| { |
| "best_metric": 0.14199036359786987, |
| "best_model_checkpoint": "saves/psy-course-info/Ministral-8B-Instruct-2410/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": 2.1133830547332764, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.8163, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.960137963294983, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.9518, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 2.245347499847412, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.9656, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 2.2406439781188965, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.9331, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 2.0736091136932373, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.9031, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 2.027510643005371, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.7551, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 1.8065158128738403, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.6011, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 1.5644067525863647, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.5294, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.6535420417785645, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.6166, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.1826376914978027, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.4174, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.35372456908226013, |
| "eval_runtime": 23.2718, |
| "eval_samples_per_second": 1.934, |
| "eval_steps_per_second": 1.934, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.3359867334365845, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.3735, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 1.2220722436904907, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.3338, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.8286646604537964, |
| "learning_rate": 0.0001, |
| "loss": 0.2569, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.830769956111908, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.3398, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.8217406272888184, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.2382, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 1.104914903640747, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.2643, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.6462150812149048, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1863, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.822726309299469, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.2088, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.6053947806358337, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.2041, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.6828872561454773, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1926, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.1861436367034912, |
| "eval_runtime": 23.1305, |
| "eval_samples_per_second": 1.945, |
| "eval_steps_per_second": 1.945, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.7504855990409851, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1668, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.5776033997535706, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1004, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.6058062314987183, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1672, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.5855321884155273, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.141, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.6271630525588989, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1333, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 1.1367470026016235, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.2066, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.6898078918457031, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1356, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.6170883178710938, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.1271, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.7181650996208191, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.138, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.8500134348869324, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1219, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.15728320181369781, |
| "eval_runtime": 23.1433, |
| "eval_samples_per_second": 1.944, |
| "eval_steps_per_second": 1.944, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.555647611618042, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0871, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.5834464430809021, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1048, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.7507017850875854, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1122, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.7359830141067505, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.1613, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.9755268096923828, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1388, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.5624356865882874, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1121, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.5258103013038635, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0922, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.5814852118492126, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1275, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.9419199228286743, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1103, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.6801099181175232, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.1156, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.14530666172504425, |
| "eval_runtime": 23.1508, |
| "eval_samples_per_second": 1.944, |
| "eval_steps_per_second": 1.944, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.5828931927680969, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0987, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.8340241312980652, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1434, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.5500354766845703, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0901, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.6403986811637878, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.1341, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.9554204344749451, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.1259, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.65843266248703, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.1279, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.5520516633987427, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0872, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.5638436079025269, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.1353, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.6331632137298584, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1217, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5768002867698669, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1196, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.1508501023054123, |
| "eval_runtime": 23.1934, |
| "eval_samples_per_second": 1.94, |
| "eval_steps_per_second": 1.94, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.5737069845199585, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.101, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.3964419364929199, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.0767, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.362837016582489, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0542, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.4791572093963623, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.1004, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.44061943888664246, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0678, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.5124072432518005, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.1053, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.6215721368789673, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.0914, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.4216948449611664, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.1042, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.5729345679283142, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0935, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.5648484230041504, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0994, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.14861640334129333, |
| "eval_runtime": 23.1986, |
| "eval_samples_per_second": 1.94, |
| "eval_steps_per_second": 1.94, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.3977755606174469, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.071, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5475702881813049, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0689, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.5031222105026245, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0807, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.4980502724647522, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0625, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.4893190562725067, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0694, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.6684648394584656, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0893, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.5168462991714478, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0799, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.5542368292808533, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0664, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.7075352668762207, |
| "learning_rate": 5e-05, |
| "loss": 0.1004, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.5200499892234802, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0806, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.14549987018108368, |
| "eval_runtime": 23.198, |
| "eval_samples_per_second": 1.94, |
| "eval_steps_per_second": 1.94, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.6475802659988403, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0681, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.7281832098960876, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0981, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.45621952414512634, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0643, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.6728904843330383, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0942, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.5897018313407898, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.0852, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.5507437586784363, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.0664, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.4569501578807831, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0544, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.5081137418746948, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0742, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.4767453968524933, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0567, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.49080368876457214, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.058, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.14199036359786987, |
| "eval_runtime": 23.2048, |
| "eval_samples_per_second": 1.939, |
| "eval_steps_per_second": 1.939, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.5734049081802368, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0649, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.3990074396133423, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0597, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.5875536203384399, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0572, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.4592146873474121, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0605, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.4735570549964905, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0668, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.4874242842197418, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0621, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.5969957709312439, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0655, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.5287556648254395, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.041, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.56488436460495, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0558, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.4211632311344147, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0492, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.14404471218585968, |
| "eval_runtime": 23.2229, |
| "eval_samples_per_second": 1.938, |
| "eval_steps_per_second": 1.938, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.9151549339294434, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.0412, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.5012921094894409, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0531, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.37206462025642395, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0423, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.5976440906524658, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0553, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.5776558518409729, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0623, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.4063349664211273, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0399, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.5824398398399353, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0638, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.6697022318840027, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0929, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.5798482298851013, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0465, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.5786239504814148, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.041, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.1470015048980713, |
| "eval_runtime": 23.2183, |
| "eval_samples_per_second": 1.938, |
| "eval_steps_per_second": 1.938, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.46617135405540466, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0391, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.5097420811653137, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0542, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.4701959192752838, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0477, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.36094674468040466, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0372, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.44540145993232727, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0486, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.4206129312515259, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0439, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.5581309199333191, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0367, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.45739996433258057, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0439, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.5128577351570129, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0502, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.47219428420066833, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0391, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.1494264155626297, |
| "eval_runtime": 23.2204, |
| "eval_samples_per_second": 1.938, |
| "eval_steps_per_second": 1.938, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.5311831831932068, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0359, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.5830100178718567, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0615, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.36969226598739624, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0346, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.7431719303131104, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0491, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.5429864525794983, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0402, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.45994076132774353, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0296, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.5812681913375854, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0489, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.5192630887031555, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0666, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.4089965224266052, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.035, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.48551565408706665, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0489, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.14789894223213196, |
| "eval_runtime": 23.1845, |
| "eval_samples_per_second": 1.941, |
| "eval_steps_per_second": 1.941, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.5202046632766724, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0455, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.5919499397277832, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0426, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.41226810216903687, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0363, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.58610999584198, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0486, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.40098315477371216, |
| "learning_rate": 0.0, |
| "loss": 0.0416, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.2928277374835098e+17, |
| "train_loss": 0.14784522449970244, |
| "train_runtime": 3746.4291, |
| "train_samples_per_second": 0.541, |
| "train_steps_per_second": 0.033 |
| } |
| ], |
| "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": 1.2928277374835098e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
