| { | |
| "best_metric": 0.062494438141584396, | |
| "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold1/checkpoint-120", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 0.44478148221969604, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.3343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.5385306477546692, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.4162, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.6095714569091797, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.4341, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.47496941685676575, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3668, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.5141810178756714, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.3602, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.540473461151123, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.3732, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.46084773540496826, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.3127, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.5002647042274475, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.3413, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.4936830401420593, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.3125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.43015724420547485, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.2938, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.25964680314064026, | |
| "eval_runtime": 30.6583, | |
| "eval_samples_per_second": 1.468, | |
| "eval_steps_per_second": 1.468, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.396648645401001, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.254, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.3509025573730469, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.2075, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.426551878452301, | |
| "learning_rate": 0.0001, | |
| "loss": 0.2242, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.4979262948036194, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.2219, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.43321555852890015, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.1911, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.45270997285842896, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1803, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.3437568247318268, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1679, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.424480676651001, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1541, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.27685222029685974, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1437, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.3876860439777374, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1405, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.1402113288640976, | |
| "eval_runtime": 30.751, | |
| "eval_samples_per_second": 1.463, | |
| "eval_steps_per_second": 1.463, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.3897685706615448, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1484, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.3773362934589386, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.126, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.3374909460544586, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1236, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.397943377494812, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1199, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.35545614361763, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1336, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.46098098158836365, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.1889, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.6561580896377563, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1086, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.3807108402252197, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0993, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.26344549655914307, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1194, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.2795717418193817, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0894, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.10573732852935791, | |
| "eval_runtime": 30.9461, | |
| "eval_samples_per_second": 1.454, | |
| "eval_steps_per_second": 1.454, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.3880772590637207, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0846, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.24407631158828735, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.0999, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.2581547796726227, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1086, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.20670779049396515, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0849, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.29543644189834595, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1013, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.2804070711135864, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0918, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.21450816094875336, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0667, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.2983039915561676, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1002, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.28091034293174744, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0931, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.23121729493141174, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0836, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.08777261525392532, | |
| "eval_runtime": 30.8805, | |
| "eval_samples_per_second": 1.457, | |
| "eval_steps_per_second": 1.457, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.3718112111091614, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0915, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.4334879517555237, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0769, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.31612250208854675, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0791, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.33394724130630493, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.08, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.28282955288887024, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0789, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.2502811551094055, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0725, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.3168867826461792, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.076, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.23627623915672302, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0574, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.20135019719600677, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0781, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.2263675481081009, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0632, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.07712282240390778, | |
| "eval_runtime": 30.9641, | |
| "eval_samples_per_second": 1.453, | |
| "eval_steps_per_second": 1.453, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.6360402703285217, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1044, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.2483687549829483, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0594, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.18324077129364014, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.048, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.38257041573524475, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0757, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.21322084963321686, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0519, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.2339179366827011, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0584, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.2843327820301056, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0674, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.253025621175766, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0475, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.24246560037136078, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0491, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.34790652990341187, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0616, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.0708819031715393, | |
| "eval_runtime": 31.027, | |
| "eval_samples_per_second": 1.45, | |
| "eval_steps_per_second": 1.45, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.3825662136077881, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0617, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.26856595277786255, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0658, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.31630709767341614, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0601, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.23516355454921722, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0535, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.2980981767177582, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0791, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.1936686635017395, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0434, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.2221946120262146, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0647, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.21494506299495697, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0627, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.21586652100086212, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0453, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.2135646790266037, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0534, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.0676499605178833, | |
| "eval_runtime": 30.9347, | |
| "eval_samples_per_second": 1.455, | |
| "eval_steps_per_second": 1.455, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.2403670996427536, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0467, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.25769734382629395, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0656, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.21171779930591583, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0562, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.2183218151330948, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0495, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.1923147290945053, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0571, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.3822780251502991, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1027, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.22823572158813477, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0462, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.2592290937900543, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0585, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.20861704647541046, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0492, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.20866037905216217, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0435, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.0655478984117508, | |
| "eval_runtime": 29.6029, | |
| "eval_samples_per_second": 1.52, | |
| "eval_steps_per_second": 1.52, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.17823277413845062, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0426, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.21056115627288818, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0543, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.19217325747013092, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0416, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.24306239187717438, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0471, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.192055344581604, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0443, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.20384933054447174, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0461, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.21211786568164825, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0491, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.24135001003742218, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0449, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.23463758826255798, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0454, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.22934697568416595, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0402, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.0642411857843399, | |
| "eval_runtime": 30.9307, | |
| "eval_samples_per_second": 1.455, | |
| "eval_steps_per_second": 1.455, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.19857145845890045, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.051, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.20673440396785736, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0471, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.2791655659675598, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0458, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.2152906209230423, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0483, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.394836962223053, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.05, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.21582813560962677, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0426, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.22523251175880432, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0498, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.26090893149375916, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0496, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.23331314325332642, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0464, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.25828394293785095, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.046, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.06307210773229599, | |
| "eval_runtime": 30.8721, | |
| "eval_samples_per_second": 1.458, | |
| "eval_steps_per_second": 1.458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.24209009110927582, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0585, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.41729259490966797, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0715, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.15453512966632843, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.035, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.2188461422920227, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0387, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.1829191893339157, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0414, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.165192112326622, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0388, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.19496972858905792, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0489, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.1800810694694519, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0429, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.2024528682231903, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0532, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.15986360609531403, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0391, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.0626833513379097, | |
| "eval_runtime": 30.8845, | |
| "eval_samples_per_second": 1.457, | |
| "eval_steps_per_second": 1.457, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.17635105550289154, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0371, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.20033977925777435, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0491, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.2096446305513382, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0491, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.1790723204612732, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0408, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.1745312362909317, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0476, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.1665850281715393, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0346, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.18399165570735931, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0501, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.1748495101928711, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0332, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.16490259766578674, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0396, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.22601744532585144, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0555, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.062494438141584396, | |
| "eval_runtime": 31.0518, | |
| "eval_samples_per_second": 1.449, | |
| "eval_steps_per_second": 1.449, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.18678942322731018, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0381, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.18404996395111084, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0453, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.16794678568840027, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0421, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.17076590657234192, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0368, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.1844700276851654, | |
| "learning_rate": 0.0, | |
| "loss": 0.0389, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.6912169839794586e+17, | |
| "train_loss": 0.09745681342482566, | |
| "train_runtime": 5409.8491, | |
| "train_samples_per_second": 0.374, | |
| "train_steps_per_second": 0.023 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6912169839794586e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |