| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 432.43243243243245, | |
| "eval_steps": 1500, | |
| "global_step": 16000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.3513513513513513, | |
| "grad_norm": 0.5760506987571716, | |
| "learning_rate": 1.9364864864864865e-06, | |
| "loss": 0.0736, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7027027027027026, | |
| "grad_norm": 0.4748266339302063, | |
| "learning_rate": 3.2743243243243245e-06, | |
| "loss": 0.0682, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.054054054054054, | |
| "grad_norm": 0.4784703552722931, | |
| "learning_rate": 4.612162162162162e-06, | |
| "loss": 0.0661, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 5.405405405405405, | |
| "grad_norm": 0.4363403022289276, | |
| "learning_rate": 5.95e-06, | |
| "loss": 0.0646, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.756756756756757, | |
| "grad_norm": 0.49891752004623413, | |
| "learning_rate": 7.287837837837838e-06, | |
| "loss": 0.0624, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.108108108108109, | |
| "grad_norm": 0.47630417346954346, | |
| "learning_rate": 8.625675675675676e-06, | |
| "loss": 0.0635, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.45945945945946, | |
| "grad_norm": 0.5554671287536621, | |
| "learning_rate": 9.963513513513515e-06, | |
| "loss": 0.0617, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 10.81081081081081, | |
| "grad_norm": 0.4327123165130615, | |
| "learning_rate": 1.1301351351351353e-05, | |
| "loss": 0.0595, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.162162162162161, | |
| "grad_norm": 0.5002420544624329, | |
| "learning_rate": 1.263918918918919e-05, | |
| "loss": 0.0585, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 13.513513513513514, | |
| "grad_norm": 0.42524299025535583, | |
| "learning_rate": 1.3977027027027028e-05, | |
| "loss": 0.0579, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 14.864864864864865, | |
| "grad_norm": 0.44030219316482544, | |
| "learning_rate": 1.5314864864864867e-05, | |
| "loss": 0.0575, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 16.216216216216218, | |
| "grad_norm": 0.46804261207580566, | |
| "learning_rate": 1.6625945945945947e-05, | |
| "loss": 0.0579, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 17.56756756756757, | |
| "grad_norm": 0.5248824954032898, | |
| "learning_rate": 1.7963783783783787e-05, | |
| "loss": 0.0556, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 18.91891891891892, | |
| "grad_norm": 0.43462327122688293, | |
| "learning_rate": 1.9301621621621623e-05, | |
| "loss": 0.0546, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 20.27027027027027, | |
| "grad_norm": 0.48718762397766113, | |
| "learning_rate": 2.0639459459459462e-05, | |
| "loss": 0.0529, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 21.62162162162162, | |
| "grad_norm": 0.40828168392181396, | |
| "learning_rate": 2.19772972972973e-05, | |
| "loss": 0.0523, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 22.972972972972972, | |
| "grad_norm": 0.4686122238636017, | |
| "learning_rate": 2.3315135135135137e-05, | |
| "loss": 0.0531, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 24.324324324324323, | |
| "grad_norm": 0.4426785707473755, | |
| "learning_rate": 2.4652972972972976e-05, | |
| "loss": 0.051, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 25.675675675675677, | |
| "grad_norm": 0.4910499155521393, | |
| "learning_rate": 2.5990810810810812e-05, | |
| "loss": 0.0486, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 27.027027027027028, | |
| "grad_norm": 0.4253314435482025, | |
| "learning_rate": 2.7328648648648652e-05, | |
| "loss": 0.0491, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 28.37837837837838, | |
| "grad_norm": 0.3838571012020111, | |
| "learning_rate": 2.866648648648649e-05, | |
| "loss": 0.049, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 29.72972972972973, | |
| "grad_norm": 0.39428308606147766, | |
| "learning_rate": 3.0004324324324327e-05, | |
| "loss": 0.0478, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 31.08108108108108, | |
| "grad_norm": 0.3973025381565094, | |
| "learning_rate": 3.134216216216216e-05, | |
| "loss": 0.0473, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 32.432432432432435, | |
| "grad_norm": 0.47299668192863464, | |
| "learning_rate": 3.268e-05, | |
| "loss": 0.047, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 33.78378378378378, | |
| "grad_norm": 0.5077139139175415, | |
| "learning_rate": 3.4017837837837835e-05, | |
| "loss": 0.0459, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 35.13513513513514, | |
| "grad_norm": 0.3789336085319519, | |
| "learning_rate": 3.535567567567568e-05, | |
| "loss": 0.0462, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 36.486486486486484, | |
| "grad_norm": 0.3798762857913971, | |
| "learning_rate": 3.669351351351351e-05, | |
| "loss": 0.045, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 37.83783783783784, | |
| "grad_norm": 0.41409873962402344, | |
| "learning_rate": 3.803135135135135e-05, | |
| "loss": 0.0438, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 39.189189189189186, | |
| "grad_norm": 0.4816993176937103, | |
| "learning_rate": 3.936918918918919e-05, | |
| "loss": 0.0432, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 40.54054054054054, | |
| "grad_norm": 0.31075775623321533, | |
| "learning_rate": 4.070702702702703e-05, | |
| "loss": 0.0415, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 41.891891891891895, | |
| "grad_norm": 0.5353565812110901, | |
| "learning_rate": 4.2044864864864864e-05, | |
| "loss": 0.0414, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 43.24324324324324, | |
| "grad_norm": 0.3337886333465576, | |
| "learning_rate": 4.3382702702702707e-05, | |
| "loss": 0.0406, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 44.5945945945946, | |
| "grad_norm": 0.3847792446613312, | |
| "learning_rate": 4.472054054054054e-05, | |
| "loss": 0.0404, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 45.945945945945944, | |
| "grad_norm": 0.4075019657611847, | |
| "learning_rate": 4.605837837837838e-05, | |
| "loss": 0.0409, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 47.2972972972973, | |
| "grad_norm": 0.4205191433429718, | |
| "learning_rate": 4.7396216216216214e-05, | |
| "loss": 0.0399, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 48.648648648648646, | |
| "grad_norm": 0.5053867101669312, | |
| "learning_rate": 4.873405405405406e-05, | |
| "loss": 0.0387, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "grad_norm": 0.43625885248184204, | |
| "learning_rate": 5.007189189189189e-05, | |
| "loss": 0.0393, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 51.351351351351354, | |
| "grad_norm": 0.44896236062049866, | |
| "learning_rate": 5.140972972972973e-05, | |
| "loss": 0.0376, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 52.7027027027027, | |
| "grad_norm": 0.42207279801368713, | |
