| { |
| "best_metric": 0.08841148763895035, |
| "best_model_checkpoint": "saves/psy-course-info-chain/Llama-3.1-8B-Instruct/train/fold4/checkpoint-90", |
| "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": 1.7893654108047485, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.5647, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 1.6944242715835571, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.4853, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 1.762972116470337, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.4952, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 1.6563661098480225, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.4993, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 1.8746416568756104, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.6071, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.7228838205337524, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 0.4338, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 1.689962387084961, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.366, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 2.0440218448638916, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.3467, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.297780156135559, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.2793, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.8609126210212708, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.1747, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.15557608008384705, |
| "eval_runtime": 21.9168, |
| "eval_samples_per_second": 2.053, |
| "eval_steps_per_second": 2.053, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 0.6602189540863037, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.164, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.6148247122764587, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.1309, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.9601317048072815, |
| "learning_rate": 0.0001, |
| "loss": 0.2547, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.6050714254379272, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.1333, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.6211292147636414, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1824, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.5211519002914429, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1743, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.635984480381012, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1446, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.4963870644569397, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1882, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.41110146045684814, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.098, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.43514522910118103, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1682, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.12813250720500946, |
| "eval_runtime": 21.8121, |
| "eval_samples_per_second": 2.063, |
| "eval_steps_per_second": 2.063, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.3875369429588318, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1504, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.4483822286128998, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1089, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.3075816035270691, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1089, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.40808549523353577, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1083, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.427717000246048, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1036, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.7880978584289551, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.1581, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.4812042713165283, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.1077, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.33424699306488037, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.0813, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.47559985518455505, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.1136, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.3227177560329437, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.0983, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.11371863633394241, |
| "eval_runtime": 21.7238, |
| "eval_samples_per_second": 2.071, |
| "eval_steps_per_second": 2.071, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.4674253761768341, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.1096, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.42745712399482727, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.1155, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.4282006025314331, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.0852, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.524542510509491, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0824, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.4515324532985687, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.0831, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.5202172994613647, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.1234, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.3815147280693054, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.1152, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.5595164895057678, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1418, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.3878497779369354, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.0889, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.43271952867507935, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0705, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.10113523155450821, |
| "eval_runtime": 21.7891, |
| "eval_samples_per_second": 2.065, |
| "eval_steps_per_second": 2.065, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.48822808265686035, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0831, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.4346986711025238, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1237, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.31086185574531555, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0863, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.3033164143562317, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.077, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 0.25381264090538025, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.0419, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.36458200216293335, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0901, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.3282243609428406, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.1081, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.28459620475769043, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0826, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.4922046363353729, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.1105, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.5012510418891907, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1026, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.09666277468204498, |
| "eval_runtime": 21.7602, |
| "eval_samples_per_second": 2.068, |
| "eval_steps_per_second": 2.068, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.7022793889045715, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1291, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.3334976136684418, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.089, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.2961658239364624, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0664, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.2832334041595459, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0437, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.35461145639419556, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.062, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.3664144277572632, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0699, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.47728827595710754, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.1214, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.40710604190826416, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0904, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.3391262888908386, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.0662, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.29483145475387573, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.05, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.09379304945468903, |
| "eval_runtime": 21.7369, |
| "eval_samples_per_second": 2.07, |
| "eval_steps_per_second": 2.07, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.44295740127563477, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0778, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.5085375308990479, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0759, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.4813602566719055, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.085, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.5302850604057312, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.048, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.3778950273990631, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0863, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.38740935921669006, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0574, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.3280600309371948, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0453, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.3629118800163269, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0653, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.37119215726852417, |
| "learning_rate": 5e-05, |
| "loss": 0.047, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.3339580297470093, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0522, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.0925813764333725, |
| "eval_runtime": 21.7042, |
| "eval_samples_per_second": 2.073, |
| "eval_steps_per_second": 2.073, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.46560269594192505, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0716, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.33357498049736023, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0493, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.45005089044570923, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0858, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.38660141825675964, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.0701, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.44667738676071167, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.1025, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.7721458077430725, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1228, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.319786936044693, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0421, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.45113691687583923, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.0635, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.4147253930568695, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0556, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.46284615993499756, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0499, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.0913093239068985, |
| "eval_runtime": 21.6861, |
| "eval_samples_per_second": 2.075, |
| "eval_steps_per_second": 2.075, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.35295870900154114, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0574, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.3766631484031677, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0391, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.3066927492618561, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.0492, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.43100881576538086, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0671, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.3461545705795288, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0609, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.5299054384231567, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0849, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.2925124168395996, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0376, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.3212495446205139, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0676, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.5487353801727295, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0705, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.3794885575771332, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0483, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.08841148763895035, |
| "eval_runtime": 21.6721, |
| "eval_samples_per_second": 2.076, |
| "eval_steps_per_second": 2.076, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.35193079710006714, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.055, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.5537732839584351, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.0802, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.28870755434036255, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0467, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.46234211325645447, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0527, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.4573204815387726, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0437, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.2804117798805237, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0365, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.37261638045310974, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0504, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.32586434483528137, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0484, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.3231528401374817, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0478, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.3470210134983063, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0378, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.0910976305603981, |
| "eval_runtime": 21.6536, |
| "eval_samples_per_second": 2.078, |
| "eval_steps_per_second": 2.078, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.47441366314888, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0729, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.9417346119880676, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0976, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.2739392817020416, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.037, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.2701776325702667, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.034, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.4344828724861145, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0523, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.2973400056362152, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0287, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.40095168352127075, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0653, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.32921138405799866, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0417, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.3560103178024292, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0573, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.38488849997520447, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0576, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.0906403511762619, |
| "eval_runtime": 21.6589, |
| "eval_samples_per_second": 2.078, |
| "eval_steps_per_second": 2.078, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.4193676710128784, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0543, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.5083053708076477, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0418, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.4243244528770447, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0518, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.3570016324520111, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.0473, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.3688740134239197, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0358, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.4244699478149414, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0442, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.3988695740699768, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.0536, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.3600539565086365, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0273, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.3812147378921509, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.0445, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.553927481174469, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0681, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.09137943387031555, |
| "eval_runtime": 21.6502, |
| "eval_samples_per_second": 2.079, |
| "eval_steps_per_second": 2.079, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.37785211205482483, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0429, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.42605820298194885, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.0397, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.41262227296829224, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.0337, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.5549388527870178, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0497, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 0.2603388726711273, |
| "learning_rate": 0.0, |
| "loss": 0.0223, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.3302485114565427e+17, |
| "train_loss": 0.10700682479143142, |
| "train_runtime": 3725.7076, |
| "train_samples_per_second": 0.544, |
| "train_steps_per_second": 0.034 |
| } |
| ], |
| "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": 1.3302485114565427e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
