| { |
| "best_metric": 0.08639644831418991, |
| "best_model_checkpoint": "saves/psy-course-info-chain/MentaLLaMA-chat-7B/train/fold2/checkpoint-110", |
| "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": 0.772149384021759, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.64, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07901234567901234, |
| "grad_norm": 0.8438737988471985, |
| "learning_rate": 1.5384615384615387e-05, |
| "loss": 0.7052, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.11851851851851852, |
| "grad_norm": 0.7375575304031372, |
| "learning_rate": 2.307692307692308e-05, |
| "loss": 0.5818, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.1580246913580247, |
| "grad_norm": 0.8077000975608826, |
| "learning_rate": 3.0769230769230774e-05, |
| "loss": 0.6531, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.7314829230308533, |
| "learning_rate": 3.846153846153846e-05, |
| "loss": 0.6428, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.23703703703703705, |
| "grad_norm": 1.3161226511001587, |
| "learning_rate": 4.615384615384616e-05, |
| "loss": 1.2319, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.2765432098765432, |
| "grad_norm": 0.8937004804611206, |
| "learning_rate": 5.384615384615385e-05, |
| "loss": 0.5189, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.3160493827160494, |
| "grad_norm": 0.9438484311103821, |
| "learning_rate": 6.153846153846155e-05, |
| "loss": 0.6509, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.0674121379852295, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.5228, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 1.0031065940856934, |
| "learning_rate": 7.692307692307693e-05, |
| "loss": 0.3866, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 0.32570451498031616, |
| "eval_runtime": 24.8124, |
| "eval_samples_per_second": 1.814, |
| "eval_steps_per_second": 1.814, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4345679012345679, |
| "grad_norm": 1.117361307144165, |
| "learning_rate": 8.461538461538461e-05, |
| "loss": 0.3251, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4740740740740741, |
| "grad_norm": 0.6498613357543945, |
| "learning_rate": 9.230769230769232e-05, |
| "loss": 0.2418, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5135802469135803, |
| "grad_norm": 0.3887569308280945, |
| "learning_rate": 0.0001, |
| "loss": 0.1588, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.5530864197530864, |
| "grad_norm": 0.40630266070365906, |
| "learning_rate": 9.998033131915266e-05, |
| "loss": 0.2048, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.4417363703250885, |
| "learning_rate": 9.992134075089084e-05, |
| "loss": 0.1627, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6320987654320988, |
| "grad_norm": 0.35771891474723816, |
| "learning_rate": 9.982307470588098e-05, |
| "loss": 0.1805, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.671604938271605, |
| "grad_norm": 0.5804832577705383, |
| "learning_rate": 9.968561049466214e-05, |
| "loss": 0.1509, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 0.28622952103614807, |
| "learning_rate": 9.950905626682228e-05, |
| "loss": 0.1125, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.7506172839506173, |
| "grad_norm": 0.46204349398612976, |
| "learning_rate": 9.92935509259118e-05, |
| "loss": 0.1409, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.48902198672294617, |
| "learning_rate": 9.903926402016153e-05, |
| "loss": 0.1461, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 0.14785434305667877, |
| "eval_runtime": 24.7788, |
| "eval_samples_per_second": 1.816, |
| "eval_steps_per_second": 1.816, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8296296296296296, |
| "grad_norm": 0.3153349459171295, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 0.1261, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.8691358024691358, |