| "learning_rate": 5.274756756756757e-05, | |
| "loss": 0.0392, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 54.054054054054056, | |
| "grad_norm": 0.4605530798435211, | |
| "learning_rate": 5.408540540540541e-05, | |
| "loss": 0.0384, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 55.4054054054054, | |
| "grad_norm": 0.4523848295211792, | |
| "learning_rate": 5.5423243243243243e-05, | |
| "loss": 0.0366, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 56.75675675675676, | |
| "grad_norm": 0.37463346123695374, | |
| "learning_rate": 5.6761081081081086e-05, | |
| "loss": 0.037, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 58.108108108108105, | |
| "grad_norm": 0.5655389428138733, | |
| "learning_rate": 5.809891891891892e-05, | |
| "loss": 0.0383, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 59.45945945945946, | |
| "grad_norm": 0.441587895154953, | |
| "learning_rate": 5.943675675675676e-05, | |
| "loss": 0.0392, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 60.810810810810814, | |
| "grad_norm": 0.44860920310020447, | |
| "learning_rate": 6.074783783783784e-05, | |
| "loss": 0.0372, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 62.16216216216216, | |
| "grad_norm": 0.4874947965145111, | |
| "learning_rate": 6.208567567567567e-05, | |
| "loss": 0.0372, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 63.513513513513516, | |
| "grad_norm": 0.44674238562583923, | |
| "learning_rate": 6.342351351351351e-05, | |
| "loss": 0.0368, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 64.86486486486487, | |
| "grad_norm": 0.535265326499939, | |
| "learning_rate": 6.476135135135136e-05, | |
| "loss": 0.0372, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 66.21621621621621, | |
| "grad_norm": 0.38546523451805115, | |
| "learning_rate": 6.60991891891892e-05, | |
| "loss": 0.0349, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 67.56756756756756, | |
| "grad_norm": 0.4751232862472534, | |
| "learning_rate": 6.743702702702703e-05, | |
| "loss": 0.038, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 68.91891891891892, | |
| "grad_norm": 0.6618958115577698, | |
| "learning_rate": 6.877486486486487e-05, | |
| "loss": 0.0512, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 70.27027027027027, | |
| "grad_norm": 0.4467822015285492, | |
| "learning_rate": 7.01127027027027e-05, | |
| "loss": 0.0517, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 71.62162162162163, | |
| "grad_norm": 0.5807027816772461, | |
| "learning_rate": 7.145054054054054e-05, | |
| "loss": 0.0506, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 72.97297297297297, | |
| "grad_norm": 0.44088873267173767, | |
| "learning_rate": 7.278837837837837e-05, | |
| "loss": 0.0517, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 74.32432432432432, | |
| "grad_norm": 0.5117065906524658, | |
| "learning_rate": 7.412621621621622e-05, | |
| "loss": 0.0497, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 75.67567567567568, | |
| "grad_norm": 0.5457988381385803, | |
| "learning_rate": 7.546405405405406e-05, | |
| "loss": 0.0494, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 77.02702702702703, | |
| "grad_norm": 0.35911738872528076, | |
| "learning_rate": 7.68018918918919e-05, | |
| "loss": 0.0476, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 78.37837837837837, | |
| "grad_norm": 0.5895106196403503, | |
| "learning_rate": 7.813972972972973e-05, | |
| "loss": 0.0479, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 79.72972972972973, | |
| "grad_norm": 0.39779385924339294, | |
| "learning_rate": 7.947756756756757e-05, | |
| "loss": 0.0479, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 81.08108108108108, | |
| "grad_norm": 0.5251230001449585, | |
| "learning_rate": 8.08154054054054e-05, | |
| "loss": 0.0468, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 81.08108108108108, | |
| "eval_loss": 0.5344434976577759, | |
| "eval_runtime": 19.3274, | |
| "eval_samples_per_second": 81.076, | |
| "eval_steps_per_second": 0.259, | |
| "eval_wer": 0.18456803226491192, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 82.43243243243244, | |
| "grad_norm": 0.44322407245635986, | |
| "learning_rate": 8.215324324324325e-05, | |
| "loss": 0.0458, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 83.78378378378379, | |
| "grad_norm": 0.47398409247398376, | |
| "learning_rate": 8.349108108108109e-05, | |
| "loss": 0.0461, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 85.13513513513513, | |
| "grad_norm": 0.452659010887146, | |
| "learning_rate": 8.482891891891893e-05, | |
| "loss": 0.045, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 86.48648648648648, | |
| "grad_norm": 0.6125317215919495, | |
| "learning_rate": 8.616675675675676e-05, | |
| "loss": 0.046, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 87.83783783783784, | |
| "grad_norm": 0.4655373692512512, | |
| "learning_rate": 8.75045945945946e-05, | |
| "loss": 0.0462, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 89.1891891891892, | |
| "grad_norm": 0.5071247220039368, | |
| "learning_rate": 8.884243243243243e-05, | |
| "loss": 0.0455, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 90.54054054054055, | |
| "grad_norm": 0.4586324691772461, | |
| "learning_rate": 9.018027027027027e-05, | |
| "loss": 0.0443, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 91.89189189189189, | |
| "grad_norm": 0.49810245633125305, | |
| "learning_rate": 9.151810810810812e-05, | |
| "loss": 0.0444, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 93.24324324324324, | |
| "grad_norm": 0.4874321222305298, | |
| "learning_rate": 9.285594594594595e-05, | |
| "loss": 0.0424, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 94.5945945945946, | |
| "grad_norm": 0.5060502886772156, | |
| "learning_rate": 9.419378378378379e-05, | |
| "loss": 0.0432, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 95.94594594594595, | |
| "grad_norm": 0.4356514513492584, | |
| "learning_rate": 9.553162162162163e-05, | |
| "loss": 0.042, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 97.29729729729729, | |
| "grad_norm": 0.5080994367599487, | |
| "learning_rate": 9.684270270270271e-05, | |
| "loss": 0.0424, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 98.64864864864865, | |
| "grad_norm": 0.6090648174285889, | |
| "learning_rate": 9.818054054054055e-05, | |
| "loss": 0.0423, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.6025941967964172, | |
| "learning_rate": 9.951837837837838e-05, | |
| "loss": 0.0445, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 101.35135135135135, | |
| "grad_norm": 0.592052161693573, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0425, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 102.70270270270271, | |
| "grad_norm": 0.5158424973487854, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0423, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 104.05405405405405, | |
