|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.7843866171003717, |
|
"eval_steps": 20, |
|
"global_step": 600, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4.999999514321732e-06, |
|
"loss": 1.0024, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.999998057287116e-06, |
|
"loss": 0.9077, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.999995628896718e-06, |
|
"loss": 0.8987, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.99999222915148e-06, |
|
"loss": 0.8454, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.999987858052726e-06, |
|
"loss": 0.8209, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.999982515602153e-06, |
|
"loss": 0.7772, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.999976201801837e-06, |
|
"loss": 0.8463, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.9999689166542295e-06, |
|
"loss": 0.7919, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.999960660162164e-06, |
|
"loss": 0.7842, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.999951432328846e-06, |
|
"loss": 0.7671, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.9999412331578625e-06, |
|
"loss": 0.8076, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.999930062653175e-06, |
|
"loss": 0.7818, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.999917920819125e-06, |
|
"loss": 0.7552, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.9999048076604286e-06, |
|
"loss": 0.7159, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.999890723182183e-06, |
|
"loss": 0.7466, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.999875667389858e-06, |
|
"loss": 0.7511, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.999859640289305e-06, |
|
"loss": 0.7242, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.999842641886752e-06, |
|
"loss": 0.7401, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.9998246721888025e-06, |
|
"loss": 0.724, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.999805731202437e-06, |
|
"loss": 0.7502, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"eval_loss": 0.7227846384048462, |
|
"eval_runtime": 39.5283, |
|
"eval_samples_per_second": 43.994, |
|
"eval_steps_per_second": 2.758, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.999785818935018e-06, |
|
"loss": 0.7096, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.99976493539428e-06, |
|
"loss": 0.7067, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.999743080588338e-06, |
|
"loss": 0.719, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.999720254525684e-06, |
|
"loss": 0.7228, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.999696457215186e-06, |
|
"loss": 0.7068, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.99967168866609e-06, |
|
"loss": 0.7037, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.9996459488880215e-06, |
|
"loss": 0.7121, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.9996192378909785e-06, |
|
"loss": 0.7234, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.999591555685342e-06, |
|
"loss": 0.6974, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.999562902281866e-06, |
|
"loss": 0.6859, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.999533277691686e-06, |
|
"loss": 0.7148, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.999502681926309e-06, |
|
"loss": 0.677, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.9994711149976254e-06, |
|
"loss": 0.6884, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.999438576917899e-06, |
|
"loss": 0.7021, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.999405067699773e-06, |
|
"loss": 0.68, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.999370587356267e-06, |
|
"loss": 0.6944, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.999335135900778e-06, |
|
"loss": 0.7073, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.999298713347079e-06, |
|
"loss": 0.6861, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.9992613197093246e-06, |
|
"loss": 0.714, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.999222955002041e-06, |
|
"loss": 0.7165, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"eval_loss": 0.6958964467048645, |
|
"eval_runtime": 39.5063, |
|
"eval_samples_per_second": 44.018, |
|
"eval_steps_per_second": 2.759, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.999183619240137e-06, |
|
"loss": 0.677, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.999143312438893e-06, |
|
"loss": 0.6901, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.999102034613974e-06, |
|
"loss": 0.6868, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.999059785781415e-06, |
|
"loss": 0.6457, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.999016565957633e-06, |
|
"loss": 0.7124, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.99897237515942e-06, |
|
"loss": 0.6921, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.998927213403946e-06, |
|
"loss": 0.7235, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.998881080708759e-06, |
|
"loss": 0.6866, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.998833977091783e-06, |
|
"loss": 0.6991, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.998785902571319e-06, |
|
"loss": 0.6874, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.998736857166048e-06, |
|
"loss": 0.689, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.998686840895025e-06, |
|
"loss": 0.6745, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.998635853777683e-06, |
|
"loss": 0.6948, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.998583895833834e-06, |
|
"loss": 0.6492, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.998530967083664e-06, |
|
"loss": 0.6781, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.99847706754774e-06, |
|
"loss": 0.6466, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.998422197247003e-06, |
|
"loss": 0.6823, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.998366356202773e-06, |
|
"loss": 0.7007, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.998309544436745e-06, |
|
"loss": 0.6563, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.998251761970997e-06, |
|
"loss": 0.6936, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"eval_loss": 0.6835957765579224, |
|
"eval_runtime": 39.5096, |
|
"eval_samples_per_second": 44.015, |
|
"eval_steps_per_second": 2.759, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.9981930088279755e-06, |
|
"loss": 0.7045, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.998133285030511e-06, |
|
"loss": 0.6713, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.998072590601808e-06, |
|
"loss": 0.6591, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.998010925565449e-06, |
|
"loss": 0.7107, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.997948289945392e-06, |
|
"loss": 0.6633, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.997884683765977e-06, |
|
"loss": 0.6693, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.997820107051915e-06, |
|
"loss": 0.6733, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.997754559828297e-06, |
|
"loss": 0.6679, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.997688042120592e-06, |
|
"loss": 0.6516, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.997620553954645e-06, |
|
"loss": 0.6691, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.997552095356677e-06, |
|
"loss": 0.6721, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.997482666353287e-06, |
|
"loss": 0.7046, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.997412266971452e-06, |
|
"loss": 0.6813, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.997340897238525e-06, |
|
"loss": 0.6672, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.9972685571822355e-06, |
|
"loss": 0.7085, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.997195246830692e-06, |
|
"loss": 0.672, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.9971209662123774e-06, |
|
"loss": 0.6817, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.997045715356153e-06, |
|
"loss": 0.6671, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.996969494291258e-06, |
|
"loss": 0.6941, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.996892303047306e-06, |
|
"loss": 0.6579, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"eval_loss": 0.6751722693443298, |
|
"eval_runtime": 39.5352, |
|
"eval_samples_per_second": 43.986, |
|
"eval_steps_per_second": 2.757, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.996814141654291e-06, |
|
"loss": 0.6922, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.996735010142581e-06, |
|
"loss": 0.681, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.9966549085429204e-06, |
