| { |
| "best_metric": 0.05879095941781998, |
| "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold9/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": 0.4063067138195038, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3425, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.4316953122615814, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3774, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.4792387783527374, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.4089, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.3870411217212677, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.3477, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.4074084162712097, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.3223, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.5163209438323975, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.3532, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.5156098008155823, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.3572, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.39383232593536377, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.2926, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.33500438928604126, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2891, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.35906198620796204, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2819, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.27251380681991577, |
| "eval_runtime": 26.706, |
| "eval_samples_per_second": 1.685, |
| "eval_steps_per_second": 1.685, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.5291590094566345, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.2555, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.5386393070220947, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2211, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.4480850398540497, |
| "learning_rate": 0.0001, |
| "loss": 0.2439, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.3647579550743103, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.2432, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.35696449875831604, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.2076, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.34398970007896423, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1758, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.3204639256000519, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1919, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.331540048122406, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1708, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.33994361758232117, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.167, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.30505087971687317, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1426, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.15021011233329773, |
| "eval_runtime": 26.49, |
| "eval_samples_per_second": 1.699, |
| "eval_steps_per_second": 1.699, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.2872495949268341, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1575, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.3209335505962372, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1464, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.39963310956954956, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1596, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.3331773281097412, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.14, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.3660478889942169, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1336, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.6551069617271423, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.1975, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.2889031171798706, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1082, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.3180329501628876, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1298, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.2754991054534912, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1207, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.2595630884170532, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1008, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.11172691732645035, |
| "eval_runtime": 26.5004, |
| "eval_samples_per_second": 1.698, |
| "eval_steps_per_second": 1.698, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.22208629548549652, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1093, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.2612311542034149, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1091, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.22123077511787415, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.089, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.3076501488685608, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.1044, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.22303079068660736, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0807, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.2716505825519562, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.0968, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.25045260787010193, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0797, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.23908188939094543, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1017, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.2775971591472626, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1139, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.2259189933538437, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0861, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.08980392664670944, |
| "eval_runtime": 26.526, |
| "eval_samples_per_second": 1.696, |
| "eval_steps_per_second": 1.696, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.24728190898895264, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0747, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.2257414311170578, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.0724, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.27135658264160156, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0895, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.25338509678840637, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0931, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.3271442651748657, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0641, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.2366122156381607, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0703, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.26225823163986206, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0829, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.26299262046813965, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0839, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.28448936343193054, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0698, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.24087700247764587, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0701, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.07599332183599472, |
| "eval_runtime": 26.5369, |
| "eval_samples_per_second": 1.696, |
| "eval_steps_per_second": 1.696, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.48809030652046204, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1032, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.2458564043045044, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0714, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.4227047860622406, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0712, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.3087698221206665, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0674, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.22231844067573547, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0504, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.23391246795654297, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0618, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.2895395755767822, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0668, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.24403393268585205, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0562, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.2556283175945282, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.08, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.24531902372837067, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0667, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.0694720521569252, |
| "eval_runtime": 26.5343, |
| "eval_samples_per_second": 1.696, |
| "eval_steps_per_second": 1.696, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.39697951078414917, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0512, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.2602863311767578, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0635, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.20471230149269104, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.05, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.2144995480775833, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0769, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.24907667934894562, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0605, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.17963653802871704, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0571, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.18250861763954163, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0625, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.22476238012313843, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0643, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.22584670782089233, |
| "learning_rate": 5e-05, |
| "loss": 0.0515, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.21389563381671906, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0528, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.06598708778619766, |
| "eval_runtime": 26.5449, |
| "eval_samples_per_second": 1.695, |
| "eval_steps_per_second": 1.695, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.23191913962364197, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0622, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.17287056148052216, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0546, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.20901846885681152, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0633, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.2821616530418396, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0688, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.2311544269323349, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.052, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.37475040555000305, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1074, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.18028177320957184, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0445, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.16001994907855988, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0507, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.19877727329730988, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0403, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.2131386250257492, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0625, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.06223076581954956, |
| "eval_runtime": 26.5748, |
| "eval_samples_per_second": 1.693, |
| "eval_steps_per_second": 1.693, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.2057497799396515, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0573, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.15936654806137085, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0342, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.17954827845096588, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0469, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.17580585181713104, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0403, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.18718543648719788, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.053, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.186039999127388, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0559, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.2269793003797531, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0462, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.20859213173389435, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0576, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.160583958029747, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0428, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.1881675124168396, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0423, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.061292946338653564, |
| "eval_runtime": 26.5815, |
| "eval_samples_per_second": 1.693, |
| "eval_steps_per_second": 1.693, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.18899428844451904, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0631, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.20826087892055511, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0476, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.1759757548570633, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0439, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.1977178156375885, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0586, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.23913554847240448, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0572, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.23223862051963806, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0471, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.19236724078655243, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0497, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.18039290606975555, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0431, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.22131459414958954, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0518, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.192755788564682, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0437, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.060089729726314545, |
| "eval_runtime": 26.617, |
| "eval_samples_per_second": 1.691, |
| "eval_steps_per_second": 1.691, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.28676581382751465, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0583, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.36796289682388306, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0826, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.14883147180080414, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0447, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.15263670682907104, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0341, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.204126238822937, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0527, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.20537212491035461, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0392, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.1895202100276947, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0455, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.15626400709152222, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0452, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.20171894133090973, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0489, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.14761555194854736, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.03, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.05931313335895538, |
| "eval_runtime": 26.6258, |
| "eval_samples_per_second": 1.69, |
| "eval_steps_per_second": 1.69, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.19279694557189941, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0479, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.23241457343101501, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0521, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.1818530410528183, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0522, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.17940661311149597, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0426, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.16701090335845947, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0402, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.20336280763149261, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0496, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.14979569613933563, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.039, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.18385568261146545, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0478, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.18979382514953613, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0553, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.16114217042922974, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0385, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.05879095941781998, |
| "eval_runtime": 26.6268, |
| "eval_samples_per_second": 1.69, |
| "eval_steps_per_second": 1.69, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.23579876124858856, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0563, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.15971121191978455, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0457, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.17713138461112976, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0427, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.17822183668613434, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.05, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.1886035054922104, |
| "learning_rate": 0.0, |
| "loss": 0.0433, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.6673099211001037e+17, |
| "train_loss": 0.10069006884098053, |
| "train_runtime": 4781.8231, |
| "train_samples_per_second": 0.423, |
| "train_steps_per_second": 0.026 |
| } |
| ], |
| "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": 1.6673099211001037e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