| "grad_norm": 0.45459866523742676, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0411, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 105.4054054054054, | |
| "grad_norm": 0.4477308392524719, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0426, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 106.75675675675676, | |
| "grad_norm": 0.5172644853591919, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0413, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 108.10810810810811, | |
| "grad_norm": 0.4363681674003601, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0418, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 109.45945945945945, | |
| "grad_norm": 0.3899792730808258, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0386, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 110.8108108108108, | |
| "grad_norm": 0.3736754357814789, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0397, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 112.16216216216216, | |
| "grad_norm": 0.4031231999397278, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0372, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 113.51351351351352, | |
| "grad_norm": 0.3616081774234772, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0381, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 114.86486486486487, | |
| "grad_norm": 0.46817055344581604, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0366, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 116.21621621621621, | |
| "grad_norm": 0.4078225791454315, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0383, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 117.56756756756756, | |
| "grad_norm": 0.3821820020675659, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0348, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 118.91891891891892, | |
| "grad_norm": 0.44808605313301086, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0358, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 120.27027027027027, | |
| "grad_norm": 0.3535892367362976, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0337, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 121.62162162162163, | |
| "grad_norm": 0.32362979650497437, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0344, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 121.62162162162163, | |
| "eval_loss": 0.5824956893920898, | |
| "eval_runtime": 17.5119, | |
| "eval_samples_per_second": 89.482, | |
| "eval_steps_per_second": 0.286, | |
| "eval_wer": 0.18653152196985778, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 122.97297297297297, | |
| "grad_norm": 0.5193214416503906, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0361, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 124.32432432432432, | |
| "grad_norm": 0.3041287362575531, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0335, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 125.67567567567568, | |
| "grad_norm": 0.44249922037124634, | |
| "learning_rate": 0.0001, | |
| "loss": 0.034, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 127.02702702702703, | |
| "grad_norm": 0.357164204120636, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0326, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 128.3783783783784, | |
| "grad_norm": 0.30578091740608215, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0307, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 129.72972972972974, | |
| "grad_norm": 0.4774022102355957, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0321, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 131.0810810810811, | |
| "grad_norm": 0.3393169343471527, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0336, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 132.43243243243242, | |
| "grad_norm": 0.42481565475463867, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0317, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 133.78378378378378, | |
| "grad_norm": 0.45170778036117554, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0309, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 135.13513513513513, | |
| "grad_norm": 0.44404086470603943, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0331, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 136.48648648648648, | |
| "grad_norm": 0.4285108149051666, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0304, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 137.83783783783784, | |
| "grad_norm": 0.3434101343154907, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0294, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 139.1891891891892, | |
| "grad_norm": 0.41777992248535156, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0302, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 140.54054054054055, | |
| "grad_norm": 0.3897533714771271, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0303, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 141.8918918918919, | |
| "grad_norm": 0.3457304537296295, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0297, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 143.24324324324326, | |
| "grad_norm": 0.38188374042510986, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0291, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 144.59459459459458, | |
| "grad_norm": 0.44426918029785156, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0308, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 145.94594594594594, | |
| "grad_norm": 0.46593207120895386, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0306, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 147.2972972972973, | |
| "grad_norm": 0.5084848403930664, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0293, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 148.64864864864865, | |
| "grad_norm": 0.35385948419570923, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0307, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 150.0, | |
| "grad_norm": 0.2549344003200531, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0274, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 151.35135135135135, | |
| "grad_norm": 0.40980347990989685, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0294, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 152.7027027027027, | |
| "grad_norm": 0.413776695728302, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0285, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 154.05405405405406, | |
| "grad_norm": 0.4476383626461029, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0276, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 155.40540540540542, | |
| "grad_norm": 0.3967137336730957, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0286, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 156.75675675675674, | |
| "grad_norm": 0.3066927492618561, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0285, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 158.1081081081081, | |