|
"loss": 0.6792, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.9965738368864345e-06, |
|
"loss": 0.6483, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.996491795204623e-06, |
|
"loss": 0.6644, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.996408783529361e-06, |
|
"loss": 0.6983, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.996324801892904e-06, |
|
"loss": 0.6903, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.99623985032788e-06, |
|
"loss": 0.6619, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.996153928867298e-06, |
|
"loss": 0.6652, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.996067037544542e-06, |
|
"loss": 0.6716, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.995979176393372e-06, |
|
"loss": 0.6627, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.995890345447928e-06, |
|
"loss": 0.6508, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.9958005447427225e-06, |
|
"loss": 0.6599, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.995709774312647e-06, |
|
"loss": 0.673, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 4.99561803419297e-06, |
|
"loss": 0.641, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.995525324419338e-06, |
|
"loss": 0.6521, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.995431645027772e-06, |
|
"loss": 0.6697, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.995336996054668e-06, |
|
"loss": 0.6851, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 4.9952413775368034e-06, |
|
"loss": 0.6923, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 4.9951447895113305e-06, |
|
"loss": 0.6363, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"eval_loss": 0.6683968305587769, |
|
"eval_runtime": 39.5326, |
|
"eval_samples_per_second": 43.989, |
|
"eval_steps_per_second": 2.757, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 4.995047232015776e-06, |
|
"loss": 0.6792, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 4.994948705088047e-06, |
|
"loss": 0.6318, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 4.994849208766424e-06, |
|
"loss": 0.6595, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 4.994748743089566e-06, |
|
"loss": 0.6378, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 4.994647308096509e-06, |
|
"loss": 0.66, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.9945449038266645e-06, |
|
"loss": 0.6639, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.99444153031982e-06, |
|
"loss": 0.667, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.99433718761614e-06, |
|
"loss": 0.6599, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.994231875756169e-06, |
|
"loss": 0.6432, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 4.9941255947808226e-06, |
|
"loss": 0.6605, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 4.9940183447313964e-06, |
|
"loss": 0.685, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 4.993910125649561e-06, |
|
"loss": 0.6442, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.993800937577365e-06, |
|
"loss": 0.6691, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.993690780557232e-06, |
|
"loss": 0.6888, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.993579654631963e-06, |
|
"loss": 0.644, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 4.993467559844734e-06, |
|
"loss": 0.6655, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.993354496239101e-06, |
|
"loss": 0.6807, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.993240463858993e-06, |
|
"loss": 0.6774, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.993125462748714e-06, |
|
"loss": 0.6882, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 4.993009492952951e-06, |
|
"loss": 0.6522, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_loss": 0.6635560989379883, |
|
"eval_runtime": 39.5158, |
|
"eval_samples_per_second": 44.008, |
|
"eval_steps_per_second": 2.758, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 4.99289255451676e-06, |
|
"loss": 0.6465, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 4.9927746474855785e-06, |
|
"loss": 0.6759, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.992655771905217e-06, |
|
"loss": 0.6687, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.992535927821865e-06, |
|
"loss": 0.6463, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.992415115282085e-06, |
|
"loss": 0.6463, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.992293334332821e-06, |
|
"loss": 0.6412, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 4.9921705850213865e-06, |
|
"loss": 0.6528, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 4.992046867395478e-06, |
|
"loss": 0.668, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 4.9919221815031625e-06, |
|
"loss": 0.6377, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 4.991796527392888e-06, |
|
"loss": 0.6498, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 4.991669905113476e-06, |
|
"loss": 0.6552, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 4.991542314714122e-06, |
|
"loss": 0.6648, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.991413756244404e-06, |
|
"loss": 0.6717, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.99128422975427e-06, |
|
"loss": 0.6821, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.9911537352940485e-06, |
|
"loss": 0.6653, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.99102227291444e-06, |
|
"loss": 0.6698, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.990889842666525e-06, |
|
"loss": 0.6763, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.990756444601757e-06, |
|
"loss": 0.6918, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.990622078771968e-06, |
|
"loss": 0.6492, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 4.990486745229364e-06, |
|
"loss": 0.6223, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"eval_loss": 0.6595442295074463, |
|
"eval_runtime": 39.5303, |
|
"eval_samples_per_second": 43.992, |
|
"eval_steps_per_second": 2.757, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 4.990350444026528e-06, |
|
"loss": 0.6477, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 4.99021317521642e-06, |
|
"loss": 0.6559, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.990074938852373e-06, |
|
"loss": 0.6681, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.989935734988098e-06, |
|
"loss": 0.6726, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.9897955636776824e-06, |
|
"loss": 0.6502, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.9896544249755885e-06, |
|
"loss": 0.6779, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 4.989512318936654e-06, |
|
"loss": 0.6774, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 4.9893692456160955e-06, |
|
"loss": 0.6677, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 4.9892252050695e-06, |
|
"loss": 0.6616, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 4.989080197352834e-06, |
|
"loss": 0.6497, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 4.988934222522442e-06, |
|
"loss": 0.6399, |
|
"step": 151 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 4.9887872806350376e-06, |
|
"loss": 0.6145, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.988639371747717e-06, |
|
"loss": 0.695, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.988490495917948e-06, |
|
"loss": 0.6569, |
|
"step": 154 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.9883406532035735e-06, |
|
"loss": 0.657, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 4.9881898436628165e-06, |
|
"loss": 0.6438, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.988038067354272e-06, |
|
"loss": 0.6654, |
|
"step": 157 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.987885324336911e-06, |
|
"loss": 0.6643, |
|
"step": 158 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.98773161467008e-06, |
|
"loss": 0.6412, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.987576938413504e-06, |
|
"loss": 0.6371, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"eval_loss": 0.6561623215675354, |
|
"eval_runtime": 39.5223, |
|
"eval_samples_per_second": 44.0, |
|
"eval_steps_per_second": 2.758, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.987421295627279e-06, |
|
"loss": 0.6445, |
|
"step": 161 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.987264686371881e-06, |
|
"loss": 0.6584, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.987107110708158e-06, |
|
"loss": 0.6544, |
|
"step": 163 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.986948568697335e-06, |
|