| "grad_norm": 0.3094187378883362, |
| "learning_rate": 9.841517610611309e-05, |
| "loss": 0.1409, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.908641975308642, |
| "grad_norm": 0.2341873198747635, |
| "learning_rate": 9.804586609725499e-05, |
| "loss": 0.1007, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.9481481481481482, |
| "grad_norm": 0.20925667881965637, |
| "learning_rate": 9.763875613614482e-05, |
| "loss": 0.1027, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.23388352990150452, |
| "learning_rate": 9.719416651541839e-05, |
| "loss": 0.1216, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.0271604938271606, |
| "grad_norm": 0.6843671202659607, |
| "learning_rate": 9.671244701472999e-05, |
| "loss": 0.268, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 0.22474437952041626, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.0738, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.106172839506173, |
| "grad_norm": 0.3029688000679016, |
| "learning_rate": 9.563916325306594e-05, |
| "loss": 0.163, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.145679012345679, |
| "grad_norm": 0.2332800328731537, |
| "learning_rate": 9.504844339512095e-05, |
| "loss": 0.0913, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "grad_norm": 0.3389436602592468, |
| "learning_rate": 9.442228179894362e-05, |
| "loss": 0.1416, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.1851851851851851, |
| "eval_loss": 0.11412136256694794, |
| "eval_runtime": 24.7848, |
| "eval_samples_per_second": 1.816, |
| "eval_steps_per_second": 1.816, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.2246913580246914, |
| "grad_norm": 0.23156620562076569, |
| "learning_rate": 9.376117109543769e-05, |
| "loss": 0.0958, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.2641975308641975, |
| "grad_norm": 0.1964586228132248, |
| "learning_rate": 9.306563141162046e-05, |
| "loss": 0.0906, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.3037037037037038, |
| "grad_norm": 0.3127536177635193, |
| "learning_rate": 9.233620996141421e-05, |
| "loss": 0.1221, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.34320987654321, |
| "grad_norm": 0.2193470150232315, |
| "learning_rate": 9.157348061512727e-05, |
| "loss": 0.0756, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.382716049382716, |
| "grad_norm": 0.3020366430282593, |
| "learning_rate": 9.077804344796302e-05, |
| "loss": 0.1097, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 0.2154160439968109, |
| "learning_rate": 8.995052426791247e-05, |
| "loss": 0.096, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.4617283950617284, |
| "grad_norm": 0.16960011422634125, |
| "learning_rate": 8.90915741234015e-05, |
| "loss": 0.0619, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.5012345679012347, |
| "grad_norm": 0.2908982038497925, |
| "learning_rate": 8.820186879108038e-05, |
| "loss": 0.1137, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.5407407407407407, |
| "grad_norm": 0.2491985559463501, |
| "learning_rate": 8.728210824415827e-05, |
| "loss": 0.1078, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "grad_norm": 0.22408314049243927, |
| "learning_rate": 8.633301610170135e-05, |
| "loss": 0.0776, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.5802469135802468, |
| "eval_loss": 0.10050783306360245, |
| "eval_runtime": 24.7945, |
| "eval_samples_per_second": 1.815, |
| "eval_steps_per_second": 1.815, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.6197530864197531, |
| "grad_norm": 0.23565658926963806, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 0.0753, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.6592592592592592, |
| "grad_norm": 0.2485012710094452, |
| "learning_rate": 8.434984630174509e-05, |
| "loss": 0.1028, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.6987654320987655, |
| "grad_norm": 0.2391873449087143, |
| "learning_rate": 8.33173288976002e-05, |
| "loss": 0.0812, |
| "step": 43 |
| }, |
| { |
| "epoch": 1.7382716049382716, |
| "grad_norm": 0.2207205444574356, |
| "learning_rate": 8.225859917710439e-05, |
| "loss": 0.0868, |
| "step": 44 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 1.3163838386535645, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 0.6011, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.817283950617284, |
| "grad_norm": 0.28205960988998413, |
| "learning_rate": 8.006585456492029e-05, |
| "loss": 0.0981, |
| "step": 46 |
| }, |
| { |
| "epoch": 1.8567901234567903, |
| "grad_norm": 0.2213909775018692, |
| "learning_rate": 7.89335648089903e-05, |
| "loss": 0.0795, |
| "step": 47 |
| }, |
| { |
| "epoch": 1.8962962962962964, |
| "grad_norm": 0.22839370369911194, |
| "learning_rate": 7.777851165098012e-05, |
| "loss": 0.0714, |
| "step": 48 |
| }, |
| { |
| "epoch": 1.9358024691358025, |
| "grad_norm": 0.22298012673854828, |
| "learning_rate": 7.660160382576683e-05, |
| "loss": 0.0705, |
| "step": 49 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "grad_norm": 0.26656123995780945, |
| "learning_rate": 7.540376726232648e-05, |
| "loss": 0.1284, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.9753086419753085, |
| "eval_loss": 0.09547383338212967, |
| "eval_runtime": 24.7961, |
| "eval_samples_per_second": 1.815, |
| "eval_steps_per_second": 1.815, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.0148148148148146, |
| "grad_norm": 0.4964837431907654, |
| "learning_rate": 7.4185944355262e-05, |
| "loss": 0.1919, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.054320987654321, |
| "grad_norm": 0.20750653743743896, |
| "learning_rate": 7.294909322337689e-05, |
| "loss": 0.068, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.093827160493827, |
| "grad_norm": 0.19626370072364807, |
| "learning_rate": 7.169418695587791e-05, |
| "loss": 0.0801, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 0.2759949862957001, |
| "learning_rate": 7.042221284679982e-05, |
| "loss": 0.0982, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.1728395061728394, |
| "grad_norm": 0.2729087769985199, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 0.0578, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.212345679012346, |
| "grad_norm": 0.21501068770885468, |
| "learning_rate": 6.783107663311565e-05, |
| "loss": 0.0686, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.251851851851852, |
| "grad_norm": 0.2189883589744568, |
| "learning_rate": 6.651395309775837e-05, |
| "loss": 0.1039, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.291358024691358, |
| "grad_norm": 0.21976900100708008, |
| "learning_rate": 6.518383725548074e-05, |
| "loss": 0.0606, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.330864197530864, |
| "grad_norm": 0.2630636990070343, |
| "learning_rate": 6.384177557124247e-05, |
| "loss": 0.1034, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "grad_norm": 0.25591370463371277, |
| "learning_rate": 6.248882390836135e-05, |
| "loss": 0.0614, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.3703703703703702, |
| "eval_loss": 0.0925067812204361, |
| "eval_runtime": 24.7877, |
| "eval_samples_per_second": 1.815, |
| "eval_steps_per_second": 1.815, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.4098765432098768, |
| "grad_norm": 0.2179541289806366, |
| "learning_rate": 6.112604669781572e-05, |
| "loss": 0.0442, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.449382716049383, |
| "grad_norm": 0.3989110589027405, |
| "learning_rate": 5.9754516100806423e-05, |
| "loss": 0.0716, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 0.23151126503944397, |
| "learning_rate": 5.837531116523682e-05, |
| "loss": 0.0765, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.528395061728395, |