| "grad_norm": 0.43991604447364807, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0297, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 159.45945945945945, | |
| "grad_norm": 0.6042722463607788, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0291, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 160.8108108108108, | |
| "grad_norm": 0.3852483034133911, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0291, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 162.16216216216216, | |
| "grad_norm": 0.3369120657444, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0273, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 162.16216216216216, | |
| "eval_loss": 0.613073468208313, | |
| "eval_runtime": 21.311, | |
| "eval_samples_per_second": 73.53, | |
| "eval_steps_per_second": 0.235, | |
| "eval_wer": 0.18998089577584376, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 163.51351351351352, | |
| "grad_norm": 0.3259856402873993, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0264, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 164.86486486486487, | |
| "grad_norm": 0.3508945405483246, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0274, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 166.21621621621622, | |
| "grad_norm": 0.3457798957824707, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0269, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 167.56756756756758, | |
| "grad_norm": 0.4306040406227112, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0264, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 168.9189189189189, | |
| "grad_norm": 1.110560417175293, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0262, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 170.27027027027026, | |
| "grad_norm": 0.3896867632865906, | |
| "learning_rate": 0.0001, | |
| "loss": 0.026, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 171.6216216216216, | |
| "grad_norm": 0.28667861223220825, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0264, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 172.97297297297297, | |
| "grad_norm": 0.3063699007034302, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0257, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 174.32432432432432, | |
| "grad_norm": 0.3457682132720947, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0241, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 175.67567567567568, | |
| "grad_norm": 0.3746369183063507, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0246, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 177.02702702702703, | |
| "grad_norm": 0.3032655715942383, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0238, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 178.3783783783784, | |
| "grad_norm": 0.3203031122684479, | |
| "learning_rate": 0.0001, | |
| "loss": 0.026, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 179.72972972972974, | |
| "grad_norm": 0.4081636965274811, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0251, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 181.0810810810811, | |
| "grad_norm": 0.38508379459381104, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0232, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 182.43243243243242, | |
| "grad_norm": 0.43911251425743103, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0242, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 183.78378378378378, | |
| "grad_norm": 0.38736340403556824, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0237, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 185.13513513513513, | |
| "grad_norm": 0.6214938163757324, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0235, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 186.48648648648648, | |
| "grad_norm": 0.3473169505596161, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0234, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 187.83783783783784, | |
| "grad_norm": 0.34946322441101074, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0232, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 189.1891891891892, | |
| "grad_norm": 0.3939970135688782, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0244, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 190.54054054054055, | |
| "grad_norm": 0.37184515595436096, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0238, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 191.8918918918919, | |
| "grad_norm": 0.39142072200775146, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0238, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 193.24324324324326, | |
| "grad_norm": 0.35670343041419983, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0234, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 194.59459459459458, | |
| "grad_norm": 0.5025286674499512, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0237, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 195.94594594594594, | |
| "grad_norm": 0.4491577744483948, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0245, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 197.2972972972973, | |
| "grad_norm": 0.30056050419807434, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0222, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 198.64864864864865, | |
| "grad_norm": 0.332044780254364, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0219, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "grad_norm": 0.2828930914402008, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0232, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 201.35135135135135, | |
| "grad_norm": 0.3619934022426605, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0244, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 202.7027027027027, | |
| "grad_norm": 0.4312371015548706, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0238, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 202.7027027027027, | |
| "eval_loss": 0.6532334685325623, | |
| "eval_runtime": 29.8357, | |
| "eval_samples_per_second": 52.521, | |
| "eval_steps_per_second": 0.168, | |
| "eval_wer": 0.19167904903417535, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 204.05405405405406, | |
| "grad_norm": 0.3734581470489502, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0234, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 205.40540540540542, | |
| "grad_norm": 0.4595019519329071, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0229, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 206.75675675675674, | |
| "grad_norm": 0.2700786888599396, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0227, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 208.1081081081081, | |
| "grad_norm": 0.24691906571388245, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0229, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 209.45945945945945, | |
| "grad_norm": 0.3328978717327118, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0217, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 210.8108108108108, | |
