Training in progress, step 15000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3555c37af26548a1cc6ba4bb87ff4de4041837d85d33ec18def68b87e3fae3c7
+oid sha256:d4468a83477bf767bd4dc4ed3ee94382b2a078b3007f2c0ba309f499d4e2d462
 size 50161688

trainer_log.jsonl

@@ -314,3 +314,158 @@
 {"current_steps": 10048, "total_steps": 20000, "loss": 3.6073, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016611382475833068, "epoch": 0.5723073418009911, "percentage": 50.24}
 {"current_steps": 10080, "total_steps": 20000, "loss": 3.5213, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000165428398279221, "epoch": 0.574129976647491, "percentage": 50.4}
 {"current_steps": 10112, "total_steps": 20000, "loss": 3.6138, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016474296075637306, "epoch": 0.575952611493991, "percentage": 50.56}
+{"current_steps": 10144, "total_steps": 20000, "loss": 3.4554, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016405752985977517, "epoch": 0.5777752463404909, "percentage": 50.72}
+{"current_steps": 10176, "total_steps": 20000, "loss": 3.5282, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016337212325924494, "epoch": 0.579597881186991, "percentage": 50.88}
+{"current_steps": 10208, "total_steps": 20000, "loss": 3.5451, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001626867586239736, "epoch": 0.5814205160334909, "percentage": 51.04}
+{"current_steps": 10240, "total_steps": 20000, "loss": 3.5618, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001620014536220705, "epoch": 0.5832431508799909, "percentage": 51.2}
+{"current_steps": 10272, "total_steps": 20000, "loss": 3.4401, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016131622592010784, "epoch": 0.5850657857264908, "percentage": 51.36}
+{"current_steps": 10304, "total_steps": 20000, "loss": 3.5091, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00016063109318266487, "epoch": 0.5868884205729908, "percentage": 51.52}
+{"current_steps": 10336, "total_steps": 20000, "loss": 3.402, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001599460730718729, "epoch": 0.5887110554194908, "percentage": 51.68}
+{"current_steps": 10368, "total_steps": 20000, "loss": 3.4552, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015926118324695982, "epoch": 0.5905336902659908, "percentage": 51.84}
+{"current_steps": 10400, "total_steps": 20000, "loss": 3.477, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001585764413637948, "epoch": 0.5923563251124907, "percentage": 52.0}
+{"current_steps": 10432, "total_steps": 20000, "loss": 3.4806, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015789186507443324, "epoch": 0.5941789599589907, "percentage": 52.16}
+{"current_steps": 10464, "total_steps": 20000, "loss": 3.5359, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015720747202666163, "epoch": 0.5960015948054906, "percentage": 52.32}
+{"current_steps": 10496, "total_steps": 20000, "loss": 3.5038, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001565232798635427, "epoch": 0.5978242296519907, "percentage": 52.48}
+{"current_steps": 10528, "total_steps": 20000, "loss": 3.7714, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001558393062229605, "epoch": 0.5996468644984906, "percentage": 52.64}
+{"current_steps": 10560, "total_steps": 20000, "loss": 3.443, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015515556873716584, "epoch": 0.6014694993449906, "percentage": 52.8}
+{"current_steps": 10592, "total_steps": 20000, "loss": 3.5814, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015447208503232158, "epoch": 0.6032921341914905, "percentage": 52.96}
+{"current_steps": 10624, "total_steps": 20000, "loss": 3.4096, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015378887272804838, "epoch": 0.6051147690379906, "percentage": 53.12}
+{"current_steps": 10656, "total_steps": 20000, "loss": 3.4768, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015310594943697032, "epoch": 0.6069374038844905, "percentage": 53.28}
+{"current_steps": 10688, "total_steps": 20000, "loss": 3.4686, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015242333276426108, "epoch": 0.6087600387309905, "percentage": 53.44}
+{"current_steps": 10720, "total_steps": 20000, "loss": 3.4216, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015174104030718998, "epoch": 0.6105826735774904, "percentage": 53.6}
