| { |
| "best_metric": 0.050360918045043945, |
| "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/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": 0.4353592097759247, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.3629, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.40444207191467285, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.3432, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.4893626272678375, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.4203, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.45704585313796997, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.376, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.44205373525619507, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.3479, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 0.4127894639968872, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.3229, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.43905192613601685, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.3101, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.47922036051750183, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.3385, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 0.3739234209060669, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.307, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.4245363771915436, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.2661, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.2526589632034302, |
| "eval_runtime": 31.5062, |
| "eval_samples_per_second": 1.428, |
| "eval_steps_per_second": 1.428, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.590603768825531, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.2975, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.4575861990451813, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2301, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.47086411714553833, |
| "learning_rate": 0.0001, |
| "loss": 0.2377, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.3809368312358856, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.2553, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.34457433223724365, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.2183, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.3693653345108032, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2086, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.3513469398021698, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1849, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.3359338045120239, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1728, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.3057917654514313, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1614, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.25292491912841797, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1395, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.13725514709949493, |
| "eval_runtime": 31.2762, |
| "eval_samples_per_second": 1.439, |
| "eval_steps_per_second": 1.439, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.2828061282634735, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1526, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.3805382549762726, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1454, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.3378148674964905, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1319, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.36367371678352356, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1244, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.29944369196891785, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.126, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.5355746746063232, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.185, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.3078809082508087, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1269, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.27109044790267944, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1172, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.2456284463405609, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1136, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.3070136308670044, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.116, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.09867291152477264, |
| "eval_runtime": 31.2485, |
| "eval_samples_per_second": 1.44, |
| "eval_steps_per_second": 1.44, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.26388129591941833, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0865, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.30106160044670105, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1171, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.26238104701042175, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0921, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.2620663046836853, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0937, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.3024697005748749, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1089, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.22913743555545807, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.0968, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.26147690415382385, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0871, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.2482328861951828, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.0798, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.2863333225250244, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1015, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.20923635363578796, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0782, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.07687743753194809, |
| "eval_runtime": 31.1865, |
| "eval_samples_per_second": 1.443, |
| "eval_steps_per_second": 1.443, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.23428183794021606, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0727, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.2109469175338745, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.065, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.22286754846572876, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0754, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.2502075433731079, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0782, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.32675835490226746, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0763, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.3092488944530487, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0792, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.26074719429016113, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0936, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.19969512522220612, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0656, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.3014928698539734, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0722, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.19610442221164703, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.0692, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.0652308538556099, |
| "eval_runtime": 31.1418, |
| "eval_samples_per_second": 1.445, |
| "eval_steps_per_second": 1.445, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.43229931592941284, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1115, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.3589022755622864, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0653, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.23734773695468903, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0569, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.31635046005249023, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0776, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.27951252460479736, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.068, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.2925910949707031, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0504, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.2287999987602234, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0752, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.21635882556438446, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0574, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.25230440497398376, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0654, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.29036661982536316, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0573, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.05993087962269783, |
| "eval_runtime": 31.0012, |
| "eval_samples_per_second": 1.452, |
| "eval_steps_per_second": 1.452, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.3638366460800171, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0811, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.25481390953063965, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.061, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.26851552724838257, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0557, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.3412621319293976, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0568, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.2842773199081421, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0767, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.24247275292873383, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0593, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.27267876267433167, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0559, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.23071271181106567, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0468, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.2186797708272934, |
| "learning_rate": 5e-05, |
| "loss": 0.0471, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.24669602513313293, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0554, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.05662938579916954, |
| "eval_runtime": 31.0926, |
| "eval_samples_per_second": 1.447, |
| "eval_steps_per_second": 1.447, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.28331971168518066, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0549, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.21966201066970825, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0625, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.20437771081924438, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0473, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.2248862236738205, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0545, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.222778782248497, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0495, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.4245017468929291, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0885, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.17247839272022247, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0516, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.17405420541763306, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0517, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.1877407431602478, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.046, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.2224157601594925, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0614, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.052356719970703125, |
| "eval_runtime": 31.074, |
| "eval_samples_per_second": 1.448, |
| "eval_steps_per_second": 1.448, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.21588926017284393, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0465, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.18236391246318817, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.056, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.1782270073890686, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0482, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.1661483347415924, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0386, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.26128333806991577, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0414, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.1797957569360733, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0455, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.20818091928958893, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0495, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.20282180607318878, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0499, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.19183722138404846, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0425, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.2299984246492386, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0617, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.05090329796075821, |
| "eval_runtime": 31.056, |
| "eval_samples_per_second": 1.449, |
| "eval_steps_per_second": 1.449, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.19467410445213318, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0487, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.1810794174671173, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0463, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.2266715168952942, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0495, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.20401708781719208, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.053, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.23080001771450043, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0494, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.28232234716415405, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0534, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.22797513008117676, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0406, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.204454705119133, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0436, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.22826434671878815, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0552, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.22450368106365204, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.044, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.05043966323137283, |
| "eval_runtime": 31.038, |
| "eval_samples_per_second": 1.45, |
| "eval_steps_per_second": 1.45, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.24854688346385956, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0628, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.26210111379623413, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0684, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.2108144909143448, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0419, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.28008073568344116, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0407, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.25848641991615295, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0445, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.20415572822093964, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0396, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.23283669352531433, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0465, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.19796988368034363, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0507, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.21270360052585602, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0509, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.18524792790412903, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.046, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.05060172453522682, |
| "eval_runtime": 31.0357, |
| "eval_samples_per_second": 1.45, |
| "eval_steps_per_second": 1.45, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.18089579045772552, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0367, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.1873471736907959, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0517, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.19102250039577484, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0422, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.22974446415901184, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0481, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.19767746329307556, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0433, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.19402767717838287, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0464, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.20142078399658203, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0427, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.19227831065654755, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0391, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.15140675008296967, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0317, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.20731525123119354, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0518, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.050360918045043945, |
| "eval_runtime": 30.9932, |
| "eval_samples_per_second": 1.452, |
| "eval_steps_per_second": 1.452, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.22078165411949158, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.046, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.2053665965795517, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0446, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.18161465227603912, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0522, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.1688094586133957, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0423, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.15920940041542053, |
| "learning_rate": 0.0, |
| "loss": 0.0413, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.6454691682792243e+17, |
| "train_loss": 0.099944845110178, |
| "train_runtime": 4752.2927, |
| "train_samples_per_second": 0.426, |
| "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": 1.6454691682792243e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