| "grad_norm": 0.286808580160141, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0205, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 212.16216216216216, | |
| "grad_norm": 0.27080458402633667, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0202, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 213.51351351351352, | |
| "grad_norm": 0.398179292678833, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0215, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 214.86486486486487, | |
| "grad_norm": 0.3541491627693176, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0218, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 216.21621621621622, | |
| "grad_norm": 0.3138297498226166, | |
| "learning_rate": 0.0001, | |
| "loss": 0.022, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 217.56756756756758, | |
| "grad_norm": 0.38513001799583435, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0215, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 218.9189189189189, | |
| "grad_norm": 0.400036484003067, | |
| "learning_rate": 0.0001, | |
| "loss": 0.021, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 220.27027027027026, | |
| "grad_norm": 0.3203113377094269, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0207, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 221.6216216216216, | |
| "grad_norm": 0.3765117824077606, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0197, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 222.97297297297297, | |
| "grad_norm": 0.3336365222930908, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0211, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 224.32432432432432, | |
| "grad_norm": 0.29828354716300964, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0188, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 225.67567567567568, | |
| "grad_norm": 0.34553930163383484, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0199, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 227.02702702702703, | |
| "grad_norm": 0.3510328531265259, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0215, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 228.3783783783784, | |
| "grad_norm": 0.48810675740242004, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0217, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 229.72972972972974, | |
| "grad_norm": 0.34023284912109375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0225, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 231.0810810810811, | |
| "grad_norm": 0.31986966729164124, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0217, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 232.43243243243242, | |
| "grad_norm": 0.27697187662124634, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0205, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 233.78378378378378, | |
| "grad_norm": 0.3078053593635559, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0185, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 235.13513513513513, | |
| "grad_norm": 0.24676857888698578, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0202, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 236.48648648648648, | |
| "grad_norm": 0.2980283498764038, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0202, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 237.83783783783784, | |
| "grad_norm": 0.34748488664627075, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0188, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 239.1891891891892, | |
| "grad_norm": 0.31379759311676025, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0195, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 240.54054054054055, | |
| "grad_norm": 0.31512585282325745, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0197, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 241.8918918918919, | |
| "grad_norm": 0.28801149129867554, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0188, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 243.24324324324326, | |
| "grad_norm": 0.29776033759117126, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0196, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 243.24324324324326, | |
| "eval_loss": 0.6647829413414001, | |
| "eval_runtime": 22.108, | |
| "eval_samples_per_second": 70.879, | |
| "eval_steps_per_second": 0.226, | |
| "eval_wer": 0.19295266397792402, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 244.59459459459458, | |
| "grad_norm": 0.2917761206626892, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0194, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 245.94594594594594, | |
| "grad_norm": 0.28261467814445496, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 247.2972972972973, | |
| "grad_norm": 0.44025787711143494, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0191, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 248.64864864864865, | |
| "grad_norm": 0.26063069701194763, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0182, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 250.0, | |
| "grad_norm": 0.3038322329521179, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0185, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 251.35135135135135, | |
| "grad_norm": 0.30964452028274536, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0188, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 252.7027027027027, | |
| "grad_norm": 0.34113481640815735, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0189, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 254.05405405405406, | |
| "grad_norm": 0.28624454140663147, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 255.40540540540542, | |
| "grad_norm": 0.28637397289276123, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0189, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 256.7567567567568, | |
| "grad_norm": 0.3362099230289459, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0194, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 258.1081081081081, | |
| "grad_norm": 0.30529114603996277, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 259.4594594594595, | |
| "grad_norm": 0.257412314414978, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 260.81081081081084, | |
| "grad_norm": 0.34228768944740295, | |
| "learning_rate": 0.0001, | |
| "loss": 0.019, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 262.1621621621622, | |
| "grad_norm": 0.43392807245254517, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0188, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 263.5135135135135, | |
| "grad_norm": 0.2830718457698822, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0191, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 264.86486486486484, | |
| "grad_norm": 0.33202308416366577, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0179, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 266.2162162162162, | |
| "grad_norm": 0.4601031243801117, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0176, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 267.56756756756755, | |
| "grad_norm": 0.33976060152053833, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0183, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 268.9189189189189, | |
| "grad_norm": 0.23951521515846252, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0171, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 270.27027027027026, | |
| "grad_norm": 0.7073889970779419, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0165, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 271.6216216216216, | |
| "grad_norm": 0.31089919805526733, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 272.97297297297297, | |
| "grad_norm": 0.38815826177597046, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0184, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 274.3243243243243, | |
| "grad_norm": 0.2964986562728882, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0172, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 275.6756756756757, | |
| "grad_norm": 0.2726752460002899, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 277.02702702702703, | |
| "grad_norm": 0.29586270451545715, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0169, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 278.3783783783784, | |
| "grad_norm": 0.3921571671962738, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 279.72972972972974, | |
| "grad_norm": 0.3076343238353729, | |
| "learning_rate": 0.0001, | |
| "loss": 0.02, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 281.0810810810811, | |
| "grad_norm": 0.3205571472644806, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0198, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 282.43243243243245, | |
| "grad_norm": 0.43506285548210144, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0186, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 283.7837837837838, | |
| "grad_norm": 0.31954890489578247, | |
| "learning_rate": 0.0001, | |
| "loss": 0.018, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 283.7837837837838, | |
| "eval_loss": 0.6387069821357727, | |
| "eval_runtime": 41.5803, | |
| "eval_samples_per_second": 37.686, | |
| "eval_steps_per_second": 0.12, | |
| "eval_wer": 0.19608363404797283, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 285.13513513513516, | |
| "grad_norm": 0.32306522130966187, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0174, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 286.4864864864865, | |
| "grad_norm": 0.2770741879940033, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0172, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 287.8378378378378, | |
| "grad_norm": 0.2585732936859131, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0162, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 289.18918918918916, | |
| "grad_norm": 0.2847765386104584, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0161, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 290.5405405405405, | |
| "grad_norm": 0.2730112075805664, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0178, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 291.8918918918919, | |
| "grad_norm": 0.29540035128593445, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0177, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 293.2432432432432, | |
| "grad_norm": 0.38015422224998474, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0166, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 294.5945945945946, | |
| "grad_norm": 0.3097437918186188, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0175, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 295.94594594594594, | |
| "grad_norm": 0.2496563345193863, | |
| "learning_rate": 0.0001, | |
| "loss": 0.016, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 297.2972972972973, | |
| "grad_norm": 0.29481038451194763, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 298.64864864864865, | |
| "grad_norm": 0.30355343222618103, | |
| "learning_rate": 0.0001, | |
| "loss": 0.017, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "grad_norm": 0.2778134047985077, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0165, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 301.35135135135135, | |
| "grad_norm": 0.29996800422668457, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0158, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 302.7027027027027, | |
| "grad_norm": 0.3584728240966797, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0155, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 304.05405405405406, | |
| "grad_norm": 0.5590859055519104, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0162, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 305.4054054054054, | |
| "grad_norm": 0.22827082872390747, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0166, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 306.7567567567568, | |
| "grad_norm": 0.37123405933380127, | |
| "learning_rate": 0.0001, | |
| "loss": 0.016, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 308.1081081081081, | |
| "grad_norm": 0.230214461684227, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0168, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 309.4594594594595, | |
| "grad_norm": 0.23933345079421997, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0164, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 310.81081081081084, | |
| "grad_norm": 0.3098168969154358, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0152, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 312.1621621621622, | |
| "grad_norm": 0.3287512958049774, | |
| "learning_rate": 0.0001, | |
| "loss": 0.014, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 313.5135135135135, | |
| "grad_norm": 0.46195220947265625, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0154, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 314.86486486486484, | |
| "grad_norm": 0.3282325863838196, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0158, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 316.2162162162162, | |
| "grad_norm": 0.2945399284362793, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0151, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 317.56756756756755, | |
| "grad_norm": 0.27878549695014954, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 318.9189189189189, | |
| "grad_norm": 0.252695232629776, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 320.27027027027026, | |
| "grad_norm": 0.26799729466438293, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 321.6216216216216, | |
| "grad_norm": 0.2436702400445938, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0147, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 322.97297297297297, | |
| "grad_norm": 0.40171217918395996, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 324.3243243243243, | |