+{"current_steps": 10752, "total_steps": 20000, "loss": 3.6679, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001510590896546683, "epoch": 0.6124053084239904, "percentage": 53.76}
+{"current_steps": 10784, "total_steps": 20000, "loss": 3.5821, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00015037749838679593, "epoch": 0.6142279432704904, "percentage": 53.92}
+{"current_steps": 10816, "total_steps": 20000, "loss": 3.3491, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014969628407440806, "epoch": 0.6160505781169904, "percentage": 54.08}
+{"current_steps": 10848, "total_steps": 20000, "loss": 3.6548, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014901546427862234, "epoch": 0.6178732129634903, "percentage": 54.24}
+{"current_steps": 10880, "total_steps": 20000, "loss": 3.417, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001483350565503862, "epoch": 0.6196958478099903, "percentage": 54.4}
+{"current_steps": 10912, "total_steps": 20000, "loss": 3.6446, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014765507843002418, "epoch": 0.6215184826564902, "percentage": 54.56}
+{"current_steps": 10944, "total_steps": 20000, "loss": 3.625, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014697554744678596, "epoch": 0.6233411175029903, "percentage": 54.72}
+{"current_steps": 10976, "total_steps": 20000, "loss": 3.2869, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014629648111839452, "epoch": 0.6251637523494903, "percentage": 54.88}
+{"current_steps": 11008, "total_steps": 20000, "loss": 3.4686, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001456178969505942, "epoch": 0.6269863871959902, "percentage": 55.04}
+{"current_steps": 11040, "total_steps": 20000, "loss": 3.5408, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014493981243669983, "epoch": 0.6288090220424902, "percentage": 55.2}
+{"current_steps": 11072, "total_steps": 20000, "loss": 3.4927, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014426224505714556, "epoch": 0.6306316568889901, "percentage": 55.36}
+{"current_steps": 11104, "total_steps": 20000, "loss": 3.5431, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001435852122790343, "epoch": 0.6324542917354902, "percentage": 55.52}
+{"current_steps": 11136, "total_steps": 20000, "loss": 3.6149, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001429087315556873, "epoch": 0.6342769265819901, "percentage": 55.68}
+{"current_steps": 11168, "total_steps": 20000, "loss": 3.3114, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014223282032619445, "epoch": 0.6360995614284901, "percentage": 55.84}
+{"current_steps": 11200, "total_steps": 20000, "loss": 3.5707, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001415574960149644, "epoch": 0.63792219627499, "percentage": 56.0}
+{"current_steps": 11232, "total_steps": 20000, "loss": 3.5028, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014088277603127567, "epoch": 0.63974483112149, "percentage": 56.16}
+{"current_steps": 11264, "total_steps": 20000, "loss": 3.4124, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00014020867776882778, "epoch": 0.64156746596799, "percentage": 56.32}
+{"current_steps": 11296, "total_steps": 20000, "loss": 3.4529, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001395352186052927, "epoch": 0.64339010081449, "percentage": 56.48}
+{"current_steps": 11328, "total_steps": 20000, "loss": 3.5608, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000138862415901867, "epoch": 0.6452127356609899, "percentage": 56.64}
+{"current_steps": 11360, "total_steps": 20000, "loss": 3.4213, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001381902870028244, "epoch": 0.6470353705074899, "percentage": 56.8}
+{"current_steps": 11392, "total_steps": 20000, "loss": 3.5092, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013751884923506833, "epoch": 0.6488580053539899, "percentage": 56.96}
+{"current_steps": 11424, "total_steps": 20000, "loss": 3.621, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013684811990768558, "epoch": 0.6506806402004899, "percentage": 57.12}
+{"current_steps": 11456, "total_steps": 20000, "loss": 3.5347, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013617811631149988, "epoch": 0.6525032750469898, "percentage": 57.28}
+{"current_steps": 11488, "total_steps": 20000, "loss": 3.6315, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013550885571862647, "epoch": 0.6543259098934898, "percentage": 57.44}
+{"current_steps": 11520, "total_steps": 20000, "loss": 3.5082, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013484035538202616, "epoch": 0.6561485447399897, "percentage": 57.6}
+{"current_steps": 11552, "total_steps": 20000, "loss": 3.6399, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013417263253506147, "epoch": 0.6579711795864898, "percentage": 57.76}
+{"current_steps": 11584, "total_steps": 20000, "loss": 3.3577, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013350570439105158, "epoch": 0.6597938144329897, "percentage": 57.92}
+{"current_steps": 11616, "total_steps": 20000, "loss": 3.4638, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001328395881428292, "epoch": 0.6616164492794897, "percentage": 58.08}
+{"current_steps": 11648, "total_steps": 20000, "loss": 3.4155, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001321743009622967, "epoch": 0.6634390841259896, "percentage": 58.24}
+{"current_steps": 11680, "total_steps": 20000, "loss": 3.5051, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013150985999998415, "epoch": 0.6652617189724896, "percentage": 58.4}
+{"current_steps": 11712, "total_steps": 20000, "loss": 3.4756, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001308462823846066, "epoch": 0.6670843538189896, "percentage": 58.56}
+{"current_steps": 11744, "total_steps": 20000, "loss": 3.6026, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00013018358522262288, "epoch": 0.6689069886654896, "percentage": 58.72}
+{"current_steps": 11776, "total_steps": 20000, "loss": 3.5048, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012952178559779454, "epoch": 0.6707296235119895, "percentage": 58.88}
+{"current_steps": 11808, "total_steps": 20000, "loss": 3.4404, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001288609005707453, "epoch": 0.6725522583584895, "percentage": 59.04}
+{"current_steps": 11840, "total_steps": 20000, "loss": 3.5206, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001282009471785213, "epoch": 0.6743748932049894, "percentage": 59.2}
+{"current_steps": 11872, "total_steps": 20000, "loss": 3.4797, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012754194243415202, "epoch": 0.6761975280514895, "percentage": 59.36}
+{"current_steps": 11904, "total_steps": 20000, "loss": 3.3544, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012688390332621165, "epoch": 0.6780201628979894, "percentage": 59.52}
+{"current_steps": 11936, "total_steps": 20000, "loss": 3.4025, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012622684681838102, "epoch": 0.6798427977444894, "percentage": 59.68}
+{"current_steps": 11968, "total_steps": 20000, "loss": 3.4585, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012557078984901042, "epoch": 0.6816654325909893, "percentage": 59.84}
+{"current_steps": 12000, "total_steps": 20000, "loss": 3.4265, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012491574933068292, "epoch": 0.6834880674374894, "percentage": 60.0}
+{"current_steps": 12032, "total_steps": 20000, "loss": 3.5471, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012426174214977823, "epoch": 0.6853107022839893, "percentage": 60.16}
+{"current_steps": 12064, "total_steps": 20000, "loss": 3.508, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012360878516603764, "epoch": 0.6871333371304893, "percentage": 60.32}
+{"current_steps": 12096, "total_steps": 20000, "loss": 3.4596, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001229568952121293, "epoch": 0.6889559719769892, "percentage": 60.48}
+{"current_steps": 12128, "total_steps": 20000, "loss": 3.4163, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012230608909321412, "epoch": 0.6907786068234892, "percentage": 60.64}
+{"current_steps": 12160, "total_steps": 20000, "loss": 3.4927, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012165638358651273, "epoch": 0.6926012416699892, "percentage": 60.8}
+{"current_steps": 12192, "total_steps": 20000, "loss": 3.4337, "eval_loss": null, "predict_loss": null, "learning_rate": 0.000121007795440873, "epoch": 0.6944238765164892, "percentage": 60.96}
+{"current_steps": 12224, "total_steps": 20000, "loss": 3.509, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00012036034137633809, "epoch": 0.6962465113629891, "percentage": 61.12}
+{"current_steps": 12256, "total_steps": 20000, "loss": 3.4267, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011971403808371557, "epoch": 0.6980691462094891, "percentage": 61.28}
+{"current_steps": 12288, "total_steps": 20000, "loss": 3.3582, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011906890222414711, "epoch": 0.699891781055989, "percentage": 61.44}
+{"current_steps": 12320, "total_steps": 20000, "loss": 3.451, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011842495042867899, "epoch": 0.7017144159024891, "percentage": 61.6}
+{"current_steps": 12352, "total_steps": 20000, "loss": 3.47, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011778219929783322, "epoch": 0.703537050748989, "percentage": 61.76}
+{"current_steps": 12384, "total_steps": 20000, "loss": 3.4529, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011714066540117983, "epoch": 0.705359685595489, "percentage": 61.92}
+{"current_steps": 12416, "total_steps": 20000, "loss": 3.492, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011650036527690956, "epoch": 0.7071823204419889, "percentage": 62.08}
+{"current_steps": 12448, "total_steps": 20000, "loss": 3.3875, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011586131543140762, "epoch": 0.709004955288489, "percentage": 62.24}
+{"current_steps": 12480, "total_steps": 20000, "loss": 3.3402, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011522353233882803, "epoch": 0.7108275901349889, "percentage": 62.4}
+{"current_steps": 12512, "total_steps": 20000, "loss": 3.2325, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011458703244066896, "epoch": 0.7126502249814889, "percentage": 62.56}
+{"current_steps": 12544, "total_steps": 20000, "loss": 3.4461, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001139518321453491, "epoch": 0.7144728598279888, "percentage": 62.72}
+{"current_steps": 12576, "total_steps": 20000, "loss": 3.5156, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011331794782778444, "epoch": 0.7162954946744888, "percentage": 62.88}
+{"current_steps": 12608, "total_steps": 20000, "loss": 3.5607, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001126853958289661, "epoch": 0.7181181295209887, "percentage": 63.04}
+{"current_steps": 12640, "total_steps": 20000, "loss": 3.3353, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011205419245553924, "epoch": 0.7199407643674888, "percentage": 63.2}
+{"current_steps": 12672, "total_steps": 20000, "loss": 3.4358, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011142435397938273, "epoch": 0.7217633992139887, "percentage": 63.36}
+{"current_steps": 12704, "total_steps": 20000, "loss": 3.4256, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011079589663718931, "epoch": 0.7235860340604887, "percentage": 63.52}
+{"current_steps": 12736, "total_steps": 20000, "loss": 3.3999, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00011016883663004754, "epoch": 0.7254086689069886, "percentage": 63.68}
+{"current_steps": 12768, "total_steps": 20000, "loss": 3.3563, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010954319012302369, "epoch": 0.7272313037534887, "percentage": 63.84}
+{"current_steps": 12800, "total_steps": 20000, "loss": 3.3537, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010891897324474534, "epoch": 0.7290539385999886, "percentage": 64.0}
+{"current_steps": 12832, "total_steps": 20000, "loss": 3.3277, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010829620208698547, "epoch": 0.7308765734464886, "percentage": 64.16}
+{"current_steps": 12864, "total_steps": 20000, "loss": 3.4189, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001076748927042475, "epoch": 0.7326992082929885, "percentage": 64.32}
+{"current_steps": 12896, "total_steps": 20000, "loss": 3.4289, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010705506111335171, "epoch": 0.7345218431394885, "percentage": 64.48}
+{"current_steps": 12928, "total_steps": 20000, "loss": 3.4348, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010643672329302207, "epoch": 0.7363444779859885, "percentage": 64.64}