"loss": 0.6247, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.9867890604010125e-06, |
|
"loss": 0.6767, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.986628585881167e-06, |
|
"loss": 0.6595, |
|
"step": 166 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 4.986467145200148e-06, |
|
"loss": 0.6309, |
|
"step": 167 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 4.986304738420684e-06, |
|
"loss": 0.6716, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 4.9861413656058755e-06, |
|
"loss": 0.641, |
|
"step": 169 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 4.9859770268192e-06, |
|
"loss": 0.6891, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 4.98581172212451e-06, |
|
"loss": 0.6505, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 4.985645451586035e-06, |
|
"loss": 0.6502, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 4.985478215268377e-06, |
|
"loss": 0.6353, |
|
"step": 173 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 4.985310013236514e-06, |
|
"loss": 0.6867, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 4.985140845555799e-06, |
|
"loss": 0.656, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 4.984970712291963e-06, |
|
"loss": 0.6503, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.98479961351111e-06, |
|
"loss": 0.6861, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.984627549279717e-06, |
|
"loss": 0.6341, |
|
"step": 178 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.984454519664639e-06, |
|
"loss": 0.6204, |
|
"step": 179 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.984280524733107e-06, |
|
"loss": 0.6576, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"eval_loss": 0.6528674364089966, |
|
"eval_runtime": 39.5337, |
|
"eval_samples_per_second": 43.988, |
|
"eval_steps_per_second": 2.757, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.9841055645527234e-06, |
|
"loss": 0.6314, |
|
"step": 181 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.9839296391914696e-06, |
|
"loss": 0.6408, |
|
"step": 182 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.9837527487176975e-06, |
|
"loss": 0.6288, |
|
"step": 183 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.983574893200139e-06, |
|
"loss": 0.6423, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.983396072707898e-06, |
|
"loss": 0.6718, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.983216287310453e-06, |
|
"loss": 0.6591, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.983035537077659e-06, |
|
"loss": 0.6423, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.982853822079746e-06, |
|
"loss": 0.6556, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.982671142387316e-06, |
|
"loss": 0.6323, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 4.982487498071349e-06, |
|
"loss": 0.6533, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 4.9823028892031985e-06, |
|
"loss": 0.6631, |
|
"step": 191 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 4.982117315854594e-06, |
|
"loss": 0.664, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 4.981930778097637e-06, |
|
"loss": 0.6493, |
|
"step": 193 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 4.981743276004805e-06, |
|
"loss": 0.6734, |
|
"step": 194 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 4.981554809648952e-06, |
|
"loss": 0.6283, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 4.981365379103306e-06, |
|
"loss": 0.6392, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.981174984441466e-06, |
|
"loss": 0.6378, |
|
"step": 197 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.980983625737411e-06, |
|
"loss": 0.6466, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.98079130306549e-06, |
|
"loss": 0.6427, |
|
"step": 199 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.980598016500431e-06, |
|
"loss": 0.6068, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"eval_loss": 0.6502168774604797, |
|
"eval_runtime": 39.5276, |
|
"eval_samples_per_second": 43.995, |
|
"eval_steps_per_second": 2.758, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.980403766117332e-06, |
|
"loss": 0.645, |
|
"step": 201 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.980208551991668e-06, |
|
"loss": 0.6227, |
|
"step": 202 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.980012374199288e-06, |
|
"loss": 0.6326, |
|
"step": 203 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.9798152328164165e-06, |
|
"loss": 0.6256, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.97961712791965e-06, |
|
"loss": 0.6248, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 4.97941805958596e-06, |
|
"loss": 0.6727, |
|
"step": 206 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.979218027892696e-06, |
|
"loss": 0.6513, |
|
"step": 207 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.979017032917576e-06, |
|
"loss": 0.6224, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.9788150747386965e-06, |
|
"loss": 0.6665, |
|
"step": 209 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.978612153434527e-06, |
|
"loss": 0.6644, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 4.9784082690839095e-06, |
|
"loss": 0.6526, |
|
"step": 211 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 4.978203421766064e-06, |
|
"loss": 0.6274, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 4.97799761156058e-06, |
|
"loss": 0.6677, |
|
"step": 213 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.9777908385474256e-06, |
|
"loss": 0.6453, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.97758310280694e-06, |
|
"loss": 0.6374, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.977374404419838e-06, |
|
"loss": 0.6428, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.977164743467206e-06, |
|
"loss": 0.6282, |
|
"step": 217 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.976954120030508e-06, |
|
"loss": 0.6553, |
|
"step": 218 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.976742534191581e-06, |
|
"loss": 0.6646, |
|
"step": 219 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.976529986032632e-06, |
|
"loss": 0.6222, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"eval_loss": 0.6474757790565491, |
|
"eval_runtime": 39.5181, |
|
"eval_samples_per_second": 44.005, |
|
"eval_steps_per_second": 2.758, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.976316475636248e-06, |
|
"loss": 0.6518, |
|
"step": 221 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.9761020030853854e-06, |
|
"loss": 0.6461, |
|
"step": 222 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 4.975886568463376e-06, |
|
"loss": 0.6306, |
|
"step": 223 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 4.975670171853926e-06, |
|
"loss": 0.6416, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 4.9754528133411144e-06, |
|
"loss": 0.6922, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 4.975234493009394e-06, |
|
"loss": 0.6384, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.975015210943591e-06, |
|
"loss": 0.6433, |
|
"step": 227 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.9747949672289075e-06, |
|
"loss": 0.6179, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.974573761950916e-06, |
|
"loss": 0.6767, |
|
"step": 229 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 4.9743515951955655e-06, |
|
"loss": 0.6406, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.974128467049177e-06, |
|
"loss": 0.6374, |
|
"step": 231 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.973904377598443e-06, |
|
"loss": 0.6378, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.973679326930434e-06, |
|
"loss": 0.63, |
|
"step": 233 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.973453315132592e-06, |
|
"loss": 0.6733, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.973226342292732e-06, |
|
"loss": 0.6531, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.972998408499041e-06, |
|
"loss": 0.6445, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.972769513840083e-06, |
|
"loss": 0.6307, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.972539658404793e-06, |
|
"loss": 0.6201, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.972308842282478e-06, |
|
"loss": 0.6496, |
|
"step": 239 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.9720770655628216e-06, |
|
"loss": 0.6283, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"eval_loss": 0.6447574496269226, |
|
"eval_runtime": 39.5185, |
|
"eval_samples_per_second": 44.005, |
|
"eval_steps_per_second": 2.758, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.9718443283358785e-06, |
|
"loss": 0.6369, |
|
"step": 241 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.971610630692077e-06, |
|
"loss": 0.6612, |
|
"step": 242 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.9713759727222184e-06, |
|
"loss": 0.62, |
|
"step": 243 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 4.971140354517477e-06, |
|
"loss": 0.6574, |
|
"step": 244 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 4.970903776169403e-06, |
|
"loss": 0.6248, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 4.970666237769913e-06, |
|
"loss": 0.6576, |
|
"step": 246 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 4.970427739411303e-06, |
|
"loss": 0.6548, |
|
"step": 247 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.970188281186241e-06, |
|
"loss": 0.6369, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.969947863187764e-06, |
|
"loss": 0.6373, |
|
"step": 249 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.969706485509287e-06, |
|
"loss": 0.6432, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 4.969464148244595e-06, |
|
"loss": 0.632, |
|
"step": 251 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 4.9692208514878445e-06, |
|
"loss": 0.6077, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 4.968976595333569e-06, |
|
"loss": 0.6217, |
|
"step": 253 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 4.9687313798766714e-06, |
|
"loss": 0.6337, |
|
"step": 254 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 4.968485205212429e-06, |
|
"loss": 0.6033, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 4.9682380714364895e-06, |
|
"loss": 0.6411, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 4.967989978644877e-06, |
|
"loss": 0.6525, |
|
"step": 257 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 4.967740926933985e-06, |
|
"loss": 0.6295, |
|
"step": 258 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 4.9674909164005805e-06, |
|
"loss": 0.6217, |
|
"step": 259 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 4.967239947141803e-06, |
|
"loss": 0.6687, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"eval_loss": 0.6423989534378052, |
|
"eval_runtime": 39.5124, |
|
"eval_samples_per_second": 44.012, |
|
"eval_steps_per_second": 2.759, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 4.966988019255167e-06, |
|
"loss": 0.6373, |
|
"step": 261 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 4.9667351328385535e-06, |
|
"loss": 0.6775, |
|
"step": 262 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 4.966481287990223e-06, |
|
"loss": 0.6396, |
|
"step": 263 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.966226484808804e-06, |
|
"loss": 0.6435, |
|
"step": 264 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.965970723393297e-06, |
|
"loss": 0.6212, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.965714003843079e-06, |
|
"loss": 0.6087, |
|
"step": 266 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 4.965456326257894e-06, |
|
"loss": 0.6403, |
|
"step": 267 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.965197690737862e-06, |
|
"loss": 0.6155, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.964938097383472e-06, |
|
"loss": 0.6329, |
|
"step": 269 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.96467754629559e-06, |
|
"loss": 0.6584, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 4.9644160375754495e-06, |
|
"loss": 0.6187, |
|
"step": 271 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 4.964153571324658e-06, |
|
"loss": 0.627, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 4.963890147645195e-06, |
|
"loss": 0.6162, |
|
"step": 273 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 4.9636257666394115e-06, |
|
"loss": 0.6269, |
|
"step": 274 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 4.963360428410031e-06, |
|
"loss": 0.627, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 4.963094133060148e-06, |
|
"loss": 0.6189, |
|
"step": 276 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 4.9628268806932315e-06, |
|
"loss": 0.6563, |
|
"step": 277 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 4.962558671413119e-06, |
|
"loss": 0.6775, |
|
"step": 278 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 4.962289505324021e-06, |
|
"loss": 0.6539, |
|
"step": 279 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 4.962019382530521e-06, |
|
"loss": 0.6355, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"eval_loss": 0.6408971548080444, |
|
"eval_runtime": 39.5077, |
|
"eval_samples_per_second": 44.017, |
|
"eval_steps_per_second": 2.759, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.9617483031375716e-06, |
|
"loss": 0.6297, |
|
"step": 281 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.961476267250501e-06, |
|
"loss": 0.6523, |
|
"step": 282 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.961203274975005e-06, |
|
"loss": 0.6365, |
|
"step": 283 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 4.960929326417153e-06, |
|
"loss": 0.6268, |
|
"step": 284 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.9606544216833865e-06, |
|
"loss": 0.6205, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.960378560880516e-06, |
|
"loss": 0.6789, |
|
"step": 286 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.960101744115727e-06, |
|
"loss": 0.6482, |
|
"step": 287 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 4.959823971496575e-06, |
|
"loss": 0.6485, |
|
"step": 288 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 4.959545243130984e-06, |
|
"loss": 0.6342, |
|
"step": 289 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 4.959265559127253e-06, |
|
"loss": 0.6549, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 4.958984919594053e-06, |
|
"loss": 0.6364, |
|
"step": 291 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 4.9587033246404215e-06, |
|
"loss": 0.6296, |
|
"step": 292 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 4.958420774375772e-06, |
|
"loss": 0.6016, |
|
"step": 293 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 4.958137268909887e-06, |
|
"loss": 0.644, |
|
"step": 294 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.95785280835292e-06, |
|
"loss": 0.6439, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.957567392815396e-06, |
|
"loss": 0.6293, |
|
"step": 296 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 4.957281022408212e-06, |
|
"loss": 0.6798, |
|
"step": 297 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 4.956993697242634e-06, |
|
"loss": 0.6547, |
|
"step": 298 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 4.956705417430301e-06, |
|
"loss": 0.6492, |
|
"step": 299 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 4.9564161830832214e-06, |
|
"loss": 0.6338, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"eval_loss": 0.639053225517273, |
|
"eval_runtime": 39.5137, |
|
"eval_samples_per_second": 44.01, |
|
"eval_steps_per_second": 2.759, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.956125994313775e-06, |
|
"loss": 0.6629, |
|
"step": 301 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.955834851234712e-06, |
|
"loss": 0.6254, |
|
"step": 302 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.955542753959156e-06, |
|
"loss": 0.6427, |
|
"step": 303 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.955249702600598e-06, |
|
"loss": 0.6149, |
|
"step": 304 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.954955697272899e-06, |
|
"loss": 0.6363, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.954660738090297e-06, |
|
"loss": 0.6476, |
|
"step": 306 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.954364825167392e-06, |
|
"loss": 0.677, |
|
"step": 307 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 4.9540679586191605e-06, |
|
"loss": 0.6239, |
|
"step": 308 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 4.953770138560947e-06, |
|
"loss": 0.6511, |
|
"step": 309 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 4.95347136510847e-06, |
|
"loss": 0.6352, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 4.9531716383778115e-06, |
|
"loss": 0.6302, |
|
"step": 311 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 4.9528709584854316e-06, |
|
"loss": 0.643, |
|
"step": 312 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 4.952569325548156e-06, |
|
"loss": 0.6185, |
|
"step": 313 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 4.952266739683182e-06, |
|
"loss": 0.6017, |
|
"step": 314 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 4.9519632010080765e-06, |
|
"loss": 0.6292, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 4.951658709640778e-06, |
|