| "grad_norm": 0.2604866027832031, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0154, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 324.3243243243243, | |
| "eval_loss": 0.6963035464286804, | |
| "eval_runtime": 17.3801, | |
| "eval_samples_per_second": 90.161, | |
| "eval_steps_per_second": 0.288, | |
| "eval_wer": 0.19910846953937592, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 325.6756756756757, | |
| "grad_norm": 0.28629496693611145, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0159, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 327.02702702702703, | |
| "grad_norm": 0.24716606736183167, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0152, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 328.3783783783784, | |
| "grad_norm": 0.2562699019908905, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0153, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 329.72972972972974, | |
| "grad_norm": 0.27679792046546936, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0147, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 331.0810810810811, | |
| "grad_norm": 0.2266552597284317, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0149, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 332.43243243243245, | |
| "grad_norm": 0.2453828752040863, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0151, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 333.7837837837838, | |
| "grad_norm": 0.3448384702205658, | |
| "learning_rate": 0.0001, | |
| "loss": 0.014, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 335.13513513513516, | |
| "grad_norm": 0.20089378952980042, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0148, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 336.4864864864865, | |
| "grad_norm": 0.2895062267780304, | |
| "learning_rate": 0.0001, | |
| "loss": 0.016, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 337.8378378378378, | |
| "grad_norm": 0.3491511642932892, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0153, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 339.18918918918916, | |
| "grad_norm": 0.2785622179508209, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0152, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 340.5405405405405, | |
| "grad_norm": 0.25130748748779297, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0148, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 341.8918918918919, | |
| "grad_norm": 0.3330935835838318, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0147, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 343.2432432432432, | |
| "grad_norm": 0.2657862901687622, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0156, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 344.5945945945946, | |
| "grad_norm": 0.3090120553970337, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 345.94594594594594, | |
| "grad_norm": 0.31333035230636597, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 347.2972972972973, | |
| "grad_norm": 0.33461394906044006, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0139, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 348.64864864864865, | |
| "grad_norm": 0.21069389581680298, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0138, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 350.0, | |
| "grad_norm": 0.23119139671325684, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 351.35135135135135, | |
| "grad_norm": 0.23619785904884338, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0131, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 352.7027027027027, | |
| "grad_norm": 0.4682454466819763, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0129, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 354.05405405405406, | |
| "grad_norm": 0.3268776834011078, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0144, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 355.4054054054054, | |
| "grad_norm": 0.3269369900226593, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 356.7567567567568, | |
| "grad_norm": 0.34849807620048523, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 358.1081081081081, | |
| "grad_norm": 0.24423350393772125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0148, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 359.4594594594595, | |
| "grad_norm": 0.2239474058151245, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0146, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 360.81081081081084, | |
| "grad_norm": 0.2930073142051697, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0145, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 362.1621621621622, | |
| "grad_norm": 0.25597310066223145, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 363.5135135135135, | |
| "grad_norm": 0.3600046932697296, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0142, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 364.86486486486484, | |
| "grad_norm": 0.37317752838134766, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0134, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 364.86486486486484, | |
| "eval_loss": 0.7163126468658447, | |
| "eval_runtime": 17.4822, | |
| "eval_samples_per_second": 89.634, | |
| "eval_steps_per_second": 0.286, | |
| "eval_wer": 0.20101889195499895, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 366.2162162162162, | |
| "grad_norm": 0.2017332762479782, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0134, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 367.56756756756755, | |
| "grad_norm": 0.26539239287376404, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0148, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 368.9189189189189, | |
| "grad_norm": 0.2736688256263733, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0148, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 370.27027027027026, | |
| "grad_norm": 0.28902319073677063, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 371.6216216216216, | |
| "grad_norm": 0.1861814558506012, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0132, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 372.97297297297297, | |
| "grad_norm": 0.2393738031387329, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 374.3243243243243, | |
| "grad_norm": 0.3993573486804962, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 375.6756756756757, | |
| "grad_norm": 0.3024432361125946, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0134, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 377.02702702702703, | |
| "grad_norm": 0.35330072045326233, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0143, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 378.3783783783784, | |
| "grad_norm": 0.21859917044639587, | |
| "learning_rate": 0.0001, | |
| "loss": 0.014, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 379.72972972972974, | |