+{"current_steps": 12960, "total_steps": 20000, "loss": 3.3893, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010581989518347453, "epoch": 0.7381671128324885, "percentage": 64.8}
+{"current_steps": 12992, "total_steps": 20000, "loss": 3.4882, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010520459268600592, "epoch": 0.7399897476789884, "percentage": 64.96}
+{"current_steps": 13024, "total_steps": 20000, "loss": 3.3666, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010459083166258416, "epoch": 0.7418123825254884, "percentage": 65.12}
+{"current_steps": 13056, "total_steps": 20000, "loss": 3.4322, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001039786279354392, "epoch": 0.7436350173719883, "percentage": 65.28}
+{"current_steps": 13088, "total_steps": 20000, "loss": 3.4917, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010336799728665537, "epoch": 0.7454576522184884, "percentage": 65.44}
+{"current_steps": 13120, "total_steps": 20000, "loss": 3.4772, "eval_loss": null, "predict_loss": null, "learning_rate": 0.0001027589554577643, "epoch": 0.7472802870649883, "percentage": 65.6}
+{"current_steps": 13152, "total_steps": 20000, "loss": 3.3115, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010215151814933922, "epoch": 0.7491029219114883, "percentage": 65.76}
+{"current_steps": 13184, "total_steps": 20000, "loss": 3.2641, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010154570102059024, "epoch": 0.7509255567579882, "percentage": 65.92}
+{"current_steps": 13216, "total_steps": 20000, "loss": 3.275, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010094151968896062, "epoch": 0.7527481916044882, "percentage": 66.08}
+{"current_steps": 13248, "total_steps": 20000, "loss": 3.4733, "eval_loss": null, "predict_loss": null, "learning_rate": 0.00010033898972972423, "epoch": 0.7545708264509882, "percentage": 66.24}
+{"current_steps": 13280, "total_steps": 20000, "loss": 3.3793, "eval_loss": null, "predict_loss": null, "learning_rate": 9.973812667558385e-05, "epoch": 0.7563934612974882, "percentage": 66.4}
+{"current_steps": 13312, "total_steps": 20000, "loss": 3.2858, "eval_loss": null, "predict_loss": null, "learning_rate": 9.913894601627107e-05, "epoch": 0.7582160961439881, "percentage": 66.56}
+{"current_steps": 13344, "total_steps": 20000, "loss": 3.4737, "eval_loss": null, "predict_loss": null, "learning_rate": 9.854146319814667e-05, "epoch": 0.7600387309904881, "percentage": 66.72}
+{"current_steps": 13376, "total_steps": 20000, "loss": 3.3573, "eval_loss": null, "predict_loss": null, "learning_rate": 9.794569362380249e-05, "epoch": 0.761861365836988, "percentage": 66.88}
+{"current_steps": 13408, "total_steps": 20000, "loss": 3.5501, "eval_loss": null, "predict_loss": null, "learning_rate": 9.735165265166456e-05, "epoch": 0.7636840006834881, "percentage": 67.04}
+{"current_steps": 13440, "total_steps": 20000, "loss": 3.4229, "eval_loss": null, "predict_loss": null, "learning_rate": 9.675935559559702e-05, "epoch": 0.765506635529988, "percentage": 67.2}
+{"current_steps": 13472, "total_steps": 20000, "loss": 3.6122, "eval_loss": null, "predict_loss": null, "learning_rate": 9.616881772450724e-05, "epoch": 0.767329270376488, "percentage": 67.36}
+{"current_steps": 13504, "total_steps": 20000, "loss": 3.4147, "eval_loss": null, "predict_loss": null, "learning_rate": 9.558005426195242e-05, "epoch": 0.7691519052229879, "percentage": 67.52}
+{"current_steps": 13536, "total_steps": 20000, "loss": 3.2421, "eval_loss": null, "predict_loss": null, "learning_rate": 9.499308038574699e-05, "epoch": 0.770974540069488, "percentage": 67.68}
+{"current_steps": 13568, "total_steps": 20000, "loss": 3.4786, "eval_loss": null, "predict_loss": null, "learning_rate": 9.440791122757145e-05, "epoch": 0.7727971749159879, "percentage": 67.84}
+{"current_steps": 13600, "total_steps": 20000, "loss": 3.2896, "eval_loss": null, "predict_loss": null, "learning_rate": 9.382456187258217e-05, "epoch": 0.7746198097624879, "percentage": 68.0}
+{"current_steps": 13632, "total_steps": 20000, "loss": 3.2801, "eval_loss": null, "predict_loss": null, "learning_rate": 9.324304735902253e-05, "epoch": 0.7764424446089878, "percentage": 68.16}
+{"current_steps": 13664, "total_steps": 20000, "loss": 3.2701, "eval_loss": null, "predict_loss": null, "learning_rate": 9.266338267783541e-05, "epoch": 0.7782650794554878, "percentage": 68.32}
+{"current_steps": 13696, "total_steps": 20000, "loss": 3.4045, "eval_loss": null, "predict_loss": null, "learning_rate": 9.208558277227653e-05, "epoch": 0.7800877143019878, "percentage": 68.48}
+{"current_steps": 13728, "total_steps": 20000, "loss": 3.3077, "eval_loss": null, "predict_loss": null, "learning_rate": 9.150966253752919e-05, "epoch": 0.7819103491484878, "percentage": 68.64}
+{"current_steps": 13760, "total_steps": 20000, "loss": 3.4493, "eval_loss": null, "predict_loss": null, "learning_rate": 9.093563682032058e-05, "epoch": 0.7837329839949878, "percentage": 68.8}
+{"current_steps": 13792, "total_steps": 20000, "loss": 3.3479, "eval_loss": null, "predict_loss": null, "learning_rate": 9.036352041853875e-05, "epoch": 0.7855556188414877, "percentage": 68.96}
+{"current_steps": 13824, "total_steps": 20000, "loss": 3.3557, "eval_loss": null, "predict_loss": null, "learning_rate": 8.979332808085124e-05, "epoch": 0.7873782536879878, "percentage": 69.12}
+{"current_steps": 13856, "total_steps": 20000, "loss": 3.3459, "eval_loss": null, "predict_loss": null, "learning_rate": 8.922507450632498e-05, "epoch": 0.7892008885344877, "percentage": 69.28}
+{"current_steps": 13888, "total_steps": 20000, "loss": 3.3632, "eval_loss": null, "predict_loss": null, "learning_rate": 8.865877434404718e-05, "epoch": 0.7910235233809877, "percentage": 69.44}
+{"current_steps": 13920, "total_steps": 20000, "loss": 3.377, "eval_loss": null, "predict_loss": null, "learning_rate": 8.809444219274776e-05, "epoch": 0.7928461582274876, "percentage": 69.6}
+{"current_steps": 13952, "total_steps": 20000, "loss": 3.3761, "eval_loss": null, "predict_loss": null, "learning_rate": 8.753209260042303e-05, "epoch": 0.7946687930739876, "percentage": 69.76}
+{"current_steps": 13984, "total_steps": 20000, "loss": 3.3294, "eval_loss": null, "predict_loss": null, "learning_rate": 8.697174006396064e-05, "epoch": 0.7964914279204875, "percentage": 69.92}
+{"current_steps": 14016, "total_steps": 20000, "loss": 3.3279, "eval_loss": null, "predict_loss": null, "learning_rate": 8.641339902876595e-05, "epoch": 0.7983140627669876, "percentage": 70.08}
+{"current_steps": 14048, "total_steps": 20000, "loss": 3.3793, "eval_loss": null, "predict_loss": null, "learning_rate": 8.585708388838935e-05, "epoch": 0.8001366976134875, "percentage": 70.24}
+{"current_steps": 14080, "total_steps": 20000, "loss": 3.367, "eval_loss": null, "predict_loss": null, "learning_rate": 8.530280898415551e-05, "epoch": 0.8019593324599875, "percentage": 70.4}
+{"current_steps": 14112, "total_steps": 20000, "loss": 3.3546, "eval_loss": null, "predict_loss": null, "learning_rate": 8.475058860479362e-05, "epoch": 0.8037819673064874, "percentage": 70.56}
+{"current_steps": 14144, "total_steps": 20000, "loss": 3.275, "eval_loss": null, "predict_loss": null, "learning_rate": 8.420043698606898e-05, "epoch": 0.8056046021529875, "percentage": 70.72}
+{"current_steps": 14176, "total_steps": 20000, "loss": 3.3093, "eval_loss": null, "predict_loss": null, "learning_rate": 8.365236831041596e-05, "epoch": 0.8074272369994874, "percentage": 70.88}
+{"current_steps": 14208, "total_steps": 20000, "loss": 3.3178, "eval_loss": null, "predict_loss": null, "learning_rate": 8.31063967065725e-05, "epoch": 0.8092498718459874, "percentage": 71.04}
+{"current_steps": 14240, "total_steps": 20000, "loss": 3.3699, "eval_loss": null, "predict_loss": null, "learning_rate": 8.256253624921584e-05, "epoch": 0.8110725066924873, "percentage": 71.2}
+{"current_steps": 14272, "total_steps": 20000, "loss": 3.0534, "eval_loss": null, "predict_loss": null, "learning_rate": 8.202080095859966e-05, "epoch": 0.8128951415389873, "percentage": 71.36}
+{"current_steps": 14304, "total_steps": 20000, "loss": 3.4639, "eval_loss": null, "predict_loss": null, "learning_rate": 8.148120480019276e-05, "epoch": 0.8147177763854873, "percentage": 71.52}
+{"current_steps": 14336, "total_steps": 20000, "loss": 3.3887, "eval_loss": null, "predict_loss": null, "learning_rate": 8.094376168431873e-05, "epoch": 0.8165404112319873, "percentage": 71.68}
+{"current_steps": 14368, "total_steps": 20000, "loss": 3.2464, "eval_loss": null, "predict_loss": null, "learning_rate": 8.040848546579788e-05, "epoch": 0.8183630460784872, "percentage": 71.84}
+{"current_steps": 14400, "total_steps": 20000, "loss": 3.3145, "eval_loss": null, "predict_loss": null, "learning_rate": 7.98753899435895e-05, "epoch": 0.8201856809249872, "percentage": 72.0}
+{"current_steps": 14432, "total_steps": 20000, "loss": 3.3964, "eval_loss": null, "predict_loss": null, "learning_rate": 7.93444888604366e-05, "epoch": 0.8220083157714871, "percentage": 72.16}
+{"current_steps": 14464, "total_steps": 20000, "loss": 3.2644, "eval_loss": null, "predict_loss": null, "learning_rate": 7.881579590251135e-05, "epoch": 0.8238309506179872, "percentage": 72.32}
+{"current_steps": 14496, "total_steps": 20000, "loss": 3.4409, "eval_loss": null, "predict_loss": null, "learning_rate": 7.82893246990624e-05, "epoch": 0.8256535854644871, "percentage": 72.48}
+{"current_steps": 14528, "total_steps": 20000, "loss": 3.3595, "eval_loss": null, "predict_loss": null, "learning_rate": 7.77650888220635e-05, "epoch": 0.8274762203109871, "percentage": 72.64}
+{"current_steps": 14560, "total_steps": 20000, "loss": 3.2493, "eval_loss": null, "predict_loss": null, "learning_rate": 7.72431017858635e-05, "epoch": 0.829298855157487, "percentage": 72.8}
+{"current_steps": 14592, "total_steps": 20000, "loss": 3.35, "eval_loss": null, "predict_loss": null, "learning_rate": 7.672337704683824e-05, "epoch": 0.831121490003987, "percentage": 72.96}
+{"current_steps": 14624, "total_steps": 20000, "loss": 3.2696, "eval_loss": null, "predict_loss": null, "learning_rate": 7.620592800304338e-05, "epoch": 0.832944124850487, "percentage": 73.12}
+{"current_steps": 14656, "total_steps": 20000, "loss": 3.3989, "eval_loss": null, "predict_loss": null, "learning_rate": 7.569076799386909e-05, "epoch": 0.834766759696987, "percentage": 73.28}
+{"current_steps": 14688, "total_steps": 20000, "loss": 3.3166, "eval_loss": null, "predict_loss": null, "learning_rate": 7.517791029969627e-05, "epoch": 0.8365893945434869, "percentage": 73.44}
+{"current_steps": 14720, "total_steps": 20000, "loss": 3.3701, "eval_loss": null, "predict_loss": null, "learning_rate": 7.466736814155418e-05, "epoch": 0.8384120293899869, "percentage": 73.6}
+{"current_steps": 14752, "total_steps": 20000, "loss": 3.3479, "eval_loss": null, "predict_loss": null, "learning_rate": 7.415915468077937e-05, "epoch": 0.8402346642364869, "percentage": 73.76}
+{"current_steps": 14784, "total_steps": 20000, "loss": 3.3405, "eval_loss": null, "predict_loss": null, "learning_rate": 7.365328301867673e-05, "epoch": 0.8420572990829869, "percentage": 73.92}
+{"current_steps": 14816, "total_steps": 20000, "loss": 3.4364, "eval_loss": null, "predict_loss": null, "learning_rate": 7.31497661961816e-05, "epoch": 0.8438799339294868, "percentage": 74.08}
+{"current_steps": 14848, "total_steps": 20000, "loss": 3.3318, "eval_loss": null, "predict_loss": null, "learning_rate": 7.264861719352352e-05, "epoch": 0.8457025687759868, "percentage": 74.24}
+{"current_steps": 14880, "total_steps": 20000, "loss": 3.282, "eval_loss": null, "predict_loss": null, "learning_rate": 7.21498489298917e-05, "epoch": 0.8475252036224867, "percentage": 74.4}
+{"current_steps": 14912, "total_steps": 20000, "loss": 3.3532, "eval_loss": null, "predict_loss": null, "learning_rate": 7.165347426310198e-05, "epoch": 0.8493478384689868, "percentage": 74.56}
+{"current_steps": 14944, "total_steps": 20000, "loss": 3.189, "eval_loss": null, "predict_loss": null, "learning_rate": 7.115950598926533e-05, "epoch": 0.8511704733154867, "percentage": 74.72}
+{"current_steps": 14976, "total_steps": 20000, "loss": 3.3579, "eval_loss": null, "predict_loss": null, "learning_rate": 7.066795684245788e-05, "epoch": 0.8529931081619867, "percentage": 74.88}
+{"current_steps": 15008, "total_steps": 20000, "loss": 3.2985, "eval_loss": null, "predict_loss": null, "learning_rate": 7.017883949439288e-05, "epoch": 0.8548157430084866, "percentage": 75.04}
+{"current_steps": 15040, "total_steps": 20000, "loss": 3.4314, "eval_loss": null, "predict_loss": null, "learning_rate": 6.969216655409388e-05, "epoch": 0.8566383778549866, "percentage": 75.2}
+{"current_steps": 15072, "total_steps": 20000, "loss": 3.3598, "eval_loss": null, "predict_loss": null, "learning_rate": 6.92079505675697e-05, "epoch": 0.8584610127014866, "percentage": 75.36}