"loss": 0.6513, |
|
"step": 316 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 4.951353265699594e-06, |
|
"loss": 0.6489, |
|
"step": 317 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 4.951046869303202e-06, |
|
"loss": 0.6368, |
|
"step": 318 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 4.950739520570652e-06, |
|
"loss": 0.6547, |
|
"step": 319 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 4.9504312196213596e-06, |
|
"loss": 0.6711, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"eval_loss": 0.637545108795166, |
|
"eval_runtime": 39.5156, |
|
"eval_samples_per_second": 44.008, |
|
"eval_steps_per_second": 2.758, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 4.950121966575115e-06, |
|
"loss": 0.6619, |
|
"step": 321 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 4.949811761552074e-06, |
|
"loss": 0.6505, |
|
"step": 322 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 4.949500604672767e-06, |
|
"loss": 0.6282, |
|
"step": 323 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 4.949188496058089e-06, |
|
"loss": 0.6256, |
|
"step": 324 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 4.94887543582931e-06, |
|
"loss": 0.6062, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 4.9485614241080655e-06, |
|
"loss": 0.6364, |
|
"step": 326 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 4.948246461016362e-06, |
|
"loss": 0.6439, |
|
"step": 327 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 4.9479305466765796e-06, |
|
"loss": 0.6166, |
|
"step": 328 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 4.94761368121146e-06, |
|
"loss": 0.64, |
|
"step": 329 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 4.947295864744121e-06, |
|
"loss": 0.6348, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.98, |
|
"learning_rate": 4.946977097398049e-06, |
|
"loss": 0.6365, |
|
"step": 331 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 4.946657379297096e-06, |
|
"loss": 0.6683, |
|
"step": 332 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 4.946336710565489e-06, |
|
"loss": 0.6458, |
|
"step": 333 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 4.946015091327819e-06, |
|
"loss": 0.6634, |
|
"step": 334 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 4.94569252170905e-06, |
|
"loss": 0.6629, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 4.9453690018345144e-06, |
|
"loss": 0.6152, |
|
"step": 336 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 4.945044531829913e-06, |
|
"loss": 0.6139, |
|
"step": 337 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 4.944719111821316e-06, |
|
"loss": 0.5501, |
|
"step": 338 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 4.944392741935162e-06, |
|
"loss": 0.5941, |
|
"step": 339 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 4.944065422298262e-06, |
|
"loss": 0.5949, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"eval_loss": 0.638019323348999, |
|
"eval_runtime": 39.5312, |
|
"eval_samples_per_second": 43.991, |
|
"eval_steps_per_second": 2.757, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 4.943737153037792e-06, |
|
"loss": 0.572, |
|
"step": 341 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 4.943407934281298e-06, |
|
"loss": 0.5997, |
|
"step": 342 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 4.943077766156698e-06, |
|
"loss": 0.5769, |
|
"step": 343 |
|
}, |
|
{ |
|
"epoch": 1.02, |
|
"learning_rate": 4.942746648792274e-06, |
|
"loss": 0.5817, |
|
"step": 344 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 4.942414582316679e-06, |
|
"loss": 0.5676, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 4.942081566858938e-06, |
|
"loss": 0.5879, |
|
"step": 346 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 4.941747602548439e-06, |
|
"loss": 0.5621, |
|
"step": 347 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 4.941412689514941e-06, |
|
"loss": 0.569, |
|
"step": 348 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 4.941076827888575e-06, |
|
"loss": 0.6097, |
|
"step": 349 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 4.9407400177998335e-06, |
|
"loss": 0.5921, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 4.940402259379585e-06, |
|
"loss": 0.5743, |
|
"step": 351 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 4.940063552759061e-06, |
|
"loss": 0.57, |
|
"step": 352 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 4.9397238980698645e-06, |
|
"loss": 0.5717, |
|
"step": 353 |
|
}, |
|
{ |
|
"epoch": 1.05, |
|
"learning_rate": 4.939383295443966e-06, |
|
"loss": 0.6106, |
|
"step": 354 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 4.939041745013703e-06, |
|
"loss": 0.5952, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 4.938699246911783e-06, |
|
"loss": 0.585, |
|
"step": 356 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 4.938355801271282e-06, |
|
"loss": 0.5651, |
|
"step": 357 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 4.938011408225642e-06, |
|
"loss": 0.5774, |
|
"step": 358 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 4.937666067908675e-06, |
|
"loss": 0.5878, |
|
"step": 359 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 4.937319780454559e-06, |
|
"loss": 0.5681, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"eval_loss": 0.6371431350708008, |
|
"eval_runtime": 39.5244, |
|
"eval_samples_per_second": 43.998, |
|
"eval_steps_per_second": 2.758, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 4.936972545997844e-06, |
|
"loss": 0.5938, |
|
"step": 361 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 4.936624364673444e-06, |
|
"loss": 0.6068, |
|
"step": 362 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 4.936275236616641e-06, |
|
"loss": 0.5925, |
|
"step": 363 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 4.935925161963089e-06, |
|
"loss": 0.587, |
|
"step": 364 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 4.9355741408488045e-06, |
|
"loss": 0.5683, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 4.9352221734101745e-06, |
|
"loss": 0.5803, |
|
"step": 366 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 4.934869259783955e-06, |
|
"loss": 0.5782, |
|
"step": 367 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 4.934515400107266e-06, |
|
"loss": 0.613, |
|
"step": 368 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 4.934160594517598e-06, |
|
"loss": 0.5732, |
|
"step": 369 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 4.933804843152808e-06, |
|
"loss": 0.5916, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.1, |
|
"learning_rate": 4.933448146151122e-06, |
|
"loss": 0.6108, |
|
"step": 371 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 4.933090503651129e-06, |
|
"loss": 0.5972, |
|
"step": 372 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 4.93273191579179e-06, |
|
"loss": 0.582, |
|
"step": 373 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 4.932372382712432e-06, |
|
"loss": 0.61, |
|
"step": 374 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.932011904552749e-06, |
|
"loss": 0.5777, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.931650481452801e-06, |
|
"loss": 0.6123, |
|
"step": 376 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.931288113553017e-06, |
|
"loss": 0.5762, |
|
"step": 377 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.930924800994192e-06, |
|
"loss": 0.5837, |
|
"step": 378 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 4.930560543917489e-06, |
|
"loss": 0.5738, |
|
"step": 379 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 4.930195342464437e-06, |
|
"loss": 0.587, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"eval_loss": 0.6362231373786926, |
|
"eval_runtime": 39.5188, |
|
"eval_samples_per_second": 44.004, |
|
"eval_steps_per_second": 2.758, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.13, |
|
"learning_rate": 4.929829196776932e-06, |
|
"loss": 0.5699, |
|
"step": 381 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 4.9294621069972385e-06, |
|
"loss": 0.5855, |
|
"step": 382 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 4.929094073267985e-06, |
|
"loss": 0.5666, |
|
"step": 383 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 4.9287250957321685e-06, |
|
"loss": 0.5724, |
|
"step": 384 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 4.928355174533153e-06, |
|
"loss": 0.598, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 4.92798430981467e-06, |
|
"loss": 0.5712, |
|
"step": 386 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 4.9276125017208144e-06, |
|
"loss": 0.5902, |
|