| "grad_norm": 0.31557369232177734, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0135, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 381.0810810810811, | |
| "grad_norm": 0.2256789207458496, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0124, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 382.43243243243245, | |
| "grad_norm": 0.2742190659046173, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0131, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 383.7837837837838, | |
| "grad_norm": 0.21607190370559692, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0135, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 385.13513513513516, | |
| "grad_norm": 0.2626590430736542, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0126, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 386.4864864864865, | |
| "grad_norm": 0.18108737468719482, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0133, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 387.8378378378378, | |
| "grad_norm": 0.27729663252830505, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0143, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 389.18918918918916, | |
| "grad_norm": 0.38008466362953186, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0138, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 390.5405405405405, | |
| "grad_norm": 0.26434582471847534, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0138, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 391.8918918918919, | |
| "grad_norm": 0.2773403823375702, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0138, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 393.2432432432432, | |
| "grad_norm": 0.23838981986045837, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0137, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 394.5945945945946, | |
| "grad_norm": 0.2961066663265228, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0136, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 395.94594594594594, | |
| "grad_norm": 0.24311979115009308, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0133, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 397.2972972972973, | |
| "grad_norm": 0.3343033492565155, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0138, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 398.64864864864865, | |
| "grad_norm": 0.23256798088550568, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0133, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "grad_norm": 0.31679514050483704, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0131, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 401.35135135135135, | |
| "grad_norm": 0.24046526849269867, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0115, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 402.7027027027027, | |
| "grad_norm": 0.2563251852989197, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0121, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 404.05405405405406, | |
| "grad_norm": 0.18860304355621338, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 405.4054054054054, | |
| "grad_norm": 0.27949538826942444, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0117, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 405.4054054054054, | |
| "eval_loss": 0.7209838628768921, | |
| "eval_runtime": 55.6252, | |
| "eval_samples_per_second": 28.171, | |
| "eval_steps_per_second": 0.09, | |
| "eval_wer": 0.19634897049458713, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 406.7567567567568, | |
| "grad_norm": 0.25572505593299866, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0126, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 408.1081081081081, | |
| "grad_norm": 0.2233952134847641, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0127, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 409.4594594594595, | |
| "grad_norm": 0.30835413932800293, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0113, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 410.81081081081084, | |
| "grad_norm": 0.24969109892845154, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 412.1621621621622, | |
| "grad_norm": 0.2240106463432312, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0125, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 413.5135135135135, | |
| "grad_norm": 0.2874402403831482, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0118, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 414.86486486486484, | |
| "grad_norm": 0.3226901590824127, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 416.2162162162162, | |
| "grad_norm": 0.2564234733581543, | |
| "learning_rate": 0.0001, | |
| "loss": 0.012, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 417.56756756756755, | |
| "grad_norm": 0.34858137369155884, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0114, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 418.9189189189189, | |
| "grad_norm": 0.20746035873889923, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0129, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 420.27027027027026, | |
| "grad_norm": 0.35932862758636475, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0133, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 421.6216216216216, | |
| "grad_norm": 0.20093189179897308, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0126, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 422.97297297297297, | |
| "grad_norm": 0.32909420132637024, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0128, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 424.3243243243243, | |
| "grad_norm": 0.28278329968452454, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0117, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 425.6756756756757, | |
| "grad_norm": 0.1597350388765335, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0119, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 427.02702702702703, | |
| "grad_norm": 0.20241086184978485, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0114, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 428.3783783783784, | |
| "grad_norm": 0.24632301926612854, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0115, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 429.72972972972974, | |
| "grad_norm": 0.36104726791381836, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0114, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 431.0810810810811, | |
| "grad_norm": 0.23273630440235138, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0115, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 432.43243243243245, | |
| "grad_norm": 0.2528134882450104, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0113, | |
| "step": 16000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 37000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1000, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.491310429887309e+20, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |