| { | |
| "best_metric": 0.05696810781955719, | |
| "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold6/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": 0.23006705939769745, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.2049, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.19004066288471222, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.267, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.23602378368377686, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.2001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.1938808262348175, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.2333, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.16573303937911987, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.2653, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.19568459689617157, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.2419, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.16969193518161774, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2786, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.16407939791679382, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.2522, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.17536291480064392, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.2574, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.16471357643604279, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1931, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.17603637278079987, | |
| "eval_runtime": 21.0155, | |
| "eval_samples_per_second": 2.141, | |
| "eval_steps_per_second": 2.141, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.15783743560314178, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.2049, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.1257561892271042, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1622, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.11062349379062653, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1741, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.09861240535974503, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1589, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.08910652250051498, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.2054, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.10411472618579865, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.2202, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.09902472794055939, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1557, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.11778475344181061, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1672, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.09728971123695374, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0924, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.0922301784157753, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1153, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.1065211370587349, | |
| "eval_runtime": 21.0212, | |
| "eval_samples_per_second": 2.141, | |
| "eval_steps_per_second": 2.141, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.1054314449429512, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1054, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.09465184807777405, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1777, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.0903925895690918, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1867, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.10415477305650711, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.0773, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.09852281957864761, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.2464, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.15348634123802185, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.2742, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.06527777016162872, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0776, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.06390483677387238, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1331, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.07615907490253448, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0857, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.07111846655607224, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.07791721075773239, | |
| "eval_runtime": 21.0111, | |
| "eval_samples_per_second": 2.142, | |
| "eval_steps_per_second": 2.142, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.08180934935808182, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1292, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.07233917713165283, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1311, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.07313521206378937, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1383, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.07188054174184799, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1362, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.08207601308822632, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1109, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.09252337366342545, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0664, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.08216474950313568, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1072, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.08958999067544937, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1418, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.07074102014303207, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0816, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.06975780427455902, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.1038, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.06751615554094315, | |
| "eval_runtime": 20.9935, | |
| "eval_samples_per_second": 2.144, | |
| "eval_steps_per_second": 2.144, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.0830402746796608, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1109, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.08013243973255157, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1163, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.07397525012493134, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1097, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.06479930877685547, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.0997, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.08707942813634872, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.108, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.09689672291278839, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0891, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.06440558284521103, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1033, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.06031625717878342, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0966, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.07349102944135666, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0743, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.07102738320827484, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0667, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.06309894472360611, | |
| "eval_runtime": 20.9844, | |
| "eval_samples_per_second": 2.144, | |
| "eval_steps_per_second": 2.144, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.12325175851583481, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.222, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.06146053597331047, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.087, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.06311003118753433, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.1137, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.0686122328042984, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1252, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.07071152329444885, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1066, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.06821539998054504, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1066, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.06482325494289398, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.108, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.07280994206666946, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.1443, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.068442203104496, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0945, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.08196698874235153, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0452, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.06020430102944374, | |
| "eval_runtime": 20.9938, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.0718734934926033, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0685, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.06415705382823944, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0689, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.07515713572502136, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.1256, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.055660758167505264, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.058, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.06444253027439117, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.1067, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.07450485229492188, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.1323, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.058116402477025986, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.087, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.05832255259156227, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0741, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.07582145184278488, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0563, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.06223681941628456, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.059, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.05867083743214607, | |
| "eval_runtime": 20.996, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.0630589947104454, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0905, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.06927289813756943, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0552, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.06818821281194687, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.1094, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.06682397425174713, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0827, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.061283402144908905, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0847, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.10883212089538574, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1473, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.06906551867723465, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.1039, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.06280723214149475, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0647, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.06857577711343765, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.116, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.0737842246890068, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0793, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.05813055485486984, | |
| "eval_runtime": 20.997, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.05655964836478233, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0768, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.057393141090869904, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0763, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.06812737137079239, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0961, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.0761374905705452, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.1285, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.05985535308718681, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0676, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.061587728559970856, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0605, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.06323757767677307, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0319, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.06391361355781555, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0616, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.07350856810808182, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0844, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.07672153413295746, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1098, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.05778714269399643, | |
| "eval_runtime": 20.9961, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.07611905038356781, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.1093, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.07405214011669159, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0698, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.06995782256126404, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0821, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.07919204980134964, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0697, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.07098802179098129, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0892, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.06889598071575165, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0615, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.08111726492643356, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1079, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.07246220111846924, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.1348, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.07455697655677795, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.1332, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.06881789118051529, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0713, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.05709902569651604, | |
| "eval_runtime": 20.9915, | |
| "eval_samples_per_second": 2.144, | |
| "eval_steps_per_second": 2.144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.07569389045238495, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0915, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.13333821296691895, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1232, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.07332560420036316, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.1242, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.050120461732149124, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0234, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.06105691194534302, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.1008, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.054447051137685776, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0623, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.07106304913759232, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.1264, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.07980970293283463, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0914, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.058284368366003036, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0725, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.0736161470413208, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0583, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.05718456953763962, | |
| "eval_runtime": 21.0013, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.06461604684591293, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0964, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.050343986600637436, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0537, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.06479498744010925, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0806, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.06768783181905746, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.1028, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.06913737952709198, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.1297, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.0697401836514473, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0751, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.06719011068344116, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0774, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.06760405004024506, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0709, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.057106081396341324, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0556, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.06609610468149185, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0629, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.05696810781955719, | |
| "eval_runtime": 21.0032, | |
| "eval_samples_per_second": 2.143, | |
| "eval_steps_per_second": 2.143, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.06594976782798767, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0881, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.07333142310380936, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.1093, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.07577481120824814, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.119, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.06197281926870346, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0293, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.06462372839450836, | |
| "learning_rate": 0.0, | |
| "loss": 0.0954, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.4511801673816474e+17, | |
| "train_loss": 0.11507274171710015, | |
| "train_runtime": 3430.5353, | |
| "train_samples_per_second": 0.59, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "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": 1.4511801673816474e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |