| { |
| "best_metric": 0.09059713035821915, |
| "best_model_checkpoint": "saves/psy-course-info-chain/Llama-3.1-8B-Instruct/train/fold2/checkpoint-90", |
| "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": 1.730302333831787, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.5166, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.821152925491333, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.5505, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 1.7518483400344849, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.516, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 1.692018985748291, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.4995, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 1.7859671115875244, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.5699, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.6878613233566284, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.4483, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 1.5904568433761597, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.3611, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 2.085228681564331, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.3997, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.3033466339111328, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2323, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.6968575119972229, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.1814, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.16879451274871826, |
| "eval_runtime": 22.2135, |
| "eval_samples_per_second": 2.026, |
| "eval_steps_per_second": 2.026, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.6443188786506653, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.1752, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.8221743106842041, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.1718, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.8537706732749939, |
| "learning_rate": 0.0001, |
| "loss": 0.1753, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.88401198387146, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.1992, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.5518884658813477, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1401, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.44944822788238525, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1413, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.49551957845687866, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1184, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.5271273255348206, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1325, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.43580150604248047, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1255, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.40137752890586853, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1215, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.13750457763671875, |
| "eval_runtime": 22.0692, |
| "eval_samples_per_second": 2.039, |
| "eval_steps_per_second": 2.039, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.41625654697418213, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1309, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.519428551197052, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1416, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.31693851947784424, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.0837, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.43993517756462097, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.0952, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.3809512257575989, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1033, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 1.3764491081237793, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.2519, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.2892516255378723, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0659, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.45570656657218933, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.134, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.4302602708339691, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.0828, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.5742453336715698, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1413, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.11990995705127716, |
| "eval_runtime": 22.1012, |
| "eval_samples_per_second": 2.036, |
| "eval_steps_per_second": 2.036, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.41473710536956787, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0896, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.38482871651649475, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.0976, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.44322657585144043, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1263, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.41218897700309753, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0747, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.503483235836029, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1199, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.38045117259025574, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1015, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.2762906551361084, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0554, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.40541738271713257, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1255, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.41214829683303833, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1084, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.46613410115242004, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0717, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.11102399975061417, |
| "eval_runtime": 22.1061, |
| "eval_samples_per_second": 2.036, |
| "eval_steps_per_second": 2.036, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.3403998017311096, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0781, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.4648915231227875, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0895, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.37358811497688293, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0722, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.3286556005477905, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0873, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.3757028579711914, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0653, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.4056745767593384, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0843, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.3625050187110901, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0839, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.30936935544013977, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0632, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.4329220950603485, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0709, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5462491512298584, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.129, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.10084036737680435, |
| "eval_runtime": 22.0875, |
| "eval_samples_per_second": 2.037, |
| "eval_steps_per_second": 2.037, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.8488268256187439, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1968, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.35594692826271057, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0635, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.3750673532485962, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0785, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.3855476677417755, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0718, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.4454019367694855, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0581, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.44082796573638916, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0541, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.44501322507858276, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0932, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.2795521914958954, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0534, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.4501102864742279, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.1063, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.40202176570892334, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0456, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.10345388948917389, |
| "eval_runtime": 22.1051, |
| "eval_samples_per_second": 2.036, |
| "eval_steps_per_second": 2.036, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.2995350956916809, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0467, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5943306684494019, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0703, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.47660431265830994, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.082, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.4918467104434967, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0807, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.3578384220600128, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0648, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.6130046844482422, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0986, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.2883036732673645, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0237, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.49993959069252014, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0708, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.5276492238044739, |
| "learning_rate": 5e-05, |
| "loss": 0.0859, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.3840155005455017, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0676, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.09622037410736084, |
| "eval_runtime": 22.1255, |
| "eval_samples_per_second": 2.034, |
| "eval_steps_per_second": 2.034, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.4367842376232147, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0551, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.6070219874382019, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0689, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.2828626036643982, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.053, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.4681467115879059, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0684, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.4275868237018585, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.1118, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.8362476825714111, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1062, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.3787271976470947, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0518, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.3022363781929016, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0635, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.4683820307254791, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0631, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.2676425874233246, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.036, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.0939740315079689, |
| "eval_runtime": 22.1228, |
| "eval_samples_per_second": 2.034, |
| "eval_steps_per_second": 2.034, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.5432534217834473, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0756, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.3696906268596649, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0423, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.363397479057312, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.045, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.3725789487361908, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0665, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.30975142121315, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0431, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.3544711172580719, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0674, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.4027630090713501, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0324, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.3476358950138092, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0331, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.4126283526420593, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0549, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.3562937080860138, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0359, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.09059713035821915, |
| "eval_runtime": 22.1181, |
| "eval_samples_per_second": 2.035, |
| "eval_steps_per_second": 2.035, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.49792736768722534, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.1039, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.36720460653305054, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0564, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.3547471761703491, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0399, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.3392581641674042, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0394, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.41860881447792053, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0675, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.36804094910621643, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0514, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.3428463637828827, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0424, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.36598441004753113, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.046, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.5016573071479797, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0551, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.4710913598537445, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0469, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.0942782312631607, |
| "eval_runtime": 22.1363, |
| "eval_samples_per_second": 2.033, |
| "eval_steps_per_second": 2.033, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.4926367700099945, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0803, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.7655474543571472, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0812, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.3012935221195221, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0298, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.6197513341903687, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0646, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.39786604046821594, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0443, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.349339097738266, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0357, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.41611623764038086, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0499, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.4074726998806, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0488, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.4438275098800659, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.05, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.2823483347892761, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0334, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.09471254050731659, |
| "eval_runtime": 22.1081, |
| "eval_samples_per_second": 2.035, |
| "eval_steps_per_second": 2.035, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.4568904936313629, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0421, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.48719003796577454, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0417, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.4547186493873596, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0457, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.531100869178772, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0766, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.26290592551231384, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0185, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.39898186922073364, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0413, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.3609587252140045, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0255, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.6262484192848206, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0543, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.5820310711860657, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0534, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.4505619406700134, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0513, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.09455964714288712, |
| "eval_runtime": 22.1429, |
| "eval_samples_per_second": 2.032, |
| "eval_steps_per_second": 2.032, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.4251250922679901, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.067, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.31920307874679565, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0306, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.3993942439556122, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0657, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.3516554534435272, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0362, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.30183789134025574, |
| "learning_rate": 0.0, |
| "loss": 0.0308, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.3129919325241344e+17, |
| "train_loss": 0.10588172161579132, |
| "train_runtime": 3689.8695, |
| "train_samples_per_second": 0.549, |
| "train_steps_per_second": 0.034 |
| } |
| ], |
| "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": 1.3129919325241344e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
