| { |
| "best_metric": 0.04266023263335228, |
| "best_model_checkpoint": "saves/psy-course-doc-info/Ministral-8B-Instruct-2410/train/fold7/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": 0.720118522644043, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3582, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.7227882146835327, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3461, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.7438307404518127, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.3813, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.7236274480819702, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.3431, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.7195573449134827, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.334, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.6174019575119019, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.314, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.41937533020973206, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.254, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.4872221350669861, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.2813, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.532328188419342, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2727, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.5962247252464294, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2278, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.2078080028295517, |
| "eval_runtime": 32.4782, |
| "eval_samples_per_second": 1.386, |
| "eval_steps_per_second": 1.386, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.6221776604652405, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.2608, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.5033315420150757, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2033, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.47051966190338135, |
| "learning_rate": 0.0001, |
| "loss": 0.1892, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.5114531517028809, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.203, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.5060470700263977, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1613, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.5526648163795471, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1466, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.44486695528030396, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1278, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.36465537548065186, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1228, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.5478339195251465, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1035, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.6580950617790222, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.09350533038377762, |
| "eval_runtime": 32.3144, |
| "eval_samples_per_second": 1.393, |
| "eval_steps_per_second": 1.393, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.41753047704696655, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1057, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.358600914478302, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.0997, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.3796774446964264, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.0969, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.30783775448799133, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.0812, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.2928963601589203, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.0858, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.2552763521671295, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.0724, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.30312830209732056, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0894, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.2865533232688904, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.0832, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.2755861282348633, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.0832, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.3185134828090668, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.075, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.07005371153354645, |
| "eval_runtime": 32.3136, |
| "eval_samples_per_second": 1.393, |
| "eval_steps_per_second": 1.393, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.3179952800273895, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0628, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.23399020731449127, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.0722, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.3227664530277252, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0755, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.30311089754104614, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0734, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.24753715097904205, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0702, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.25862714648246765, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.0682, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.27846798300743103, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0616, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.29482507705688477, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0609, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.2984561622142792, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0656, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.28025490045547485, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0667, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.057147763669490814, |
| "eval_runtime": 32.3325, |
| "eval_samples_per_second": 1.392, |
| "eval_steps_per_second": 1.392, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.41065704822540283, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0548, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.2745906710624695, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0548, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.22857949137687683, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0559, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.3559105396270752, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0634, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.22069723904132843, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0539, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.2468593865633011, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0586, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.21954365074634552, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0614, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.2682884633541107, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0567, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.41456180810928345, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0551, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.313581258058548, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0563, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.051966845989227295, |
| "eval_runtime": 32.3119, |
| "eval_samples_per_second": 1.393, |
| "eval_steps_per_second": 1.393, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.224249467253685, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.0504, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.4663204848766327, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0517, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.23792335391044617, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0478, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.33545202016830444, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0587, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.5505682826042175, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0484, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.23464356362819672, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0414, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.1805098056793213, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0544, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.32829272747039795, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0431, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.3564479947090149, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.048, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.2288617193698883, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0424, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.046083830296993256, |
| "eval_runtime": 32.2875, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.20578420162200928, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0522, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.25712060928344727, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0476, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.21758539974689484, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0401, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.21046088635921478, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0429, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.22265493869781494, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0486, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.19519077241420746, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0442, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.1945420503616333, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0391, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.21965011954307556, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0373, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.25152477622032166, |
| "learning_rate": 5e-05, |
| "loss": 0.0392, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.23363439738750458, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0474, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.04592122137546539, |
| "eval_runtime": 32.2827, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.2333303689956665, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0382, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.23191705346107483, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.05, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.20226968824863434, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0406, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.2499319165945053, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0416, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.18354077637195587, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0359, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.17552267014980316, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0368, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.20057572424411774, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0352, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.16224372386932373, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0326, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.16333343088626862, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.037, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.1877480298280716, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0448, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.043607987463474274, |
| "eval_runtime": 32.2767, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.17834073305130005, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.032, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.19408364593982697, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.046, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.1855461299419403, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0351, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.16761887073516846, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0305, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.23398953676223755, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0331, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.23411838710308075, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0329, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.20339253544807434, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0364, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.1765601933002472, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.03, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.20249101519584656, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0332, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.22374211251735687, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0435, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.04325132071971893, |
| "eval_runtime": 32.2793, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.2195817232131958, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0325, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.19201979041099548, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0374, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.2168620526790619, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0356, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.19724707305431366, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0386, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.22672489285469055, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0378, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.2050279676914215, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0328, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.18740125000476837, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.029, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.1969558596611023, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0356, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.22171731293201447, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0389, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.20306746661663055, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0278, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.04297015815973282, |
| "eval_runtime": 32.2774, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.2480797916650772, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0372, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.20272274315357208, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0379, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.18087390065193176, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0283, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.19846919178962708, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0273, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.19102555513381958, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.032, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.17672573029994965, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0276, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.1970769762992859, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0297, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.19131401181221008, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0372, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.16050294041633606, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.035, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.17585837841033936, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0369, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.04271083325147629, |
| "eval_runtime": 32.2697, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.18199016153812408, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0276, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.17828278243541718, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0378, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.19302254915237427, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0281, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.17057864367961884, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0315, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.19988223910331726, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0297, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.23526224493980408, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0361, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.18049852550029755, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0298, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.1841994822025299, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0291, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.14839883148670197, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.026, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.15063868463039398, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0301, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.04266023263335228, |
| "eval_runtime": 32.2837, |
| "eval_samples_per_second": 1.394, |
| "eval_steps_per_second": 1.394, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.17129740118980408, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0322, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.2015349417924881, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0301, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.20649702847003937, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0339, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.16695256531238556, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0312, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.17962034046649933, |
| "learning_rate": 0.0, |
| "loss": 0.0325, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.717800129307607e+17, |
| "train_loss": 0.0772989460080862, |
| "train_runtime": 5083.9206, |
| "train_samples_per_second": 0.398, |
| "train_steps_per_second": 0.025 |
| } |
| ], |
| "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": 1.717800129307607e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