"step": 387 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 4.927239750396049e-06, |
|
"loss": 0.5906, |
|
"step": 388 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 4.926866055985205e-06, |
|
"loss": 0.5757, |
|
"step": 389 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 4.9264914186334775e-06, |
|
"loss": 0.5972, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 4.926115838486431e-06, |
|
"loss": 0.5932, |
|
"step": 391 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 4.925739315689991e-06, |
|
"loss": 0.5793, |
|
"step": 392 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 4.9253618503904566e-06, |
|
"loss": 0.609, |
|
"step": 393 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 4.924983442734487e-06, |
|
"loss": 0.602, |
|
"step": 394 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 4.924604092869109e-06, |
|
"loss": 0.6133, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 4.924223800941718e-06, |
|
"loss": 0.5706, |
|
"step": 396 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 4.923842567100072e-06, |
|
"loss": 0.6194, |
|
"step": 397 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 4.923460391492298e-06, |
|
"loss": 0.6161, |
|
"step": 398 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 4.923077274266886e-06, |
|
"loss": 0.5833, |
|
"step": 399 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 4.922693215572695e-06, |
|
"loss": 0.5706, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"eval_loss": 0.6345230340957642, |
|
"eval_runtime": 39.5154, |
|
"eval_samples_per_second": 44.008, |
|
"eval_steps_per_second": 2.758, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 4.922308215558948e-06, |
|
"loss": 0.5776, |
|
"step": 401 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.921922274375232e-06, |
|
"loss": 0.6127, |
|
"step": 402 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.921535392171504e-06, |
|
"loss": 0.5659, |
|
"step": 403 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.9211475690980825e-06, |
|
"loss": 0.5987, |
|
"step": 404 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 4.920758805305654e-06, |
|
"loss": 0.5821, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 4.92036910094527e-06, |
|
"loss": 0.5623, |
|
"step": 406 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 4.919978456168347e-06, |
|
"loss": 0.6118, |
|
"step": 407 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 4.919586871126667e-06, |
|
"loss": 0.6078, |
|
"step": 408 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 4.9191943459723764e-06, |
|
"loss": 0.5703, |
|
"step": 409 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 4.918800880857991e-06, |
|
"loss": 0.585, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 4.9184064759363865e-06, |
|
"loss": 0.5796, |
|
"step": 411 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 4.9180111313608055e-06, |
|
"loss": 0.5782, |
|
"step": 412 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 4.917614847284858e-06, |
|
"loss": 0.5682, |
|
"step": 413 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 4.917217623862516e-06, |
|
"loss": 0.575, |
|
"step": 414 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 4.916819461248119e-06, |
|
"loss": 0.6286, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 4.916420359596369e-06, |
|
"loss": 0.587, |
|
"step": 416 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 4.916020319062334e-06, |
|
"loss": 0.5912, |
|
"step": 417 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 4.9156193398014464e-06, |
|
"loss": 0.5933, |
|
"step": 418 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 4.915217421969505e-06, |
|
"loss": 0.5765, |
|
"step": 419 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 4.914814565722671e-06, |
|
"loss": 0.5567, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"eval_loss": 0.6341472864151001, |
|
"eval_runtime": 39.5152, |
|
"eval_samples_per_second": 44.008, |
|
"eval_steps_per_second": 2.758, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 4.9144107712174724e-06, |
|
"loss": 0.5904, |
|
"step": 421 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.914006038610799e-06, |
|
"loss": 0.5786, |
|
"step": 422 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.913600368059908e-06, |
|
"loss": 0.6183, |
|
"step": 423 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.913193759722419e-06, |
|
"loss": 0.5825, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 4.912786213756316e-06, |
|
"loss": 0.5825, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 4.912377730319951e-06, |
|
"loss": 0.5916, |
|
"step": 426 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 4.9119683095720325e-06, |
|
"loss": 0.6113, |
|
"step": 427 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 4.911557951671641e-06, |
|
"loss": 0.5842, |
|
"step": 428 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 4.911146656778219e-06, |
|
"loss": 0.5973, |
|
"step": 429 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 4.91073442505157e-06, |
|
"loss": 0.597, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 4.910321256651863e-06, |
|
"loss": 0.6115, |
|
"step": 431 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 4.909907151739634e-06, |
|
"loss": 0.6106, |
|
"step": 432 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 4.909492110475778e-06, |
|
"loss": 0.5963, |
|
"step": 433 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 4.909076133021558e-06, |
|
"loss": 0.5695, |
|
"step": 434 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 4.908659219538598e-06, |
|
"loss": 0.6013, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 4.908241370188887e-06, |
|
"loss": 0.5798, |
|
"step": 436 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 4.907822585134777e-06, |
|
"loss": 0.6025, |
|
"step": 437 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 4.907402864538984e-06, |
|
"loss": 0.5943, |
|
"step": 438 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 4.906982208564588e-06, |
|
"loss": 0.6074, |
|
"step": 439 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 4.90656061737503e-06, |
|
"loss": 0.59, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"eval_loss": 0.6325353384017944, |
|
"eval_runtime": 39.5204, |
|
"eval_samples_per_second": 44.003, |
|
"eval_steps_per_second": 2.758, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 4.906138091134118e-06, |
|
"loss": 0.5754, |
|
"step": 441 |
|
}, |
|
{ |
|
"epoch": 1.31, |
|
"learning_rate": 4.905714630006022e-06, |
|
"loss": 0.5871, |
|
"step": 442 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 4.9052902341552715e-06, |
|
"loss": 0.5681, |
|
"step": 443 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 4.904864903746765e-06, |
|
"loss": 0.5601, |
|
"step": 444 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 4.904438638945761e-06, |
|
"loss": 0.5848, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 4.904011439917881e-06, |
|
"loss": 0.5901, |
|
"step": 446 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 4.903583306829111e-06, |
|
"loss": 0.5771, |
|
"step": 447 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 4.903154239845798e-06, |
|
"loss": 0.5802, |
|
"step": 448 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 4.902724239134653e-06, |
|
"loss": 0.5727, |
|
"step": 449 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 4.9022933048627496e-06, |
|
"loss": 0.5939, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 4.901861437197524e-06, |
|
"loss": 0.5802, |
|
"step": 451 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 4.901428636306776e-06, |
|
"loss": 0.6126, |
|
"step": 452 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 4.9009949023586665e-06, |
|
"loss": 0.6091, |
|
"step": 453 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 4.90056023552172e-06, |
|
"loss": 0.5896, |
|
"step": 454 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 4.900124635964823e-06, |
|
"loss": 0.5885, |
|
"step": 455 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 4.899688103857223e-06, |
|
"loss": 0.5761, |
|
"step": 456 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 4.899250639368534e-06, |
|
"loss": 0.603, |
|
"step": 457 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 4.898812242668727e-06, |
|
"loss": 0.5811, |
|
"step": 458 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 4.89837291392814e-06, |
|
"loss": 0.5833, |
|
"step": 459 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 4.8979326533174696e-06, |
|
"loss": 0.5829, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"eval_loss": 0.6320897340774536, |
|
"eval_runtime": 39.5185, |
|
"eval_samples_per_second": 44.005, |
|
"eval_steps_per_second": 2.758, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 4.897491461007777e-06, |
|
"loss": 0.5855, |
|
"step": 461 |
|
}, |
|
{ |
|
"epoch": 1.37, |
|
"learning_rate": 4.897049337170483e-06, |
|
"loss": 0.5877, |
|
"step": 462 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 4.896606281977372e-06, |
|
"loss": 0.5679, |
|
"step": 463 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 4.8961622956005895e-06, |
|
"loss": 0.5822, |
|
"step": 464 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 4.895717378212644e-06, |
|
"loss": 0.6133, |
|
"step": 465 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 4.895271529986404e-06, |
|
"loss": 0.5935, |
|
"step": 466 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 4.8948247510951004e-06, |
|
"loss": 0.5794, |
|
"step": 467 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 4.894377041712327e-06, |
|
"loss": 0.5675, |
|
"step": 468 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 4.8939284020120365e-06, |
|
"loss": 0.5841, |
|
"step": 469 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 4.893478832168545e-06, |
|
"loss": 0.6006, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 4.893028332356531e-06, |
|
"loss": 0.5886, |
|
"step": 471 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 4.892576902751031e-06, |
|
"loss": 0.5754, |
|
"step": 472 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 4.892124543527446e-06, |
|
"loss": 0.5897, |
|
"step": 473 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 4.891671254861535e-06, |
|
"loss": 0.5957, |
|
"step": 474 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 4.891217036929422e-06, |
|
"loss": 0.5853, |
|
"step": 475 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 4.890761889907589e-06, |
|
"loss": 0.5753, |
|
"step": 476 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 4.89030581397288e-06, |
|
"loss": 0.5786, |
|
"step": 477 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 4.8898488093025005e-06, |
|
"loss": 0.5841, |
|
"step": 478 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 4.889390876074016e-06, |
|
"loss": 0.5829, |
|
"step": 479 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 4.8889320144653525e-06, |
|
"loss": 0.5696, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"eval_loss": 0.6306838989257812, |
|
"eval_runtime": 39.5161, |
|
"eval_samples_per_second": 44.007, |
|
"eval_steps_per_second": 2.758, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 4.888472224654798e-06, |
|
"loss": 0.6056, |
|
"step": 481 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 4.888011506821e-06, |
|
"loss": 0.5949, |
|
"step": 482 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.887549861142967e-06, |
|
"loss": 0.5899, |
|
"step": 483 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.887087287800069e-06, |
|
"loss": 0.5888, |
|
"step": 484 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.8866237869720334e-06, |
|
"loss": 0.5751, |
|
"step": 485 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 4.886159358838952e-06, |
|
"loss": 0.6141, |
|
"step": 486 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 4.885694003581275e-06, |
|
"loss": 0.5674, |
|
"step": 487 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 4.885227721379811e-06, |
|
"loss": 0.6058, |
|
"step": 488 |
|
}, |
|
{ |
|
"epoch": 1.45, |
|
"learning_rate": 4.8847605124157315e-06, |
|
"loss": 0.558, |
|
"step": 489 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 4.884292376870567e-06, |
|
"loss": 0.585, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 4.88382331492621e-06, |
|
"loss": 0.6116, |
|
"step": 491 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 4.883353326764907e-06, |
|
"loss": 0.5761, |
|
"step": 492 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 4.882882412569272e-06, |
|
"loss": 0.5612, |
|
"step": 493 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 4.882410572522273e-06, |
|
"loss": 0.5834, |
|
"step": 494 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 4.881937806807241e-06, |
|
"loss": 0.604, |
|
"step": 495 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 4.881464115607866e-06, |
|
"loss": 0.5949, |
|
"step": 496 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 4.880989499108196e-06, |
|
"loss": 0.5843, |
|
"step": 497 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 4.880513957492641e-06, |
|
"loss": 0.5648, |
|
"step": 498 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 4.880037490945968e-06, |
|
"loss": 0.59, |
|
"step": 499 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 4.879560099653306e-06, |
|
"loss": 0.5811, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"eval_loss": 0.6309075355529785, |
|
"eval_runtime": 39.5278, |
|
"eval_samples_per_second": 43.994, |
|
"eval_steps_per_second": 2.758, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 4.879081783800141e-06, |
|
"loss": 0.5881, |
|
"step": 501 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 4.87860254357232e-06, |
|
"loss": 0.605, |
|
"step": 502 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 4.878122379156045e-06, |
|
"loss": 0.5986, |
|
"step": 503 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 4.8776412907378845e-06, |
|
"loss": 0.5791, |
|
"step": 504 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 4.877159278504759e-06, |
|
"loss": 0.5823, |
|
"step": 505 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 4.876676342643953e-06, |
|
"loss": 0.5889, |
|
"step": 506 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 4.876192483343106e-06, |
|
"loss": 0.5844, |
|
"step": 507 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 4.875707700790218e-06, |
|
"loss": 0.581, |
|
"step": 508 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 4.875221995173649e-06, |
|
"loss": 0.5877, |
|
"step": 509 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 4.8747353666821155e-06, |
|
"loss": 0.5731, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 4.874247815504693e-06, |
|
"loss": 0.6024, |
|
"step": 511 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 4.873759341830816e-06, |
|
"loss": 0.5948, |
|
"step": 512 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 4.873269945850279e-06, |
|
"loss": 0.5826, |
|
"step": 513 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 4.87277962775323e-06, |
|
"loss": 0.6059, |
|
"step": 514 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 4.872288387730182e-06, |
|
"loss": 0.591, |
|
"step": 515 |
|
}, |
|
{ |
|
"epoch": 1.53, |
|
"learning_rate": 4.871796225972e-06, |
|
"loss": 0.5979, |
|
"step": 516 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 4.871303142669911e-06, |
|
"loss": 0.6112, |
|
"step": 517 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 4.870809138015499e-06, |
|
"loss": 0.551, |
|
"step": 518 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 4.870314212200705e-06, |
|
"loss": 0.5821, |
|
"step": 519 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 4.86981836541783e-06, |
|
"loss": 0.5708, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"eval_loss": 0.6294764280319214, |
|
"eval_runtime": 39.5161, |
|
"eval_samples_per_second": 44.007, |
|
"eval_steps_per_second": 2.758, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 4.8693215978595305e-06, |
|
"loss": 0.5718, |
|
"step": 521 |
|
}, |
|
{ |
|
"epoch": 1.55, |
|
"learning_rate": 4.868823909718823e-06, |
|
"loss": 0.5724, |
|
"step": 522 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 4.868325301189079e-06, |
|
"loss": 0.6142, |
|
"step": 523 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 4.86782577246403e-06, |
|
"loss": 0.5738, |
|
"step": 524 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 4.867325323737765e-06, |
|
"loss": 0.5721, |
|
"step": 525 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 4.866823955204728e-06, |
|
"loss": 0.568, |
|
"step": 526 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 4.866321667059724e-06, |
|
"loss": 0.5848, |
|
"step": 527 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 4.865818459497911e-06, |
|
"loss": 0.5624, |
|
"step": 528 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 4.865314332714808e-06, |
|
"loss": 0.5815, |
|
"step": 529 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 4.86480928690629e-06, |
|
"loss": 0.5705, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 4.864303322268588e-06, |
|
"loss": 0.5526, |
|
