| { |
| "best_metric": 0.1666204035282135, |
| "best_model_checkpoint": "saves/psy-course-info/Llama-3.1-8B-Instruct/train/fold5/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": 2.390590190887451, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.9745, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 2.110008955001831, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 1.1372, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 2.4071006774902344, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 1.0848, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.4010870456695557, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 1.0268, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 2.381700038909912, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 1.0938, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 2.4948089122772217, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.9037, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 2.316774845123291, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.7979, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 2.3302149772644043, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.7169, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 2.632554531097412, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.8378, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.5894763469696045, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.5084, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.44762614369392395, |
| "eval_runtime": 22.1152, |
| "eval_samples_per_second": 2.035, |
| "eval_steps_per_second": 2.035, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.0913043022155762, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.4427, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.0444154739379883, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.5056, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 1.0997925996780396, |
| "learning_rate": 0.0001, |
| "loss": 0.3871, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 1.1726300716400146, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.4969, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.8532429337501526, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.3259, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 1.0293227434158325, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.3617, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.872860312461853, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.2679, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.7107505798339844, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.3148, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.6841442584991455, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.326, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.6877167820930481, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.2794, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.2594798803329468, |
| "eval_runtime": 21.9154, |
| "eval_samples_per_second": 2.053, |
| "eval_steps_per_second": 2.053, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.7281572818756104, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.2566, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.6940970420837402, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1588, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.6639460921287537, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.2212, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.5774286389350891, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1787, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.4488324522972107, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1872, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.92247474193573, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.3576, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.5308850407600403, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1652, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.5793072581291199, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1802, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.6736124753952026, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.2188, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.5424795746803284, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1812, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.198435977101326, |
| "eval_runtime": 21.965, |
| "eval_samples_per_second": 2.049, |
| "eval_steps_per_second": 2.049, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.44624239206314087, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1176, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.5322471261024475, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1486, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.5887348651885986, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1616, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.6617743372917175, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.2294, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.5999974012374878, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1573, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.47161704301834106, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1303, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.4772252142429352, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1349, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.7842425107955933, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.2103, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.5398549437522888, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1215, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.5042911171913147, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.1498, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.17972540855407715, |
| "eval_runtime": 21.9712, |
| "eval_samples_per_second": 2.048, |
| "eval_steps_per_second": 2.048, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.5407368540763855, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.1332, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.8680931329727173, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.2058, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.48436468839645386, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.1413, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.5790000557899475, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1767, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.7610799670219421, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1541, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.5956255197525024, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.163, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.5833412408828735, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.1345, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.5361647605895996, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1928, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.5345762372016907, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1687, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5725259184837341, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1475, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.17796014249324799, |
| "eval_runtime": 21.9669, |
| "eval_samples_per_second": 2.049, |
| "eval_steps_per_second": 2.049, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 1.1865423917770386, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.2784, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.3902151584625244, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.1138, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.4235444664955139, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0823, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.5299235582351685, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.131, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.49596738815307617, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0977, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.49976620078086853, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.1321, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.49383699893951416, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.1059, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.49068155884742737, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.1514, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.5515344738960266, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.1363, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.5593041777610779, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.1495, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.17032824456691742, |
| "eval_runtime": 21.9739, |
| "eval_samples_per_second": 2.048, |
| "eval_steps_per_second": 2.048, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.40486207604408264, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0954, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5411071181297302, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.1011, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.5609597563743591, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.1167, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.568415641784668, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0958, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.5101826190948486, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.1015, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.4852781593799591, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.1167, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.5387051701545715, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.1038, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.4680575132369995, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0768, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.6288416385650635, |
| "learning_rate": 5e-05, |
| "loss": 0.1365, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.5937770009040833, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.1039, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.17246553301811218, |
| "eval_runtime": 21.9715, |
| "eval_samples_per_second": 2.048, |
| "eval_steps_per_second": 2.048, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.5549561381340027, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0944, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.7670385837554932, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.1455, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.6014059782028198, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.1061, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.6209520697593689, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.1343, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.6865787506103516, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.1419, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 1.1496647596359253, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1537, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.47055432200431824, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0762, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.48365387320518494, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.1097, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.46377551555633545, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0793, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.4647303819656372, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0745, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.1666204035282135, |
| "eval_runtime": 21.9744, |
| "eval_samples_per_second": 2.048, |
| "eval_steps_per_second": 2.048, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.5422425866127014, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0784, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.5297046899795532, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0839, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.5124645233154297, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0675, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.494450181722641, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.081, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.5631364583969116, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0965, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.4911467730998993, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0818, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.675358772277832, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.095, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.4832693338394165, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0627, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.5909997820854187, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.089, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.5229184031486511, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0695, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.1706753820180893, |
| "eval_runtime": 21.9828, |
| "eval_samples_per_second": 2.047, |
| "eval_steps_per_second": 2.047, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.49932220578193665, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0592, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.5896933078765869, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0659, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.5277208089828491, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0552, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.5943085551261902, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.1017, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.7712522745132446, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.1155, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.4662316143512726, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0601, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.6322402954101562, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.1154, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.7817052602767944, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.14, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.561113715171814, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0635, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.5774763226509094, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0591, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.1791609227657318, |
| "eval_runtime": 21.9667, |
| "eval_samples_per_second": 2.049, |
| "eval_steps_per_second": 2.049, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.8871971368789673, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0849, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 1.1692612171173096, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.1375, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.564195454120636, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0687, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.4295189678668976, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0476, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.558070957660675, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0625, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.4711402356624603, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0706, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.7063688039779663, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0614, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.49132922291755676, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0672, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.6347060203552246, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0792, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.4597353935241699, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0568, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.17797401547431946, |
| "eval_runtime": 21.968, |
| "eval_samples_per_second": 2.048, |
| "eval_steps_per_second": 2.048, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.4777275621891022, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0515, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.7299063801765442, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.1076, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.5107489824295044, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0668, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.5860312581062317, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0701, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.6165737509727478, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0742, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.554375410079956, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.05, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.617376446723938, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0717, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.7092514038085938, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.1007, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.5481498837471008, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0704, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.5922465920448303, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0763, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.17861603200435638, |
| "eval_runtime": 21.9719, |
| "eval_samples_per_second": 2.048, |
| "eval_steps_per_second": 2.048, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.5411617159843445, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0703, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.5783974528312683, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0596, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.7459236979484558, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0596, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.5713012218475342, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0833, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.4777219593524933, |
| "learning_rate": 0.0, |
| "loss": 0.0533, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.2544994631765197e+17, |
| "train_loss": 0.20047055861353874, |
| "train_runtime": 3505.2142, |
| "train_samples_per_second": 0.578, |
| "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": 1.2544994631765197e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