| "grad_norm": 0.3186756670475006, |
| "learning_rate": 5.698951697677498e-05, |
| "loss": 0.0867, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.567901234567901, |
| "grad_norm": 0.23965106904506683, |
| "learning_rate": 5.559822380516539e-05, |
| "loss": 0.0693, |
| "step": 65 |
| }, |
| { |
| "epoch": 2.6074074074074076, |
| "grad_norm": 0.2724037766456604, |
| "learning_rate": 5.420252624646238e-05, |
| "loss": 0.0883, |
| "step": 66 |
| }, |
| { |
| "epoch": 2.6469135802469137, |
| "grad_norm": 0.19838418066501617, |
| "learning_rate": 5.2803522361859594e-05, |
| "loss": 0.0374, |
| "step": 67 |
| }, |
| { |
| "epoch": 2.68641975308642, |
| "grad_norm": 0.2965606451034546, |
| "learning_rate": 5.140231281379345e-05, |
| "loss": 0.0747, |
| "step": 68 |
| }, |
| { |
| "epoch": 2.725925925925926, |
| "grad_norm": 0.2672410309314728, |
| "learning_rate": 5e-05, |
| "loss": 0.0884, |
| "step": 69 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "grad_norm": 0.3098633885383606, |
| "learning_rate": 4.859768718620656e-05, |
| "loss": 0.0718, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.765432098765432, |
| "eval_loss": 0.09093321859836578, |
| "eval_runtime": 24.7969, |
| "eval_samples_per_second": 1.815, |
| "eval_steps_per_second": 1.815, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8049382716049385, |
| "grad_norm": 0.3163372874259949, |
| "learning_rate": 4.7196477638140404e-05, |
| "loss": 0.0539, |
| "step": 71 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 0.2201339453458786, |
| "learning_rate": 4.579747375353763e-05, |
| "loss": 0.0621, |
| "step": 72 |
| }, |
| { |
| "epoch": 2.8839506172839506, |
| "grad_norm": 0.23914173245429993, |
| "learning_rate": 4.4401776194834613e-05, |
| "loss": 0.0695, |
| "step": 73 |
| }, |
| { |
| "epoch": 2.9234567901234567, |
| "grad_norm": 0.9590194821357727, |
| "learning_rate": 4.3010483023225045e-05, |
| "loss": 0.5062, |
| "step": 74 |
| }, |
| { |
| "epoch": 2.962962962962963, |
| "grad_norm": 0.35146364569664, |
| "learning_rate": 4.162468883476319e-05, |
| "loss": 0.114, |
| "step": 75 |
| }, |
| { |
| "epoch": 3.0024691358024693, |
| "grad_norm": 0.48039498925209045, |
| "learning_rate": 4.0245483899193595e-05, |
| "loss": 0.1096, |
| "step": 76 |
| }, |
| { |
| "epoch": 3.0419753086419754, |
| "grad_norm": 0.24013695120811462, |
| "learning_rate": 3.887395330218429e-05, |
| "loss": 0.0575, |
| "step": 77 |
| }, |
| { |
| "epoch": 3.0814814814814815, |
| "grad_norm": 0.6489439606666565, |
| "learning_rate": 3.7511176091638653e-05, |
| "loss": 0.4444, |
| "step": 78 |
| }, |
| { |
| "epoch": 3.1209876543209876, |
| "grad_norm": 0.35072818398475647, |
| "learning_rate": 3.6158224428757535e-05, |
| "loss": 0.0686, |
| "step": 79 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "grad_norm": 0.24817728996276855, |
| "learning_rate": 3.4816162744519263e-05, |
| "loss": 0.0483, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.1604938271604937, |
| "eval_loss": 0.08724228292703629, |
| "eval_runtime": 24.7767, |
| "eval_samples_per_second": 1.816, |
| "eval_steps_per_second": 1.816, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.23139391839504242, |
| "learning_rate": 3.3486046902241664e-05, |
| "loss": 0.0758, |
| "step": 81 |
| }, |
| { |
| "epoch": 3.2395061728395063, |
| "grad_norm": 0.2520310580730438, |
| "learning_rate": 3.216892336688435e-05, |
| "loss": 0.0552, |
| "step": 82 |
| }, |
| { |
| "epoch": 3.2790123456790123, |
| "grad_norm": 0.2255639284849167, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 0.055, |
| "step": 83 |
| }, |
| { |
| "epoch": 3.3185185185185184, |
| "grad_norm": 0.2261783480644226, |
| "learning_rate": 2.9577787153200197e-05, |
| "loss": 0.0749, |
| "step": 84 |
| }, |
| { |
| "epoch": 3.3580246913580245, |
| "grad_norm": 0.24274060130119324, |
| "learning_rate": 2.8305813044122097e-05, |
| "loss": 0.0586, |
| "step": 85 |
| }, |
| { |
| "epoch": 3.397530864197531, |
| "grad_norm": 0.24875684082508087, |
| "learning_rate": 2.705090677662311e-05, |
| "loss": 0.0792, |
| "step": 86 |
| }, |
| { |
| "epoch": 3.437037037037037, |
| "grad_norm": 0.24777759611606598, |
| "learning_rate": 2.581405564473801e-05, |
| "loss": 0.0442, |
| "step": 87 |
| }, |
| { |
| "epoch": 3.476543209876543, |
| "grad_norm": 0.21496568620204926, |
| "learning_rate": 2.459623273767354e-05, |
| "loss": 0.0389, |
| "step": 88 |
| }, |
| { |
| "epoch": 3.5160493827160493, |
| "grad_norm": 0.2810584306716919, |
| "learning_rate": 2.3398396174233178e-05, |
| "loss": 0.0569, |
| "step": 89 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "grad_norm": 0.19330354034900665, |
| "learning_rate": 2.2221488349019903e-05, |
| "loss": 0.0421, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.5555555555555554, |
| "eval_loss": 0.08732187002897263, |
| "eval_runtime": 24.7583, |
| "eval_samples_per_second": 1.818, |
| "eval_steps_per_second": 1.818, |
| "step": 90 |
| }, |
| { |
| "epoch": 3.595061728395062, |
| "grad_norm": 0.27564504742622375, |
| "learning_rate": 2.1066435191009715e-05, |
| "loss": 0.1067, |
| "step": 91 |
| }, |
| { |
| "epoch": 3.634567901234568, |
| "grad_norm": 0.22622695565223694, |
| "learning_rate": 1.9934145435079702e-05, |
| "loss": 0.061, |
| "step": 92 |
| }, |
| { |
| "epoch": 3.674074074074074, |
| "grad_norm": 0.22893360257148743, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 0.0501, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.71358024691358, |
| "grad_norm": 0.19763456284999847, |
| "learning_rate": 1.774140082289563e-05, |
| "loss": 0.0622, |
| "step": 94 |
| }, |
| { |
| "epoch": 3.753086419753086, |
| "grad_norm": 0.24398531019687653, |
| "learning_rate": 1.6682671102399805e-05, |
| "loss": 0.0896, |
| "step": 95 |
| }, |
| { |
| "epoch": 3.7925925925925927, |
| "grad_norm": 0.23638160526752472, |
| "learning_rate": 1.5650153698254916e-05, |
| "loss": 0.0658, |
| "step": 96 |
| }, |
| { |
| "epoch": 3.832098765432099, |
| "grad_norm": 0.19654731452465057, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 0.0421, |
| "step": 97 |
| }, |
| { |
| "epoch": 3.871604938271605, |
| "grad_norm": 0.26146942377090454, |
| "learning_rate": 1.3666983898298657e-05, |
| "loss": 0.0634, |
| "step": 98 |
| }, |
| { |
| "epoch": 3.911111111111111, |
| "grad_norm": 0.286037802696228, |
| "learning_rate": 1.2717891755841722e-05, |
| "loss": 0.0618, |
| "step": 99 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "grad_norm": 0.23712097108364105, |
| "learning_rate": 1.1798131208919627e-05, |
| "loss": 0.0594, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.950617283950617, |
| "eval_loss": 0.08704684674739838, |
| "eval_runtime": 24.7479, |
| "eval_samples_per_second": 1.818, |
| "eval_steps_per_second": 1.818, |
| "step": 100 |
| }, |
| { |
| "epoch": 3.9901234567901236, |
| "grad_norm": 0.38823768496513367, |
| "learning_rate": 1.090842587659851e-05, |
| "loss": 0.0889, |
| "step": 101 |
| }, |
| { |
| "epoch": 4.029629629629629, |
| "grad_norm": 0.5831246972084045, |
| "learning_rate": 1.004947573208756e-05, |
| "loss": 0.0997, |
| "step": 102 |
| }, |
| { |
| "epoch": 4.069135802469136, |
| "grad_norm": 0.2512650787830353, |
| "learning_rate": 9.221956552036992e-06, |
| "loss": 0.0529, |
| "step": 103 |
| }, |
| { |
| "epoch": 4.108641975308642, |
| "grad_norm": 0.22888073325157166, |
| "learning_rate": 8.426519384872733e-06, |
| "loss": 0.0553, |
| "step": 104 |
| }, |
| { |
| "epoch": 4.148148148148148, |
| "grad_norm": 0.22015266120433807, |
| "learning_rate": 7.663790038585793e-06, |
| "loss": 0.0529, |
| "step": 105 |
| }, |
| { |
| "epoch": 4.187654320987654, |
| "grad_norm": 0.21228307485580444, |
| "learning_rate": 6.934368588379553e-06, |
| "loss": 0.0505, |
