| { | |
| "best_metric": 0.05779074504971504, | |
| "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold10/checkpoint-80", | |
| "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": 0.28413283824920654, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.2122, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.25477471947669983, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.2224, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.2753009796142578, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.1749, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.25359660387039185, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.2466, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.2832784056663513, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.2216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.25216978788375854, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.2093, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.2684244215488434, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2611, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.2361615002155304, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.1887, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.26674574613571167, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.1552, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.17600630223751068, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.12334010004997253, | |
| "eval_runtime": 24.771, | |
| "eval_samples_per_second": 1.817, | |
| "eval_steps_per_second": 1.817, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.23330706357955933, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1299, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.21831607818603516, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1486, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.20809274911880493, | |
| "learning_rate": 0.0001, | |
| "loss": 0.117, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.16792432963848114, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.0877, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.23858265578746796, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.0641, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.1769315004348755, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.0936, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.13790637254714966, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1148, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.14945350587368011, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1053, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.15074005722999573, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0958, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.1316339373588562, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0608, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.0774250477552414, | |
| "eval_runtime": 24.7316, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.15631632506847382, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0946, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.13229282200336456, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.099, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.12399251013994217, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0784, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.1257980912923813, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0501, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.09666812419891357, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.0755, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.10715252161026001, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.1225, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.11905093491077423, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0734, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.10602163523435593, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0824, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.11154142767190933, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1056, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.1033911257982254, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0714, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.06558807939291, | |
| "eval_runtime": 24.7267, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.11579924076795578, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.052, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.10651890933513641, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.0896, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.10591977089643478, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.082, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.11899186670780182, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0761, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.10313864797353745, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0941, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.10155633836984634, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.099, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.12267760932445526, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0678, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.14669956266880035, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0547, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.14021643996238708, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0789, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.12097448110580444, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0917, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.062420330941677094, | |
| "eval_runtime": 24.7276, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.12276095151901245, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0677, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.09951354563236237, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0493, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.10264607518911362, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0645, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.10700056701898575, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.078, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.0994463786482811, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0378, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.12085193395614624, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0621, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.09922127425670624, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0858, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.09377089142799377, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0402, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.1400793343782425, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0618, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.1069316491484642, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.066, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.06059914827346802, | |
| "eval_runtime": 24.7592, | |
| "eval_samples_per_second": 1.818, | |
| "eval_steps_per_second": 1.818, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.09457878768444061, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0388, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.10518480837345123, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0628, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.0973023772239685, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0761, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.10101500898599625, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0763, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.10114068537950516, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.082, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.08355744183063507, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0615, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.13527168333530426, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.1334, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.10329608619213104, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0464, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.10606429725885391, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0341, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.08424171060323715, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0459, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.05976991727948189, | |
| "eval_runtime": 24.7211, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.11451079696416855, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0434, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.09713170677423477, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0379, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.11811358481645584, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.028, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.09441724419593811, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0474, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.12918536365032196, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0992, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.0881912037730217, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0314, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.1037907749414444, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0774, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.098909392952919, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0752, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.12600263953208923, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0904, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.0999891459941864, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0691, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.05866017937660217, | |
| "eval_runtime": 24.7193, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.11161404103040695, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0483, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.11763858795166016, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0748, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.12454231083393097, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0559, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.1035308837890625, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0776, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.104798324406147, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0482, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.08901401609182358, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0301, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.1009877398610115, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0391, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.10123448073863983, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0659, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.0760452002286911, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0199, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.11321450769901276, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0705, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.05779074504971504, | |
| "eval_runtime": 24.7227, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.10015323013067245, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.042, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.09268462657928467, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0361, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.10827892273664474, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.066, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.11729864776134491, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0776, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.09658899158239365, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.061, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.1301175355911255, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0715, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.1092754527926445, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0601, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.12985698878765106, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0863, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.10170172899961472, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0328, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.09787644445896149, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.033, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.05865492299199104, | |
| "eval_runtime": 24.7131, | |
| "eval_samples_per_second": 1.821, | |
| "eval_steps_per_second": 1.821, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.12000403553247452, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0511, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.13291755318641663, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0675, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.08657632768154144, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.03, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.14524148404598236, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0569, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.12864600121974945, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0681, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.10922625660896301, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0415, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.09023148566484451, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0243, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.13381652534008026, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0977, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.10810990631580353, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0474, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.1143050491809845, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.04, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.05797123908996582, | |
| "eval_runtime": 24.7213, | |
| "eval_samples_per_second": 1.82, | |
| "eval_steps_per_second": 1.82, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.12431560456752777, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0661, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.09330152720212936, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.034, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.09827505797147751, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0347, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.10131639987230301, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.037, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.08862192183732986, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0343, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.08679339289665222, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0274, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.12229841947555542, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0779, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.08158275485038757, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0197, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.11970161646604538, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0611, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.11641004681587219, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.054, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.05803883820772171, | |
| "eval_runtime": 24.742, | |
| "eval_samples_per_second": 1.819, | |
| "eval_steps_per_second": 1.819, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.10314659029245377, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0364, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.12414620816707611, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0528, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.09220043569803238, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0243, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.18792866170406342, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0785, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.09553711861371994, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0398, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.1216602697968483, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0649, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.13219916820526123, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0843, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.13477922976016998, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0741, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.14402148127555847, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0923, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.11771170794963837, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0507, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.058232393115758896, | |
| "eval_runtime": 24.7472, | |
| "eval_samples_per_second": 1.818, | |
| "eval_steps_per_second": 1.818, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.11197802424430847, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0479, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.07007748633623123, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0165, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.09508809447288513, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0296, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.09024827182292938, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0263, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.11864247918128967, | |
| "learning_rate": 0.0, | |
| "loss": 0.0548, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.527948892445737e+17, | |
| "train_loss": 0.07522290875017643, | |
| "train_runtime": 3930.8797, | |
| "train_samples_per_second": 0.515, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "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": 1.527948892445737e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |