0.1732, + "epoch": 0.6952380952380952, + "grad_norm": 0.9432739019393921, + "learning_rate": 1.5365079365079368e-05, + "loss": 0.1372, "step": 219 }, { - "epoch": 0.8870967741935484, - "grad_norm": 2.252589225769043, - "learning_rate": 1.4086021505376346e-05, - "loss": 0.1329, + "epoch": 0.6984126984126984, + "grad_norm": 6.008212089538574, + "learning_rate": 1.5343915343915344e-05, + "loss": 0.2399, "step": 220 }, { - "epoch": 0.8911290322580645, - "grad_norm": 3.943742275238037, - "learning_rate": 1.405913978494624e-05, - "loss": 0.1473, + "epoch": 0.7015873015873015, + "grad_norm": 3.830331325531006, + "learning_rate": 1.5322751322751324e-05, + "loss": 0.1825, "step": 221 }, { - "epoch": 0.8951612903225806, - "grad_norm": 4.05203104019165, - "learning_rate": 1.4032258064516131e-05, - "loss": 0.1647, + "epoch": 0.7047619047619048, + "grad_norm": 2.75203275680542, + "learning_rate": 1.53015873015873e-05, + "loss": 0.196, "step": 222 }, { - "epoch": 0.8991935483870968, - "grad_norm": 4.86761474609375, - "learning_rate": 1.4005376344086024e-05, - "loss": 0.118, + "epoch": 0.707936507936508, + "grad_norm": 5.1560444831848145, + "learning_rate": 1.528042328042328e-05, + "loss": 0.1832, "step": 223 }, { - "epoch": 0.9032258064516129, - "grad_norm": 2.4546005725860596, - "learning_rate": 1.3978494623655916e-05, - "loss": 0.2356, + "epoch": 0.7111111111111111, + "grad_norm": 6.417674541473389, + "learning_rate": 1.525925925925926e-05, + "loss": 0.1773, "step": 224 }, { - "epoch": 0.907258064516129, - "grad_norm": 1.0434294939041138, - "learning_rate": 1.3951612903225809e-05, - "loss": 0.1536, + "epoch": 0.7142857142857143, + "grad_norm": 3.6337361335754395, + "learning_rate": 1.523809523809524e-05, + "loss": 0.1186, "step": 225 }, { - "epoch": 0.9112903225806451, - "grad_norm": 1.4482147693634033, - "learning_rate": 1.39247311827957e-05, - "loss": 0.1479, + "epoch": 0.7174603174603175, + "grad_norm": 2.539357900619507, + "learning_rate": 1.521693121693122e-05, + "loss": 0.1886, "step": 226 }, { - "epoch": 0.9153225806451613, - "grad_norm": 2.1162939071655273, - "learning_rate": 1.3897849462365594e-05, - "loss": 0.2139, + "epoch": 0.7206349206349206, + "grad_norm": 1.9577362537384033, + "learning_rate": 1.5195767195767198e-05, + "loss": 0.1879, "step": 227 }, { - "epoch": 0.9193548387096774, - "grad_norm": 1.401563048362732, - "learning_rate": 1.3870967741935486e-05, - "loss": 0.2074, + "epoch": 0.7238095238095238, + "grad_norm": 3.703106641769409, + "learning_rate": 1.5174603174603176e-05, + "loss": 0.2008, "step": 228 }, { - "epoch": 0.9233870967741935, - "grad_norm": 2.659918785095215, - "learning_rate": 1.3844086021505379e-05, - "loss": 0.1711, + "epoch": 0.726984126984127, + "grad_norm": 2.486844301223755, + "learning_rate": 1.5153439153439156e-05, + "loss": 0.1421, "step": 229 }, { - "epoch": 0.9274193548387096, - "grad_norm": 2.3634390830993652, - "learning_rate": 1.381720430107527e-05, - "loss": 0.1347, + "epoch": 0.7301587301587301, + "grad_norm": 1.7644110918045044, + "learning_rate": 1.5132275132275134e-05, + "loss": 0.1294, "step": 230 }, { - "epoch": 0.9314516129032258, - "grad_norm": 3.2036492824554443, - "learning_rate": 1.3790322580645164e-05, - "loss": 0.1348, + "epoch": 0.7333333333333333, + "grad_norm": 2.7202088832855225, + "learning_rate": 1.5111111111111112e-05, + "loss": 0.1468, "step": 231 }, { - "epoch": 0.9354838709677419, - "grad_norm": 2.362253427505493, - "learning_rate": 1.3763440860215056e-05, - "loss": 0.1623, + "epoch": 0.7365079365079366, + "grad_norm": 1.8587985038757324, + "learning_rate": 1.508994708994709e-05, + "loss": 0.119, "step": 232 }, { - "epoch": 0.9395161290322581, - "grad_norm": 4.0349860191345215, - "learning_rate": 1.3736559139784945e-05, - "loss": 0.1421, + "epoch": 0.7396825396825397, + "grad_norm": 1.7913789749145508, + "learning_rate": 1.506878306878307e-05, + "loss": 0.1237, "step": 233 }, { - "epoch": 0.9435483870967742, - "grad_norm": 2.3942513465881348, - "learning_rate": 1.3709677419354839e-05, - "loss": 0.1678, + "epoch": 0.7428571428571429, + "grad_norm": 3.2184860706329346, + "learning_rate": 1.5047619047619049e-05, + "loss": 0.192, "step": 234 }, { - "epoch": 0.9475806451612904, - "grad_norm": 2.3485310077667236, - "learning_rate": 1.3682795698924732e-05, - "loss": 0.1327, + "epoch": 0.746031746031746, + "grad_norm": 2.406770706176758, + "learning_rate": 1.5026455026455027e-05, + "loss": 0.1613, "step": 235 }, { - "epoch": 0.9516129032258065, - "grad_norm": 1.8485794067382812, - "learning_rate": 1.3655913978494624e-05, - "loss": 0.0943, + "epoch": 0.7492063492063492, + "grad_norm": 2.8346099853515625, + "learning_rate": 1.5005291005291007e-05, + "loss": 0.2054, "step": 236 }, { - "epoch": 0.9556451612903226, - "grad_norm": 2.820059299468994, - "learning_rate": 1.3629032258064517e-05, - "loss": 0.1664, + "epoch": 0.7523809523809524, + "grad_norm": 1.3359458446502686, + "learning_rate": 1.4984126984126985e-05, + "loss": 0.1245, "step": 237 }, { - "epoch": 0.9596774193548387, - "grad_norm": 3.143728256225586, - "learning_rate": 1.3602150537634409e-05, - "loss": 0.2003, + "epoch": 0.7555555555555555, + "grad_norm": 2.8359599113464355, + "learning_rate": 1.4962962962962964e-05, + "loss": 0.0974, "step": 238 }, { - "epoch": 0.9637096774193549, - "grad_norm": 3.496140241622925, - "learning_rate": 1.3575268817204302e-05, - "loss": 0.1833, + "epoch": 0.7587301587301587, + "grad_norm": 1.970118761062622, + "learning_rate": 1.4941798941798944e-05, + "loss": 0.218, "step": 239 }, { - "epoch": 0.967741935483871, - "grad_norm": 2.736649751663208, - "learning_rate": 1.3548387096774194e-05, - "loss": 0.1505, + "epoch": 0.7619047619047619, + "grad_norm": 1.6468356847763062, + "learning_rate": 1.4920634920634922e-05, + "loss": 0.1568, "step": 240 }, { - "epoch": 0.9717741935483871, - "grad_norm": 2.9205009937286377, - "learning_rate": 1.3521505376344087e-05, - "loss": 0.22, + "epoch": 0.765079365079365, + "grad_norm": 0.9836739897727966, + "learning_rate": 1.48994708994709e-05, + "loss": 0.1585, "step": 241 }, { - "epoch": 0.9758064516129032, - "grad_norm": 2.8891749382019043, - "learning_rate": 1.3494623655913978e-05, - "loss": 0.1415, + "epoch": 0.7682539682539683, + "grad_norm": 4.700778007507324, + "learning_rate": 1.4878306878306878e-05, + "loss": 0.1211, "step": 242 }, { - "epoch": 0.9798387096774194, - "grad_norm": 2.7234678268432617, - "learning_rate": 1.3467741935483872e-05, - "loss": 0.1112, + "epoch": 0.7714285714285715, + "grad_norm": 3.2379305362701416, + "learning_rate": 1.4857142857142858e-05, + "loss": 0.1633, "step": 243 }, { - "epoch": 0.9838709677419355, - "grad_norm": 2.395036220550537, - "learning_rate": 1.3440860215053763e-05, - "loss": 0.1288, + "epoch": 0.7746031746031746, + "grad_norm": 1.5439188480377197, + "learning_rate": 1.4835978835978837e-05, + "loss": 0.1714, "step": 244 }, { - "epoch": 0.9879032258064516, - "grad_norm": 3.214719772338867, - "learning_rate": 1.3413978494623657e-05, - "loss": 0.1637, + "epoch": 0.7777777777777778, + "grad_norm": 1.4068561792373657, + "learning_rate": 1.4814814814814815e-05, + "loss": 0.1735, "step": 245 }, { - "epoch": 0.9919354838709677, - "grad_norm": 3.2017691135406494, - "learning_rate": 1.3387096774193548e-05, - "loss": 0.1614, + "epoch": 0.780952380952381, + "grad_norm": 1.447561264038086, + "learning_rate": 1.4793650793650795e-05, + "loss": 0.1428, "step": 246 }, { - "epoch": 0.9959677419354839, - "grad_norm": 2.6992430686950684, - "learning_rate": 1.3360215053763442e-05, - "loss": 0.125, + "epoch": 0.7841269841269841, + "grad_norm": 2.3292582035064697, + "learning_rate": 1.4772486772486773e-05, + "loss": 0.1815, "step": 247 }, { - "epoch": 1.0, - "grad_norm": 3.5830893516540527, - "learning_rate": 1.3333333333333333e-05, - "loss": 0.1237, - "step": 248 - }, - { - "epoch": 1.0, - "eval_accuracy": 0.7306818181818182, - "eval_f1": 0.8891346419684821, - "eval_loss": 0.1686243861913681, - "eval_runtime": 2.375, - "eval_samples_per_second": 370.523, - "eval_steps_per_second": 11.789, + "epoch": 0.7873015873015873, + "grad_norm": 1.2992013692855835, + "learning_rate": 1.4751322751322751e-05, + "loss": 0.1565, "step": 248 }, { - "epoch": 1.0040322580645162, - "grad_norm": 3.1516823768615723, - "learning_rate": 1.3306451612903227e-05, - "loss": 0.2192, + "epoch": 0.7904761904761904, + "grad_norm": 3.4182655811309814, + "learning_rate": 1.4730158730158733e-05, + "loss": 0.1582, "step": 249 }, { - "epoch": 1.0080645161290323, - "grad_norm": 3.530272960662842, - "learning_rate": 1.3279569892473118e-05, - "loss": 0.2153, + "epoch": 0.7936507936507936, + "grad_norm": 1.3405699729919434, + "learning_rate": 1.470899470899471e-05, + "loss": 0.1245, "step": 250 }, { - "epoch": 1.0120967741935485, - "grad_norm": 1.239799976348877, - "learning_rate": 1.3252688172043012e-05, - "loss": 0.1496, + "epoch": 0.7968253968253968, + "grad_norm": 0.7003010511398315, + "learning_rate": 1.4687830687830688e-05, + "loss": 0.0957, "step": 251 }, { - "epoch": 1.0161290322580645, - "grad_norm": 1.6457215547561646, - "learning_rate": 1.3225806451612903e-05, - "loss": 0.1542, + "epoch": 0.8, + "grad_norm": 1.5681325197219849, + "learning_rate": 1.4666666666666666e-05, + "loss": 0.1137, "step": 252 }, { - "epoch": 1.0201612903225807, - "grad_norm": 3.6155178546905518, - "learning_rate": 1.3198924731182796e-05, - "loss": 0.2078, + "epoch": 0.8031746031746032, + "grad_norm": 3.576540946960449, + "learning_rate": 1.4645502645502648e-05, + "loss": 0.1487, "step": 253 }, { - "epoch": 1.0241935483870968, - "grad_norm": 1.6368227005004883, - "learning_rate": 1.3172043010752688e-05, - "loss": 0.1271, + "epoch": 0.8063492063492064, + "grad_norm": 4.849172592163086, + "learning_rate": 1.4624338624338626e-05, + "loss": 0.1998, "step": 254 }, { - "epoch": 1.028225806451613, - "grad_norm": 3.2075986862182617, - "learning_rate": 1.3145161290322581e-05, - "loss": 0.2012, + "epoch": 0.8095238095238095, + "grad_norm": 2.1816165447235107, + "learning_rate": 1.4603174603174603e-05, + "loss": 0.1335, "step": 255 }, { - "epoch": 1.032258064516129, - "grad_norm": 2.500032901763916, - "learning_rate": 1.3118279569892473e-05, - "loss": 0.1093, + "epoch": 0.8126984126984127, + "grad_norm": 1.8356610536575317, + "learning_rate": 1.4582010582010584e-05, + "loss": 0.1827, "step": 256 }, { - "epoch": 1.0362903225806452, - "grad_norm": 2.440420150756836, - "learning_rate": 1.3091397849462366e-05, - "loss": 0.1072, + "epoch": 0.8158730158730159, + "grad_norm": 1.5214511156082153, + "learning_rate": 1.4560846560846563e-05, + "loss": 0.0861, "step": 257 }, { - "epoch": 1.0403225806451613, - "grad_norm": 3.545008659362793, - "learning_rate": 1.3064516129032258e-05, - "loss": 0.1596, + "epoch": 0.819047619047619, + "grad_norm": 2.309945821762085, + "learning_rate": 1.4539682539682541e-05, + "loss": 0.2561, "step": 258 }, { - "epoch": 1.0443548387096775, - "grad_norm": 3.0299694538116455, - "learning_rate": 1.3037634408602151e-05, - "loss": 0.1784, + "epoch": 0.8222222222222222, + "grad_norm": 2.698942184448242, + "learning_rate": 1.4518518518518521e-05, + "loss": 0.1723, "step": 259 }, { - "epoch": 1.0483870967741935, - "grad_norm": 1.5560317039489746, - "learning_rate": 1.3010752688172043e-05, - "loss": 0.1254, + "epoch": 0.8253968253968254, + "grad_norm": 1.6148662567138672, + "learning_rate": 1.44973544973545e-05, + "loss": 0.141, "step": 260 }, { - "epoch": 1.0524193548387097, - "grad_norm": 3.661555528640747, - "learning_rate": 1.2983870967741936e-05, - "loss": 0.1665, + "epoch": 0.8285714285714286, + "grad_norm": 4.186668395996094, + "learning_rate": 1.4476190476190478e-05, + "loss": 0.1033, "step": 261 }, { - "epoch": 1.0564516129032258, - "grad_norm": 2.275700092315674, - "learning_rate": 1.2956989247311828e-05, - "loss": 0.113, + "epoch": 0.8317460317460318, + "grad_norm": 2.2213001251220703, + "learning_rate": 1.4455026455026456e-05, + "loss": 0.1235, "step": 262 }, { - "epoch": 1.060483870967742, - "grad_norm": 0.8315228223800659, - "learning_rate": 1.2930107526881721e-05, - "loss": 0.1173, + "epoch": 0.834920634920635, + "grad_norm": 3.6843039989471436, + "learning_rate": 1.4433862433862436e-05, + "loss": 0.1018, "step": 263 }, { - "epoch": 1.064516129032258, - "grad_norm": 1.0392459630966187, - "learning_rate": 1.2903225806451613e-05, - "loss": 0.0891, + "epoch": 0.8380952380952381, + "grad_norm": 0.9706499576568604, + "learning_rate": 1.4412698412698414e-05, + "loss": 0.1001, "step": 264 }, { - "epoch": 1.0685483870967742, - "grad_norm": 1.7290191650390625, - "learning_rate": 1.2876344086021506e-05, - "loss": 0.1432, + "epoch": 0.8412698412698413, + "grad_norm": 1.6345038414001465, + "learning_rate": 1.4391534391534392e-05, + "loss": 0.1367, "step": 265 }, { - "epoch": 1.0725806451612903, - "grad_norm": 4.252922058105469, - "learning_rate": 1.28494623655914e-05, - "loss": 0.1772, + "epoch": 0.8444444444444444, + "grad_norm": 1.3537975549697876, + "learning_rate": 1.4370370370370372e-05, + "loss": 0.175, "step": 266 }, { - "epoch": 1.0766129032258065, - "grad_norm": 3.656017303466797, - "learning_rate": 1.2822580645161291e-05, - "loss": 0.1832, + "epoch": 0.8476190476190476, + "grad_norm": 1.4531346559524536, + "learning_rate": 1.434920634920635e-05, + "loss": 0.1876, "step": 267 }, { - "epoch": 1.0806451612903225, - "grad_norm": 8.33147144317627, - "learning_rate": 1.2795698924731184e-05, - "loss": 0.219, + "epoch": 0.8507936507936508, + "grad_norm": 1.668214201927185, + "learning_rate": 1.4328042328042329e-05, + "loss": 0.168, "step": 268 }, { - "epoch": 1.0846774193548387, - "grad_norm": 2.9899277687072754, - "learning_rate": 1.2768817204301076e-05, - "loss": 0.1716, + "epoch": 0.8539682539682539, + "grad_norm": 1.1716333627700806, + "learning_rate": 1.4306878306878309e-05, + "loss": 0.1414, "step": 269 }, { - "epoch": 1.0887096774193548, - "grad_norm": 1.3610584735870361, - "learning_rate": 1.274193548387097e-05, - "loss": 0.145, + "epoch": 0.8571428571428571, + "grad_norm": 3.607603073120117, + "learning_rate": 1.4285714285714287e-05, + "loss": 0.1904, "step": 270 }, { - "epoch": 1.092741935483871, - "grad_norm": 3.155823230743408, - "learning_rate": 1.2715053763440861e-05, - "loss": 0.1671, + "epoch": 0.8603174603174604, + "grad_norm": 2.1476221084594727, + "learning_rate": 1.4264550264550265e-05, + "loss": 0.2695, "step": 271 }, { - "epoch": 1.096774193548387, - "grad_norm": 2.408665657043457, - "learning_rate": 1.2688172043010754e-05, - "loss": 0.1151, + "epoch": 0.8634920634920635, + "grad_norm": 3.314110279083252, + "learning_rate": 1.4243386243386244e-05, + "loss": 0.194, "step": 272 }, { - "epoch": 1.1008064516129032, - "grad_norm": 1.192688226699829, - "learning_rate": 1.2661290322580646e-05, - "loss": 0.1489, + "epoch": 0.8666666666666667, + "grad_norm": 2.1999711990356445, + "learning_rate": 1.4222222222222224e-05, + "loss": 0.2319, "step": 273 }, { - "epoch": 1.1048387096774193, - "grad_norm": 2.6764822006225586, - "learning_rate": 1.2634408602150539e-05, - "loss": 0.1593, + "epoch": 0.8698412698412699, + "grad_norm": 1.2907705307006836, + "learning_rate": 1.4201058201058202e-05, + "loss": 0.105, "step": 274 }, { - "epoch": 1.1088709677419355, - "grad_norm": 4.13783073425293, - "learning_rate": 1.260752688172043e-05, - "loss": 0.1911, + "epoch": 0.873015873015873, + "grad_norm": 4.240512847900391, + "learning_rate": 1.417989417989418e-05, + "loss": 0.1439, "step": 275 }, { - "epoch": 1.1129032258064515, - "grad_norm": 1.4944156408309937, - "learning_rate": 1.2580645161290324e-05, - "loss": 0.2192, + "epoch": 0.8761904761904762, + "grad_norm": 3.2701852321624756, + "learning_rate": 1.415873015873016e-05, + "loss": 0.1819, "step": 276 }, { - "epoch": 1.1169354838709677, - "grad_norm": 1.162097692489624, - "learning_rate": 1.2553763440860216e-05, - "loss": 0.1277, + "epoch": 0.8793650793650793, + "grad_norm": 1.739965558052063, + "learning_rate": 1.4137566137566138e-05, + "loss": 0.1291, "step": 277 }, { - "epoch": 1.120967741935484, - "grad_norm": 2.7152187824249268, - "learning_rate": 1.2526881720430109e-05, - "loss": 0.2191, + "epoch": 0.8825396825396825, + "grad_norm": 2.036005735397339, + "learning_rate": 1.4116402116402117e-05, + "loss": 0.2069, "step": 278 }, { - "epoch": 1.125, - "grad_norm": 2.895779609680176, - "learning_rate": 1.25e-05, - "loss": 0.1696, + "epoch": 0.8857142857142857, + "grad_norm": 2.5953922271728516, + "learning_rate": 1.4095238095238097e-05, + "loss": 0.2029, "step": 279 }, { - "epoch": 1.129032258064516, - "grad_norm": 2.1827454566955566, - "learning_rate": 1.2473118279569894e-05, - "loss": 0.0868, + "epoch": 0.8888888888888888, + "grad_norm": 1.72487211227417, + "learning_rate": 1.4074074074074075e-05, + "loss": 0.1147, "step": 280 }, { - "epoch": 1.1330645161290323, - "grad_norm": 2.273141860961914, - "learning_rate": 1.2446236559139786e-05, - "loss": 0.214, + "epoch": 0.8920634920634921, + "grad_norm": 1.705685019493103, + "learning_rate": 1.4052910052910053e-05, + "loss": 0.1854, "step": 281 }, { - "epoch": 1.1370967741935485, - "grad_norm": 1.9680695533752441, - "learning_rate": 1.2419354838709679e-05, - "loss": 0.1716, + "epoch": 0.8952380952380953, + "grad_norm": 3.095240831375122, + "learning_rate": 1.4031746031746032e-05, + "loss": 0.2166, "step": 282 }, { - "epoch": 1.1411290322580645, - "grad_norm": 1.9214951992034912, - "learning_rate": 1.239247311827957e-05, - "loss": 0.1965, + "epoch": 0.8984126984126984, + "grad_norm": 2.2673282623291016, + "learning_rate": 1.4010582010582011e-05, + "loss": 0.139, "step": 283 }, { - "epoch": 1.1451612903225807, - "grad_norm": 5.198123931884766, - "learning_rate": 1.2365591397849464e-05, - "loss": 0.1683, + "epoch": 0.9015873015873016, + "grad_norm": 3.7579991817474365, + "learning_rate": 1.398941798941799e-05, + "loss": 0.1745, "step": 284 }, { - "epoch": 1.1491935483870968, - "grad_norm": 1.6851317882537842, - "learning_rate": 1.2338709677419355e-05, - "loss": 0.1698, + "epoch": 0.9047619047619048, + "grad_norm": 6.235836029052734, + "learning_rate": 1.3968253968253968e-05, + "loss": 0.179, "step": 285 }, { - "epoch": 1.153225806451613, - "grad_norm": 2.037721633911133, - "learning_rate": 1.2311827956989249e-05, - "loss": 0.1484, + "epoch": 0.9079365079365079, + "grad_norm": 1.3303059339523315, + "learning_rate": 1.394708994708995e-05, + "loss": 0.1535, "step": 286 }, { - "epoch": 1.157258064516129, - "grad_norm": 1.9201178550720215, - "learning_rate": 1.228494623655914e-05, - "loss": 0.1128, + "epoch": 0.9111111111111111, + "grad_norm": 1.2757624387741089, + "learning_rate": 1.3925925925925928e-05, + "loss": 0.1452, "step": 287 }, { - "epoch": 1.1612903225806452, - "grad_norm": 2.517728090286255, - "learning_rate": 1.2258064516129034e-05, - "loss": 0.1865, + "epoch": 0.9142857142857143, + "grad_norm": 2.2414748668670654, + "learning_rate": 1.3904761904761905e-05, + "loss": 0.156, "step": 288 }, { - "epoch": 1.1653225806451613, - "grad_norm": 2.0093541145324707, - "learning_rate": 1.2231182795698925e-05, - "loss": 0.1765, + "epoch": 0.9174603174603174, + "grad_norm": 2.7450666427612305, + "learning_rate": 1.3883597883597886e-05, + "loss": 0.1768, "step": 289 }, { - "epoch": 1.1693548387096775, - "grad_norm": 2.9235808849334717, - "learning_rate": 1.2204301075268819e-05, - "loss": 0.2289, + "epoch": 0.9206349206349206, + "grad_norm": 2.581735610961914, + "learning_rate": 1.3862433862433865e-05, + "loss": 0.1784, "step": 290 }, { - "epoch": 1.1733870967741935, - "grad_norm": 2.3604586124420166, - "learning_rate": 1.217741935483871e-05, - "loss": 0.1056, + "epoch": 0.9238095238095239, + "grad_norm": 1.9631057977676392, + "learning_rate": 1.3841269841269843e-05, + "loss": 0.0879, "step": 291 }, { - "epoch": 1.1774193548387097, - "grad_norm": 2.574960947036743, - "learning_rate": 1.2150537634408604e-05, - "loss": 0.1599, + "epoch": 0.926984126984127, + "grad_norm": 2.2261180877685547, + "learning_rate": 1.3820105820105821e-05, + "loss": 0.1594, "step": 292 }, { - "epoch": 1.1814516129032258, - "grad_norm": 3.23299241065979, - "learning_rate": 1.2123655913978495e-05, - "loss": 0.0828, + "epoch": 0.9301587301587302, + "grad_norm": 1.0249488353729248, + "learning_rate": 1.3798941798941801e-05, + "loss": 0.1111, "step": 293 }, { - "epoch": 1.185483870967742, - "grad_norm": 3.568268299102783, - "learning_rate": 1.2096774193548388e-05, - "loss": 0.168, + "epoch": 0.9333333333333333, + "grad_norm": 1.885877251625061, + "learning_rate": 1.377777777777778e-05, + "loss": 0.1575, "step": 294 }, { - "epoch": 1.189516129032258, - "grad_norm": 1.8116379976272583, - "learning_rate": 1.2069892473118282e-05, - "loss": 0.1233, + "epoch": 0.9365079365079365, + "grad_norm": 4.145503997802734, + "learning_rate": 1.3756613756613758e-05, + "loss": 0.1411, "step": 295 }, { - "epoch": 1.1935483870967742, - "grad_norm": 2.839566469192505, - "learning_rate": 1.2043010752688173e-05, - "loss": 0.1286, + "epoch": 0.9396825396825397, + "grad_norm": 2.669419765472412, + "learning_rate": 1.3735449735449738e-05, + "loss": 0.1651, "step": 296 }, { - "epoch": 1.1975806451612903, - "grad_norm": 1.3624751567840576, - "learning_rate": 1.2016129032258067e-05, - "loss": 0.1815, + "epoch": 0.9428571428571428, + "grad_norm": 2.4611153602600098, + "learning_rate": 1.3714285714285716e-05, + "loss": 0.1304, "step": 297 }, { - "epoch": 1.2016129032258065, - "grad_norm": 1.082029938697815, - "learning_rate": 1.1989247311827958e-05, - "loss": 0.1486, + "epoch": 0.946031746031746, + "grad_norm": 12.934194564819336, + "learning_rate": 1.3693121693121694e-05, + "loss": 0.1564, "step": 298 }, { - "epoch": 1.2056451612903225, - "grad_norm": 1.6093990802764893, - "learning_rate": 1.1962365591397852e-05, - "loss": 0.176, + "epoch": 0.9492063492063492, + "grad_norm": 2.1498193740844727, + "learning_rate": 1.3671957671957674e-05, + "loss": 0.1515, "step": 299 }, { - "epoch": 1.2096774193548387, - "grad_norm": 1.5934983491897583, - "learning_rate": 1.1935483870967743e-05, - "loss": 0.1167, + "epoch": 0.9523809523809523, + "grad_norm": 13.072610855102539, + "learning_rate": 1.3650793650793652e-05, + "loss": 0.1777, "step": 300 }, { - "epoch": 1.2137096774193548, - "grad_norm": 1.5063905715942383, - "learning_rate": 1.1908602150537637e-05, - "loss": 0.1091, + "epoch": 0.9555555555555556, + "grad_norm": 2.69329833984375, + "learning_rate": 1.362962962962963e-05, + "loss": 0.2195, "step": 301 }, { - "epoch": 1.217741935483871, - "grad_norm": 2.482288122177124, - "learning_rate": 1.1881720430107528e-05, - "loss": 0.171, + "epoch": 0.9587301587301588, + "grad_norm": 7.85850191116333, + "learning_rate": 1.3608465608465609e-05, + "loss": 0.2148, "step": 302 }, { - "epoch": 1.221774193548387, - "grad_norm": 2.164362907409668, - "learning_rate": 1.1854838709677421e-05, - "loss": 0.1996, + "epoch": 0.9619047619047619, + "grad_norm": 1.2001575231552124, + "learning_rate": 1.3587301587301589e-05, + "loss": 0.176, "step": 303 }, { - "epoch": 1.2258064516129032, - "grad_norm": 1.5960315465927124, - "learning_rate": 1.1827956989247313e-05, - "loss": 0.1211, + "epoch": 0.9650793650793651, + "grad_norm": 4.107234001159668, + "learning_rate": 1.3566137566137567e-05, + "loss": 0.1262, "step": 304 }, { - "epoch": 1.2298387096774193, - "grad_norm": 3.244338274002075, - "learning_rate": 1.1801075268817206e-05, - "loss": 0.1378, + "epoch": 0.9682539682539683, + "grad_norm": 2.228184223175049, + "learning_rate": 1.3544973544973545e-05, + "loss": 0.1622, "step": 305 }, { - "epoch": 1.2338709677419355, - "grad_norm": 1.7096904516220093, - "learning_rate": 1.1774193548387098e-05, - "loss": 0.1706, + "epoch": 0.9714285714285714, + "grad_norm": 3.4293947219848633, + "learning_rate": 1.3523809523809525e-05, + "loss": 0.1509, "step": 306 }, { - "epoch": 1.2379032258064515, - "grad_norm": 1.980499505996704, - "learning_rate": 1.1747311827956991e-05, - "loss": 0.1233, + "epoch": 0.9746031746031746, + "grad_norm": 4.10245943069458, + "learning_rate": 1.3502645502645504e-05, + "loss": 0.1495, "step": 307 }, { - "epoch": 1.2419354838709677, - "grad_norm": 1.3346567153930664, - "learning_rate": 1.1720430107526883e-05, - "loss": 0.1496, + "epoch": 0.9777777777777777, + "grad_norm": 5.105010986328125, + "learning_rate": 1.3481481481481482e-05, + "loss": 0.1396, "step": 308 }, { - "epoch": 1.245967741935484, - "grad_norm": 1.437386393547058, - "learning_rate": 1.1693548387096776e-05, - "loss": 0.1306, + "epoch": 0.9809523809523809, + "grad_norm": 7.8616204261779785, + "learning_rate": 1.3460317460317462e-05, + "loss": 0.2472, "step": 309 }, { - "epoch": 1.25, - "grad_norm": 1.8189259767532349, - "learning_rate": 1.1666666666666668e-05, - "loss": 0.1579, + "epoch": 0.9841269841269841, + "grad_norm": 1.4933618307113647, + "learning_rate": 1.343915343915344e-05, + "loss": 0.1244, "step": 310 }, { - "epoch": 1.254032258064516, - "grad_norm": 2.060695171356201, - "learning_rate": 1.1639784946236561e-05, - "loss": 0.1289, + "epoch": 0.9873015873015873, + "grad_norm": 1.834869384765625, + "learning_rate": 1.3417989417989418e-05, + "loss": 0.1622, "step": 311 }, { - "epoch": 1.2580645161290323, - "grad_norm": 2.4348952770233154, - "learning_rate": 1.1612903225806453e-05, - "loss": 0.1002, + "epoch": 0.9904761904761905, + "grad_norm": 4.037169456481934, + "learning_rate": 1.3396825396825397e-05, + "loss": 0.1314, "step": 312 }, { - "epoch": 1.2620967741935485, - "grad_norm": 1.843311071395874, - "learning_rate": 1.1586021505376346e-05, - "loss": 0.1457, + "epoch": 0.9936507936507937, + "grad_norm": 2.5830981731414795, + "learning_rate": 1.3375661375661377e-05, + "loss": 0.1215, "step": 313 }, { - "epoch": 1.2661290322580645, - "grad_norm": 2.4911584854125977, - "learning_rate": 1.1559139784946238e-05, - "loss": 0.1832, + "epoch": 0.9968253968253968, + "grad_norm": 2.4278595447540283, + "learning_rate": 1.3354497354497355e-05, + "loss": 0.1286, "step": 314 }, { - "epoch": 1.2701612903225805, - "grad_norm": 4.787015438079834, - "learning_rate": 1.1532258064516131e-05, - "loss": 0.1762, + "epoch": 1.0, + "grad_norm": 2.330660104751587, + "learning_rate": 1.3333333333333333e-05, + "loss": 0.2047, "step": 315 }, { - "epoch": 1.2741935483870968, - "grad_norm": 2.0192394256591797, - "learning_rate": 1.1505376344086023e-05, - "loss": 0.1286, + "epoch": 1.0, + "eval_accuracy": 0.7267857142857143, + "eval_f1": 0.8863636363636364, + "eval_loss": 0.16110745072364807, + "eval_runtime": 2.9484, + "eval_samples_per_second": 379.864, + "eval_steps_per_second": 11.871, + "step": 315 + }, + { + "epoch": 1.0031746031746032, + "grad_norm": 1.493116021156311, + "learning_rate": 1.3312169312169313e-05, + "loss": 0.1066, "step": 316 }, { - "epoch": 1.278225806451613, - "grad_norm": 0.9655114412307739, - "learning_rate": 1.1478494623655916e-05, - "loss": 0.0727, + "epoch": 1.0063492063492063, + "grad_norm": 0.9289090037345886, + "learning_rate": 1.3291005291005292e-05, + "loss": 0.1167, "step": 317 }, { - "epoch": 1.282258064516129, - "grad_norm": 1.3966825008392334, - "learning_rate": 1.1451612903225808e-05, - "loss": 0.1365, + "epoch": 1.0095238095238095, + "grad_norm": 3.8022475242614746, + "learning_rate": 1.326984126984127e-05, + "loss": 0.1556, "step": 318 }, { - "epoch": 1.2862903225806452, - "grad_norm": 1.7151025533676147, - "learning_rate": 1.1424731182795701e-05, - "loss": 0.1583, + "epoch": 1.0126984126984127, + "grad_norm": 2.4524595737457275, + "learning_rate": 1.3248677248677251e-05, + "loss": 0.1208, "step": 319 }, { - "epoch": 1.2903225806451613, - "grad_norm": 2.77651309967041, - "learning_rate": 1.1397849462365593e-05, - "loss": 0.0976, + "epoch": 1.0158730158730158, + "grad_norm": 3.6084091663360596, + "learning_rate": 1.322751322751323e-05, + "loss": 0.2097, "step": 320 }, { - "epoch": 1.2943548387096775, - "grad_norm": 1.6842812299728394, - "learning_rate": 1.1370967741935486e-05, - "loss": 0.0929, + "epoch": 1.019047619047619, + "grad_norm": 2.7822537422180176, + "learning_rate": 1.3206349206349206e-05, + "loss": 0.0952, "step": 321 }, { - "epoch": 1.2983870967741935, - "grad_norm": 1.3794842958450317, - "learning_rate": 1.1344086021505377e-05, - "loss": 0.2264, + "epoch": 1.0222222222222221, + "grad_norm": 2.6857662200927734, + "learning_rate": 1.3185185185185185e-05, + "loss": 0.1895, "step": 322 }, { - "epoch": 1.3024193548387097, - "grad_norm": 1.75082266330719, - "learning_rate": 1.131720430107527e-05, - "loss": 0.1209, + "epoch": 1.0253968253968253, + "grad_norm": 2.6811914443969727, + "learning_rate": 1.3164021164021166e-05, + "loss": 0.17, "step": 323 }, { - "epoch": 1.3064516129032258, - "grad_norm": 3.0138330459594727, - "learning_rate": 1.1290322580645164e-05, - "loss": 0.1394, + "epoch": 1.0285714285714285, + "grad_norm": 3.0869393348693848, + "learning_rate": 1.3142857142857145e-05, + "loss": 0.2138, "step": 324 }, { - "epoch": 1.310483870967742, - "grad_norm": 1.3630236387252808, - "learning_rate": 1.1263440860215056e-05, - "loss": 0.0678, + "epoch": 1.0317460317460316, + "grad_norm": 2.0946178436279297, + "learning_rate": 1.3121693121693123e-05, + "loss": 0.1921, "step": 325 }, { - "epoch": 1.314516129032258, - "grad_norm": 3.041550636291504, - "learning_rate": 1.1236559139784946e-05, - "loss": 0.2057, + "epoch": 1.034920634920635, + "grad_norm": 2.0854218006134033, + "learning_rate": 1.3100529100529103e-05, + "loss": 0.105, "step": 326 }, { - "epoch": 1.3185483870967742, - "grad_norm": 1.457026720046997, - "learning_rate": 1.1209677419354839e-05, - "loss": 0.1104, + "epoch": 1.0380952380952382, + "grad_norm": 2.6408188343048096, + "learning_rate": 1.3079365079365081e-05, + "loss": 0.2082, "step": 327 }, { - "epoch": 1.3225806451612903, - "grad_norm": 2.0328333377838135, - "learning_rate": 1.118279569892473e-05, - "loss": 0.13, + "epoch": 1.0412698412698413, + "grad_norm": 2.556913375854492, + "learning_rate": 1.305820105820106e-05, + "loss": 0.188, "step": 328 }, { - "epoch": 1.3266129032258065, - "grad_norm": 1.102391242980957, - "learning_rate": 1.1155913978494624e-05, - "loss": 0.1015, + "epoch": 1.0444444444444445, + "grad_norm": 4.279627799987793, + "learning_rate": 1.303703703703704e-05, + "loss": 0.2104, "step": 329 }, { - "epoch": 1.3306451612903225, - "grad_norm": 1.9321506023406982, - "learning_rate": 1.1129032258064516e-05, - "loss": 0.085, + "epoch": 1.0476190476190477, + "grad_norm": 2.2577993869781494, + "learning_rate": 1.3015873015873018e-05, + "loss": 0.115, "step": 330 }, { - "epoch": 1.3346774193548387, - "grad_norm": 1.9749724864959717, - "learning_rate": 1.1102150537634409e-05, - "loss": 0.1343, + "epoch": 1.0507936507936508, + "grad_norm": 2.118206024169922, + "learning_rate": 1.2994708994708996e-05, + "loss": 0.2383, "step": 331 }, { - "epoch": 1.3387096774193548, - "grad_norm": 2.8448033332824707, - "learning_rate": 1.10752688172043e-05, - "loss": 0.1639, + "epoch": 1.053968253968254, + "grad_norm": 2.9431445598602295, + "learning_rate": 1.2973544973544974e-05, + "loss": 0.159, "step": 332 }, { - "epoch": 1.342741935483871, - "grad_norm": 1.1829770803451538, - "learning_rate": 1.1048387096774194e-05, - "loss": 0.0986, + "epoch": 1.0571428571428572, + "grad_norm": 2.5980441570281982, + "learning_rate": 1.2952380952380954e-05, + "loss": 0.1263, "step": 333 }, { - "epoch": 1.346774193548387, - "grad_norm": 3.9288711547851562, - "learning_rate": 1.1021505376344085e-05, - "loss": 0.1465, + "epoch": 1.0603174603174603, + "grad_norm": 6.694130897521973, + "learning_rate": 1.2931216931216932e-05, + "loss": 0.1362, "step": 334 }, { - "epoch": 1.3508064516129032, - "grad_norm": 2.407360553741455, - "learning_rate": 1.0994623655913979e-05, - "loss": 0.1261, + "epoch": 1.0634920634920635, + "grad_norm": 2.063152313232422, + "learning_rate": 1.291005291005291e-05, + "loss": 0.1782, "step": 335 }, { - "epoch": 1.3548387096774195, - "grad_norm": 3.4650471210479736, - "learning_rate": 1.096774193548387e-05, - "loss": 0.1828, + "epoch": 1.0666666666666667, + "grad_norm": 6.061702728271484, + "learning_rate": 1.288888888888889e-05, + "loss": 0.1393, "step": 336 }, { - "epoch": 1.3588709677419355, - "grad_norm": 2.9928531646728516, - "learning_rate": 1.0940860215053764e-05, - "loss": 0.1139, + "epoch": 1.0698412698412698, + "grad_norm": 3.2280876636505127, + "learning_rate": 1.2867724867724869e-05, + "loss": 0.1995, "step": 337 }, { - "epoch": 1.3629032258064515, - "grad_norm": 4.049187183380127, - "learning_rate": 1.0913978494623655e-05, - "loss": 0.1622, + "epoch": 1.073015873015873, + "grad_norm": 5.355496883392334, + "learning_rate": 1.2846560846560847e-05, + "loss": 0.2004, "step": 338 }, { - "epoch": 1.3669354838709677, - "grad_norm": 3.758409023284912, - "learning_rate": 1.0887096774193549e-05, - "loss": 0.1058, + "epoch": 1.0761904761904761, + "grad_norm": 1.330000877380371, + "learning_rate": 1.2825396825396827e-05, + "loss": 0.1392, "step": 339 }, { - "epoch": 1.370967741935484, - "grad_norm": 3.3022146224975586, - "learning_rate": 1.086021505376344e-05, - "loss": 0.1414, + "epoch": 1.0793650793650793, + "grad_norm": 1.7811537981033325, + "learning_rate": 1.2804232804232805e-05, + "loss": 0.1415, "step": 340 }, { - "epoch": 1.375, - "grad_norm": 6.569581985473633, - "learning_rate": 1.0833333333333334e-05, - "loss": 0.2535, + "epoch": 1.0825396825396825, + "grad_norm": 2.6287171840667725, + "learning_rate": 1.2783068783068784e-05, + "loss": 0.1555, "step": 341 }, { - "epoch": 1.379032258064516, - "grad_norm": 1.4087936878204346, - "learning_rate": 1.0806451612903225e-05, - "loss": 0.1063, + "epoch": 1.0857142857142856, + "grad_norm": 1.5245591402053833, + "learning_rate": 1.2761904761904762e-05, + "loss": 0.123, "step": 342 }, { - "epoch": 1.3830645161290323, - "grad_norm": 1.7777235507965088, - "learning_rate": 1.0779569892473118e-05, - "loss": 0.1408, + "epoch": 1.0888888888888888, + "grad_norm": 4.02030086517334, + "learning_rate": 1.2740740740740742e-05, + "loss": 0.1671, "step": 343 }, { - "epoch": 1.3870967741935485, - "grad_norm": 1.5745316743850708, - "learning_rate": 1.0752688172043012e-05, - "loss": 0.0839, + "epoch": 1.0920634920634922, + "grad_norm": 2.0448102951049805, + "learning_rate": 1.271957671957672e-05, + "loss": 0.1719, "step": 344 }, { - "epoch": 1.3911290322580645, - "grad_norm": 3.317399024963379, - "learning_rate": 1.0725806451612903e-05, - "loss": 0.1597, + "epoch": 1.0952380952380953, + "grad_norm": 2.516223907470703, + "learning_rate": 1.2698412698412699e-05, + "loss": 0.1329, "step": 345 }, { - "epoch": 1.3951612903225805, - "grad_norm": 2.1819188594818115, - "learning_rate": 1.0698924731182797e-05, - "loss": 0.0801, + "epoch": 1.0984126984126985, + "grad_norm": 1.3673611879348755, + "learning_rate": 1.2677248677248679e-05, + "loss": 0.1308, "step": 346 }, { - "epoch": 1.3991935483870968, - "grad_norm": 3.0169897079467773, - "learning_rate": 1.0672043010752688e-05, - "loss": 0.1419, + "epoch": 1.1015873015873017, + "grad_norm": 2.084986448287964, + "learning_rate": 1.2656084656084657e-05, + "loss": 0.2182, "step": 347 }, { - "epoch": 1.403225806451613, - "grad_norm": 2.023202419281006, - "learning_rate": 1.0645161290322582e-05, - "loss": 0.1038, + "epoch": 1.1047619047619048, + "grad_norm": 3.738492488861084, + "learning_rate": 1.2634920634920635e-05, + "loss": 0.1789, "step": 348 }, { - "epoch": 1.407258064516129, - "grad_norm": 1.4076378345489502, - "learning_rate": 1.0618279569892473e-05, - "loss": 0.1048, + "epoch": 1.107936507936508, + "grad_norm": 2.746943473815918, + "learning_rate": 1.2613756613756615e-05, + "loss": 0.1501, "step": 349 }, { - "epoch": 1.4112903225806452, - "grad_norm": 2.562121629714966, - "learning_rate": 1.0591397849462367e-05, - "loss": 0.2181, + "epoch": 1.1111111111111112, + "grad_norm": 1.7954941987991333, + "learning_rate": 1.2592592592592593e-05, + "loss": 0.1399, "step": 350 }, { - "epoch": 1.4153225806451613, - "grad_norm": 2.308161973953247, - "learning_rate": 1.0564516129032258e-05, - "loss": 0.1669, + "epoch": 1.1142857142857143, + "grad_norm": 2.192413091659546, + "learning_rate": 1.2571428571428572e-05, + "loss": 0.1544, "step": 351 }, { - "epoch": 1.4193548387096775, - "grad_norm": 1.25361168384552, - "learning_rate": 1.0537634408602151e-05, - "loss": 0.0966, + "epoch": 1.1174603174603175, + "grad_norm": 2.0586042404174805, + "learning_rate": 1.255026455026455e-05, + "loss": 0.1245, "step": 352 }, { - "epoch": 1.4233870967741935, - "grad_norm": 4.17478609085083, - "learning_rate": 1.0510752688172043e-05, - "loss": 0.169, + "epoch": 1.1206349206349207, + "grad_norm": 4.064761638641357, + "learning_rate": 1.2529100529100532e-05, + "loss": 0.1876, "step": 353 }, { - "epoch": 1.4274193548387097, - "grad_norm": 3.2306907176971436, - "learning_rate": 1.0483870967741936e-05, - "loss": 0.1613, + "epoch": 1.1238095238095238, + "grad_norm": 2.473125696182251, + "learning_rate": 1.2507936507936508e-05, + "loss": 0.1306, "step": 354 }, { - "epoch": 1.4314516129032258, - "grad_norm": 4.039083957672119, - "learning_rate": 1.0456989247311828e-05, - "loss": 0.334, + "epoch": 1.126984126984127, + "grad_norm": 1.7009042501449585, + "learning_rate": 1.2486772486772486e-05, + "loss": 0.1535, "step": 355 }, { - "epoch": 1.435483870967742, - "grad_norm": 3.141918182373047, - "learning_rate": 1.0430107526881721e-05, - "loss": 0.1727, + "epoch": 1.1301587301587301, + "grad_norm": 3.833268404006958, + "learning_rate": 1.2465608465608468e-05, + "loss": 0.1056, "step": 356 }, { - "epoch": 1.439516129032258, - "grad_norm": 4.222794532775879, - "learning_rate": 1.0403225806451613e-05, - "loss": 0.1147, + "epoch": 1.1333333333333333, + "grad_norm": 3.7939813137054443, + "learning_rate": 1.2444444444444446e-05, + "loss": 0.1871, "step": 357 }, { - "epoch": 1.4435483870967742, - "grad_norm": 1.3107784986495972, - "learning_rate": 1.0376344086021506e-05, - "loss": 0.0728, + "epoch": 1.1365079365079365, + "grad_norm": 1.6830247640609741, + "learning_rate": 1.2423280423280425e-05, + "loss": 0.1766, "step": 358 }, { - "epoch": 1.4475806451612903, - "grad_norm": 5.24909782409668, - "learning_rate": 1.0349462365591398e-05, - "loss": 0.2182, + "epoch": 1.1396825396825396, + "grad_norm": 3.6669888496398926, + "learning_rate": 1.2402116402116405e-05, + "loss": 0.0969, "step": 359 }, { - "epoch": 1.4516129032258065, - "grad_norm": 4.10903787612915, - "learning_rate": 1.0322580645161291e-05, - "loss": 0.1699, + "epoch": 1.1428571428571428, + "grad_norm": 2.666825771331787, + "learning_rate": 1.2380952380952383e-05, + "loss": 0.1329, "step": 360 }, { - "epoch": 1.4556451612903225, - "grad_norm": 2.6097729206085205, - "learning_rate": 1.0295698924731183e-05, - "loss": 0.1172, + "epoch": 1.146031746031746, + "grad_norm": 4.495283126831055, + "learning_rate": 1.2359788359788361e-05, + "loss": 0.0912, "step": 361 }, { - "epoch": 1.4596774193548387, - "grad_norm": 2.7892961502075195, - "learning_rate": 1.0268817204301076e-05, - "loss": 0.1382, + "epoch": 1.1492063492063491, + "grad_norm": 1.503815770149231, + "learning_rate": 1.233862433862434e-05, + "loss": 0.1575, "step": 362 }, { - "epoch": 1.4637096774193548, - "grad_norm": 4.481143474578857, - "learning_rate": 1.0241935483870968e-05, - "loss": 0.171, + "epoch": 1.1523809523809523, + "grad_norm": 1.1922160387039185, + "learning_rate": 1.231746031746032e-05, + "loss": 0.0874, "step": 363 }, { - "epoch": 1.467741935483871, - "grad_norm": 2.8739893436431885, - "learning_rate": 1.0215053763440861e-05, - "loss": 0.0895, + "epoch": 1.1555555555555554, + "grad_norm": 2.732219696044922, + "learning_rate": 1.2296296296296298e-05, + "loss": 0.1588, "step": 364 }, { - "epoch": 1.471774193548387, - "grad_norm": 2.5068511962890625, - "learning_rate": 1.0188172043010753e-05, - "loss": 0.1144, + "epoch": 1.1587301587301586, + "grad_norm": 2.1192362308502197, + "learning_rate": 1.2275132275132276e-05, + "loss": 0.0888, "step": 365 }, { - "epoch": 1.4758064516129032, - "grad_norm": 2.39939284324646, - "learning_rate": 1.0161290322580646e-05, - "loss": 0.1195, + "epoch": 1.161904761904762, + "grad_norm": 1.5947315692901611, + "learning_rate": 1.2253968253968256e-05, + "loss": 0.1014, "step": 366 }, { - "epoch": 1.4798387096774195, - "grad_norm": 2.4179749488830566, - "learning_rate": 1.0134408602150538e-05, - "loss": 0.1791, + "epoch": 1.1650793650793652, + "grad_norm": 1.8248993158340454, + "learning_rate": 1.2232804232804234e-05, + "loss": 0.1451, "step": 367 }, { - "epoch": 1.4838709677419355, - "grad_norm": 1.944332480430603, - "learning_rate": 1.0107526881720431e-05, - "loss": 0.1656, + "epoch": 1.1682539682539683, + "grad_norm": 2.3389058113098145, + "learning_rate": 1.2211640211640212e-05, + "loss": 0.1634, "step": 368 }, { - "epoch": 1.4879032258064515, - "grad_norm": 4.383450031280518, - "learning_rate": 1.0080645161290323e-05, - "loss": 0.1545, + "epoch": 1.1714285714285715, + "grad_norm": 2.0244433879852295, + "learning_rate": 1.2190476190476192e-05, + "loss": 0.1799, "step": 369 }, { - "epoch": 1.4919354838709677, - "grad_norm": 1.622109293937683, - "learning_rate": 1.0053763440860216e-05, - "loss": 0.0967, + "epoch": 1.1746031746031746, + "grad_norm": 1.8519314527511597, + "learning_rate": 1.216931216931217e-05, + "loss": 0.2465, "step": 370 }, { - "epoch": 1.495967741935484, - "grad_norm": 1.5308200120925903, - "learning_rate": 1.0026881720430108e-05, - "loss": 0.0721, + "epoch": 1.1777777777777778, + "grad_norm": 1.5464658737182617, + "learning_rate": 1.2148148148148149e-05, + "loss": 0.0812, "step": 371 }, { - "epoch": 1.5, - "grad_norm": 2.9791924953460693, - "learning_rate": 1e-05, - "loss": 0.1107, + "epoch": 1.180952380952381, + "grad_norm": 4.360240936279297, + "learning_rate": 1.2126984126984127e-05, + "loss": 0.2037, "step": 372 }, { - "epoch": 1.504032258064516, - "grad_norm": 2.284703254699707, - "learning_rate": 9.973118279569894e-06, - "loss": 0.1647, + "epoch": 1.1841269841269841, + "grad_norm": 2.2095305919647217, + "learning_rate": 1.2105820105820107e-05, + "loss": 0.1369, "step": 373 }, { - "epoch": 1.5080645161290323, - "grad_norm": 3.273378849029541, - "learning_rate": 9.946236559139786e-06, - "loss": 0.1238, + "epoch": 1.1873015873015873, + "grad_norm": 2.2598092555999756, + "learning_rate": 1.2084656084656086e-05, + "loss": 0.1198, "step": 374 }, { - "epoch": 1.5120967741935485, - "grad_norm": 1.6005984544754028, - "learning_rate": 9.919354838709679e-06, - "loss": 0.1222, + "epoch": 1.1904761904761905, + "grad_norm": 3.205904722213745, + "learning_rate": 1.2063492063492064e-05, + "loss": 0.1102, "step": 375 }, { - "epoch": 1.5161290322580645, - "grad_norm": 3.7144405841827393, - "learning_rate": 9.89247311827957e-06, + "epoch": 1.1936507936507936, + "grad_norm": 3.458714485168457, + "learning_rate": 1.2042328042328044e-05, "loss": 0.1352, "step": 376 }, { - "epoch": 1.5201612903225805, - "grad_norm": 2.2433135509490967, - "learning_rate": 9.865591397849464e-06, - "loss": 0.1353, + "epoch": 1.1968253968253968, + "grad_norm": 2.200188159942627, + "learning_rate": 1.2021164021164022e-05, + "loss": 0.1641, "step": 377 }, { - "epoch": 1.5241935483870968, - "grad_norm": 1.9060373306274414, - "learning_rate": 9.838709677419356e-06, - "loss": 0.0938, + "epoch": 1.2, + "grad_norm": 3.4656319618225098, + "learning_rate": 1.2e-05, + "loss": 0.2136, "step": 378 }, { - "epoch": 1.528225806451613, - "grad_norm": 2.5664989948272705, - "learning_rate": 9.811827956989249e-06, - "loss": 0.1925, + "epoch": 1.2031746031746031, + "grad_norm": 2.7244536876678467, + "learning_rate": 1.1978835978835979e-05, + "loss": 0.132, "step": 379 }, { - "epoch": 1.532258064516129, - "grad_norm": 3.4527804851531982, - "learning_rate": 9.78494623655914e-06, - "loss": 0.17, + "epoch": 1.2063492063492063, + "grad_norm": 2.0819435119628906, + "learning_rate": 1.1957671957671959e-05, + "loss": 0.18, "step": 380 }, { - "epoch": 1.536290322580645, - "grad_norm": 1.0636487007141113, - "learning_rate": 9.758064516129034e-06, - "loss": 0.0896, + "epoch": 1.2095238095238094, + "grad_norm": 3.7383503913879395, + "learning_rate": 1.1936507936507937e-05, + "loss": 0.1707, "step": 381 }, { - "epoch": 1.5403225806451613, - "grad_norm": 2.5372161865234375, - "learning_rate": 9.731182795698925e-06, - "loss": 0.2065, + "epoch": 1.2126984126984126, + "grad_norm": 2.3290884494781494, + "learning_rate": 1.1915343915343915e-05, + "loss": 0.1736, "step": 382 }, { - "epoch": 1.5443548387096775, - "grad_norm": 3.2576494216918945, - "learning_rate": 9.704301075268819e-06, + "epoch": 1.215873015873016, + "grad_norm": 1.484189748764038, + "learning_rate": 1.1894179894179895e-05, "loss": 0.1855, "step": 383 }, { - "epoch": 1.5483870967741935, - "grad_norm": 3.3559024333953857, - "learning_rate": 9.67741935483871e-06, - "loss": 0.2192, + "epoch": 1.2190476190476192, + "grad_norm": 1.6194794178009033, + "learning_rate": 1.1873015873015873e-05, + "loss": 0.1736, "step": 384 }, { - "epoch": 1.5524193548387095, - "grad_norm": 3.2494945526123047, - "learning_rate": 9.650537634408604e-06, - "loss": 0.1617, + "epoch": 1.2222222222222223, + "grad_norm": 1.0732182264328003, + "learning_rate": 1.1851851851851852e-05, + "loss": 0.159, "step": 385 }, { - "epoch": 1.5564516129032258, - "grad_norm": 2.113792896270752, - "learning_rate": 9.623655913978495e-06, - "loss": 0.187, + "epoch": 1.2253968253968255, + "grad_norm": 1.5404976606369019, + "learning_rate": 1.1830687830687833e-05, + "loss": 0.0842, "step": 386 }, { - "epoch": 1.560483870967742, - "grad_norm": 1.530720829963684, - "learning_rate": 9.596774193548389e-06, - "loss": 0.0767, + "epoch": 1.2285714285714286, + "grad_norm": 1.1594895124435425, + "learning_rate": 1.180952380952381e-05, + "loss": 0.0572, "step": 387 }, { - "epoch": 1.564516129032258, - "grad_norm": 1.9626264572143555, - "learning_rate": 9.56989247311828e-06, - "loss": 0.1725, + "epoch": 1.2317460317460318, + "grad_norm": 3.7111027240753174, + "learning_rate": 1.1788359788359788e-05, + "loss": 0.1789, "step": 388 }, { - "epoch": 1.5685483870967742, - "grad_norm": 1.6587375402450562, - "learning_rate": 9.543010752688174e-06, - "loss": 0.0998, + "epoch": 1.234920634920635, + "grad_norm": 2.3408119678497314, + "learning_rate": 1.1767195767195766e-05, + "loss": 0.1262, "step": 389 }, { - "epoch": 1.5725806451612905, - "grad_norm": 1.3230797052383423, - "learning_rate": 9.516129032258065e-06, - "loss": 0.1522, + "epoch": 1.2380952380952381, + "grad_norm": 2.6401970386505127, + "learning_rate": 1.1746031746031748e-05, + "loss": 0.1321, "step": 390 }, { - "epoch": 1.5766129032258065, - "grad_norm": 2.594186305999756, - "learning_rate": 9.489247311827959e-06, - "loss": 0.2221, + "epoch": 1.2412698412698413, + "grad_norm": 1.632755160331726, + "learning_rate": 1.1724867724867726e-05, + "loss": 0.154, "step": 391 }, { - "epoch": 1.5806451612903225, - "grad_norm": 3.0997118949890137, - "learning_rate": 9.46236559139785e-06, - "loss": 0.1009, + "epoch": 1.2444444444444445, + "grad_norm": 2.0486555099487305, + "learning_rate": 1.1703703703703703e-05, + "loss": 0.1461, "step": 392 }, { - "epoch": 1.5846774193548387, - "grad_norm": 4.0840325355529785, - "learning_rate": 9.435483870967743e-06, - "loss": 0.1231, + "epoch": 1.2476190476190476, + "grad_norm": 2.263009548187256, + "learning_rate": 1.1682539682539685e-05, + "loss": 0.1542, "step": 393 }, { - "epoch": 1.588709677419355, - "grad_norm": 3.59895658493042, - "learning_rate": 9.408602150537635e-06, - "loss": 0.1296, + "epoch": 1.2507936507936508, + "grad_norm": 2.359335422515869, + "learning_rate": 1.1661375661375663e-05, + "loss": 0.13, "step": 394 }, { - "epoch": 1.592741935483871, - "grad_norm": 1.21365487575531, - "learning_rate": 9.381720430107528e-06, - "loss": 0.1062, + "epoch": 1.253968253968254, + "grad_norm": 1.9592351913452148, + "learning_rate": 1.1640211640211641e-05, + "loss": 0.1052, "step": 395 }, { - "epoch": 1.596774193548387, - "grad_norm": 2.8088643550872803, - "learning_rate": 9.35483870967742e-06, - "loss": 0.1877, + "epoch": 1.2571428571428571, + "grad_norm": 2.915741443634033, + "learning_rate": 1.1619047619047621e-05, + "loss": 0.2004, "step": 396 }, { - "epoch": 1.6008064516129032, - "grad_norm": 2.218878746032715, - "learning_rate": 9.327956989247312e-06, - "loss": 0.1258, + "epoch": 1.2603174603174603, + "grad_norm": 3.8908677101135254, + "learning_rate": 1.15978835978836e-05, + "loss": 0.1126, "step": 397 }, { - "epoch": 1.6048387096774195, - "grad_norm": 1.3823351860046387, - "learning_rate": 9.301075268817205e-06, - "loss": 0.1048, + "epoch": 1.2634920634920634, + "grad_norm": 2.165616035461426, + "learning_rate": 1.1576719576719578e-05, + "loss": 0.1358, "step": 398 }, { - "epoch": 1.6088709677419355, - "grad_norm": 2.248091220855713, - "learning_rate": 9.274193548387097e-06, - "loss": 0.2004, + "epoch": 1.2666666666666666, + "grad_norm": 3.1054470539093018, + "learning_rate": 1.1555555555555556e-05, + "loss": 0.12, "step": 399 }, { - "epoch": 1.6129032258064515, - "grad_norm": 2.475921392440796, - "learning_rate": 9.24731182795699e-06, - "loss": 0.1216, + "epoch": 1.2698412698412698, + "grad_norm": 1.4660547971725464, + "learning_rate": 1.1534391534391536e-05, + "loss": 0.1011, "step": 400 }, { - "epoch": 1.6169354838709677, - "grad_norm": 1.0884982347488403, - "learning_rate": 9.220430107526881e-06, - "loss": 0.099, + "epoch": 1.273015873015873, + "grad_norm": 1.8497107028961182, + "learning_rate": 1.1513227513227514e-05, + "loss": 0.1406, "step": 401 }, { - "epoch": 1.620967741935484, - "grad_norm": 2.633883237838745, - "learning_rate": 9.193548387096775e-06, - "loss": 0.1015, + "epoch": 1.276190476190476, + "grad_norm": 3.7915897369384766, + "learning_rate": 1.1492063492063492e-05, + "loss": 0.1291, "step": 402 }, { - "epoch": 1.625, - "grad_norm": 1.0618445873260498, - "learning_rate": 9.166666666666666e-06, - "loss": 0.1017, + "epoch": 1.2793650793650793, + "grad_norm": 2.6062843799591064, + "learning_rate": 1.1470899470899472e-05, + "loss": 0.1131, "step": 403 }, { - "epoch": 1.629032258064516, - "grad_norm": 6.406484127044678, - "learning_rate": 9.13978494623656e-06, - "loss": 0.159, + "epoch": 1.2825396825396824, + "grad_norm": 2.563063383102417, + "learning_rate": 1.144973544973545e-05, + "loss": 0.1427, "step": 404 }, { - "epoch": 1.6330645161290323, - "grad_norm": 1.9261949062347412, - "learning_rate": 9.112903225806451e-06, - "loss": 0.1234, + "epoch": 1.2857142857142856, + "grad_norm": 2.4731216430664062, + "learning_rate": 1.1428571428571429e-05, + "loss": 0.1172, "step": 405 }, { - "epoch": 1.6370967741935485, - "grad_norm": 4.344938278198242, - "learning_rate": 9.086021505376345e-06, - "loss": 0.1519, + "epoch": 1.2888888888888888, + "grad_norm": 1.9257644414901733, + "learning_rate": 1.1407407407407409e-05, + "loss": 0.1743, "step": 406 }, { - "epoch": 1.6411290322580645, - "grad_norm": 1.627624273300171, - "learning_rate": 9.059139784946236e-06, - "loss": 0.1154, + "epoch": 1.2920634920634921, + "grad_norm": 1.8497525453567505, + "learning_rate": 1.1386243386243387e-05, + "loss": 0.1665, "step": 407 }, { - "epoch": 1.6451612903225805, - "grad_norm": 1.8751394748687744, - "learning_rate": 9.03225806451613e-06, - "loss": 0.1693, + "epoch": 1.2952380952380953, + "grad_norm": 1.9645222425460815, + "learning_rate": 1.1365079365079366e-05, + "loss": 0.1574, "step": 408 }, { - "epoch": 1.6491935483870968, - "grad_norm": 2.318906784057617, - "learning_rate": 9.005376344086021e-06, - "loss": 0.1491, + "epoch": 1.2984126984126985, + "grad_norm": 2.4440035820007324, + "learning_rate": 1.1343915343915344e-05, + "loss": 0.2244, "step": 409 }, { - "epoch": 1.653225806451613, - "grad_norm": 5.5316853523254395, - "learning_rate": 8.978494623655915e-06, - "loss": 0.2173, + "epoch": 1.3015873015873016, + "grad_norm": 2.251098394393921, + "learning_rate": 1.1322751322751324e-05, + "loss": 0.1275, "step": 410 }, { - "epoch": 1.657258064516129, - "grad_norm": 2.1360862255096436, - "learning_rate": 8.951612903225806e-06, - "loss": 0.1482, + "epoch": 1.3047619047619048, + "grad_norm": 3.4208028316497803, + "learning_rate": 1.1301587301587302e-05, + "loss": 0.2193, "step": 411 }, { - "epoch": 1.661290322580645, - "grad_norm": 1.136660099029541, - "learning_rate": 8.9247311827957e-06, - "loss": 0.1142, + "epoch": 1.307936507936508, + "grad_norm": 1.5413507223129272, + "learning_rate": 1.128042328042328e-05, + "loss": 0.2252, "step": 412 }, { - "epoch": 1.6653225806451613, - "grad_norm": 5.797788143157959, - "learning_rate": 8.897849462365593e-06, - "loss": 0.1382, + "epoch": 1.3111111111111111, + "grad_norm": 1.6421838998794556, + "learning_rate": 1.125925925925926e-05, + "loss": 0.1307, "step": 413 }, { - "epoch": 1.6693548387096775, - "grad_norm": 4.6974287033081055, - "learning_rate": 8.870967741935484e-06, - "loss": 0.1369, + "epoch": 1.3142857142857143, + "grad_norm": 1.3964706659317017, + "learning_rate": 1.1238095238095239e-05, + "loss": 0.1246, "step": 414 }, { - "epoch": 1.6733870967741935, - "grad_norm": 7.289107799530029, - "learning_rate": 8.844086021505378e-06, - "loss": 0.2441, + "epoch": 1.3174603174603174, + "grad_norm": 1.642468810081482, + "learning_rate": 1.1216931216931217e-05, + "loss": 0.1766, "step": 415 }, { - "epoch": 1.6774193548387095, - "grad_norm": 4.214983940124512, - "learning_rate": 8.81720430107527e-06, - "loss": 0.213, + "epoch": 1.3206349206349206, + "grad_norm": 2.7999608516693115, + "learning_rate": 1.1195767195767197e-05, + "loss": 0.235, "step": 416 }, { - "epoch": 1.6814516129032258, - "grad_norm": 3.4454896450042725, - "learning_rate": 8.790322580645163e-06, - "loss": 0.0803, + "epoch": 1.3238095238095238, + "grad_norm": 3.28043532371521, + "learning_rate": 1.1174603174603175e-05, + "loss": 0.2378, "step": 417 }, { - "epoch": 1.685483870967742, - "grad_norm": 2.8119094371795654, - "learning_rate": 8.763440860215054e-06, - "loss": 0.1307, + "epoch": 1.326984126984127, + "grad_norm": 2.990582227706909, + "learning_rate": 1.1153439153439153e-05, + "loss": 0.2378, "step": 418 }, { - "epoch": 1.689516129032258, - "grad_norm": 3.920039653778076, - "learning_rate": 8.736559139784948e-06, - "loss": 0.1729, + "epoch": 1.33015873015873, + "grad_norm": 1.7411229610443115, + "learning_rate": 1.1132275132275132e-05, + "loss": 0.1623, "step": 419 }, { - "epoch": 1.6935483870967742, - "grad_norm": 4.052835941314697, - "learning_rate": 8.70967741935484e-06, - "loss": 0.0988, + "epoch": 1.3333333333333333, + "grad_norm": 1.6513471603393555, + "learning_rate": 1.1111111111111113e-05, + "loss": 0.1472, "step": 420 }, { - "epoch": 1.6975806451612905, - "grad_norm": 2.297703742980957, - "learning_rate": 8.682795698924733e-06, - "loss": 0.1176, + "epoch": 1.3365079365079366, + "grad_norm": 2.166264772415161, + "learning_rate": 1.108994708994709e-05, + "loss": 0.1486, "step": 421 }, { - "epoch": 1.7016129032258065, - "grad_norm": 2.6884663105010986, - "learning_rate": 8.655913978494624e-06, - "loss": 0.1113, + "epoch": 1.3396825396825398, + "grad_norm": 2.0432753562927246, + "learning_rate": 1.1068783068783068e-05, + "loss": 0.1142, "step": 422 }, { - "epoch": 1.7056451612903225, - "grad_norm": 2.510374069213867, - "learning_rate": 8.629032258064517e-06, - "loss": 0.1428, + "epoch": 1.342857142857143, + "grad_norm": 1.8136858940124512, + "learning_rate": 1.104761904761905e-05, + "loss": 0.1368, "step": 423 }, { - "epoch": 1.7096774193548387, - "grad_norm": 1.734438419342041, - "learning_rate": 8.602150537634409e-06, - "loss": 0.0651, + "epoch": 1.3460317460317461, + "grad_norm": 2.9821174144744873, + "learning_rate": 1.1026455026455028e-05, + "loss": 0.1528, "step": 424 }, { - "epoch": 1.713709677419355, - "grad_norm": 2.6852872371673584, - "learning_rate": 8.575268817204302e-06, - "loss": 0.1801, + "epoch": 1.3492063492063493, + "grad_norm": 2.000311851501465, + "learning_rate": 1.1005291005291006e-05, + "loss": 0.0732, "step": 425 }, { - "epoch": 1.717741935483871, - "grad_norm": 1.1802809238433838, - "learning_rate": 8.548387096774194e-06, - "loss": 0.1295, + "epoch": 1.3523809523809525, + "grad_norm": 2.790471076965332, + "learning_rate": 1.0984126984126986e-05, + "loss": 0.1527, "step": 426 }, { - "epoch": 1.721774193548387, - "grad_norm": 3.5888192653656006, - "learning_rate": 8.521505376344087e-06, - "loss": 0.1373, + "epoch": 1.3555555555555556, + "grad_norm": 1.0484459400177002, + "learning_rate": 1.0962962962962965e-05, + "loss": 0.1365, "step": 427 }, { - "epoch": 1.7258064516129032, - "grad_norm": 3.463402271270752, - "learning_rate": 8.494623655913979e-06, - "loss": 0.104, + "epoch": 1.3587301587301588, + "grad_norm": 3.243304967880249, + "learning_rate": 1.0941798941798943e-05, + "loss": 0.1532, "step": 428 }, { - "epoch": 1.7298387096774195, - "grad_norm": 2.838108777999878, - "learning_rate": 8.467741935483872e-06, - "loss": 0.1541, + "epoch": 1.361904761904762, + "grad_norm": 2.3727264404296875, + "learning_rate": 1.0920634920634921e-05, + "loss": 0.1974, "step": 429 }, { - "epoch": 1.7338709677419355, - "grad_norm": 3.127835512161255, - "learning_rate": 8.440860215053764e-06, - "loss": 0.1103, + "epoch": 1.3650793650793651, + "grad_norm": 4.584876537322998, + "learning_rate": 1.0899470899470901e-05, + "loss": 0.1592, "step": 430 }, { - "epoch": 1.7379032258064515, - "grad_norm": 2.3887135982513428, - "learning_rate": 8.413978494623657e-06, - "loss": 0.1686, + "epoch": 1.3682539682539683, + "grad_norm": 1.9815607070922852, + "learning_rate": 1.087830687830688e-05, + "loss": 0.1676, "step": 431 }, { - "epoch": 1.7419354838709677, - "grad_norm": 2.5920352935791016, - "learning_rate": 8.387096774193549e-06, - "loss": 0.1187, + "epoch": 1.3714285714285714, + "grad_norm": 2.2886874675750732, + "learning_rate": 1.0857142857142858e-05, + "loss": 0.1119, "step": 432 }, { - "epoch": 1.745967741935484, - "grad_norm": 4.120633125305176, - "learning_rate": 8.360215053763442e-06, - "loss": 0.1966, + "epoch": 1.3746031746031746, + "grad_norm": 4.179121494293213, + "learning_rate": 1.0835978835978838e-05, + "loss": 0.1119, "step": 433 }, { - "epoch": 1.75, - "grad_norm": 1.4372769594192505, - "learning_rate": 8.333333333333334e-06, - "loss": 0.1419, + "epoch": 1.3777777777777778, + "grad_norm": 7.003319263458252, + "learning_rate": 1.0814814814814816e-05, + "loss": 0.1166, "step": 434 }, { - "epoch": 1.754032258064516, - "grad_norm": 2.421602964401245, - "learning_rate": 8.306451612903227e-06, - "loss": 0.145, + "epoch": 1.380952380952381, + "grad_norm": 1.0844429731369019, + "learning_rate": 1.0793650793650794e-05, + "loss": 0.0952, "step": 435 }, { - "epoch": 1.7580645161290323, - "grad_norm": 2.807343006134033, - "learning_rate": 8.279569892473119e-06, - "loss": 0.0802, + "epoch": 1.384126984126984, + "grad_norm": 1.321943759918213, + "learning_rate": 1.0772486772486774e-05, + "loss": 0.0926, "step": 436 }, { - "epoch": 1.7620967741935485, - "grad_norm": 2.304760217666626, - "learning_rate": 8.252688172043012e-06, - "loss": 0.1192, + "epoch": 1.3873015873015873, + "grad_norm": 4.837040424346924, + "learning_rate": 1.0751322751322753e-05, + "loss": 0.1381, "step": 437 }, { - "epoch": 1.7661290322580645, - "grad_norm": 2.381269693374634, - "learning_rate": 8.225806451612904e-06, - "loss": 0.1027, + "epoch": 1.3904761904761904, + "grad_norm": 1.1705752611160278, + "learning_rate": 1.073015873015873e-05, + "loss": 0.1152, "step": 438 }, { - "epoch": 1.7701612903225805, - "grad_norm": 2.1986842155456543, - "learning_rate": 8.198924731182797e-06, - "loss": 0.1012, + "epoch": 1.3936507936507936, + "grad_norm": 1.5615822076797485, + "learning_rate": 1.0708994708994709e-05, + "loss": 0.0935, "step": 439 }, { - "epoch": 1.7741935483870968, - "grad_norm": 2.638580560684204, - "learning_rate": 8.172043010752689e-06, - "loss": 0.1746, + "epoch": 1.3968253968253967, + "grad_norm": 1.4646861553192139, + "learning_rate": 1.0687830687830689e-05, + "loss": 0.1382, "step": 440 }, { - "epoch": 1.778225806451613, - "grad_norm": 4.079723358154297, - "learning_rate": 8.145161290322582e-06, - "loss": 0.1684, + "epoch": 1.4, + "grad_norm": 2.181800365447998, + "learning_rate": 1.0666666666666667e-05, + "loss": 0.1216, "step": 441 }, { - "epoch": 1.782258064516129, - "grad_norm": 1.7967092990875244, - "learning_rate": 8.118279569892473e-06, - "loss": 0.2538, + "epoch": 1.403174603174603, + "grad_norm": 1.352748990058899, + "learning_rate": 1.0645502645502646e-05, + "loss": 0.1135, "step": 442 }, { - "epoch": 1.786290322580645, - "grad_norm": 2.0538618564605713, - "learning_rate": 8.091397849462365e-06, - "loss": 0.1666, + "epoch": 1.4063492063492062, + "grad_norm": 2.702324390411377, + "learning_rate": 1.0624338624338626e-05, + "loss": 0.1025, "step": 443 }, { - "epoch": 1.7903225806451613, - "grad_norm": 3.8617451190948486, - "learning_rate": 8.064516129032258e-06, - "loss": 0.1725, + "epoch": 1.4095238095238094, + "grad_norm": 2.2290923595428467, + "learning_rate": 1.0603174603174604e-05, + "loss": 0.1118, "step": 444 }, { - "epoch": 1.7943548387096775, - "grad_norm": 3.2343311309814453, - "learning_rate": 8.03763440860215e-06, - "loss": 0.1595, + "epoch": 1.4126984126984126, + "grad_norm": 1.0538023710250854, + "learning_rate": 1.0582010582010582e-05, + "loss": 0.0943, "step": 445 }, { - "epoch": 1.7983870967741935, - "grad_norm": 2.797788619995117, - "learning_rate": 8.010752688172043e-06, - "loss": 0.0903, + "epoch": 1.415873015873016, + "grad_norm": 1.6394612789154053, + "learning_rate": 1.0560846560846562e-05, + "loss": 0.0909, "step": 446 }, { - "epoch": 1.8024193548387095, - "grad_norm": 3.4088759422302246, - "learning_rate": 7.983870967741935e-06, - "loss": 0.1113, + "epoch": 1.4190476190476191, + "grad_norm": 1.717358112335205, + "learning_rate": 1.053968253968254e-05, + "loss": 0.0854, "step": 447 }, { - "epoch": 1.8064516129032258, - "grad_norm": 3.5541694164276123, - "learning_rate": 7.956989247311828e-06, - "loss": 0.1433, + "epoch": 1.4222222222222223, + "grad_norm": 4.03108549118042, + "learning_rate": 1.0518518518518519e-05, + "loss": 0.1479, "step": 448 }, { - "epoch": 1.810483870967742, - "grad_norm": 1.529510736465454, - "learning_rate": 7.93010752688172e-06, - "loss": 0.0728, + "epoch": 1.4253968253968254, + "grad_norm": 1.4749667644500732, + "learning_rate": 1.0497354497354497e-05, + "loss": 0.1792, "step": 449 }, { - "epoch": 1.814516129032258, - "grad_norm": 1.9386626482009888, - "learning_rate": 7.903225806451613e-06, - "loss": 0.1112, + "epoch": 1.4285714285714286, + "grad_norm": 2.0299808979034424, + "learning_rate": 1.0476190476190477e-05, + "loss": 0.2274, "step": 450 }, { - "epoch": 1.8185483870967742, - "grad_norm": 2.3068759441375732, - "learning_rate": 7.876344086021507e-06, - "loss": 0.0967, + "epoch": 1.4317460317460318, + "grad_norm": 1.4367117881774902, + "learning_rate": 1.0455026455026455e-05, + "loss": 0.152, "step": 451 }, { - "epoch": 1.8225806451612905, - "grad_norm": 2.4969186782836914, - "learning_rate": 7.849462365591398e-06, - "loss": 0.0896, + "epoch": 1.434920634920635, + "grad_norm": 1.9471023082733154, + "learning_rate": 1.0433862433862433e-05, + "loss": 0.108, "step": 452 }, { - "epoch": 1.8266129032258065, - "grad_norm": 2.4641716480255127, - "learning_rate": 7.822580645161291e-06, - "loss": 0.1365, + "epoch": 1.438095238095238, + "grad_norm": 1.4798860549926758, + "learning_rate": 1.0412698412698415e-05, + "loss": 0.0844, "step": 453 }, { - "epoch": 1.8306451612903225, - "grad_norm": 4.361322402954102, - "learning_rate": 7.795698924731183e-06, - "loss": 0.1544, + "epoch": 1.4412698412698413, + "grad_norm": 1.770192265510559, + "learning_rate": 1.0391534391534392e-05, + "loss": 0.1158, "step": 454 }, { - "epoch": 1.8346774193548387, - "grad_norm": 1.1930088996887207, - "learning_rate": 7.768817204301076e-06, - "loss": 0.0941, + "epoch": 1.4444444444444444, + "grad_norm": 2.4035627841949463, + "learning_rate": 1.037037037037037e-05, + "loss": 0.092, "step": 455 }, { - "epoch": 1.838709677419355, - "grad_norm": 1.9687577486038208, - "learning_rate": 7.741935483870968e-06, - "loss": 0.114, + "epoch": 1.4476190476190476, + "grad_norm": 1.1264840364456177, + "learning_rate": 1.0349206349206352e-05, + "loss": 0.1356, "step": 456 }, { - "epoch": 1.842741935483871, - "grad_norm": 4.404200077056885, - "learning_rate": 7.715053763440861e-06, - "loss": 0.153, + "epoch": 1.4507936507936507, + "grad_norm": 2.7628140449523926, + "learning_rate": 1.032804232804233e-05, + "loss": 0.182, "step": 457 }, { - "epoch": 1.846774193548387, - "grad_norm": 0.9312377572059631, - "learning_rate": 7.688172043010753e-06, - "loss": 0.1008, + "epoch": 1.453968253968254, + "grad_norm": 1.8275346755981445, + "learning_rate": 1.0306878306878308e-05, + "loss": 0.1452, "step": 458 }, { - "epoch": 1.8508064516129032, - "grad_norm": 2.732656717300415, - "learning_rate": 7.661290322580646e-06, - "loss": 0.0629, + "epoch": 1.457142857142857, + "grad_norm": 2.4717936515808105, + "learning_rate": 1.0285714285714285e-05, + "loss": 0.1559, "step": 459 }, { - "epoch": 1.8548387096774195, - "grad_norm": 1.351778268814087, - "learning_rate": 7.634408602150538e-06, - "loss": 0.0842, + "epoch": 1.4603174603174602, + "grad_norm": 4.867701053619385, + "learning_rate": 1.0264550264550266e-05, + "loss": 0.102, "step": 460 }, { - "epoch": 1.8588709677419355, - "grad_norm": 1.4621678590774536, - "learning_rate": 7.60752688172043e-06, - "loss": 0.0929, + "epoch": 1.4634920634920636, + "grad_norm": 3.203871250152588, + "learning_rate": 1.0243386243386245e-05, + "loss": 0.1958, "step": 461 }, { - "epoch": 1.8629032258064515, - "grad_norm": 2.530639171600342, - "learning_rate": 7.580645161290323e-06, - "loss": 0.1128, + "epoch": 1.4666666666666668, + "grad_norm": 1.2240495681762695, + "learning_rate": 1.0222222222222223e-05, + "loss": 0.0732, "step": 462 }, { - "epoch": 1.8669354838709677, - "grad_norm": 1.704332709312439, - "learning_rate": 7.553763440860215e-06, - "loss": 0.1268, + "epoch": 1.46984126984127, + "grad_norm": 2.1159071922302246, + "learning_rate": 1.0201058201058203e-05, + "loss": 0.0912, "step": 463 }, { - "epoch": 1.870967741935484, - "grad_norm": 1.6047230958938599, - "learning_rate": 7.526881720430108e-06, - "loss": 0.1598, + "epoch": 1.4730158730158731, + "grad_norm": 2.4375686645507812, + "learning_rate": 1.0179894179894181e-05, + "loss": 0.1203, "step": 464 }, { - "epoch": 1.875, - "grad_norm": 1.620526909828186, - "learning_rate": 7.500000000000001e-06, - "loss": 0.0815, + "epoch": 1.4761904761904763, + "grad_norm": 4.799310207366943, + "learning_rate": 1.015873015873016e-05, + "loss": 0.1718, "step": 465 }, { - "epoch": 1.879032258064516, - "grad_norm": 3.030583620071411, - "learning_rate": 7.4731182795698935e-06, - "loss": 0.1197, + "epoch": 1.4793650793650794, + "grad_norm": 0.9188675880432129, + "learning_rate": 1.013756613756614e-05, + "loss": 0.0902, "step": 466 }, { - "epoch": 1.8830645161290323, - "grad_norm": 2.4432520866394043, - "learning_rate": 7.446236559139786e-06, - "loss": 0.2071, + "epoch": 1.4825396825396826, + "grad_norm": 2.0594594478607178, + "learning_rate": 1.0116402116402118e-05, + "loss": 0.1171, "step": 467 }, { - "epoch": 1.8870967741935485, - "grad_norm": 1.968050241470337, - "learning_rate": 7.4193548387096784e-06, - "loss": 0.0968, + "epoch": 1.4857142857142858, + "grad_norm": 5.205246925354004, + "learning_rate": 1.0095238095238096e-05, + "loss": 0.149, "step": 468 }, { - "epoch": 1.8911290322580645, - "grad_norm": 1.4884843826293945, - "learning_rate": 7.392473118279571e-06, - "loss": 0.0825, + "epoch": 1.488888888888889, + "grad_norm": 3.3321728706359863, + "learning_rate": 1.0074074074074074e-05, + "loss": 0.1113, "step": 469 }, { - "epoch": 1.8951612903225805, - "grad_norm": 1.9214873313903809, - "learning_rate": 7.365591397849463e-06, - "loss": 0.1782, + "epoch": 1.492063492063492, + "grad_norm": 1.6766455173492432, + "learning_rate": 1.0052910052910054e-05, + "loss": 0.1152, "step": 470 }, { - "epoch": 1.8991935483870968, - "grad_norm": 2.7788476943969727, - "learning_rate": 7.338709677419356e-06, - "loss": 0.1283, + "epoch": 1.4952380952380953, + "grad_norm": 2.981928825378418, + "learning_rate": 1.0031746031746033e-05, + "loss": 0.1692, "step": 471 }, { - "epoch": 1.903225806451613, - "grad_norm": 5.547091484069824, - "learning_rate": 7.311827956989248e-06, - "loss": 0.1202, + "epoch": 1.4984126984126984, + "grad_norm": 2.2022247314453125, + "learning_rate": 1.001058201058201e-05, + "loss": 0.2189, "step": 472 }, { - "epoch": 1.907258064516129, - "grad_norm": 1.0326168537139893, - "learning_rate": 7.284946236559141e-06, - "loss": 0.1248, + "epoch": 1.5015873015873016, + "grad_norm": 2.203911542892456, + "learning_rate": 9.989417989417989e-06, + "loss": 0.0883, "step": 473 }, { - "epoch": 1.911290322580645, - "grad_norm": 2.0643792152404785, - "learning_rate": 7.258064516129033e-06, - "loss": 0.1846, + "epoch": 1.5047619047619047, + "grad_norm": 1.1142319440841675, + "learning_rate": 9.968253968253969e-06, + "loss": 0.0811, "step": 474 }, { - "epoch": 1.9153225806451613, - "grad_norm": 3.634772300720215, - "learning_rate": 7.231182795698926e-06, - "loss": 0.1574, + "epoch": 1.507936507936508, + "grad_norm": 2.4971585273742676, + "learning_rate": 9.947089947089947e-06, + "loss": 0.223, "step": 475 }, { - "epoch": 1.9193548387096775, - "grad_norm": 2.878852605819702, - "learning_rate": 7.204301075268818e-06, - "loss": 0.1066, + "epoch": 1.511111111111111, + "grad_norm": 2.635141372680664, + "learning_rate": 9.925925925925927e-06, + "loss": 0.251, "step": 476 }, { - "epoch": 1.9233870967741935, - "grad_norm": 2.5109782218933105, - "learning_rate": 7.177419354838711e-06, - "loss": 0.1653, + "epoch": 1.5142857142857142, + "grad_norm": 2.4838011264801025, + "learning_rate": 9.904761904761906e-06, + "loss": 0.1446, "step": 477 }, { - "epoch": 1.9274193548387095, - "grad_norm": 3.136270761489868, - "learning_rate": 7.150537634408603e-06, - "loss": 0.1387, + "epoch": 1.5174603174603174, + "grad_norm": 2.6901798248291016, + "learning_rate": 9.883597883597884e-06, + "loss": 0.1458, "step": 478 }, { - "epoch": 1.9314516129032258, - "grad_norm": 1.636473536491394, - "learning_rate": 7.1236559139784956e-06, - "loss": 0.2813, + "epoch": 1.5206349206349206, + "grad_norm": 4.183977127075195, + "learning_rate": 9.862433862433864e-06, + "loss": 0.2341, "step": 479 }, { - "epoch": 1.935483870967742, - "grad_norm": 1.7131333351135254, - "learning_rate": 7.096774193548388e-06, - "loss": 0.0882, + "epoch": 1.5238095238095237, + "grad_norm": 2.598080635070801, + "learning_rate": 9.841269841269842e-06, + "loss": 0.1898, "step": 480 }, { - "epoch": 1.939516129032258, - "grad_norm": 1.6337999105453491, - "learning_rate": 7.0698924731182805e-06, - "loss": 0.182, + "epoch": 1.5269841269841269, + "grad_norm": 2.1619887351989746, + "learning_rate": 9.82010582010582e-06, + "loss": 0.1588, "step": 481 }, { - "epoch": 1.9435483870967742, - "grad_norm": 3.1437745094299316, - "learning_rate": 7.043010752688173e-06, - "loss": 0.1109, + "epoch": 1.53015873015873, + "grad_norm": 2.308122396469116, + "learning_rate": 9.7989417989418e-06, + "loss": 0.1557, "step": 482 }, { - "epoch": 1.9475806451612905, - "grad_norm": 2.556929588317871, - "learning_rate": 7.0161290322580654e-06, - "loss": 0.1183, + "epoch": 1.5333333333333332, + "grad_norm": 1.7778793573379517, + "learning_rate": 9.777777777777779e-06, + "loss": 0.1617, "step": 483 }, { - "epoch": 1.9516129032258065, - "grad_norm": 1.5759491920471191, - "learning_rate": 6.989247311827958e-06, - "loss": 0.1137, + "epoch": 1.5365079365079364, + "grad_norm": 3.0859830379486084, + "learning_rate": 9.756613756613757e-06, + "loss": 0.1971, "step": 484 }, { - "epoch": 1.9556451612903225, - "grad_norm": 3.2312610149383545, - "learning_rate": 6.96236559139785e-06, - "loss": 0.1508, + "epoch": 1.5396825396825395, + "grad_norm": 2.1403231620788574, + "learning_rate": 9.735449735449735e-06, + "loss": 0.1189, "step": 485 }, { - "epoch": 1.9596774193548387, - "grad_norm": 1.5898686647415161, - "learning_rate": 6.935483870967743e-06, - "loss": 0.1276, + "epoch": 1.5428571428571427, + "grad_norm": 4.6010589599609375, + "learning_rate": 9.714285714285715e-06, + "loss": 0.1381, "step": 486 }, { - "epoch": 1.963709677419355, - "grad_norm": 2.8799052238464355, - "learning_rate": 6.908602150537635e-06, - "loss": 0.118, + "epoch": 1.5460317460317459, + "grad_norm": 1.7009965181350708, + "learning_rate": 9.693121693121693e-06, + "loss": 0.0992, "step": 487 }, { - "epoch": 1.967741935483871, - "grad_norm": 3.8616013526916504, - "learning_rate": 6.881720430107528e-06, - "loss": 0.1884, + "epoch": 1.5492063492063493, + "grad_norm": 2.0229291915893555, + "learning_rate": 9.671957671957672e-06, + "loss": 0.1332, "step": 488 }, { - "epoch": 1.971774193548387, - "grad_norm": 1.7562378644943237, - "learning_rate": 6.854838709677419e-06, - "loss": 0.1048, + "epoch": 1.5523809523809524, + "grad_norm": 3.4913041591644287, + "learning_rate": 9.650793650793652e-06, + "loss": 0.1566, "step": 489 }, { - "epoch": 1.9758064516129032, - "grad_norm": 1.8255165815353394, - "learning_rate": 6.827956989247312e-06, - "loss": 0.1632, + "epoch": 1.5555555555555556, + "grad_norm": 1.3026727437973022, + "learning_rate": 9.62962962962963e-06, + "loss": 0.192, "step": 490 }, { - "epoch": 1.9798387096774195, - "grad_norm": 1.126791000366211, - "learning_rate": 6.801075268817204e-06, - "loss": 0.1529, + "epoch": 1.5587301587301587, + "grad_norm": 1.6014870405197144, + "learning_rate": 9.60846560846561e-06, + "loss": 0.1423, "step": 491 }, { - "epoch": 1.9838709677419355, - "grad_norm": 3.804797649383545, - "learning_rate": 6.774193548387097e-06, - "loss": 0.1882, + "epoch": 1.561904761904762, + "grad_norm": 2.0798182487487793, + "learning_rate": 9.587301587301588e-06, + "loss": 0.2008, "step": 492 }, { - "epoch": 1.9879032258064515, - "grad_norm": 2.6595122814178467, - "learning_rate": 6.747311827956989e-06, - "loss": 0.1564, + "epoch": 1.565079365079365, + "grad_norm": 3.1396846771240234, + "learning_rate": 9.566137566137567e-06, + "loss": 0.1842, "step": 493 }, { - "epoch": 1.9919354838709677, - "grad_norm": 1.5479234457015991, - "learning_rate": 6.720430107526882e-06, - "loss": 0.1166, + "epoch": 1.5682539682539682, + "grad_norm": 2.383753776550293, + "learning_rate": 9.544973544973546e-06, + "loss": 0.1888, "step": 494 }, { - "epoch": 1.995967741935484, - "grad_norm": 2.059999704360962, - "learning_rate": 6.693548387096774e-06, - "loss": 0.1269, + "epoch": 1.5714285714285714, + "grad_norm": 2.7741661071777344, + "learning_rate": 9.523809523809525e-06, + "loss": 0.1972, "step": 495 }, { - "epoch": 2.0, - "grad_norm": 3.3951058387756348, - "learning_rate": 6.666666666666667e-06, - "loss": 0.153, - "step": 496 - }, - { - "epoch": 2.0, - "eval_accuracy": 0.7477272727272727, - "eval_f1": 0.8979367262723521, - "eval_loss": 0.1496548354625702, - "eval_runtime": 2.3658, - "eval_samples_per_second": 371.972, - "eval_steps_per_second": 11.835, + "epoch": 1.5746031746031746, + "grad_norm": 1.238882064819336, + "learning_rate": 9.502645502645503e-06, + "loss": 0.1571, "step": 496 }, { - "epoch": 2.004032258064516, - "grad_norm": 1.5380765199661255, - "learning_rate": 6.639784946236559e-06, - "loss": 0.09, + "epoch": 1.5777777777777777, + "grad_norm": 1.7449982166290283, + "learning_rate": 9.481481481481483e-06, + "loss": 0.1096, "step": 497 }, { - "epoch": 2.0080645161290325, - "grad_norm": 2.340376615524292, - "learning_rate": 6.612903225806452e-06, - "loss": 0.1141, + "epoch": 1.580952380952381, + "grad_norm": 2.496734380722046, + "learning_rate": 9.460317460317461e-06, + "loss": 0.1436, "step": 498 }, { - "epoch": 2.0120967741935485, - "grad_norm": 1.2891623973846436, - "learning_rate": 6.586021505376344e-06, - "loss": 0.1402, + "epoch": 1.5841269841269843, + "grad_norm": 2.6920063495635986, + "learning_rate": 9.43915343915344e-06, + "loss": 0.1759, "step": 499 }, { - "epoch": 2.0161290322580645, - "grad_norm": 2.0554511547088623, - "learning_rate": 6.5591397849462365e-06, - "loss": 0.1812, + "epoch": 1.5873015873015874, + "grad_norm": 1.6965609788894653, + "learning_rate": 9.417989417989418e-06, + "loss": 0.1147, "step": 500 }, { - "epoch": 2.0201612903225805, - "grad_norm": 3.6273601055145264, - "learning_rate": 6.532258064516129e-06, - "loss": 0.1321, + "epoch": 1.5904761904761906, + "grad_norm": 2.2788236141204834, + "learning_rate": 9.396825396825398e-06, + "loss": 0.1733, "step": 501 }, { - "epoch": 2.024193548387097, - "grad_norm": 2.3132970333099365, - "learning_rate": 6.5053763440860214e-06, - "loss": 0.1039, + "epoch": 1.5936507936507938, + "grad_norm": 2.0077788829803467, + "learning_rate": 9.375661375661376e-06, + "loss": 0.2538, "step": 502 }, { - "epoch": 2.028225806451613, - "grad_norm": 1.4552321434020996, - "learning_rate": 6.478494623655914e-06, - "loss": 0.1449, + "epoch": 1.596825396825397, + "grad_norm": 1.9064701795578003, + "learning_rate": 9.354497354497354e-06, + "loss": 0.1369, "step": 503 }, { - "epoch": 2.032258064516129, - "grad_norm": 2.3734288215637207, - "learning_rate": 6.451612903225806e-06, - "loss": 0.1196, + "epoch": 1.6, + "grad_norm": 1.5441234111785889, + "learning_rate": 9.333333333333334e-06, + "loss": 0.1535, "step": 504 }, { - "epoch": 2.036290322580645, - "grad_norm": 3.308845043182373, - "learning_rate": 6.4247311827957e-06, - "loss": 0.1678, + "epoch": 1.6031746031746033, + "grad_norm": 2.792598247528076, + "learning_rate": 9.312169312169313e-06, + "loss": 0.1387, "step": 505 }, { - "epoch": 2.0403225806451615, - "grad_norm": 2.2413101196289062, - "learning_rate": 6.397849462365592e-06, - "loss": 0.1195, + "epoch": 1.6063492063492064, + "grad_norm": 1.1883434057235718, + "learning_rate": 9.291005291005291e-06, + "loss": 0.1633, "step": 506 }, { - "epoch": 2.0443548387096775, - "grad_norm": 2.4938807487487793, - "learning_rate": 6.370967741935485e-06, - "loss": 0.1344, + "epoch": 1.6095238095238096, + "grad_norm": 2.0489578247070312, + "learning_rate": 9.26984126984127e-06, + "loss": 0.1392, "step": 507 }, { - "epoch": 2.0483870967741935, - "grad_norm": 1.7536572217941284, - "learning_rate": 6.344086021505377e-06, - "loss": 0.1037, + "epoch": 1.6126984126984127, + "grad_norm": 3.1841018199920654, + "learning_rate": 9.248677248677249e-06, + "loss": 0.1523, "step": 508 }, { - "epoch": 2.0524193548387095, - "grad_norm": 5.4296345710754395, - "learning_rate": 6.3172043010752696e-06, - "loss": 0.1651, + "epoch": 1.615873015873016, + "grad_norm": 2.180694341659546, + "learning_rate": 9.227513227513229e-06, + "loss": 0.112, "step": 509 }, { - "epoch": 2.056451612903226, - "grad_norm": 1.4947242736816406, - "learning_rate": 6.290322580645162e-06, - "loss": 0.1779, + "epoch": 1.619047619047619, + "grad_norm": 1.408069133758545, + "learning_rate": 9.206349206349207e-06, + "loss": 0.0845, "step": 510 }, { - "epoch": 2.060483870967742, - "grad_norm": 2.460106372833252, - "learning_rate": 6.2634408602150545e-06, - "loss": 0.1335, + "epoch": 1.6222222222222222, + "grad_norm": 3.167762517929077, + "learning_rate": 9.185185185185186e-06, + "loss": 0.1397, "step": 511 }, { - "epoch": 2.064516129032258, - "grad_norm": 2.0023834705352783, - "learning_rate": 6.236559139784947e-06, - "loss": 0.1134, + "epoch": 1.6253968253968254, + "grad_norm": 1.8878964185714722, + "learning_rate": 9.164021164021166e-06, + "loss": 0.096, "step": 512 }, { - "epoch": 2.068548387096774, - "grad_norm": 9.138616561889648, - "learning_rate": 6.209677419354839e-06, - "loss": 0.1426, + "epoch": 1.6285714285714286, + "grad_norm": 5.727024555206299, + "learning_rate": 9.142857142857144e-06, + "loss": 0.0988, "step": 513 }, { - "epoch": 2.0725806451612905, - "grad_norm": 2.8430464267730713, - "learning_rate": 6.182795698924732e-06, - "loss": 0.1099, + "epoch": 1.6317460317460317, + "grad_norm": 3.857280969619751, + "learning_rate": 9.121693121693122e-06, + "loss": 0.1224, "step": 514 }, { - "epoch": 2.0766129032258065, - "grad_norm": 2.494035482406616, - "learning_rate": 6.155913978494624e-06, - "loss": 0.1609, + "epoch": 1.6349206349206349, + "grad_norm": 1.3093122243881226, + "learning_rate": 9.1005291005291e-06, + "loss": 0.1134, "step": 515 }, { - "epoch": 2.0806451612903225, - "grad_norm": 0.7258223295211792, - "learning_rate": 6.129032258064517e-06, - "loss": 0.1089, + "epoch": 1.638095238095238, + "grad_norm": 1.2434587478637695, + "learning_rate": 9.07936507936508e-06, + "loss": 0.1095, "step": 516 }, { - "epoch": 2.0846774193548385, - "grad_norm": 2.798238754272461, - "learning_rate": 6.102150537634409e-06, - "loss": 0.1433, + "epoch": 1.6412698412698412, + "grad_norm": 2.1615359783172607, + "learning_rate": 9.058201058201059e-06, + "loss": 0.1066, "step": 517 }, { - "epoch": 2.088709677419355, - "grad_norm": 1.2602635622024536, - "learning_rate": 6.075268817204302e-06, - "loss": 0.0947, + "epoch": 1.6444444444444444, + "grad_norm": 1.0625678300857544, + "learning_rate": 9.037037037037037e-06, + "loss": 0.0862, "step": 518 }, { - "epoch": 2.092741935483871, - "grad_norm": 2.4262948036193848, - "learning_rate": 6.048387096774194e-06, - "loss": 0.1297, + "epoch": 1.6476190476190475, + "grad_norm": 2.721571922302246, + "learning_rate": 9.015873015873017e-06, + "loss": 0.1169, "step": 519 }, { - "epoch": 2.096774193548387, - "grad_norm": 1.0531463623046875, - "learning_rate": 6.021505376344087e-06, - "loss": 0.0798, + "epoch": 1.6507936507936507, + "grad_norm": 2.0963966846466064, + "learning_rate": 8.994708994708995e-06, + "loss": 0.159, "step": 520 }, { - "epoch": 2.100806451612903, - "grad_norm": 2.968100070953369, - "learning_rate": 5.994623655913979e-06, - "loss": 0.1638, + "epoch": 1.6539682539682539, + "grad_norm": 4.170865535736084, + "learning_rate": 8.973544973544973e-06, + "loss": 0.2292, "step": 521 }, { - "epoch": 2.1048387096774195, - "grad_norm": 1.3490394353866577, - "learning_rate": 5.967741935483872e-06, - "loss": 0.1011, + "epoch": 1.657142857142857, + "grad_norm": 2.2167277336120605, + "learning_rate": 8.952380952380953e-06, + "loss": 0.0876, "step": 522 }, { - "epoch": 2.1088709677419355, - "grad_norm": 1.9310318231582642, - "learning_rate": 5.940860215053764e-06, - "loss": 0.1442, + "epoch": 1.6603174603174602, + "grad_norm": 1.8159117698669434, + "learning_rate": 8.931216931216932e-06, + "loss": 0.1717, "step": 523 }, { - "epoch": 2.1129032258064515, - "grad_norm": 5.254608631134033, - "learning_rate": 5.9139784946236566e-06, - "loss": 0.1855, + "epoch": 1.6634920634920634, + "grad_norm": 1.1661884784698486, + "learning_rate": 8.910052910052912e-06, + "loss": 0.1562, "step": 524 }, { - "epoch": 2.1169354838709675, - "grad_norm": 1.3291866779327393, - "learning_rate": 5.887096774193549e-06, - "loss": 0.1166, + "epoch": 1.6666666666666665, + "grad_norm": 1.8784242868423462, + "learning_rate": 8.888888888888888e-06, + "loss": 0.1263, "step": 525 }, { - "epoch": 2.120967741935484, - "grad_norm": 1.8239635229110718, - "learning_rate": 5.8602150537634415e-06, - "loss": 0.1574, + "epoch": 1.6698412698412697, + "grad_norm": 1.795107364654541, + "learning_rate": 8.867724867724868e-06, + "loss": 0.1294, "step": 526 }, { - "epoch": 2.125, - "grad_norm": 1.7408251762390137, - "learning_rate": 5.833333333333334e-06, - "loss": 0.073, + "epoch": 1.673015873015873, + "grad_norm": 3.2530887126922607, + "learning_rate": 8.846560846560848e-06, + "loss": 0.1004, "step": 527 }, { - "epoch": 2.129032258064516, - "grad_norm": 1.5561959743499756, - "learning_rate": 5.806451612903226e-06, - "loss": 0.0942, + "epoch": 1.6761904761904762, + "grad_norm": 1.4608160257339478, + "learning_rate": 8.825396825396827e-06, + "loss": 0.1606, "step": 528 }, { - "epoch": 2.133064516129032, - "grad_norm": 1.163049340248108, - "learning_rate": 5.779569892473119e-06, - "loss": 0.1472, + "epoch": 1.6793650793650794, + "grad_norm": 2.608607292175293, + "learning_rate": 8.804232804232805e-06, + "loss": 0.0833, "step": 529 }, { - "epoch": 2.1370967741935485, - "grad_norm": 2.868626356124878, - "learning_rate": 5.752688172043011e-06, - "loss": 0.1565, + "epoch": 1.6825396825396826, + "grad_norm": 5.724921703338623, + "learning_rate": 8.783068783068783e-06, + "loss": 0.1458, "step": 530 }, { - "epoch": 2.1411290322580645, - "grad_norm": 4.834112644195557, - "learning_rate": 5.725806451612904e-06, - "loss": 0.1909, + "epoch": 1.6857142857142857, + "grad_norm": 1.4428870677947998, + "learning_rate": 8.761904761904763e-06, + "loss": 0.1287, "step": 531 }, { - "epoch": 2.1451612903225805, - "grad_norm": 3.0024447441101074, - "learning_rate": 5.698924731182796e-06, - "loss": 0.1108, + "epoch": 1.6888888888888889, + "grad_norm": 2.460601806640625, + "learning_rate": 8.740740740740741e-06, + "loss": 0.1276, "step": 532 }, { - "epoch": 2.149193548387097, - "grad_norm": 5.311757564544678, - "learning_rate": 5.672043010752689e-06, - "loss": 0.1366, + "epoch": 1.692063492063492, + "grad_norm": 1.6484627723693848, + "learning_rate": 8.71957671957672e-06, + "loss": 0.1295, "step": 533 }, { - "epoch": 2.153225806451613, - "grad_norm": 3.452758312225342, - "learning_rate": 5.645161290322582e-06, - "loss": 0.2077, + "epoch": 1.6952380952380952, + "grad_norm": 2.0426173210144043, + "learning_rate": 8.6984126984127e-06, + "loss": 0.1189, "step": 534 }, { - "epoch": 2.157258064516129, - "grad_norm": 1.520835280418396, - "learning_rate": 5.618279569892473e-06, - "loss": 0.0959, + "epoch": 1.6984126984126984, + "grad_norm": 1.6476037502288818, + "learning_rate": 8.677248677248678e-06, + "loss": 0.1151, "step": 535 }, { - "epoch": 2.161290322580645, - "grad_norm": 3.092453718185425, - "learning_rate": 5.591397849462365e-06, - "loss": 0.1078, + "epoch": 1.7015873015873015, + "grad_norm": 4.0629777908325195, + "learning_rate": 8.656084656084656e-06, + "loss": 0.1588, "step": 536 }, { - "epoch": 2.1653225806451615, - "grad_norm": 3.7799909114837646, - "learning_rate": 5.564516129032258e-06, - "loss": 0.0856, + "epoch": 1.704761904761905, + "grad_norm": 2.8393821716308594, + "learning_rate": 8.634920634920636e-06, + "loss": 0.1873, "step": 537 }, { - "epoch": 2.1693548387096775, - "grad_norm": 1.4819005727767944, - "learning_rate": 5.53763440860215e-06, - "loss": 0.1015, + "epoch": 1.707936507936508, + "grad_norm": 2.6728999614715576, + "learning_rate": 8.613756613756614e-06, + "loss": 0.1889, "step": 538 }, { - "epoch": 2.1733870967741935, - "grad_norm": 2.0473012924194336, - "learning_rate": 5.510752688172043e-06, - "loss": 0.1372, + "epoch": 1.7111111111111112, + "grad_norm": 1.4037930965423584, + "learning_rate": 8.592592592592593e-06, + "loss": 0.0854, "step": 539 }, { - "epoch": 2.1774193548387095, - "grad_norm": 3.29624080657959, - "learning_rate": 5.483870967741935e-06, - "loss": 0.1395, + "epoch": 1.7142857142857144, + "grad_norm": 1.8756303787231445, + "learning_rate": 8.571428571428571e-06, + "loss": 0.166, "step": 540 }, { - "epoch": 2.181451612903226, - "grad_norm": 1.8019927740097046, - "learning_rate": 5.456989247311828e-06, - "loss": 0.1426, + "epoch": 1.7174603174603176, + "grad_norm": 1.1313530206680298, + "learning_rate": 8.550264550264551e-06, + "loss": 0.127, "step": 541 }, { - "epoch": 2.185483870967742, - "grad_norm": 1.848576307296753, - "learning_rate": 5.43010752688172e-06, - "loss": 0.1854, + "epoch": 1.7206349206349207, + "grad_norm": 2.0405852794647217, + "learning_rate": 8.529100529100531e-06, + "loss": 0.1291, "step": 542 }, { - "epoch": 2.189516129032258, - "grad_norm": 1.5595825910568237, - "learning_rate": 5.4032258064516126e-06, - "loss": 0.0969, + "epoch": 1.723809523809524, + "grad_norm": 3.8676624298095703, + "learning_rate": 8.507936507936509e-06, + "loss": 0.1245, "step": 543 }, { - "epoch": 2.193548387096774, - "grad_norm": 1.914633870124817, - "learning_rate": 5.376344086021506e-06, - "loss": 0.1466, + "epoch": 1.726984126984127, + "grad_norm": 12.367810249328613, + "learning_rate": 8.486772486772487e-06, + "loss": 0.2099, "step": 544 }, { - "epoch": 2.1975806451612905, - "grad_norm": 1.185180902481079, - "learning_rate": 5.349462365591398e-06, - "loss": 0.1457, + "epoch": 1.7301587301587302, + "grad_norm": 1.5893242359161377, + "learning_rate": 8.465608465608466e-06, + "loss": 0.1289, "step": 545 }, { - "epoch": 2.2016129032258065, - "grad_norm": 4.04098653793335, - "learning_rate": 5.322580645161291e-06, - "loss": 0.0852, + "epoch": 1.7333333333333334, + "grad_norm": 3.639246940612793, + "learning_rate": 8.444444444444446e-06, + "loss": 0.1063, "step": 546 }, { - "epoch": 2.2056451612903225, - "grad_norm": 1.7851275205612183, - "learning_rate": 5.295698924731183e-06, - "loss": 0.1771, + "epoch": 1.7365079365079366, + "grad_norm": 1.3742598295211792, + "learning_rate": 8.423280423280424e-06, + "loss": 0.1586, "step": 547 }, { - "epoch": 2.2096774193548385, - "grad_norm": 2.551523208618164, - "learning_rate": 5.268817204301076e-06, - "loss": 0.1229, + "epoch": 1.7396825396825397, + "grad_norm": 3.2743642330169678, + "learning_rate": 8.402116402116402e-06, + "loss": 0.1787, "step": 548 }, { - "epoch": 2.213709677419355, - "grad_norm": 1.8646845817565918, - "learning_rate": 5.241935483870968e-06, - "loss": 0.0997, + "epoch": 1.7428571428571429, + "grad_norm": 2.7228946685791016, + "learning_rate": 8.380952380952382e-06, + "loss": 0.1098, "step": 549 }, { - "epoch": 2.217741935483871, - "grad_norm": 3.173009157180786, - "learning_rate": 5.215053763440861e-06, - "loss": 0.1498, + "epoch": 1.746031746031746, + "grad_norm": 2.6783714294433594, + "learning_rate": 8.35978835978836e-06, + "loss": 0.1117, "step": 550 }, { - "epoch": 2.221774193548387, - "grad_norm": 2.938751220703125, - "learning_rate": 5.188172043010753e-06, - "loss": 0.1432, + "epoch": 1.7492063492063492, + "grad_norm": 2.5518808364868164, + "learning_rate": 8.338624338624339e-06, + "loss": 0.1676, "step": 551 }, { - "epoch": 2.225806451612903, - "grad_norm": 1.863869071006775, - "learning_rate": 5.161290322580646e-06, - "loss": 0.1246, + "epoch": 1.7523809523809524, + "grad_norm": 1.730163335800171, + "learning_rate": 8.317460317460319e-06, + "loss": 0.1208, "step": 552 }, { - "epoch": 2.2298387096774195, - "grad_norm": 2.414386034011841, - "learning_rate": 5.134408602150538e-06, - "loss": 0.137, + "epoch": 1.7555555555555555, + "grad_norm": 1.0971652269363403, + "learning_rate": 8.296296296296297e-06, + "loss": 0.0978, "step": 553 }, { - "epoch": 2.2338709677419355, - "grad_norm": 1.476468563079834, - "learning_rate": 5.1075268817204305e-06, - "loss": 0.1444, + "epoch": 1.7587301587301587, + "grad_norm": 3.4192087650299072, + "learning_rate": 8.275132275132275e-06, + "loss": 0.1987, "step": 554 }, { - "epoch": 2.2379032258064515, - "grad_norm": 1.2723708152770996, - "learning_rate": 5.080645161290323e-06, - "loss": 0.0898, + "epoch": 1.7619047619047619, + "grad_norm": 1.0634312629699707, + "learning_rate": 8.253968253968254e-06, + "loss": 0.1066, "step": 555 }, { - "epoch": 2.241935483870968, - "grad_norm": 2.391453742980957, - "learning_rate": 5.0537634408602155e-06, - "loss": 0.0788, + "epoch": 1.765079365079365, + "grad_norm": 2.1094789505004883, + "learning_rate": 8.232804232804234e-06, + "loss": 0.1005, "step": 556 }, { - "epoch": 2.245967741935484, - "grad_norm": 1.704126000404358, - "learning_rate": 5.026881720430108e-06, - "loss": 0.1598, + "epoch": 1.7682539682539682, + "grad_norm": 3.2969939708709717, + "learning_rate": 8.211640211640213e-06, + "loss": 0.1719, "step": 557 }, { - "epoch": 2.25, - "grad_norm": 2.0079946517944336, - "learning_rate": 5e-06, - "loss": 0.115, + "epoch": 1.7714285714285714, + "grad_norm": 3.250913143157959, + "learning_rate": 8.190476190476192e-06, + "loss": 0.1363, "step": 558 }, { - "epoch": 2.254032258064516, - "grad_norm": 2.3702168464660645, - "learning_rate": 4.973118279569893e-06, - "loss": 0.1229, + "epoch": 1.7746031746031745, + "grad_norm": 2.081871271133423, + "learning_rate": 8.16931216931217e-06, + "loss": 0.1237, "step": 559 }, { - "epoch": 2.258064516129032, - "grad_norm": 4.38910436630249, - "learning_rate": 4.946236559139785e-06, - "loss": 0.1102, + "epoch": 1.7777777777777777, + "grad_norm": 3.369488000869751, + "learning_rate": 8.148148148148148e-06, + "loss": 0.1443, "step": 560 }, { - "epoch": 2.2620967741935485, - "grad_norm": 4.0716776847839355, - "learning_rate": 4.919354838709678e-06, - "loss": 0.2517, + "epoch": 1.7809523809523808, + "grad_norm": 3.4430556297302246, + "learning_rate": 8.126984126984128e-06, + "loss": 0.1244, "step": 561 }, { - "epoch": 2.2661290322580645, - "grad_norm": 0.9846423268318176, - "learning_rate": 4.89247311827957e-06, - "loss": 0.1007, + "epoch": 1.784126984126984, + "grad_norm": 3.774170398712158, + "learning_rate": 8.105820105820107e-06, + "loss": 0.1535, "step": 562 }, { - "epoch": 2.2701612903225805, - "grad_norm": 4.429399490356445, - "learning_rate": 4.865591397849463e-06, - "loss": 0.0691, + "epoch": 1.7873015873015872, + "grad_norm": 2.980259656906128, + "learning_rate": 8.084656084656085e-06, + "loss": 0.1528, "step": 563 }, { - "epoch": 2.274193548387097, - "grad_norm": 2.5109846591949463, - "learning_rate": 4.838709677419355e-06, - "loss": 0.1717, + "epoch": 1.7904761904761903, + "grad_norm": 2.020667314529419, + "learning_rate": 8.063492063492065e-06, + "loss": 0.1075, "step": 564 }, { - "epoch": 2.278225806451613, - "grad_norm": 2.3060779571533203, - "learning_rate": 4.811827956989248e-06, - "loss": 0.0871, + "epoch": 1.7936507936507935, + "grad_norm": 3.889617919921875, + "learning_rate": 8.042328042328043e-06, + "loss": 0.1431, "step": 565 }, { - "epoch": 2.282258064516129, - "grad_norm": 2.165689706802368, - "learning_rate": 4.78494623655914e-06, - "loss": 0.1648, + "epoch": 1.7968253968253967, + "grad_norm": 2.189955234527588, + "learning_rate": 8.021164021164021e-06, + "loss": 0.1069, "step": 566 }, { - "epoch": 2.286290322580645, - "grad_norm": 3.6668314933776855, - "learning_rate": 4.758064516129033e-06, - "loss": 0.093, + "epoch": 1.8, + "grad_norm": 2.471841812133789, + "learning_rate": 8.000000000000001e-06, + "loss": 0.2039, "step": 567 }, { - "epoch": 2.2903225806451615, - "grad_norm": 3.3539183139801025, - "learning_rate": 4.731182795698925e-06, - "loss": 0.1632, + "epoch": 1.8031746031746032, + "grad_norm": 2.728925943374634, + "learning_rate": 7.97883597883598e-06, + "loss": 0.121, "step": 568 }, { - "epoch": 2.2943548387096775, - "grad_norm": 2.386240243911743, - "learning_rate": 4.7043010752688175e-06, - "loss": 0.2024, + "epoch": 1.8063492063492064, + "grad_norm": 3.1814393997192383, + "learning_rate": 7.957671957671958e-06, + "loss": 0.1226, "step": 569 }, { - "epoch": 2.2983870967741935, - "grad_norm": 1.5170916318893433, - "learning_rate": 4.67741935483871e-06, - "loss": 0.1433, + "epoch": 1.8095238095238095, + "grad_norm": 2.3828225135803223, + "learning_rate": 7.936507936507936e-06, + "loss": 0.1712, "step": 570 }, { - "epoch": 2.3024193548387095, - "grad_norm": 1.2362958192825317, - "learning_rate": 4.6505376344086025e-06, - "loss": 0.0842, + "epoch": 1.8126984126984127, + "grad_norm": 1.5043867826461792, + "learning_rate": 7.915343915343916e-06, + "loss": 0.0794, "step": 571 }, { - "epoch": 2.306451612903226, - "grad_norm": 2.1873104572296143, - "learning_rate": 4.623655913978495e-06, - "loss": 0.1048, + "epoch": 1.8158730158730159, + "grad_norm": 1.7279139757156372, + "learning_rate": 7.894179894179896e-06, + "loss": 0.0659, "step": 572 }, { - "epoch": 2.310483870967742, - "grad_norm": 1.4580453634262085, - "learning_rate": 4.596774193548387e-06, - "loss": 0.0954, + "epoch": 1.819047619047619, + "grad_norm": 3.746943950653076, + "learning_rate": 7.873015873015873e-06, + "loss": 0.1184, "step": 573 }, { - "epoch": 2.314516129032258, - "grad_norm": 1.951701283454895, - "learning_rate": 4.56989247311828e-06, - "loss": 0.2442, + "epoch": 1.8222222222222222, + "grad_norm": 1.1520379781723022, + "learning_rate": 7.851851851851853e-06, + "loss": 0.0909, "step": 574 }, { - "epoch": 2.318548387096774, - "grad_norm": 1.1734662055969238, - "learning_rate": 4.543010752688172e-06, - "loss": 0.1161, + "epoch": 1.8253968253968254, + "grad_norm": 1.5874754190444946, + "learning_rate": 7.830687830687831e-06, + "loss": 0.1642, "step": 575 }, { - "epoch": 2.3225806451612905, - "grad_norm": 2.285795211791992, - "learning_rate": 4.516129032258065e-06, - "loss": 0.1039, + "epoch": 1.8285714285714287, + "grad_norm": 2.7189180850982666, + "learning_rate": 7.809523809523811e-06, + "loss": 0.1251, "step": 576 }, { - "epoch": 2.3266129032258065, - "grad_norm": 1.4747077226638794, - "learning_rate": 4.489247311827957e-06, - "loss": 0.1783, + "epoch": 1.831746031746032, + "grad_norm": 2.8076510429382324, + "learning_rate": 7.78835978835979e-06, + "loss": 0.2085, "step": 577 }, { - "epoch": 2.3306451612903225, - "grad_norm": 1.9864970445632935, - "learning_rate": 4.46236559139785e-06, - "loss": 0.1308, + "epoch": 1.834920634920635, + "grad_norm": 3.228066921234131, + "learning_rate": 7.767195767195767e-06, + "loss": 0.0969, "step": 578 }, { - "epoch": 2.3346774193548385, - "grad_norm": 1.8854461908340454, - "learning_rate": 4.435483870967742e-06, - "loss": 0.1359, + "epoch": 1.8380952380952382, + "grad_norm": 2.4557135105133057, + "learning_rate": 7.746031746031747e-06, + "loss": 0.1705, "step": 579 }, { - "epoch": 2.338709677419355, - "grad_norm": 1.6464263200759888, - "learning_rate": 4.408602150537635e-06, - "loss": 0.1447, + "epoch": 1.8412698412698414, + "grad_norm": 0.9715198278427124, + "learning_rate": 7.724867724867726e-06, + "loss": 0.0801, "step": 580 }, { - "epoch": 2.342741935483871, - "grad_norm": 1.9216904640197754, - "learning_rate": 4.381720430107527e-06, - "loss": 0.0523, + "epoch": 1.8444444444444446, + "grad_norm": 2.5380868911743164, + "learning_rate": 7.703703703703704e-06, + "loss": 0.1478, "step": 581 }, { - "epoch": 2.346774193548387, - "grad_norm": 1.3401274681091309, - "learning_rate": 4.35483870967742e-06, - "loss": 0.0718, + "epoch": 1.8476190476190477, + "grad_norm": 2.1661555767059326, + "learning_rate": 7.682539682539684e-06, + "loss": 0.1224, "step": 582 }, { - "epoch": 2.350806451612903, - "grad_norm": 1.0903416872024536, - "learning_rate": 4.327956989247312e-06, - "loss": 0.1176, + "epoch": 1.8507936507936509, + "grad_norm": 8.46414852142334, + "learning_rate": 7.661375661375662e-06, + "loss": 0.1197, "step": 583 }, { - "epoch": 2.3548387096774195, - "grad_norm": 2.7714807987213135, - "learning_rate": 4.3010752688172045e-06, - "loss": 0.1075, + "epoch": 1.853968253968254, + "grad_norm": 2.605694055557251, + "learning_rate": 7.64021164021164e-06, + "loss": 0.1843, "step": 584 }, { - "epoch": 2.3588709677419355, - "grad_norm": 0.9703463315963745, - "learning_rate": 4.274193548387097e-06, - "loss": 0.0649, + "epoch": 1.8571428571428572, + "grad_norm": 2.1432464122772217, + "learning_rate": 7.61904761904762e-06, + "loss": 0.1528, "step": 585 }, { - "epoch": 2.3629032258064515, - "grad_norm": 5.25622034072876, - "learning_rate": 4.2473118279569895e-06, - "loss": 0.1146, + "epoch": 1.8603174603174604, + "grad_norm": 2.718198537826538, + "learning_rate": 7.597883597883599e-06, + "loss": 0.1588, "step": 586 }, { - "epoch": 2.366935483870968, - "grad_norm": 1.6004530191421509, - "learning_rate": 4.220430107526882e-06, - "loss": 0.1173, + "epoch": 1.8634920634920635, + "grad_norm": 2.447756767272949, + "learning_rate": 7.576719576719578e-06, + "loss": 0.1316, "step": 587 }, { - "epoch": 2.370967741935484, - "grad_norm": 1.7906506061553955, - "learning_rate": 4.193548387096774e-06, - "loss": 0.1305, + "epoch": 1.8666666666666667, + "grad_norm": 4.97633695602417, + "learning_rate": 7.555555555555556e-06, + "loss": 0.1594, "step": 588 }, { - "epoch": 2.375, - "grad_norm": 5.008229732513428, - "learning_rate": 4.166666666666667e-06, - "loss": 0.1907, + "epoch": 1.8698412698412699, + "grad_norm": 2.0283660888671875, + "learning_rate": 7.534391534391535e-06, + "loss": 0.0916, "step": 589 }, { - "epoch": 2.379032258064516, - "grad_norm": 2.5902585983276367, - "learning_rate": 4.139784946236559e-06, - "loss": 0.1836, + "epoch": 1.873015873015873, + "grad_norm": 1.9047635793685913, + "learning_rate": 7.5132275132275136e-06, + "loss": 0.1294, "step": 590 }, { - "epoch": 2.383064516129032, - "grad_norm": 2.13139009475708, - "learning_rate": 4.112903225806452e-06, - "loss": 0.1012, + "epoch": 1.8761904761904762, + "grad_norm": 1.7151267528533936, + "learning_rate": 7.492063492063493e-06, + "loss": 0.2095, "step": 591 }, { - "epoch": 2.3870967741935485, - "grad_norm": 1.3434728384017944, - "learning_rate": 4.086021505376344e-06, - "loss": 0.1011, + "epoch": 1.8793650793650793, + "grad_norm": 2.0981991291046143, + "learning_rate": 7.470899470899472e-06, + "loss": 0.1409, "step": 592 }, { - "epoch": 2.3911290322580645, - "grad_norm": 1.74350106716156, - "learning_rate": 4.059139784946237e-06, - "loss": 0.1008, + "epoch": 1.8825396825396825, + "grad_norm": 4.416806697845459, + "learning_rate": 7.44973544973545e-06, + "loss": 0.1099, "step": 593 }, { - "epoch": 2.3951612903225805, - "grad_norm": 1.2974146604537964, - "learning_rate": 4.032258064516129e-06, - "loss": 0.0692, + "epoch": 1.8857142857142857, + "grad_norm": 1.1974761486053467, + "learning_rate": 7.428571428571429e-06, + "loss": 0.0854, "step": 594 }, { - "epoch": 2.399193548387097, - "grad_norm": 2.330141544342041, - "learning_rate": 4.005376344086022e-06, - "loss": 0.1496, + "epoch": 1.8888888888888888, + "grad_norm": 1.8332712650299072, + "learning_rate": 7.4074074074074075e-06, + "loss": 0.1047, "step": 595 }, { - "epoch": 2.403225806451613, - "grad_norm": 4.154720306396484, - "learning_rate": 3.978494623655914e-06, - "loss": 0.1431, + "epoch": 1.892063492063492, + "grad_norm": 1.5796504020690918, + "learning_rate": 7.386243386243387e-06, + "loss": 0.1296, "step": 596 }, { - "epoch": 2.407258064516129, - "grad_norm": 1.0211693048477173, - "learning_rate": 3.951612903225807e-06, - "loss": 0.1015, + "epoch": 1.8952380952380952, + "grad_norm": 1.962656021118164, + "learning_rate": 7.3650793650793666e-06, + "loss": 0.0921, "step": 597 }, { - "epoch": 2.411290322580645, - "grad_norm": 4.42000675201416, - "learning_rate": 3.924731182795699e-06, - "loss": 0.1123, + "epoch": 1.8984126984126983, + "grad_norm": 1.4445793628692627, + "learning_rate": 7.343915343915344e-06, + "loss": 0.0823, "step": 598 }, { - "epoch": 2.4153225806451615, - "grad_norm": 4.67465353012085, - "learning_rate": 3.8978494623655915e-06, - "loss": 0.2117, + "epoch": 1.9015873015873015, + "grad_norm": 1.5229748487472534, + "learning_rate": 7.322751322751324e-06, + "loss": 0.1544, "step": 599 }, { - "epoch": 2.4193548387096775, - "grad_norm": 2.3731729984283447, - "learning_rate": 3.870967741935484e-06, - "loss": 0.1847, + "epoch": 1.9047619047619047, + "grad_norm": 1.3883131742477417, + "learning_rate": 7.301587301587301e-06, + "loss": 0.0993, "step": 600 }, { - "epoch": 2.4233870967741935, - "grad_norm": 2.7813737392425537, - "learning_rate": 3.8440860215053765e-06, - "loss": 0.1696, + "epoch": 1.9079365079365078, + "grad_norm": 1.923826813697815, + "learning_rate": 7.280423280423281e-06, + "loss": 0.1147, "step": 601 }, { - "epoch": 2.4274193548387095, - "grad_norm": 1.7436891794204712, - "learning_rate": 3.817204301075269e-06, - "loss": 0.1275, + "epoch": 1.911111111111111, + "grad_norm": 2.0830509662628174, + "learning_rate": 7.2592592592592605e-06, + "loss": 0.1253, "step": 602 }, { - "epoch": 2.431451612903226, - "grad_norm": 2.3506593704223633, - "learning_rate": 3.7903225806451614e-06, - "loss": 0.1749, + "epoch": 1.9142857142857141, + "grad_norm": 2.5855178833007812, + "learning_rate": 7.238095238095239e-06, + "loss": 0.1606, "step": 603 }, { - "epoch": 2.435483870967742, - "grad_norm": 3.1209230422973633, - "learning_rate": 3.763440860215054e-06, - "loss": 0.1307, + "epoch": 1.9174603174603173, + "grad_norm": 2.4029104709625244, + "learning_rate": 7.216931216931218e-06, + "loss": 0.1807, "step": 604 }, { - "epoch": 2.439516129032258, - "grad_norm": 2.593312978744507, - "learning_rate": 3.7365591397849468e-06, - "loss": 0.1168, + "epoch": 1.9206349206349205, + "grad_norm": 3.345869541168213, + "learning_rate": 7.195767195767196e-06, + "loss": 0.1554, "step": 605 }, { - "epoch": 2.443548387096774, - "grad_norm": 2.2633056640625, - "learning_rate": 3.7096774193548392e-06, - "loss": 0.1355, + "epoch": 1.9238095238095239, + "grad_norm": 3.107938766479492, + "learning_rate": 7.174603174603175e-06, + "loss": 0.1911, "step": 606 }, { - "epoch": 2.4475806451612905, - "grad_norm": 2.898655891418457, - "learning_rate": 3.6827956989247317e-06, - "loss": 0.1298, + "epoch": 1.926984126984127, + "grad_norm": 2.9127020835876465, + "learning_rate": 7.1534391534391544e-06, + "loss": 0.1612, "step": 607 }, { - "epoch": 2.4516129032258065, - "grad_norm": 1.7566426992416382, - "learning_rate": 3.655913978494624e-06, - "loss": 0.1159, + "epoch": 1.9301587301587302, + "grad_norm": 1.363625168800354, + "learning_rate": 7.132275132275133e-06, + "loss": 0.1831, "step": 608 }, { - "epoch": 2.4556451612903225, - "grad_norm": 6.452301025390625, - "learning_rate": 3.6290322580645166e-06, - "loss": 0.1349, + "epoch": 1.9333333333333333, + "grad_norm": 1.5432355403900146, + "learning_rate": 7.111111111111112e-06, + "loss": 0.084, "step": 609 }, { - "epoch": 2.4596774193548385, - "grad_norm": 2.342876434326172, - "learning_rate": 3.602150537634409e-06, - "loss": 0.0856, + "epoch": 1.9365079365079365, + "grad_norm": 1.0660487413406372, + "learning_rate": 7.08994708994709e-06, + "loss": 0.0811, "step": 610 }, { - "epoch": 2.463709677419355, - "grad_norm": 2.236654281616211, - "learning_rate": 3.5752688172043015e-06, - "loss": 0.1418, + "epoch": 1.9396825396825397, + "grad_norm": 1.604659914970398, + "learning_rate": 7.068783068783069e-06, + "loss": 0.0911, "step": 611 }, { - "epoch": 2.467741935483871, - "grad_norm": 3.464710235595703, - "learning_rate": 3.548387096774194e-06, - "loss": 0.097, + "epoch": 1.9428571428571428, + "grad_norm": 2.114056348800659, + "learning_rate": 7.047619047619048e-06, + "loss": 0.1194, "step": 612 }, { - "epoch": 2.471774193548387, - "grad_norm": 1.936618447303772, - "learning_rate": 3.5215053763440865e-06, - "loss": 0.0876, + "epoch": 1.946031746031746, + "grad_norm": 2.1784474849700928, + "learning_rate": 7.026455026455027e-06, + "loss": 0.1306, "step": 613 }, { - "epoch": 2.475806451612903, - "grad_norm": 3.4211089611053467, - "learning_rate": 3.494623655913979e-06, - "loss": 0.1502, + "epoch": 1.9492063492063492, + "grad_norm": 5.347076416015625, + "learning_rate": 7.005291005291006e-06, + "loss": 0.1022, "step": 614 }, { - "epoch": 2.4798387096774195, - "grad_norm": 2.9869165420532227, - "learning_rate": 3.4677419354838714e-06, - "loss": 0.2398, + "epoch": 1.9523809523809523, + "grad_norm": 1.9041115045547485, + "learning_rate": 6.984126984126984e-06, + "loss": 0.1519, "step": 615 }, { - "epoch": 2.4838709677419355, - "grad_norm": 3.0065438747406006, - "learning_rate": 3.440860215053764e-06, - "loss": 0.1115, + "epoch": 1.9555555555555557, + "grad_norm": 1.5671062469482422, + "learning_rate": 6.962962962962964e-06, + "loss": 0.1625, "step": 616 }, { - "epoch": 2.4879032258064515, - "grad_norm": 1.830977439880371, - "learning_rate": 3.413978494623656e-06, - "loss": 0.1161, + "epoch": 1.9587301587301589, + "grad_norm": 1.9459840059280396, + "learning_rate": 6.941798941798943e-06, + "loss": 0.2186, "step": 617 }, { - "epoch": 2.491935483870968, - "grad_norm": 1.9489115476608276, - "learning_rate": 3.3870967741935484e-06, - "loss": 0.1224, + "epoch": 1.961904761904762, + "grad_norm": 3.3273890018463135, + "learning_rate": 6.920634920634921e-06, + "loss": 0.1345, "step": 618 }, { - "epoch": 2.495967741935484, - "grad_norm": 2.2884771823883057, - "learning_rate": 3.360215053763441e-06, - "loss": 0.1092, + "epoch": 1.9650793650793652, + "grad_norm": 2.455493211746216, + "learning_rate": 6.8994708994709005e-06, + "loss": 0.1215, "step": 619 }, { - "epoch": 2.5, - "grad_norm": 2.671285629272461, - "learning_rate": 3.3333333333333333e-06, - "loss": 0.1711, + "epoch": 1.9682539682539684, + "grad_norm": 1.6772799491882324, + "learning_rate": 6.878306878306879e-06, + "loss": 0.1183, "step": 620 }, { - "epoch": 2.504032258064516, - "grad_norm": 1.9497143030166626, - "learning_rate": 3.306451612903226e-06, - "loss": 0.1145, + "epoch": 1.9714285714285715, + "grad_norm": 2.2009174823760986, + "learning_rate": 6.857142857142858e-06, + "loss": 0.0835, "step": 621 }, { - "epoch": 2.508064516129032, - "grad_norm": 1.3452483415603638, - "learning_rate": 3.2795698924731183e-06, - "loss": 0.1217, + "epoch": 1.9746031746031747, + "grad_norm": 2.5750198364257812, + "learning_rate": 6.835978835978837e-06, + "loss": 0.1144, "step": 622 }, { - "epoch": 2.5120967741935485, - "grad_norm": 1.2507896423339844, - "learning_rate": 3.2526881720430107e-06, - "loss": 0.0931, + "epoch": 1.9777777777777779, + "grad_norm": 0.933612048625946, + "learning_rate": 6.814814814814815e-06, + "loss": 0.0727, "step": 623 }, { - "epoch": 2.5161290322580645, - "grad_norm": 1.3425334692001343, - "learning_rate": 3.225806451612903e-06, - "loss": 0.1145, + "epoch": 1.980952380952381, + "grad_norm": 1.6413253545761108, + "learning_rate": 6.7936507936507944e-06, + "loss": 0.0745, "step": 624 }, { - "epoch": 2.5201612903225805, - "grad_norm": 3.7666163444519043, - "learning_rate": 3.198924731182796e-06, - "loss": 0.1044, + "epoch": 1.9841269841269842, + "grad_norm": 1.219631314277649, + "learning_rate": 6.772486772486773e-06, + "loss": 0.0962, "step": 625 }, { - "epoch": 2.524193548387097, - "grad_norm": 2.4426252841949463, - "learning_rate": 3.1720430107526885e-06, - "loss": 0.0856, + "epoch": 1.9873015873015873, + "grad_norm": 6.836822032928467, + "learning_rate": 6.751322751322752e-06, + "loss": 0.1409, "step": 626 }, { - "epoch": 2.528225806451613, - "grad_norm": 3.1804256439208984, - "learning_rate": 3.145161290322581e-06, - "loss": 0.0867, + "epoch": 1.9904761904761905, + "grad_norm": 0.6782273054122925, + "learning_rate": 6.730158730158731e-06, + "loss": 0.059, "step": 627 }, { - "epoch": 2.532258064516129, - "grad_norm": 2.037343740463257, - "learning_rate": 3.1182795698924735e-06, - "loss": 0.1085, + "epoch": 1.9936507936507937, + "grad_norm": 2.526792049407959, + "learning_rate": 6.708994708994709e-06, + "loss": 0.1764, "step": 628 }, { - "epoch": 2.536290322580645, - "grad_norm": 4.272365093231201, - "learning_rate": 3.091397849462366e-06, - "loss": 0.174, + "epoch": 1.9968253968253968, + "grad_norm": 0.946007490158081, + "learning_rate": 6.687830687830688e-06, + "loss": 0.1188, "step": 629 }, { - "epoch": 2.540322580645161, - "grad_norm": 2.1623380184173584, - "learning_rate": 3.0645161290322584e-06, - "loss": 0.0866, + "epoch": 2.0, + "grad_norm": 6.678429126739502, + "learning_rate": 6.666666666666667e-06, + "loss": 0.1858, "step": 630 }, { - "epoch": 2.5443548387096775, - "grad_norm": 3.3426926136016846, - "learning_rate": 3.037634408602151e-06, - "loss": 0.1142, + "epoch": 2.0, + "eval_accuracy": 0.7669642857142858, + "eval_f1": 0.9028322440087145, + "eval_loss": 0.14492610096931458, + "eval_runtime": 2.9394, + "eval_samples_per_second": 381.031, + "eval_steps_per_second": 11.907, + "step": 630 + }, + { + "epoch": 2.003174603174603, + "grad_norm": 1.1040282249450684, + "learning_rate": 6.645502645502646e-06, + "loss": 0.1102, "step": 631 }, { - "epoch": 2.5483870967741935, - "grad_norm": 2.2241578102111816, - "learning_rate": 3.0107526881720433e-06, - "loss": 0.0995, + "epoch": 2.0063492063492063, + "grad_norm": 1.9316213130950928, + "learning_rate": 6.624338624338626e-06, + "loss": 0.1061, "step": 632 }, { - "epoch": 2.5524193548387095, - "grad_norm": 3.2953665256500244, - "learning_rate": 2.983870967741936e-06, - "loss": 0.1487, + "epoch": 2.0095238095238095, + "grad_norm": 3.8282930850982666, + "learning_rate": 6.603174603174603e-06, + "loss": 0.1681, "step": 633 }, { - "epoch": 2.556451612903226, - "grad_norm": 1.5125126838684082, - "learning_rate": 2.9569892473118283e-06, - "loss": 0.0567, + "epoch": 2.0126984126984127, + "grad_norm": 1.3325519561767578, + "learning_rate": 6.582010582010583e-06, + "loss": 0.1084, "step": 634 }, { - "epoch": 2.560483870967742, - "grad_norm": 2.612718343734741, - "learning_rate": 2.9301075268817207e-06, - "loss": 0.1033, + "epoch": 2.015873015873016, + "grad_norm": 2.731137990951538, + "learning_rate": 6.560846560846561e-06, + "loss": 0.1531, "step": 635 }, { - "epoch": 2.564516129032258, - "grad_norm": 1.220692753791809, - "learning_rate": 2.903225806451613e-06, - "loss": 0.0999, + "epoch": 2.019047619047619, + "grad_norm": 2.366612195968628, + "learning_rate": 6.5396825396825405e-06, + "loss": 0.0983, "step": 636 }, { - "epoch": 2.568548387096774, - "grad_norm": 1.8477866649627686, - "learning_rate": 2.8763440860215057e-06, - "loss": 0.2083, + "epoch": 2.022222222222222, + "grad_norm": 1.2040481567382812, + "learning_rate": 6.51851851851852e-06, + "loss": 0.1104, "step": 637 }, { - "epoch": 2.5725806451612905, - "grad_norm": 4.778720855712891, - "learning_rate": 2.849462365591398e-06, - "loss": 0.1335, + "epoch": 2.0253968253968253, + "grad_norm": 2.0411009788513184, + "learning_rate": 6.497354497354498e-06, + "loss": 0.1373, "step": 638 }, { - "epoch": 2.5766129032258065, - "grad_norm": 1.4977765083312988, - "learning_rate": 2.822580645161291e-06, - "loss": 0.147, + "epoch": 2.0285714285714285, + "grad_norm": 3.734283208847046, + "learning_rate": 6.476190476190477e-06, + "loss": 0.126, "step": 639 }, { - "epoch": 2.5806451612903225, - "grad_norm": 1.5701426267623901, - "learning_rate": 2.7956989247311827e-06, - "loss": 0.1333, + "epoch": 2.0317460317460316, + "grad_norm": 2.1836066246032715, + "learning_rate": 6.455026455026455e-06, + "loss": 0.1626, "step": 640 }, { - "epoch": 2.584677419354839, - "grad_norm": 1.051927924156189, - "learning_rate": 2.768817204301075e-06, - "loss": 0.0888, + "epoch": 2.034920634920635, + "grad_norm": 1.1947808265686035, + "learning_rate": 6.4338624338624345e-06, + "loss": 0.1054, "step": 641 }, { - "epoch": 2.588709677419355, - "grad_norm": 4.721953868865967, - "learning_rate": 2.7419354838709676e-06, - "loss": 0.131, + "epoch": 2.038095238095238, + "grad_norm": 2.890094041824341, + "learning_rate": 6.412698412698414e-06, + "loss": 0.1551, "step": 642 }, { - "epoch": 2.592741935483871, - "grad_norm": 2.7012953758239746, - "learning_rate": 2.71505376344086e-06, - "loss": 0.0714, + "epoch": 2.041269841269841, + "grad_norm": 2.0232725143432617, + "learning_rate": 6.391534391534392e-06, + "loss": 0.1355, "step": 643 }, { - "epoch": 2.596774193548387, - "grad_norm": 5.694790363311768, - "learning_rate": 2.688172043010753e-06, - "loss": 0.1403, + "epoch": 2.0444444444444443, + "grad_norm": 1.8651456832885742, + "learning_rate": 6.370370370370371e-06, + "loss": 0.1026, "step": 644 }, { - "epoch": 2.600806451612903, - "grad_norm": 4.28272008895874, - "learning_rate": 2.6612903225806454e-06, - "loss": 0.1169, + "epoch": 2.0476190476190474, + "grad_norm": 1.7638417482376099, + "learning_rate": 6.349206349206349e-06, + "loss": 0.133, "step": 645 }, { - "epoch": 2.6048387096774195, - "grad_norm": 1.0393054485321045, - "learning_rate": 2.634408602150538e-06, - "loss": 0.0731, + "epoch": 2.0507936507936506, + "grad_norm": 3.499927043914795, + "learning_rate": 6.328042328042328e-06, + "loss": 0.1162, "step": 646 }, { - "epoch": 2.6088709677419355, - "grad_norm": 0.9973479509353638, - "learning_rate": 2.6075268817204303e-06, - "loss": 0.1072, + "epoch": 2.0539682539682538, + "grad_norm": 4.2744975090026855, + "learning_rate": 6.3068783068783075e-06, + "loss": 0.1717, "step": 647 }, { - "epoch": 2.6129032258064515, - "grad_norm": 1.4460006952285767, - "learning_rate": 2.580645161290323e-06, - "loss": 0.1372, + "epoch": 2.057142857142857, + "grad_norm": 1.5318410396575928, + "learning_rate": 6.285714285714286e-06, + "loss": 0.0834, "step": 648 }, { - "epoch": 2.616935483870968, - "grad_norm": 2.2750110626220703, - "learning_rate": 2.5537634408602153e-06, - "loss": 0.1131, + "epoch": 2.06031746031746, + "grad_norm": 5.0771484375, + "learning_rate": 6.264550264550266e-06, + "loss": 0.1038, "step": 649 }, { - "epoch": 2.620967741935484, - "grad_norm": 2.0815539360046387, - "learning_rate": 2.5268817204301077e-06, - "loss": 0.1101, + "epoch": 2.0634920634920633, + "grad_norm": 1.74736487865448, + "learning_rate": 6.243386243386243e-06, + "loss": 0.1046, "step": 650 }, { - "epoch": 2.625, - "grad_norm": 1.0647339820861816, - "learning_rate": 2.5e-06, - "loss": 0.1106, + "epoch": 2.066666666666667, + "grad_norm": 0.7934084534645081, + "learning_rate": 6.222222222222223e-06, + "loss": 0.1174, "step": 651 }, { - "epoch": 2.629032258064516, - "grad_norm": 1.694512963294983, - "learning_rate": 2.4731182795698927e-06, - "loss": 0.1207, + "epoch": 2.06984126984127, + "grad_norm": 1.5000299215316772, + "learning_rate": 6.201058201058202e-06, + "loss": 0.1049, "step": 652 }, { - "epoch": 2.633064516129032, - "grad_norm": 1.1872451305389404, - "learning_rate": 2.446236559139785e-06, - "loss": 0.0823, + "epoch": 2.073015873015873, + "grad_norm": 2.2633683681488037, + "learning_rate": 6.1798941798941806e-06, + "loss": 0.0966, "step": 653 }, { - "epoch": 2.6370967741935485, - "grad_norm": 1.3260234594345093, - "learning_rate": 2.4193548387096776e-06, - "loss": 0.1082, + "epoch": 2.0761904761904764, + "grad_norm": 6.304328918457031, + "learning_rate": 6.15873015873016e-06, + "loss": 0.0926, "step": 654 }, { - "epoch": 2.6411290322580645, - "grad_norm": 2.025832414627075, - "learning_rate": 2.39247311827957e-06, - "loss": 0.1217, + "epoch": 2.0793650793650795, + "grad_norm": 3.255258560180664, + "learning_rate": 6.137566137566138e-06, + "loss": 0.1525, "step": 655 }, { - "epoch": 2.6451612903225805, - "grad_norm": 2.340317487716675, - "learning_rate": 2.3655913978494625e-06, - "loss": 0.1507, + "epoch": 2.0825396825396827, + "grad_norm": 1.6757506132125854, + "learning_rate": 6.116402116402117e-06, + "loss": 0.0942, "step": 656 }, { - "epoch": 2.649193548387097, - "grad_norm": 2.595576524734497, - "learning_rate": 2.338709677419355e-06, - "loss": 0.1588, + "epoch": 2.085714285714286, + "grad_norm": 3.2556090354919434, + "learning_rate": 6.095238095238096e-06, + "loss": 0.0836, "step": 657 }, { - "epoch": 2.653225806451613, - "grad_norm": 2.0549724102020264, - "learning_rate": 2.3118279569892475e-06, - "loss": 0.1111, + "epoch": 2.088888888888889, + "grad_norm": 3.6376585960388184, + "learning_rate": 6.0740740740740745e-06, + "loss": 0.182, "step": 658 }, { - "epoch": 2.657258064516129, - "grad_norm": 0.7785517573356628, - "learning_rate": 2.28494623655914e-06, - "loss": 0.0675, + "epoch": 2.092063492063492, + "grad_norm": 2.387551784515381, + "learning_rate": 6.052910052910054e-06, + "loss": 0.0962, "step": 659 }, { - "epoch": 2.661290322580645, - "grad_norm": 1.5122755765914917, - "learning_rate": 2.2580645161290324e-06, - "loss": 0.0898, + "epoch": 2.0952380952380953, + "grad_norm": 2.098965644836426, + "learning_rate": 6.031746031746032e-06, + "loss": 0.1667, "step": 660 }, { - "epoch": 2.665322580645161, - "grad_norm": 1.361331582069397, - "learning_rate": 2.231182795698925e-06, - "loss": 0.12, + "epoch": 2.0984126984126985, + "grad_norm": 1.153611183166504, + "learning_rate": 6.010582010582011e-06, + "loss": 0.0693, "step": 661 }, { - "epoch": 2.6693548387096775, - "grad_norm": 2.3188157081604004, - "learning_rate": 2.2043010752688173e-06, - "loss": 0.1406, + "epoch": 2.1015873015873017, + "grad_norm": 2.1836884021759033, + "learning_rate": 5.989417989417989e-06, + "loss": 0.1013, "step": 662 }, { - "epoch": 2.6733870967741935, - "grad_norm": 1.4102435111999512, - "learning_rate": 2.17741935483871e-06, - "loss": 0.0961, + "epoch": 2.104761904761905, + "grad_norm": 2.1978871822357178, + "learning_rate": 5.968253968253968e-06, + "loss": 0.123, "step": 663 }, { - "epoch": 2.6774193548387095, - "grad_norm": 2.144468069076538, - "learning_rate": 2.1505376344086023e-06, - "loss": 0.0633, + "epoch": 2.107936507936508, + "grad_norm": 3.277968168258667, + "learning_rate": 5.9470899470899475e-06, + "loss": 0.1236, "step": 664 }, { - "epoch": 2.681451612903226, - "grad_norm": 1.7837616205215454, - "learning_rate": 2.1236559139784947e-06, - "loss": 0.1136, + "epoch": 2.111111111111111, + "grad_norm": 2.0386297702789307, + "learning_rate": 5.925925925925926e-06, + "loss": 0.1803, "step": 665 }, { - "epoch": 2.685483870967742, - "grad_norm": 2.097506284713745, - "learning_rate": 2.096774193548387e-06, - "loss": 0.1284, + "epoch": 2.1142857142857143, + "grad_norm": 2.8552448749542236, + "learning_rate": 5.904761904761905e-06, + "loss": 0.1911, "step": 666 }, { - "epoch": 2.689516129032258, - "grad_norm": 1.8578377962112427, - "learning_rate": 2.0698924731182797e-06, - "loss": 0.0985, + "epoch": 2.1174603174603175, + "grad_norm": 3.6463711261749268, + "learning_rate": 5.883597883597883e-06, + "loss": 0.1215, "step": 667 }, { - "epoch": 2.693548387096774, - "grad_norm": 1.454514741897583, - "learning_rate": 2.043010752688172e-06, - "loss": 0.1499, + "epoch": 2.1206349206349207, + "grad_norm": 4.219704627990723, + "learning_rate": 5.862433862433863e-06, + "loss": 0.1443, "step": 668 }, { - "epoch": 2.6975806451612905, - "grad_norm": 6.206280708312988, - "learning_rate": 2.0161290322580646e-06, - "loss": 0.1131, + "epoch": 2.123809523809524, + "grad_norm": 2.983017921447754, + "learning_rate": 5.841269841269842e-06, + "loss": 0.0841, "step": 669 }, { - "epoch": 2.7016129032258065, - "grad_norm": 1.9479646682739258, - "learning_rate": 1.989247311827957e-06, - "loss": 0.0599, + "epoch": 2.126984126984127, + "grad_norm": 2.088979721069336, + "learning_rate": 5.820105820105821e-06, + "loss": 0.0758, "step": 670 }, { - "epoch": 2.7056451612903225, - "grad_norm": 1.7119982242584229, - "learning_rate": 1.9623655913978495e-06, - "loss": 0.1553, + "epoch": 2.13015873015873, + "grad_norm": 1.267215609550476, + "learning_rate": 5.7989417989418e-06, + "loss": 0.1157, "step": 671 }, { - "epoch": 2.709677419354839, - "grad_norm": 2.411572217941284, - "learning_rate": 1.935483870967742e-06, - "loss": 0.1384, + "epoch": 2.1333333333333333, + "grad_norm": 1.3805314302444458, + "learning_rate": 5.777777777777778e-06, + "loss": 0.1241, "step": 672 }, { - "epoch": 2.713709677419355, - "grad_norm": 2.9151971340179443, - "learning_rate": 1.9086021505376345e-06, - "loss": 0.1513, + "epoch": 2.1365079365079365, + "grad_norm": 1.690621256828308, + "learning_rate": 5.756613756613757e-06, + "loss": 0.1018, "step": 673 }, { - "epoch": 2.717741935483871, - "grad_norm": 1.6464580297470093, - "learning_rate": 1.881720430107527e-06, - "loss": 0.0747, + "epoch": 2.1396825396825396, + "grad_norm": 1.1262898445129395, + "learning_rate": 5.735449735449736e-06, + "loss": 0.1099, "step": 674 }, { - "epoch": 2.721774193548387, - "grad_norm": 2.2614505290985107, - "learning_rate": 1.8548387096774196e-06, - "loss": 0.1306, + "epoch": 2.142857142857143, + "grad_norm": 1.9063478708267212, + "learning_rate": 5.7142857142857145e-06, + "loss": 0.1689, "step": 675 }, { - "epoch": 2.725806451612903, - "grad_norm": 3.9104158878326416, - "learning_rate": 1.827956989247312e-06, - "loss": 0.1036, + "epoch": 2.146031746031746, + "grad_norm": 1.6672478914260864, + "learning_rate": 5.693121693121694e-06, + "loss": 0.1652, "step": 676 }, { - "epoch": 2.7298387096774195, - "grad_norm": 2.6638762950897217, - "learning_rate": 1.8010752688172045e-06, - "loss": 0.1882, + "epoch": 2.149206349206349, + "grad_norm": 1.702602744102478, + "learning_rate": 5.671957671957672e-06, + "loss": 0.075, "step": 677 }, { - "epoch": 2.7338709677419355, - "grad_norm": 2.4250168800354004, - "learning_rate": 1.774193548387097e-06, - "loss": 0.1356, + "epoch": 2.1523809523809523, + "grad_norm": 1.4827642440795898, + "learning_rate": 5.650793650793651e-06, + "loss": 0.1002, "step": 678 }, { - "epoch": 2.7379032258064515, - "grad_norm": 1.579751968383789, - "learning_rate": 1.7473118279569895e-06, - "loss": 0.0973, + "epoch": 2.1555555555555554, + "grad_norm": 1.758109211921692, + "learning_rate": 5.62962962962963e-06, + "loss": 0.1268, "step": 679 }, { - "epoch": 2.741935483870968, - "grad_norm": 1.9126899242401123, - "learning_rate": 1.720430107526882e-06, - "loss": 0.1051, + "epoch": 2.1587301587301586, + "grad_norm": 2.0651724338531494, + "learning_rate": 5.6084656084656084e-06, + "loss": 0.1619, "step": 680 }, { - "epoch": 2.745967741935484, - "grad_norm": 2.4986772537231445, - "learning_rate": 1.6935483870967742e-06, - "loss": 0.097, + "epoch": 2.1619047619047618, + "grad_norm": 2.132006883621216, + "learning_rate": 5.5873015873015876e-06, + "loss": 0.1344, "step": 681 }, { - "epoch": 2.75, - "grad_norm": 1.9752743244171143, - "learning_rate": 1.6666666666666667e-06, - "loss": 0.1827, + "epoch": 2.165079365079365, + "grad_norm": 3.0319361686706543, + "learning_rate": 5.566137566137566e-06, + "loss": 0.0885, "step": 682 }, { - "epoch": 2.754032258064516, - "grad_norm": 5.470479488372803, - "learning_rate": 1.6397849462365591e-06, - "loss": 0.156, + "epoch": 2.168253968253968, + "grad_norm": 1.782867670059204, + "learning_rate": 5.544973544973545e-06, + "loss": 0.0667, "step": 683 }, { - "epoch": 2.758064516129032, - "grad_norm": 0.6137222647666931, - "learning_rate": 1.6129032258064516e-06, - "loss": 0.0982, + "epoch": 2.1714285714285713, + "grad_norm": 2.2788290977478027, + "learning_rate": 5.523809523809525e-06, + "loss": 0.1377, "step": 684 }, { - "epoch": 2.7620967741935485, - "grad_norm": 1.8977144956588745, - "learning_rate": 1.5860215053763443e-06, - "loss": 0.1484, + "epoch": 2.1746031746031744, + "grad_norm": 0.7668473124504089, + "learning_rate": 5.502645502645503e-06, + "loss": 0.0565, "step": 685 }, { - "epoch": 2.7661290322580645, - "grad_norm": 1.982347846031189, - "learning_rate": 1.5591397849462367e-06, - "loss": 0.0805, + "epoch": 2.1777777777777776, + "grad_norm": 2.1871116161346436, + "learning_rate": 5.481481481481482e-06, + "loss": 0.153, "step": 686 }, { - "epoch": 2.7701612903225805, - "grad_norm": 1.7538466453552246, - "learning_rate": 1.5322580645161292e-06, - "loss": 0.0831, + "epoch": 2.1809523809523808, + "grad_norm": 1.0742480754852295, + "learning_rate": 5.460317460317461e-06, + "loss": 0.0436, "step": 687 }, { - "epoch": 2.774193548387097, - "grad_norm": 1.4044026136398315, - "learning_rate": 1.5053763440860217e-06, - "loss": 0.0967, + "epoch": 2.1841269841269844, + "grad_norm": 2.1612884998321533, + "learning_rate": 5.43915343915344e-06, + "loss": 0.1155, "step": 688 }, { - "epoch": 2.778225806451613, - "grad_norm": 3.4833972454071045, - "learning_rate": 1.4784946236559141e-06, - "loss": 0.1445, + "epoch": 2.1873015873015875, + "grad_norm": 1.0809170007705688, + "learning_rate": 5.417989417989419e-06, + "loss": 0.0479, "step": 689 }, { - "epoch": 2.782258064516129, - "grad_norm": 3.1198818683624268, - "learning_rate": 1.4516129032258066e-06, - "loss": 0.1556, + "epoch": 2.1904761904761907, + "grad_norm": 1.733425259590149, + "learning_rate": 5.396825396825397e-06, + "loss": 0.0833, "step": 690 }, { - "epoch": 2.786290322580645, - "grad_norm": 1.4616000652313232, - "learning_rate": 1.424731182795699e-06, - "loss": 0.1769, + "epoch": 2.193650793650794, + "grad_norm": 1.3307905197143555, + "learning_rate": 5.375661375661376e-06, + "loss": 0.1489, "step": 691 }, { - "epoch": 2.790322580645161, - "grad_norm": 0.99885493516922, - "learning_rate": 1.3978494623655913e-06, - "loss": 0.0787, + "epoch": 2.196825396825397, + "grad_norm": 5.177230358123779, + "learning_rate": 5.3544973544973545e-06, + "loss": 0.1372, "step": 692 }, { - "epoch": 2.7943548387096775, - "grad_norm": 1.395920991897583, - "learning_rate": 1.3709677419354838e-06, - "loss": 0.0763, + "epoch": 2.2, + "grad_norm": 2.178593158721924, + "learning_rate": 5.333333333333334e-06, + "loss": 0.1509, "step": 693 }, { - "epoch": 2.7983870967741935, - "grad_norm": 2.1815457344055176, - "learning_rate": 1.3440860215053765e-06, - "loss": 0.1605, + "epoch": 2.2031746031746033, + "grad_norm": 2.1247053146362305, + "learning_rate": 5.312169312169313e-06, + "loss": 0.1004, "step": 694 }, { - "epoch": 2.8024193548387095, - "grad_norm": 1.7244387865066528, - "learning_rate": 1.317204301075269e-06, - "loss": 0.0735, + "epoch": 2.2063492063492065, + "grad_norm": 1.5181992053985596, + "learning_rate": 5.291005291005291e-06, + "loss": 0.0978, "step": 695 }, { - "epoch": 2.806451612903226, - "grad_norm": 2.2874746322631836, - "learning_rate": 1.2903225806451614e-06, - "loss": 0.1302, + "epoch": 2.2095238095238097, + "grad_norm": 1.0136287212371826, + "learning_rate": 5.26984126984127e-06, + "loss": 0.0802, "step": 696 }, { - "epoch": 2.810483870967742, - "grad_norm": 0.7056113481521606, - "learning_rate": 1.2634408602150539e-06, - "loss": 0.097, + "epoch": 2.212698412698413, + "grad_norm": 1.8322035074234009, + "learning_rate": 5.2486772486772485e-06, + "loss": 0.0963, "step": 697 }, { - "epoch": 2.814516129032258, - "grad_norm": 2.458315134048462, - "learning_rate": 1.2365591397849463e-06, - "loss": 0.1269, + "epoch": 2.215873015873016, + "grad_norm": 1.418076992034912, + "learning_rate": 5.227513227513228e-06, + "loss": 0.1695, "step": 698 }, { - "epoch": 2.818548387096774, - "grad_norm": 1.1753970384597778, - "learning_rate": 1.2096774193548388e-06, - "loss": 0.0745, + "epoch": 2.219047619047619, + "grad_norm": 1.7173771858215332, + "learning_rate": 5.2063492063492076e-06, + "loss": 0.1542, "step": 699 }, { - "epoch": 2.8225806451612905, - "grad_norm": 1.3138192892074585, - "learning_rate": 1.1827956989247313e-06, - "loss": 0.1289, + "epoch": 2.2222222222222223, + "grad_norm": 2.7679505348205566, + "learning_rate": 5.185185185185185e-06, + "loss": 0.1479, "step": 700 }, { - "epoch": 2.8266129032258065, - "grad_norm": 1.3947908878326416, - "learning_rate": 1.1559139784946237e-06, - "loss": 0.1225, + "epoch": 2.2253968253968255, + "grad_norm": 1.3400449752807617, + "learning_rate": 5.164021164021165e-06, + "loss": 0.1325, "step": 701 }, { - "epoch": 2.8306451612903225, - "grad_norm": 1.4919567108154297, - "learning_rate": 1.1290322580645162e-06, - "loss": 0.119, + "epoch": 2.2285714285714286, + "grad_norm": 1.5357208251953125, + "learning_rate": 5.142857142857142e-06, + "loss": 0.1123, "step": 702 }, { - "epoch": 2.834677419354839, - "grad_norm": 1.0990135669708252, - "learning_rate": 1.1021505376344087e-06, - "loss": 0.0763, + "epoch": 2.231746031746032, + "grad_norm": 1.6993006467819214, + "learning_rate": 5.121693121693122e-06, + "loss": 0.0866, "step": 703 }, { - "epoch": 2.838709677419355, - "grad_norm": 5.159749507904053, - "learning_rate": 1.0752688172043011e-06, - "loss": 0.1223, + "epoch": 2.234920634920635, + "grad_norm": 4.492737293243408, + "learning_rate": 5.1005291005291015e-06, + "loss": 0.1158, "step": 704 }, { - "epoch": 2.842741935483871, - "grad_norm": 1.0806690454483032, - "learning_rate": 1.0483870967741936e-06, - "loss": 0.1383, + "epoch": 2.238095238095238, + "grad_norm": 1.6061910390853882, + "learning_rate": 5.07936507936508e-06, + "loss": 0.1214, "step": 705 }, { - "epoch": 2.846774193548387, - "grad_norm": 3.3874659538269043, - "learning_rate": 1.021505376344086e-06, - "loss": 0.1, + "epoch": 2.2412698412698413, + "grad_norm": 2.0195701122283936, + "learning_rate": 5.058201058201059e-06, + "loss": 0.1457, "step": 706 }, { - "epoch": 2.850806451612903, - "grad_norm": 2.235921859741211, - "learning_rate": 9.946236559139785e-07, - "loss": 0.2047, + "epoch": 2.2444444444444445, + "grad_norm": 1.9150606393814087, + "learning_rate": 5.037037037037037e-06, + "loss": 0.1449, "step": 707 }, { - "epoch": 2.8548387096774195, - "grad_norm": 1.7132419347763062, - "learning_rate": 9.67741935483871e-07, - "loss": 0.1235, + "epoch": 2.2476190476190476, + "grad_norm": 2.228717088699341, + "learning_rate": 5.015873015873016e-06, + "loss": 0.1416, "step": 708 }, { - "epoch": 2.8588709677419355, - "grad_norm": 5.385939598083496, - "learning_rate": 9.408602150537635e-07, - "loss": 0.0994, + "epoch": 2.250793650793651, + "grad_norm": 2.3263099193573, + "learning_rate": 4.9947089947089946e-06, + "loss": 0.1532, "step": 709 }, { - "epoch": 2.8629032258064515, - "grad_norm": 1.3089847564697266, - "learning_rate": 9.13978494623656e-07, - "loss": 0.0878, + "epoch": 2.253968253968254, + "grad_norm": 2.0589399337768555, + "learning_rate": 4.973544973544974e-06, + "loss": 0.0533, "step": 710 }, { - "epoch": 2.866935483870968, - "grad_norm": 1.2990398406982422, - "learning_rate": 8.870967741935485e-07, - "loss": 0.1384, + "epoch": 2.257142857142857, + "grad_norm": 1.1312892436981201, + "learning_rate": 4.952380952380953e-06, + "loss": 0.1382, "step": 711 }, { - "epoch": 2.870967741935484, - "grad_norm": 1.1270217895507812, - "learning_rate": 8.60215053763441e-07, - "loss": 0.0901, + "epoch": 2.2603174603174603, + "grad_norm": 1.5842820405960083, + "learning_rate": 4.931216931216932e-06, + "loss": 0.0849, "step": 712 }, { - "epoch": 2.875, - "grad_norm": 1.7017827033996582, - "learning_rate": 8.333333333333333e-07, - "loss": 0.1437, + "epoch": 2.2634920634920634, + "grad_norm": 1.4216231107711792, + "learning_rate": 4.91005291005291e-06, + "loss": 0.1509, "step": 713 }, { - "epoch": 2.879032258064516, - "grad_norm": 0.8682994246482849, - "learning_rate": 8.064516129032258e-07, - "loss": 0.0515, + "epoch": 2.2666666666666666, + "grad_norm": 2.1895132064819336, + "learning_rate": 4.888888888888889e-06, + "loss": 0.1357, "step": 714 }, { - "epoch": 2.883064516129032, - "grad_norm": 3.2466022968292236, - "learning_rate": 7.795698924731184e-07, - "loss": 0.1803, + "epoch": 2.2698412698412698, + "grad_norm": 2.1969082355499268, + "learning_rate": 4.867724867724868e-06, + "loss": 0.172, "step": 715 }, { - "epoch": 2.8870967741935485, - "grad_norm": 2.0208983421325684, - "learning_rate": 7.526881720430108e-07, - "loss": 0.1035, + "epoch": 2.273015873015873, + "grad_norm": 3.3672447204589844, + "learning_rate": 4.846560846560847e-06, + "loss": 0.1685, "step": 716 }, { - "epoch": 2.8911290322580645, - "grad_norm": 1.170736312866211, - "learning_rate": 7.258064516129033e-07, - "loss": 0.13, + "epoch": 2.276190476190476, + "grad_norm": 4.806187629699707, + "learning_rate": 4.825396825396826e-06, + "loss": 0.2001, "step": 717 }, { - "epoch": 2.8951612903225805, - "grad_norm": 1.7991589307785034, - "learning_rate": 6.989247311827957e-07, - "loss": 0.0715, + "epoch": 2.2793650793650793, + "grad_norm": 2.6919243335723877, + "learning_rate": 4.804232804232805e-06, + "loss": 0.1043, "step": 718 }, { - "epoch": 2.899193548387097, - "grad_norm": 1.9782204627990723, - "learning_rate": 6.720430107526882e-07, - "loss": 0.0969, + "epoch": 2.2825396825396824, + "grad_norm": 2.325645923614502, + "learning_rate": 4.783068783068783e-06, + "loss": 0.1106, "step": 719 }, { - "epoch": 2.903225806451613, - "grad_norm": 2.702655792236328, - "learning_rate": 6.451612903225807e-07, - "loss": 0.0927, + "epoch": 2.2857142857142856, + "grad_norm": 1.6905019283294678, + "learning_rate": 4.761904761904762e-06, + "loss": 0.1088, "step": 720 }, { - "epoch": 2.907258064516129, - "grad_norm": 2.2504546642303467, - "learning_rate": 6.182795698924732e-07, - "loss": 0.146, + "epoch": 2.2888888888888888, + "grad_norm": 1.4680815935134888, + "learning_rate": 4.7407407407407415e-06, + "loss": 0.0778, "step": 721 }, { - "epoch": 2.911290322580645, - "grad_norm": 2.546994209289551, - "learning_rate": 5.913978494623656e-07, - "loss": 0.0981, + "epoch": 2.292063492063492, + "grad_norm": 2.536572217941284, + "learning_rate": 4.71957671957672e-06, + "loss": 0.0993, "step": 722 }, { - "epoch": 2.915322580645161, - "grad_norm": 3.177995443344116, - "learning_rate": 5.645161290322581e-07, - "loss": 0.1493, + "epoch": 2.295238095238095, + "grad_norm": 1.3453577756881714, + "learning_rate": 4.698412698412699e-06, + "loss": 0.1546, "step": 723 }, { - "epoch": 2.9193548387096775, - "grad_norm": 1.8446640968322754, - "learning_rate": 5.376344086021506e-07, - "loss": 0.1168, + "epoch": 2.2984126984126982, + "grad_norm": 1.6215269565582275, + "learning_rate": 4.677248677248677e-06, + "loss": 0.0983, "step": 724 }, { - "epoch": 2.9233870967741935, - "grad_norm": 1.462225079536438, - "learning_rate": 5.10752688172043e-07, - "loss": 0.0658, + "epoch": 2.3015873015873014, + "grad_norm": 2.9893081188201904, + "learning_rate": 4.656084656084656e-06, + "loss": 0.1551, "step": 725 }, { - "epoch": 2.9274193548387095, - "grad_norm": 2.062228202819824, - "learning_rate": 4.838709677419355e-07, - "loss": 0.0861, + "epoch": 2.3047619047619046, + "grad_norm": 2.4195570945739746, + "learning_rate": 4.634920634920635e-06, + "loss": 0.1187, "step": 726 }, { - "epoch": 2.931451612903226, - "grad_norm": 1.066767930984497, - "learning_rate": 4.56989247311828e-07, - "loss": 0.1016, + "epoch": 2.3079365079365077, + "grad_norm": 4.250411033630371, + "learning_rate": 4.6137566137566145e-06, + "loss": 0.1755, "step": 727 }, { - "epoch": 2.935483870967742, - "grad_norm": 1.9916908740997314, - "learning_rate": 4.301075268817205e-07, - "loss": 0.0999, + "epoch": 2.311111111111111, + "grad_norm": 1.3822400569915771, + "learning_rate": 4.592592592592593e-06, + "loss": 0.1292, "step": 728 }, { - "epoch": 2.939516129032258, - "grad_norm": 2.194812536239624, - "learning_rate": 4.032258064516129e-07, - "loss": 0.1289, + "epoch": 2.314285714285714, + "grad_norm": 2.4897572994232178, + "learning_rate": 4.571428571428572e-06, + "loss": 0.081, "step": 729 }, { - "epoch": 2.943548387096774, - "grad_norm": 1.067501425743103, - "learning_rate": 3.763440860215054e-07, - "loss": 0.0866, + "epoch": 2.317460317460317, + "grad_norm": 2.441693067550659, + "learning_rate": 4.55026455026455e-06, + "loss": 0.0982, "step": 730 }, { - "epoch": 2.9475806451612905, - "grad_norm": 1.4836621284484863, - "learning_rate": 3.4946236559139783e-07, - "loss": 0.0954, + "epoch": 2.320634920634921, + "grad_norm": 1.903067708015442, + "learning_rate": 4.529100529100529e-06, + "loss": 0.0848, "step": 731 }, { - "epoch": 2.9516129032258065, - "grad_norm": 2.3710856437683105, - "learning_rate": 3.2258064516129035e-07, - "loss": 0.1969, + "epoch": 2.323809523809524, + "grad_norm": 1.4447675943374634, + "learning_rate": 4.5079365079365085e-06, + "loss": 0.0689, "step": 732 }, { - "epoch": 2.9556451612903225, - "grad_norm": 2.83674693107605, - "learning_rate": 2.956989247311828e-07, - "loss": 0.1929, + "epoch": 2.326984126984127, + "grad_norm": 5.5785231590271, + "learning_rate": 4.486772486772487e-06, + "loss": 0.1345, "step": 733 }, { - "epoch": 2.959677419354839, - "grad_norm": 2.1235055923461914, - "learning_rate": 2.688172043010753e-07, - "loss": 0.1497, + "epoch": 2.3301587301587303, + "grad_norm": 3.376317262649536, + "learning_rate": 4.465608465608466e-06, + "loss": 0.1496, "step": 734 }, { - "epoch": 2.963709677419355, - "grad_norm": 1.6132428646087646, - "learning_rate": 2.4193548387096775e-07, - "loss": 0.1602, + "epoch": 2.3333333333333335, + "grad_norm": 1.6259448528289795, + "learning_rate": 4.444444444444444e-06, + "loss": 0.1093, "step": 735 }, { - "epoch": 2.967741935483871, - "grad_norm": 2.551713228225708, - "learning_rate": 2.1505376344086024e-07, - "loss": 0.0789, + "epoch": 2.3365079365079366, + "grad_norm": 4.046261787414551, + "learning_rate": 4.423280423280424e-06, + "loss": 0.092, "step": 736 }, { - "epoch": 2.971774193548387, - "grad_norm": 1.6804261207580566, - "learning_rate": 1.881720430107527e-07, - "loss": 0.1895, + "epoch": 2.33968253968254, + "grad_norm": 2.5608232021331787, + "learning_rate": 4.402116402116402e-06, + "loss": 0.138, "step": 737 }, { - "epoch": 2.975806451612903, - "grad_norm": 1.8240628242492676, - "learning_rate": 1.6129032258064518e-07, - "loss": 0.1558, + "epoch": 2.342857142857143, + "grad_norm": 1.832879900932312, + "learning_rate": 4.3809523809523815e-06, + "loss": 0.0991, "step": 738 }, { - "epoch": 2.9798387096774195, - "grad_norm": 1.9709798097610474, - "learning_rate": 1.3440860215053764e-07, - "loss": 0.1245, + "epoch": 2.346031746031746, + "grad_norm": 2.9074578285217285, + "learning_rate": 4.35978835978836e-06, + "loss": 0.1177, "step": 739 }, { - "epoch": 2.9838709677419355, - "grad_norm": 1.7331011295318604, - "learning_rate": 1.0752688172043012e-07, - "loss": 0.0999, + "epoch": 2.3492063492063493, + "grad_norm": 4.8084940910339355, + "learning_rate": 4.338624338624339e-06, + "loss": 0.1302, "step": 740 }, { - "epoch": 2.9879032258064515, - "grad_norm": 1.3876549005508423, - "learning_rate": 8.064516129032259e-08, - "loss": 0.1744, + "epoch": 2.3523809523809525, + "grad_norm": 1.8935600519180298, + "learning_rate": 4.317460317460318e-06, + "loss": 0.122, "step": 741 }, { - "epoch": 2.991935483870968, - "grad_norm": 1.998831033706665, - "learning_rate": 5.376344086021506e-08, - "loss": 0.0876, + "epoch": 2.3555555555555556, + "grad_norm": 1.7548450231552124, + "learning_rate": 4.296296296296296e-06, + "loss": 0.145, "step": 742 }, { - "epoch": 2.995967741935484, - "grad_norm": 1.9842371940612793, - "learning_rate": 2.688172043010753e-08, - "loss": 0.1036, + "epoch": 2.358730158730159, + "grad_norm": 1.2127044200897217, + "learning_rate": 4.2751322751322754e-06, + "loss": 0.1095, "step": 743 }, { - "epoch": 3.0, - "grad_norm": 2.3604133129119873, - "learning_rate": 0.0, - "loss": 0.0957, + "epoch": 2.361904761904762, + "grad_norm": 3.2971980571746826, + "learning_rate": 4.2539682539682546e-06, + "loss": 0.1328, "step": 744 }, { - "epoch": 3.0, - "eval_accuracy": 0.7625, - "eval_f1": 0.9021978021978022, - "eval_loss": 0.14369329810142517, - "eval_runtime": 2.3693, - "eval_samples_per_second": 371.416, - "eval_steps_per_second": 11.818, - "step": 744 + "epoch": 2.365079365079365, + "grad_norm": 2.389162540435791, + "learning_rate": 4.232804232804233e-06, + "loss": 0.1532, + "step": 745 + }, + { + "epoch": 2.3682539682539683, + "grad_norm": 1.6251575946807861, + "learning_rate": 4.211640211640212e-06, + "loss": 0.1459, + "step": 746 + }, + { + "epoch": 2.3714285714285714, + "grad_norm": 2.658689260482788, + "learning_rate": 4.190476190476191e-06, + "loss": 0.1447, + "step": 747 + }, + { + "epoch": 2.3746031746031746, + "grad_norm": 1.1152836084365845, + "learning_rate": 4.169312169312169e-06, + "loss": 0.1314, + "step": 748 + }, + { + "epoch": 2.3777777777777778, + "grad_norm": 2.8088347911834717, + "learning_rate": 4.1481481481481485e-06, + "loss": 0.1519, + "step": 749 + }, + { + "epoch": 2.380952380952381, + "grad_norm": 2.6803934574127197, + "learning_rate": 4.126984126984127e-06, + "loss": 0.0974, + "step": 750 + }, + { + "epoch": 2.384126984126984, + "grad_norm": 1.6603881120681763, + "learning_rate": 4.105820105820107e-06, + "loss": 0.1633, + "step": 751 + }, + { + "epoch": 2.3873015873015873, + "grad_norm": 4.068179130554199, + "learning_rate": 4.084656084656085e-06, + "loss": 0.1135, + "step": 752 + }, + { + "epoch": 2.3904761904761904, + "grad_norm": 6.6498308181762695, + "learning_rate": 4.063492063492064e-06, + "loss": 0.1409, + "step": 753 + }, + { + "epoch": 2.3936507936507936, + "grad_norm": 1.9543097019195557, + "learning_rate": 4.042328042328042e-06, + "loss": 0.1132, + "step": 754 + }, + { + "epoch": 2.3968253968253967, + "grad_norm": 1.979831337928772, + "learning_rate": 4.0211640211640215e-06, + "loss": 0.0867, + "step": 755 + }, + { + "epoch": 2.4, + "grad_norm": 1.761592149734497, + "learning_rate": 4.000000000000001e-06, + "loss": 0.1159, + "step": 756 + }, + { + "epoch": 2.403174603174603, + "grad_norm": 2.11088228225708, + "learning_rate": 3.978835978835979e-06, + "loss": 0.1298, + "step": 757 + }, + { + "epoch": 2.4063492063492062, + "grad_norm": 1.0387389659881592, + "learning_rate": 3.957671957671958e-06, + "loss": 0.0897, + "step": 758 + }, + { + "epoch": 2.4095238095238094, + "grad_norm": 6.4743876457214355, + "learning_rate": 3.936507936507936e-06, + "loss": 0.197, + "step": 759 + }, + { + "epoch": 2.4126984126984126, + "grad_norm": 1.2603111267089844, + "learning_rate": 3.9153439153439155e-06, + "loss": 0.121, + "step": 760 + }, + { + "epoch": 2.4158730158730157, + "grad_norm": 2.491236686706543, + "learning_rate": 3.894179894179895e-06, + "loss": 0.1718, + "step": 761 + }, + { + "epoch": 2.419047619047619, + "grad_norm": 1.5929335355758667, + "learning_rate": 3.873015873015874e-06, + "loss": 0.0956, + "step": 762 + }, + { + "epoch": 2.422222222222222, + "grad_norm": 1.996605396270752, + "learning_rate": 3.851851851851852e-06, + "loss": 0.1312, + "step": 763 + }, + { + "epoch": 2.425396825396825, + "grad_norm": 4.703456401824951, + "learning_rate": 3.830687830687831e-06, + "loss": 0.1318, + "step": 764 + }, + { + "epoch": 2.4285714285714284, + "grad_norm": 0.8073280453681946, + "learning_rate": 3.80952380952381e-06, + "loss": 0.0967, + "step": 765 + }, + { + "epoch": 2.431746031746032, + "grad_norm": 2.5277130603790283, + "learning_rate": 3.788359788359789e-06, + "loss": 0.1693, + "step": 766 + }, + { + "epoch": 2.434920634920635, + "grad_norm": 2.1101698875427246, + "learning_rate": 3.7671957671957676e-06, + "loss": 0.1074, + "step": 767 + }, + { + "epoch": 2.4380952380952383, + "grad_norm": 1.54884934425354, + "learning_rate": 3.7460317460317463e-06, + "loss": 0.0788, + "step": 768 + }, + { + "epoch": 2.4412698412698415, + "grad_norm": 5.948628902435303, + "learning_rate": 3.724867724867725e-06, + "loss": 0.1844, + "step": 769 + }, + { + "epoch": 2.4444444444444446, + "grad_norm": 1.8137024641036987, + "learning_rate": 3.7037037037037037e-06, + "loss": 0.1427, + "step": 770 + }, + { + "epoch": 2.447619047619048, + "grad_norm": 1.8733800649642944, + "learning_rate": 3.6825396825396833e-06, + "loss": 0.0626, + "step": 771 + }, + { + "epoch": 2.450793650793651, + "grad_norm": 3.3979275226593018, + "learning_rate": 3.661375661375662e-06, + "loss": 0.1558, + "step": 772 + }, + { + "epoch": 2.453968253968254, + "grad_norm": 3.3467631340026855, + "learning_rate": 3.6402116402116407e-06, + "loss": 0.2243, + "step": 773 + }, + { + "epoch": 2.4571428571428573, + "grad_norm": 1.4580453634262085, + "learning_rate": 3.6190476190476194e-06, + "loss": 0.0728, + "step": 774 + }, + { + "epoch": 2.4603174603174605, + "grad_norm": 1.4997695684432983, + "learning_rate": 3.597883597883598e-06, + "loss": 0.1222, + "step": 775 + }, + { + "epoch": 2.4634920634920636, + "grad_norm": 1.5148733854293823, + "learning_rate": 3.5767195767195772e-06, + "loss": 0.0882, + "step": 776 + }, + { + "epoch": 2.466666666666667, + "grad_norm": 3.6706902980804443, + "learning_rate": 3.555555555555556e-06, + "loss": 0.1343, + "step": 777 + }, + { + "epoch": 2.46984126984127, + "grad_norm": 1.634046196937561, + "learning_rate": 3.5343915343915346e-06, + "loss": 0.0523, + "step": 778 + }, + { + "epoch": 2.473015873015873, + "grad_norm": 0.8726693391799927, + "learning_rate": 3.5132275132275133e-06, + "loss": 0.076, + "step": 779 + }, + { + "epoch": 2.4761904761904763, + "grad_norm": 3.454434871673584, + "learning_rate": 3.492063492063492e-06, + "loss": 0.0722, + "step": 780 + }, + { + "epoch": 2.4793650793650794, + "grad_norm": 0.8759881258010864, + "learning_rate": 3.4708994708994716e-06, + "loss": 0.097, + "step": 781 + }, + { + "epoch": 2.4825396825396826, + "grad_norm": 1.322967767715454, + "learning_rate": 3.4497354497354503e-06, + "loss": 0.1009, + "step": 782 + }, + { + "epoch": 2.4857142857142858, + "grad_norm": 2.510690689086914, + "learning_rate": 3.428571428571429e-06, + "loss": 0.1197, + "step": 783 + }, + { + "epoch": 2.488888888888889, + "grad_norm": 1.6605170965194702, + "learning_rate": 3.4074074074074077e-06, + "loss": 0.0695, + "step": 784 + }, + { + "epoch": 2.492063492063492, + "grad_norm": 1.268059253692627, + "learning_rate": 3.3862433862433864e-06, + "loss": 0.073, + "step": 785 + }, + { + "epoch": 2.4952380952380953, + "grad_norm": 1.4574055671691895, + "learning_rate": 3.3650793650793655e-06, + "loss": 0.1004, + "step": 786 + }, + { + "epoch": 2.4984126984126984, + "grad_norm": 1.7531797885894775, + "learning_rate": 3.343915343915344e-06, + "loss": 0.1139, + "step": 787 + }, + { + "epoch": 2.5015873015873016, + "grad_norm": 3.1249589920043945, + "learning_rate": 3.322751322751323e-06, + "loss": 0.1465, + "step": 788 + }, + { + "epoch": 2.5047619047619047, + "grad_norm": 4.9641523361206055, + "learning_rate": 3.3015873015873016e-06, + "loss": 0.2202, + "step": 789 + }, + { + "epoch": 2.507936507936508, + "grad_norm": 1.7861170768737793, + "learning_rate": 3.2804232804232807e-06, + "loss": 0.1708, + "step": 790 + }, + { + "epoch": 2.511111111111111, + "grad_norm": 1.2005184888839722, + "learning_rate": 3.25925925925926e-06, + "loss": 0.1038, + "step": 791 + }, + { + "epoch": 2.5142857142857142, + "grad_norm": 2.341322898864746, + "learning_rate": 3.2380952380952385e-06, + "loss": 0.1344, + "step": 792 + }, + { + "epoch": 2.5174603174603174, + "grad_norm": 1.9944754838943481, + "learning_rate": 3.2169312169312172e-06, + "loss": 0.1795, + "step": 793 + }, + { + "epoch": 2.5206349206349206, + "grad_norm": 2.580857515335083, + "learning_rate": 3.195767195767196e-06, + "loss": 0.0888, + "step": 794 + }, + { + "epoch": 2.5238095238095237, + "grad_norm": 3.1521358489990234, + "learning_rate": 3.1746031746031746e-06, + "loss": 0.1023, + "step": 795 + }, + { + "epoch": 2.526984126984127, + "grad_norm": 1.8199126720428467, + "learning_rate": 3.1534391534391538e-06, + "loss": 0.0928, + "step": 796 + }, + { + "epoch": 2.53015873015873, + "grad_norm": 1.8366172313690186, + "learning_rate": 3.132275132275133e-06, + "loss": 0.1172, + "step": 797 + }, + { + "epoch": 2.533333333333333, + "grad_norm": 3.267967939376831, + "learning_rate": 3.1111111111111116e-06, + "loss": 0.1057, + "step": 798 + }, + { + "epoch": 2.5365079365079364, + "grad_norm": 5.523816108703613, + "learning_rate": 3.0899470899470903e-06, + "loss": 0.1396, + "step": 799 + }, + { + "epoch": 2.5396825396825395, + "grad_norm": 2.5194506645202637, + "learning_rate": 3.068783068783069e-06, + "loss": 0.0783, + "step": 800 + }, + { + "epoch": 2.5428571428571427, + "grad_norm": 2.084998846054077, + "learning_rate": 3.047619047619048e-06, + "loss": 0.1161, + "step": 801 + }, + { + "epoch": 2.546031746031746, + "grad_norm": 1.6567469835281372, + "learning_rate": 3.026455026455027e-06, + "loss": 0.1268, + "step": 802 + }, + { + "epoch": 2.549206349206349, + "grad_norm": 3.652885675430298, + "learning_rate": 3.0052910052910055e-06, + "loss": 0.2006, + "step": 803 + }, + { + "epoch": 2.552380952380952, + "grad_norm": 1.8879823684692383, + "learning_rate": 2.984126984126984e-06, + "loss": 0.1291, + "step": 804 + }, + { + "epoch": 2.5555555555555554, + "grad_norm": 2.1518566608428955, + "learning_rate": 2.962962962962963e-06, + "loss": 0.0893, + "step": 805 + }, + { + "epoch": 2.5587301587301585, + "grad_norm": 2.5531256198883057, + "learning_rate": 2.9417989417989416e-06, + "loss": 0.1242, + "step": 806 + }, + { + "epoch": 2.5619047619047617, + "grad_norm": 1.76236093044281, + "learning_rate": 2.920634920634921e-06, + "loss": 0.083, + "step": 807 + }, + { + "epoch": 2.565079365079365, + "grad_norm": 3.7986724376678467, + "learning_rate": 2.8994708994709e-06, + "loss": 0.0989, + "step": 808 + }, + { + "epoch": 2.568253968253968, + "grad_norm": 1.1771494150161743, + "learning_rate": 2.8783068783068786e-06, + "loss": 0.0942, + "step": 809 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 2.211660146713257, + "learning_rate": 2.8571428571428573e-06, + "loss": 0.0768, + "step": 810 + }, + { + "epoch": 2.5746031746031743, + "grad_norm": 1.637126088142395, + "learning_rate": 2.835978835978836e-06, + "loss": 0.0949, + "step": 811 + }, + { + "epoch": 2.5777777777777775, + "grad_norm": 1.7225103378295898, + "learning_rate": 2.814814814814815e-06, + "loss": 0.0714, + "step": 812 + }, + { + "epoch": 2.580952380952381, + "grad_norm": 1.5344024896621704, + "learning_rate": 2.7936507936507938e-06, + "loss": 0.1135, + "step": 813 + }, + { + "epoch": 2.5841269841269843, + "grad_norm": 2.0459091663360596, + "learning_rate": 2.7724867724867725e-06, + "loss": 0.141, + "step": 814 + }, + { + "epoch": 2.5873015873015874, + "grad_norm": 2.943941354751587, + "learning_rate": 2.7513227513227516e-06, + "loss": 0.0933, + "step": 815 + }, + { + "epoch": 2.5904761904761906, + "grad_norm": 2.4562253952026367, + "learning_rate": 2.7301587301587303e-06, + "loss": 0.1349, + "step": 816 + }, + { + "epoch": 2.5936507936507938, + "grad_norm": 1.7727712392807007, + "learning_rate": 2.7089947089947094e-06, + "loss": 0.1308, + "step": 817 + }, + { + "epoch": 2.596825396825397, + "grad_norm": 2.1184957027435303, + "learning_rate": 2.687830687830688e-06, + "loss": 0.1244, + "step": 818 + }, + { + "epoch": 2.6, + "grad_norm": 1.5418163537979126, + "learning_rate": 2.666666666666667e-06, + "loss": 0.1667, + "step": 819 + }, + { + "epoch": 2.6031746031746033, + "grad_norm": 2.8710386753082275, + "learning_rate": 2.6455026455026455e-06, + "loss": 0.1169, + "step": 820 + }, + { + "epoch": 2.6063492063492064, + "grad_norm": 4.3403496742248535, + "learning_rate": 2.6243386243386242e-06, + "loss": 0.1197, + "step": 821 + }, + { + "epoch": 2.6095238095238096, + "grad_norm": 3.4465107917785645, + "learning_rate": 2.6031746031746038e-06, + "loss": 0.1391, + "step": 822 + }, + { + "epoch": 2.6126984126984127, + "grad_norm": 2.799697160720825, + "learning_rate": 2.5820105820105825e-06, + "loss": 0.1615, + "step": 823 + }, + { + "epoch": 2.615873015873016, + "grad_norm": 5.145082473754883, + "learning_rate": 2.560846560846561e-06, + "loss": 0.1263, + "step": 824 + }, + { + "epoch": 2.619047619047619, + "grad_norm": 1.5873088836669922, + "learning_rate": 2.53968253968254e-06, + "loss": 0.0567, + "step": 825 + }, + { + "epoch": 2.6222222222222222, + "grad_norm": 1.2147488594055176, + "learning_rate": 2.5185185185185186e-06, + "loss": 0.0711, + "step": 826 + }, + { + "epoch": 2.6253968253968254, + "grad_norm": 3.274872064590454, + "learning_rate": 2.4973544973544973e-06, + "loss": 0.1293, + "step": 827 + }, + { + "epoch": 2.6285714285714286, + "grad_norm": 1.126296877861023, + "learning_rate": 2.4761904761904764e-06, + "loss": 0.0992, + "step": 828 + }, + { + "epoch": 2.6317460317460317, + "grad_norm": 2.2251086235046387, + "learning_rate": 2.455026455026455e-06, + "loss": 0.2183, + "step": 829 + }, + { + "epoch": 2.634920634920635, + "grad_norm": 3.3299648761749268, + "learning_rate": 2.433862433862434e-06, + "loss": 0.1909, + "step": 830 + }, + { + "epoch": 2.638095238095238, + "grad_norm": 2.399258613586426, + "learning_rate": 2.412698412698413e-06, + "loss": 0.1175, + "step": 831 + }, + { + "epoch": 2.641269841269841, + "grad_norm": 1.605791687965393, + "learning_rate": 2.3915343915343916e-06, + "loss": 0.1356, + "step": 832 + }, + { + "epoch": 2.6444444444444444, + "grad_norm": 4.952585697174072, + "learning_rate": 2.3703703703703707e-06, + "loss": 0.1608, + "step": 833 + }, + { + "epoch": 2.6476190476190475, + "grad_norm": 1.919247031211853, + "learning_rate": 2.3492063492063494e-06, + "loss": 0.1508, + "step": 834 + }, + { + "epoch": 2.6507936507936507, + "grad_norm": 2.690411329269409, + "learning_rate": 2.328042328042328e-06, + "loss": 0.0889, + "step": 835 + }, + { + "epoch": 2.653968253968254, + "grad_norm": 2.4415993690490723, + "learning_rate": 2.3068783068783073e-06, + "loss": 0.1465, + "step": 836 + }, + { + "epoch": 2.657142857142857, + "grad_norm": 3.8582472801208496, + "learning_rate": 2.285714285714286e-06, + "loss": 0.0925, + "step": 837 + }, + { + "epoch": 2.66031746031746, + "grad_norm": 4.824801445007324, + "learning_rate": 2.2645502645502647e-06, + "loss": 0.153, + "step": 838 + }, + { + "epoch": 2.6634920634920634, + "grad_norm": 2.8278613090515137, + "learning_rate": 2.2433862433862434e-06, + "loss": 0.0997, + "step": 839 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 1.2369484901428223, + "learning_rate": 2.222222222222222e-06, + "loss": 0.06, + "step": 840 + }, + { + "epoch": 2.6698412698412697, + "grad_norm": 0.7333254814147949, + "learning_rate": 2.201058201058201e-06, + "loss": 0.0425, + "step": 841 + }, + { + "epoch": 2.6730158730158733, + "grad_norm": 1.316390872001648, + "learning_rate": 2.17989417989418e-06, + "loss": 0.088, + "step": 842 + }, + { + "epoch": 2.6761904761904765, + "grad_norm": 2.457948923110962, + "learning_rate": 2.158730158730159e-06, + "loss": 0.1722, + "step": 843 + }, + { + "epoch": 2.6793650793650796, + "grad_norm": 2.9628758430480957, + "learning_rate": 2.1375661375661377e-06, + "loss": 0.1991, + "step": 844 + }, + { + "epoch": 2.682539682539683, + "grad_norm": 1.628462791442871, + "learning_rate": 2.1164021164021164e-06, + "loss": 0.1237, + "step": 845 + }, + { + "epoch": 2.685714285714286, + "grad_norm": 3.1450557708740234, + "learning_rate": 2.0952380952380955e-06, + "loss": 0.1287, + "step": 846 + }, + { + "epoch": 2.688888888888889, + "grad_norm": 2.0330052375793457, + "learning_rate": 2.0740740740740742e-06, + "loss": 0.1374, + "step": 847 + }, + { + "epoch": 2.6920634920634923, + "grad_norm": 5.083005905151367, + "learning_rate": 2.0529100529100534e-06, + "loss": 0.0717, + "step": 848 + }, + { + "epoch": 2.6952380952380954, + "grad_norm": 1.811790108680725, + "learning_rate": 2.031746031746032e-06, + "loss": 0.1581, + "step": 849 + }, + { + "epoch": 2.6984126984126986, + "grad_norm": 2.122985601425171, + "learning_rate": 2.0105820105820108e-06, + "loss": 0.1004, + "step": 850 + }, + { + "epoch": 2.7015873015873018, + "grad_norm": 1.769423246383667, + "learning_rate": 1.9894179894179895e-06, + "loss": 0.1407, + "step": 851 + }, + { + "epoch": 2.704761904761905, + "grad_norm": 2.315749406814575, + "learning_rate": 1.968253968253968e-06, + "loss": 0.1837, + "step": 852 + }, + { + "epoch": 2.707936507936508, + "grad_norm": 0.8786990642547607, + "learning_rate": 1.9470899470899473e-06, + "loss": 0.0727, + "step": 853 + }, + { + "epoch": 2.7111111111111112, + "grad_norm": 1.5662342309951782, + "learning_rate": 1.925925925925926e-06, + "loss": 0.1583, + "step": 854 + }, + { + "epoch": 2.7142857142857144, + "grad_norm": 2.7977397441864014, + "learning_rate": 1.904761904761905e-06, + "loss": 0.139, + "step": 855 + }, + { + "epoch": 2.7174603174603176, + "grad_norm": 2.5321807861328125, + "learning_rate": 1.8835978835978838e-06, + "loss": 0.1074, + "step": 856 + }, + { + "epoch": 2.7206349206349207, + "grad_norm": 1.2418370246887207, + "learning_rate": 1.8624338624338625e-06, + "loss": 0.1273, + "step": 857 + }, + { + "epoch": 2.723809523809524, + "grad_norm": 1.5548622608184814, + "learning_rate": 1.8412698412698416e-06, + "loss": 0.1445, + "step": 858 + }, + { + "epoch": 2.726984126984127, + "grad_norm": 2.4980084896087646, + "learning_rate": 1.8201058201058203e-06, + "loss": 0.1796, + "step": 859 + }, + { + "epoch": 2.7301587301587302, + "grad_norm": 1.4402875900268555, + "learning_rate": 1.798941798941799e-06, + "loss": 0.1087, + "step": 860 + }, + { + "epoch": 2.7333333333333334, + "grad_norm": 2.567962646484375, + "learning_rate": 1.777777777777778e-06, + "loss": 0.0917, + "step": 861 + }, + { + "epoch": 2.7365079365079366, + "grad_norm": 3.931898355484009, + "learning_rate": 1.7566137566137567e-06, + "loss": 0.1706, + "step": 862 + }, + { + "epoch": 2.7396825396825397, + "grad_norm": 3.2448692321777344, + "learning_rate": 1.7354497354497358e-06, + "loss": 0.1311, + "step": 863 + }, + { + "epoch": 2.742857142857143, + "grad_norm": 4.571000099182129, + "learning_rate": 1.7142857142857145e-06, + "loss": 0.0782, + "step": 864 + }, + { + "epoch": 2.746031746031746, + "grad_norm": 2.1480748653411865, + "learning_rate": 1.6931216931216932e-06, + "loss": 0.1208, + "step": 865 + }, + { + "epoch": 2.749206349206349, + "grad_norm": 2.437474250793457, + "learning_rate": 1.671957671957672e-06, + "loss": 0.0975, + "step": 866 + }, + { + "epoch": 2.7523809523809524, + "grad_norm": 2.8579602241516113, + "learning_rate": 1.6507936507936508e-06, + "loss": 0.1226, + "step": 867 + }, + { + "epoch": 2.7555555555555555, + "grad_norm": 4.443211078643799, + "learning_rate": 1.62962962962963e-06, + "loss": 0.0853, + "step": 868 + }, + { + "epoch": 2.7587301587301587, + "grad_norm": 3.814664125442505, + "learning_rate": 1.6084656084656086e-06, + "loss": 0.1086, + "step": 869 + }, + { + "epoch": 2.761904761904762, + "grad_norm": 1.2213096618652344, + "learning_rate": 1.5873015873015873e-06, + "loss": 0.0802, + "step": 870 + }, + { + "epoch": 2.765079365079365, + "grad_norm": 0.9686720967292786, + "learning_rate": 1.5661375661375664e-06, + "loss": 0.077, + "step": 871 + }, + { + "epoch": 2.768253968253968, + "grad_norm": 4.474523067474365, + "learning_rate": 1.5449735449735451e-06, + "loss": 0.1383, + "step": 872 + }, + { + "epoch": 2.7714285714285714, + "grad_norm": 1.5818077325820923, + "learning_rate": 1.523809523809524e-06, + "loss": 0.1518, + "step": 873 + }, + { + "epoch": 2.7746031746031745, + "grad_norm": 4.660221099853516, + "learning_rate": 1.5026455026455028e-06, + "loss": 0.1291, + "step": 874 + }, + { + "epoch": 2.7777777777777777, + "grad_norm": 3.214379072189331, + "learning_rate": 1.4814814814814815e-06, + "loss": 0.1009, + "step": 875 + }, + { + "epoch": 2.780952380952381, + "grad_norm": 1.6341760158538818, + "learning_rate": 1.4603174603174606e-06, + "loss": 0.0923, + "step": 876 + }, + { + "epoch": 2.784126984126984, + "grad_norm": 3.6577823162078857, + "learning_rate": 1.4391534391534393e-06, + "loss": 0.2055, + "step": 877 + }, + { + "epoch": 2.787301587301587, + "grad_norm": 2.2492728233337402, + "learning_rate": 1.417989417989418e-06, + "loss": 0.1176, + "step": 878 + }, + { + "epoch": 2.7904761904761903, + "grad_norm": 1.2452037334442139, + "learning_rate": 1.3968253968253969e-06, + "loss": 0.1069, + "step": 879 + }, + { + "epoch": 2.7936507936507935, + "grad_norm": 1.411680817604065, + "learning_rate": 1.3756613756613758e-06, + "loss": 0.1523, + "step": 880 + }, + { + "epoch": 2.7968253968253967, + "grad_norm": 2.5875589847564697, + "learning_rate": 1.3544973544973547e-06, + "loss": 0.0881, + "step": 881 + }, + { + "epoch": 2.8, + "grad_norm": 3.2830543518066406, + "learning_rate": 1.3333333333333334e-06, + "loss": 0.1239, + "step": 882 + }, + { + "epoch": 2.803174603174603, + "grad_norm": 1.2800664901733398, + "learning_rate": 1.3121693121693121e-06, + "loss": 0.0665, + "step": 883 + }, + { + "epoch": 2.806349206349206, + "grad_norm": 2.050157070159912, + "learning_rate": 1.2910052910052912e-06, + "loss": 0.0797, + "step": 884 + }, + { + "epoch": 2.8095238095238093, + "grad_norm": 1.3595426082611084, + "learning_rate": 1.26984126984127e-06, + "loss": 0.0852, + "step": 885 + }, + { + "epoch": 2.8126984126984125, + "grad_norm": 1.666774868965149, + "learning_rate": 1.2486772486772486e-06, + "loss": 0.1016, + "step": 886 + }, + { + "epoch": 2.8158730158730156, + "grad_norm": 1.8840227127075195, + "learning_rate": 1.2275132275132276e-06, + "loss": 0.1518, + "step": 887 + }, + { + "epoch": 2.819047619047619, + "grad_norm": 2.706073045730591, + "learning_rate": 1.2063492063492065e-06, + "loss": 0.1002, + "step": 888 + }, + { + "epoch": 2.822222222222222, + "grad_norm": 1.4716928005218506, + "learning_rate": 1.1851851851851854e-06, + "loss": 0.1312, + "step": 889 + }, + { + "epoch": 2.825396825396825, + "grad_norm": 3.754307508468628, + "learning_rate": 1.164021164021164e-06, + "loss": 0.1178, + "step": 890 + }, + { + "epoch": 2.8285714285714287, + "grad_norm": 1.6274102926254272, + "learning_rate": 1.142857142857143e-06, + "loss": 0.0914, + "step": 891 + }, + { + "epoch": 2.831746031746032, + "grad_norm": 2.055757522583008, + "learning_rate": 1.1216931216931217e-06, + "loss": 0.1524, + "step": 892 + }, + { + "epoch": 2.834920634920635, + "grad_norm": 2.0142481327056885, + "learning_rate": 1.1005291005291006e-06, + "loss": 0.1517, + "step": 893 + }, + { + "epoch": 2.8380952380952382, + "grad_norm": 1.1050199270248413, + "learning_rate": 1.0793650793650795e-06, + "loss": 0.0975, + "step": 894 + }, + { + "epoch": 2.8412698412698414, + "grad_norm": 1.6837091445922852, + "learning_rate": 1.0582010582010582e-06, + "loss": 0.1279, + "step": 895 + }, + { + "epoch": 2.8444444444444446, + "grad_norm": 4.394120216369629, + "learning_rate": 1.0370370370370371e-06, + "loss": 0.1088, + "step": 896 + }, + { + "epoch": 2.8476190476190477, + "grad_norm": 1.7468510866165161, + "learning_rate": 1.015873015873016e-06, + "loss": 0.146, + "step": 897 + }, + { + "epoch": 2.850793650793651, + "grad_norm": 4.1587443351745605, + "learning_rate": 9.947089947089947e-07, + "loss": 0.163, + "step": 898 + }, + { + "epoch": 2.853968253968254, + "grad_norm": 1.949986457824707, + "learning_rate": 9.735449735449736e-07, + "loss": 0.1522, + "step": 899 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 3.3299190998077393, + "learning_rate": 9.523809523809525e-07, + "loss": 0.2279, + "step": 900 + }, + { + "epoch": 2.8603174603174604, + "grad_norm": 1.551751971244812, + "learning_rate": 9.312169312169313e-07, + "loss": 0.1193, + "step": 901 + }, + { + "epoch": 2.8634920634920635, + "grad_norm": 3.5369818210601807, + "learning_rate": 9.100529100529102e-07, + "loss": 0.1316, + "step": 902 + }, + { + "epoch": 2.8666666666666667, + "grad_norm": 2.535111427307129, + "learning_rate": 8.88888888888889e-07, + "loss": 0.099, + "step": 903 + }, + { + "epoch": 2.86984126984127, + "grad_norm": 0.9801904559135437, + "learning_rate": 8.677248677248679e-07, + "loss": 0.108, + "step": 904 + }, + { + "epoch": 2.873015873015873, + "grad_norm": 1.884214997291565, + "learning_rate": 8.465608465608466e-07, + "loss": 0.1274, + "step": 905 + }, + { + "epoch": 2.876190476190476, + "grad_norm": 1.5890765190124512, + "learning_rate": 8.253968253968254e-07, + "loss": 0.1334, + "step": 906 + }, + { + "epoch": 2.8793650793650793, + "grad_norm": 2.1401264667510986, + "learning_rate": 8.042328042328043e-07, + "loss": 0.1291, + "step": 907 + }, + { + "epoch": 2.8825396825396825, + "grad_norm": 2.939384937286377, + "learning_rate": 7.830687830687832e-07, + "loss": 0.1362, + "step": 908 + }, + { + "epoch": 2.8857142857142857, + "grad_norm": 3.7048137187957764, + "learning_rate": 7.61904761904762e-07, + "loss": 0.1187, + "step": 909 + }, + { + "epoch": 2.888888888888889, + "grad_norm": 2.1142895221710205, + "learning_rate": 7.407407407407407e-07, + "loss": 0.1003, + "step": 910 + }, + { + "epoch": 2.892063492063492, + "grad_norm": 2.990772247314453, + "learning_rate": 7.195767195767196e-07, + "loss": 0.1511, + "step": 911 + }, + { + "epoch": 2.895238095238095, + "grad_norm": 1.500454068183899, + "learning_rate": 6.984126984126984e-07, + "loss": 0.1588, + "step": 912 + }, + { + "epoch": 2.8984126984126983, + "grad_norm": 2.9437148571014404, + "learning_rate": 6.772486772486774e-07, + "loss": 0.1098, + "step": 913 + }, + { + "epoch": 2.9015873015873015, + "grad_norm": 1.2684953212738037, + "learning_rate": 6.560846560846561e-07, + "loss": 0.0875, + "step": 914 + }, + { + "epoch": 2.9047619047619047, + "grad_norm": 2.8139705657958984, + "learning_rate": 6.34920634920635e-07, + "loss": 0.1265, + "step": 915 + }, + { + "epoch": 2.907936507936508, + "grad_norm": 2.7313232421875, + "learning_rate": 6.137566137566138e-07, + "loss": 0.0759, + "step": 916 + }, + { + "epoch": 2.911111111111111, + "grad_norm": 2.4674453735351562, + "learning_rate": 5.925925925925927e-07, + "loss": 0.1483, + "step": 917 + }, + { + "epoch": 2.914285714285714, + "grad_norm": 1.356886386871338, + "learning_rate": 5.714285714285715e-07, + "loss": 0.0666, + "step": 918 + }, + { + "epoch": 2.9174603174603173, + "grad_norm": 1.554082989692688, + "learning_rate": 5.502645502645503e-07, + "loss": 0.1338, + "step": 919 + }, + { + "epoch": 2.9206349206349205, + "grad_norm": 3.9448401927948, + "learning_rate": 5.291005291005291e-07, + "loss": 0.1518, + "step": 920 + }, + { + "epoch": 2.923809523809524, + "grad_norm": 7.095467567443848, + "learning_rate": 5.07936507936508e-07, + "loss": 0.1538, + "step": 921 + }, + { + "epoch": 2.9269841269841272, + "grad_norm": 3.7418735027313232, + "learning_rate": 4.867724867724868e-07, + "loss": 0.1695, + "step": 922 + }, + { + "epoch": 2.9301587301587304, + "grad_norm": 1.4413316249847412, + "learning_rate": 4.6560846560846563e-07, + "loss": 0.1268, + "step": 923 + }, + { + "epoch": 2.9333333333333336, + "grad_norm": 1.4331938028335571, + "learning_rate": 4.444444444444445e-07, + "loss": 0.1458, + "step": 924 + }, + { + "epoch": 2.9365079365079367, + "grad_norm": 1.9505318403244019, + "learning_rate": 4.232804232804233e-07, + "loss": 0.1166, + "step": 925 + }, + { + "epoch": 2.93968253968254, + "grad_norm": 1.286590576171875, + "learning_rate": 4.0211640211640215e-07, + "loss": 0.0934, + "step": 926 + }, + { + "epoch": 2.942857142857143, + "grad_norm": 2.666092872619629, + "learning_rate": 3.80952380952381e-07, + "loss": 0.1961, + "step": 927 + }, + { + "epoch": 2.9460317460317462, + "grad_norm": 1.9119625091552734, + "learning_rate": 3.597883597883598e-07, + "loss": 0.0588, + "step": 928 + }, + { + "epoch": 2.9492063492063494, + "grad_norm": 0.7567910552024841, + "learning_rate": 3.386243386243387e-07, + "loss": 0.125, + "step": 929 + }, + { + "epoch": 2.9523809523809526, + "grad_norm": 3.4173502922058105, + "learning_rate": 3.174603174603175e-07, + "loss": 0.1361, + "step": 930 + }, + { + "epoch": 2.9555555555555557, + "grad_norm": 4.640246868133545, + "learning_rate": 2.9629629629629634e-07, + "loss": 0.1527, + "step": 931 + }, + { + "epoch": 2.958730158730159, + "grad_norm": 1.337565302848816, + "learning_rate": 2.7513227513227515e-07, + "loss": 0.085, + "step": 932 + }, + { + "epoch": 2.961904761904762, + "grad_norm": 5.011254787445068, + "learning_rate": 2.53968253968254e-07, + "loss": 0.1422, + "step": 933 + }, + { + "epoch": 2.965079365079365, + "grad_norm": 1.2437351942062378, + "learning_rate": 2.3280423280423281e-07, + "loss": 0.1361, + "step": 934 + }, + { + "epoch": 2.9682539682539684, + "grad_norm": 1.5140398740768433, + "learning_rate": 2.1164021164021165e-07, + "loss": 0.0741, + "step": 935 + }, + { + "epoch": 2.9714285714285715, + "grad_norm": 4.281813144683838, + "learning_rate": 1.904761904761905e-07, + "loss": 0.1521, + "step": 936 + }, + { + "epoch": 2.9746031746031747, + "grad_norm": 2.2877213954925537, + "learning_rate": 1.6931216931216934e-07, + "loss": 0.1248, + "step": 937 + }, + { + "epoch": 2.977777777777778, + "grad_norm": 1.4525619745254517, + "learning_rate": 1.4814814814814817e-07, + "loss": 0.0978, + "step": 938 + }, + { + "epoch": 2.980952380952381, + "grad_norm": 1.7171831130981445, + "learning_rate": 1.26984126984127e-07, + "loss": 0.0988, + "step": 939 + }, + { + "epoch": 2.984126984126984, + "grad_norm": 2.73106050491333, + "learning_rate": 1.0582010582010582e-07, + "loss": 0.0829, + "step": 940 + }, + { + "epoch": 2.9873015873015873, + "grad_norm": 2.480858325958252, + "learning_rate": 8.465608465608467e-08, + "loss": 0.141, + "step": 941 + }, + { + "epoch": 2.9904761904761905, + "grad_norm": 1.5126322507858276, + "learning_rate": 6.34920634920635e-08, + "loss": 0.0978, + "step": 942 + }, + { + "epoch": 2.9936507936507937, + "grad_norm": 1.9870737791061401, + "learning_rate": 4.2328042328042335e-08, + "loss": 0.1428, + "step": 943 + }, + { + "epoch": 2.996825396825397, + "grad_norm": 1.975643277168274, + "learning_rate": 2.1164021164021167e-08, + "loss": 0.1629, + "step": 944 + }, + { + "epoch": 3.0, + "grad_norm": 1.2699916362762451, + "learning_rate": 0.0, + "loss": 0.0882, + "step": 945 + }, + { + "epoch": 3.0, + "eval_accuracy": 0.775, + "eval_f1": 0.9067245119305856, + "eval_loss": 0.13426347076892853, + "eval_runtime": 2.9409, + "eval_samples_per_second": 380.837, + "eval_steps_per_second": 11.901, + "step": 945 } ], "logging_steps": 1, - "max_steps": 744, + "max_steps": 945, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, @@ -5265,7 +6672,7 @@ "attributes": {} } }, - "total_flos": 142052951715840.0, + "total_flos": 180794665820160.0, "train_batch_size": 32, "trial_name": null, "trial_params": null