| "step": 106 |
| }, |
| { |
| "epoch": 4.22716049382716, |
| "grad_norm": 0.23412545025348663, |
| "learning_rate": 6.238828904562316e-06, |
| "loss": 0.0619, |
| "step": 107 |
| }, |
| { |
| "epoch": 4.266666666666667, |
| "grad_norm": 0.2685701549053192, |
| "learning_rate": 5.577718201056392e-06, |
| "loss": 0.0609, |
| "step": 108 |
| }, |
| { |
| "epoch": 4.306172839506173, |
| "grad_norm": 0.28207308053970337, |
| "learning_rate": 4.951556604879048e-06, |
| "loss": 0.0626, |
| "step": 109 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "grad_norm": 0.20573092997074127, |
| "learning_rate": 4.360836746934055e-06, |
| "loss": 0.0526, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.345679012345679, |
| "eval_loss": 0.08639644831418991, |
| "eval_runtime": 24.7528, |
| "eval_samples_per_second": 1.818, |
| "eval_steps_per_second": 1.818, |
| "step": 110 |
| }, |
| { |
| "epoch": 4.385185185185185, |
| "grad_norm": 0.29032766819000244, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.0554, |
| "step": 111 |
| }, |
| { |
| "epoch": 4.424691358024692, |
| "grad_norm": 0.33361726999282837, |
| "learning_rate": 3.2875529852700147e-06, |
| "loss": 0.0519, |
| "step": 112 |
| }, |
| { |
| "epoch": 4.4641975308641975, |
| "grad_norm": 0.2849586606025696, |
| "learning_rate": 2.8058334845816213e-06, |
| "loss": 0.0707, |
| "step": 113 |
| }, |
| { |
| "epoch": 4.503703703703704, |
| "grad_norm": 0.3416891098022461, |
| "learning_rate": 2.361243863855184e-06, |
| "loss": 0.1072, |
| "step": 114 |
| }, |
| { |
| "epoch": 4.54320987654321, |
| "grad_norm": 0.2449430674314499, |
| "learning_rate": 1.9541339027450256e-06, |
| "loss": 0.0268, |
| "step": 115 |
| }, |
| { |
| "epoch": 4.582716049382716, |
| "grad_norm": 0.2408374696969986, |
| "learning_rate": 1.584823893886933e-06, |
| "loss": 0.0584, |
| "step": 116 |
| }, |
| { |
| "epoch": 4.622222222222222, |
| "grad_norm": 0.23224718868732452, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 0.039, |
| "step": 117 |
| }, |
| { |
| "epoch": 4.661728395061728, |
| "grad_norm": 0.3022216856479645, |
| "learning_rate": 9.607359798384785e-07, |
| "loss": 0.0744, |
| "step": 118 |
| }, |
| { |
| "epoch": 4.701234567901235, |
| "grad_norm": 0.2742868959903717, |
| "learning_rate": 7.064490740882057e-07, |
| "loss": 0.069, |
| "step": 119 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "grad_norm": 0.24444344639778137, |
| "learning_rate": 4.909437331777179e-07, |
| "loss": 0.0656, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.7407407407407405, |
| "eval_loss": 0.08666669577360153, |
| "eval_runtime": 24.7592, |
| "eval_samples_per_second": 1.818, |
| "eval_steps_per_second": 1.818, |
| "step": 120 |
| }, |
| { |
| "epoch": 4.780246913580247, |
| "grad_norm": 0.2698964476585388, |
| "learning_rate": 3.143895053378698e-07, |
| "loss": 0.0703, |
| "step": 121 |
| }, |
| { |
| "epoch": 4.8197530864197535, |
| "grad_norm": 0.22402559220790863, |
| "learning_rate": 1.7692529411904578e-07, |
| "loss": 0.039, |
| "step": 122 |
| }, |
| { |
| "epoch": 4.859259259259259, |
| "grad_norm": 0.1828380972146988, |
| "learning_rate": 7.865924910916977e-08, |
| "loss": 0.056, |
| "step": 123 |
| }, |
| { |
| "epoch": 4.898765432098766, |
| "grad_norm": 0.22039921581745148, |
| "learning_rate": 1.9668680847356735e-08, |
| "loss": 0.0557, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "grad_norm": 1.0016368627548218, |
| "learning_rate": 0.0, |
| "loss": 0.3846, |
| "step": 125 |
| }, |
| { |
| "epoch": 4.938271604938271, |
| "step": 125, |
| "total_flos": 1.4059466194275533e+17, |
| "train_loss": 0.14620321166515352, |
| "train_runtime": 4226.743, |
| "train_samples_per_second": 0.479, |
| "train_steps_per_second": 0.03 |
| } |
| ], |
| "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": 1.4059466194275533e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
