| { |
| "best_metric": 0.14639350771903992, |
| "best_model_checkpoint": "saves/psy-course-info/Llama-3.1-8B-Instruct/train/fold9/checkpoint-100", |
| "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": 2.3433732986450195, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 1.0295, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 2.3107364177703857, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 1.0492, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 2.320754051208496, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 1.1207, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.294484853744507, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 1.0404, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 2.3560068607330322, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 1.0988, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 2.5125012397766113, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.9848, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 2.478529691696167, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.9791, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 2.349125862121582, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.743, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 2.1266486644744873, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.6839, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.3289445638656616, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.5019, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.4766300916671753, |
| "eval_runtime": 20.7507, |
| "eval_samples_per_second": 2.169, |
| "eval_steps_per_second": 2.169, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.0614572763442993, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.403, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.128636360168457, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.4488, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 1.0990782976150513, |
| "learning_rate": 0.0001, |
| "loss": 0.4333, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 1.0117361545562744, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.3882, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.8518296480178833, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.3133, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 1.0044149160385132, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2943, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.7902452349662781, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.3758, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.678748369216919, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.2429, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.599590539932251, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.293, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.7679451704025269, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.2911, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.2839946746826172, |
| "eval_runtime": 20.5721, |
| "eval_samples_per_second": 2.187, |
| "eval_steps_per_second": 2.187, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.7295883297920227, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.339, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.6696528792381287, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.2665, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.5200027227401733, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.217, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.526070773601532, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.2549, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.5589385628700256, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1988, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 1.1842745542526245, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.3496, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.4790709912776947, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1989, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.4723813235759735, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1841, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.5220105051994324, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1841, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.7248306274414062, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.2219, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.20916315913200378, |
| "eval_runtime": 20.575, |
| "eval_samples_per_second": 2.187, |
| "eval_steps_per_second": 2.187, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.590084433555603, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1929, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.6975643634796143, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.2444, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.4736213684082031, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1489, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.5608780980110168, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.2353, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.6257180571556091, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1897, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.6651261448860168, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1552, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.4756963849067688, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1954, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.6030527353286743, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1814, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.4281989336013794, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1463, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.5276496410369873, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.1505, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.1826619952917099, |
| "eval_runtime": 20.5321, |
| "eval_samples_per_second": 2.192, |
| "eval_steps_per_second": 2.192, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.5215935707092285, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.161, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.43928977847099304, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1522, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.6431208848953247, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.2288, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.5916799902915955, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1574, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.504911482334137, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1281, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.43123072385787964, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.1043, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.5550446510314941, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.1274, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.6193316578865051, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1649, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.47269171476364136, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1218, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5566855072975159, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1645, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.16641412675380707, |
| "eval_runtime": 20.5749, |
| "eval_samples_per_second": 2.187, |
| "eval_steps_per_second": 2.187, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 1.136601448059082, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.2767, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.48069387674331665, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.1469, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.5425804257392883, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.1502, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.4298262894153595, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.1016, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.41236817836761475, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.1069, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.4563198387622833, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.1024, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.45169705152511597, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.117, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.5328837633132935, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.1264, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.48257526755332947, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.1251, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.5201582312583923, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.1279, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.1630752980709076, |
| "eval_runtime": 20.5726, |
| "eval_samples_per_second": 2.187, |
| "eval_steps_per_second": 2.187, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.4746454358100891, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0958, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.7330568432807922, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.1037, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.652062177658081, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.1217, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.6264379620552063, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.2019, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.6534165740013123, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.1271, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.6227792501449585, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.1402, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.5148375630378723, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.1015, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.5808709859848022, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.1214, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.5701559782028198, |
| "learning_rate": 5e-05, |
| "loss": 0.1112, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.6323626041412354, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.1197, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.15409977734088898, |
| "eval_runtime": 20.5815, |
| "eval_samples_per_second": 2.186, |
| "eval_steps_per_second": 2.186, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.5966387391090393, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.1137, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.6430525779724121, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.1315, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.6121845245361328, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.1201, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.4954908490180969, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0989, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.644087016582489, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.1158, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 1.1092921495437622, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1462, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.3306322693824768, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0521, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.4440493583679199, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0839, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.42902693152427673, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0844, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.5827347040176392, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.1081, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.15631836652755737, |
| "eval_runtime": 20.5626, |
| "eval_samples_per_second": 2.188, |
| "eval_steps_per_second": 2.188, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.6509520411491394, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.127, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.5014634728431702, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.051, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.5303320288658142, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0847, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.6037988066673279, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0947, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.4977920651435852, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0794, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.521597146987915, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0926, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.5522618889808655, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.1113, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.46143877506256104, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0823, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.49797937273979187, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0558, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.4893900156021118, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0618, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.14739897847175598, |
| "eval_runtime": 20.5588, |
| "eval_samples_per_second": 2.189, |
| "eval_steps_per_second": 2.189, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.6220207810401917, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.131, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.5778378248214722, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0989, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.6381025314331055, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0982, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.6460904479026794, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.1084, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.8781317472457886, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.1185, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.44647300243377686, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0544, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.46683409810066223, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0935, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.558772087097168, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0885, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.6405532956123352, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.1158, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.5889853239059448, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.1084, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.14639350771903992, |
| "eval_runtime": 20.5285, |
| "eval_samples_per_second": 2.192, |
| "eval_steps_per_second": 2.192, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.9783986806869507, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.1214, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.9813089966773987, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.1406, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.4381439983844757, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0536, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.5356153249740601, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0641, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.7133550643920898, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0756, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.4352448582649231, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0592, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.5250624418258667, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0698, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.5136817097663879, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.1071, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.563313364982605, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0891, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.439544141292572, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0523, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.14658433198928833, |
| "eval_runtime": 20.5087, |
| "eval_samples_per_second": 2.194, |
| "eval_steps_per_second": 2.194, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.612134575843811, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0849, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.602117657661438, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0899, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.37090203166007996, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0562, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.5869200825691223, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0989, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.4638131558895111, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0624, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.49883711338043213, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0726, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.5107743740081787, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0802, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.4872048795223236, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0843, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.6009746789932251, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.1064, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.3727776110172272, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0507, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.14781972765922546, |
| "eval_runtime": 20.4901, |
| "eval_samples_per_second": 2.196, |
| "eval_steps_per_second": 2.196, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.6553190350532532, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.1044, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.469949871301651, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.065, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.5292176008224487, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.061, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.5855149626731873, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0882, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.45277538895606995, |
| "learning_rate": 0.0, |
| "loss": 0.0815, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.2642241251999744e+17, |
| "train_loss": 0.20828802597522736, |
| "train_runtime": 3518.2318, |
| "train_samples_per_second": 0.576, |
| "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": 1.2642241251999744e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