"step": 531 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 4.863796438998293e-06, |
|
"loss": 0.6057, |
|
"step": 532 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 4.863288637292347e-06, |
|
"loss": 0.5767, |
|
"step": 533 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 4.862779917348055e-06, |
|
"loss": 0.5796, |
|
"step": 534 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 4.862270279363076e-06, |
|
"loss": 0.5988, |
|
"step": 535 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 4.861759723535427e-06, |
|
"loss": 0.5678, |
|
"step": 536 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 4.861248250063478e-06, |
|
"loss": 0.6022, |
|
"step": 537 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 4.860735859145961e-06, |
|
"loss": 0.5624, |
|
"step": 538 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 4.860222550981961e-06, |
|
"loss": 0.5853, |
|
"step": 539 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 4.859708325770919e-06, |
|
"loss": 0.5812, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"eval_loss": 0.6281893253326416, |
|
"eval_runtime": 39.5326, |
|
"eval_samples_per_second": 43.989, |
|
"eval_steps_per_second": 2.757, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 4.859193183712635e-06, |
|
"loss": 0.5717, |
|
"step": 541 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 4.858677125007262e-06, |
|
"loss": 0.5839, |
|
"step": 542 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 4.858160149855312e-06, |
|
"loss": 0.5661, |
|
"step": 543 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 4.8576422584576515e-06, |
|
"loss": 0.6015, |
|
"step": 544 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 4.857123451015503e-06, |
|
"loss": 0.5926, |
|
"step": 545 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 4.856603727730446e-06, |
|
"loss": 0.5964, |
|
"step": 546 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 4.856083088804415e-06, |
|
"loss": 0.5646, |
|
"step": 547 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 4.8555615344397e-06, |
|
"loss": 0.5834, |
|
"step": 548 |
|
}, |
|
{ |
|
"epoch": 1.63, |
|
"learning_rate": 4.8550390648389475e-06, |
|
"loss": 0.5774, |
|
"step": 549 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.854515680205159e-06, |
|
"loss": 0.6089, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.853991380741692e-06, |
|
"loss": 0.5577, |
|
"step": 551 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.853466166652259e-06, |
|
"loss": 0.5546, |
|
"step": 552 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.852940038140927e-06, |
|
"loss": 0.5816, |
|
"step": 553 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 4.8524129954121215e-06, |
|
"loss": 0.5693, |
|
"step": 554 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 4.851885038670618e-06, |
|
"loss": 0.5674, |
|
"step": 555 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 4.851356168121554e-06, |
|
"loss": 0.6169, |
|
"step": 556 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 4.850826383970416e-06, |
|
"loss": 0.5778, |
|
"step": 557 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 4.850295686423048e-06, |
|
"loss": 0.583, |
|
"step": 558 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 4.849764075685649e-06, |
|
"loss": 0.6038, |
|
"step": 559 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 4.849231551964771e-06, |
|
"loss": 0.6001, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"eval_loss": 0.6277775168418884, |
|
"eval_runtime": 39.5297, |
|
"eval_samples_per_second": 43.992, |
|
"eval_steps_per_second": 2.757, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 4.848698115467324e-06, |
|
"loss": 0.589, |
|
"step": 561 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 4.84816376640057e-06, |
|
"loss": 0.5979, |
|
"step": 562 |
|
}, |
|
{ |
|
"epoch": 1.67, |
|
"learning_rate": 4.847628504972127e-06, |
|
"loss": 0.5883, |
|
"step": 563 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 4.8470923313899655e-06, |
|
"loss": 0.5967, |
|
"step": 564 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 4.846555245862413e-06, |
|
"loss": 0.5845, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 4.84601724859815e-06, |
|
"loss": 0.5994, |
|
"step": 566 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 4.845478339806211e-06, |
|
"loss": 0.6005, |
|
"step": 567 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 4.844938519695985e-06, |
|
"loss": 0.5915, |
|
"step": 568 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 4.844397788477215e-06, |
|
"loss": 0.6007, |
|
"step": 569 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 4.843856146359999e-06, |
|
"loss": 0.5915, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 4.843313593554787e-06, |
|
"loss": 0.5874, |
|
"step": 571 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 4.842770130272384e-06, |
|
"loss": 0.5903, |
|
"step": 572 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 4.842225756723949e-06, |
|
"loss": 0.5684, |
|
"step": 573 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 4.841680473120994e-06, |
|
"loss": 0.5802, |
|
"step": 574 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 4.841134279675386e-06, |
|
"loss": 0.5567, |
|
"step": 575 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 4.8405871765993435e-06, |
|
"loss": 0.5836, |
|
"step": 576 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 4.840039164105439e-06, |
|
"loss": 0.5579, |
|
"step": 577 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 4.8394902424065995e-06, |
|
"loss": 0.5779, |
|
"step": 578 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 4.838940411716104e-06, |
|
"loss": 0.5678, |
|
"step": 579 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 4.838389672247585e-06, |
|
"loss": 0.5684, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"eval_loss": 0.6262981295585632, |
|
"eval_runtime": 39.5368, |
|
"eval_samples_per_second": 43.984, |
|
"eval_steps_per_second": 2.757, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 4.83783802421503e-06, |
|
"loss": 0.5697, |
|
"step": 581 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 4.837285467832775e-06, |
|
"loss": 0.5936, |
|
"step": 582 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 4.836732003315513e-06, |
|
"loss": 0.6041, |
|
"step": 583 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 4.836177630878289e-06, |
|
"loss": 0.5739, |
|
"step": 584 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 4.835622350736499e-06, |
|
"loss": 0.5788, |
|
"step": 585 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 4.835066163105896e-06, |
|
"loss": 0.5989, |
|
"step": 586 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 4.834509068202578e-06, |
|
"loss": 0.6027, |
|
"step": 587 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 4.833951066243004e-06, |
|
"loss": 0.572, |
|
"step": 588 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 4.83339215744398e-06, |
|
"loss": 0.5737, |
|
"step": 589 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 4.832832342022666e-06, |
|
"loss": 0.5881, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 4.832271620196575e-06, |
|
"loss": 0.5722, |
|
"step": 591 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 4.8317099921835695e-06, |
|
"loss": 0.5751, |
|
"step": 592 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 4.831147458201867e-06, |
|
"loss": 0.5972, |
|
"step": 593 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 4.830584018470036e-06, |
|
"loss": 0.5689, |
|
"step": 594 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 4.830019673206997e-06, |
|
"loss": 0.5537, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 4.829454422632021e-06, |
|
"loss": 0.5974, |
|
"step": 596 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 4.828888266964733e-06, |
|
"loss": 0.5989, |
|
"step": 597 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 4.82832120642511e-06, |
|
"loss": 0.5825, |
|
"step": 598 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 4.827753241233475e-06, |
|
"loss": 0.5909, |
|
"step": 599 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 4.827184371610511e-06, |
|
"loss": 0.5897, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"eval_loss": 0.6251489520072937, |
|
"eval_runtime": 39.5127, |
|
"eval_samples_per_second": 44.011, |
|
"eval_steps_per_second": 2.759, |
|
"step": 600 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 5040, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 15, |
|
"save_steps": 50, |
|
"total_flos": 2.1880457610955588e+19, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|