Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847dc02f3b38aa7e51f0cacbe1b2b80cb29380793b7bf43a6cf5d1d1b94b455c
+oid sha256:c720a82775181a4cd2276009775505c2dc411517366f8206754dd1fccf40c62d
 size 4903351912

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d2c3d23b2d39fab6fc5b5326e3c2a31e0765bee6f6567aede4042b437aa53e
+oid sha256:5b22c87f4f3bb646dab710bd893e4fa530734d56d9a72279e6a893453d39b4d5
 size 4947570872

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bfa8f575ce1b25b91c01f7da9ec0bbaa16bc12948a7636470294a65576e7ee
+oid sha256:d4b8b79e8ac0dd4b714be7323e839127acf6017d0629132db64d52403d866baf
 size 4962221464

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb16e3955e4d8454bd444cfc5cd2f4c17c1b3009e33b760fb4c8da32cefafb1
+oid sha256:98c413da2ce14d6a0f25adde5849a6505f5042fb2da230c79d76ca2814f22111
 size 3670322200

trainer_log.jsonl

@@ -88,3 +88,47 @@
 {"current_steps": 870, "total_steps": 1329, "loss": 0.5475, "learning_rate": 1.675203699451431e-06, "epoch": 1.9633286318758816, "percentage": 65.46, "elapsed_time": "21:50:40", "remaining_time": "11:31:29"}
 {"current_steps": 880, "total_steps": 1329, "loss": 0.5451, "learning_rate": 1.6153992288475608e-06, "epoch": 1.9858956276445698, "percentage": 66.22, "elapsed_time": "22:05:35", "remaining_time": "11:16:21"}
 {"current_steps": 886, "total_steps": 1329, "eval_loss": 0.5835120677947998, "epoch": 1.9994358251057829, "percentage": 66.67, "elapsed_time": "22:26:19", "remaining_time": "11:13:09"}
+{"current_steps": 890, "total_steps": 1329, "loss": 0.5758, "learning_rate": 1.556239578318598e-06, "epoch": 2.008462623413258, "percentage": 66.97, "elapsed_time": "22:33:17", "remaining_time": "11:07:31"}
+{"current_steps": 900, "total_steps": 1329, "loss": 0.4993, "learning_rate": 1.4977655645762997e-06, "epoch": 2.0310296191819464, "percentage": 67.72, "elapsed_time": "22:48:15", "remaining_time": "10:52:11"}
+{"current_steps": 910, "total_steps": 1329, "loss": 0.5018, "learning_rate": 1.4400175312829936e-06, "epoch": 2.0535966149506346, "percentage": 68.47, "elapsed_time": "23:03:08", "remaining_time": "10:36:51"}
+{"current_steps": 920, "total_steps": 1329, "loss": 0.4941, "learning_rate": 1.383035321216798e-06, "epoch": 2.076163610719323, "percentage": 69.22, "elapsed_time": "23:18:05", "remaining_time": "10:21:32"}
+{"current_steps": 930, "total_steps": 1329, "loss": 0.5008, "learning_rate": 1.3268582487824252e-06, "epoch": 2.098730606488011, "percentage": 69.98, "elapsed_time": "23:32:58", "remaining_time": "10:06:12"}
+{"current_steps": 940, "total_steps": 1329, "loss": 0.5045, "learning_rate": 1.2715250728865372e-06, "epoch": 2.1212976022566994, "percentage": 70.73, "elapsed_time": "23:47:54", "remaining_time": "9:50:54"}
+{"current_steps": 950, "total_steps": 1329, "loss": 0.5052, "learning_rate": 1.2170739701963579e-06, "epoch": 2.143864598025388, "percentage": 71.48, "elapsed_time": "1 day, 0:02:48", "remaining_time": "9:35:36"}
+{"current_steps": 960, "total_steps": 1329, "loss": 0.5012, "learning_rate": 1.1635425087999944e-06, "epoch": 2.1664315937940763, "percentage": 72.23, "elapsed_time": "1 day, 0:17:44", "remaining_time": "9:20:18"}
+{"current_steps": 970, "total_steps": 1329, "loss": 0.4979, "learning_rate": 1.1109676222866447e-06, "epoch": 2.1889985895627646, "percentage": 72.99, "elapsed_time": "1 day, 0:32:38", "remaining_time": "9:05:01"}
+{"current_steps": 980, "total_steps": 1329, "loss": 0.4922, "learning_rate": 1.0593855842645777e-06, "epoch": 2.211565585331453, "percentage": 73.74, "elapsed_time": "1 day, 0:47:35", "remaining_time": "8:49:45"}
+{"current_steps": 990, "total_steps": 1329, "loss": 0.4919, "learning_rate": 1.0088319833344533e-06, "epoch": 2.234132581100141, "percentage": 74.49, "elapsed_time": "1 day, 1:02:30", "remaining_time": "8:34:29"}
+{"current_steps": 1000, "total_steps": 1329, "loss": 0.5012, "learning_rate": 9.593416985352631e-07, "epoch": 2.2566995768688294, "percentage": 75.24, "elapsed_time": "1 day, 1:17:25", "remaining_time": "8:19:13"}
+{"current_steps": 1010, "total_steps": 1329, "loss": 0.5067, "learning_rate": 9.109488752798265e-07, "epoch": 2.2792665726375176, "percentage": 76.0, "elapsed_time": "1 day, 1:32:20", "remaining_time": "8:03:58"}
+{"current_steps": 1020, "total_steps": 1329, "loss": 0.5007, "learning_rate": 8.636869017964417e-07, "epoch": 2.301833568406206, "percentage": 76.75, "elapsed_time": "1 day, 1:47:14", "remaining_time": "7:48:43"}
+{"current_steps": 1030, "total_steps": 1329, "loss": 0.5045, "learning_rate": 8.175883860929587e-07, "epoch": 2.324400564174894, "percentage": 77.5, "elapsed_time": "1 day, 2:02:10", "remaining_time": "7:33:29"}
+{"current_steps": 1040, "total_steps": 1329, "loss": 0.5017, "learning_rate": 7.726851334591511e-07, "epoch": 2.3469675599435824, "percentage": 78.25, "elapsed_time": "1 day, 2:17:05", "remaining_time": "7:18:15"}
+{"current_steps": 1050, "total_steps": 1329, "loss": 0.4989, "learning_rate": 7.290081245229201e-07, "epoch": 2.3695345557122707, "percentage": 79.01, "elapsed_time": "1 day, 2:32:00", "remaining_time": "7:03:01"}
+{"current_steps": 1060, "total_steps": 1329, "loss": 0.498, "learning_rate": 6.865874938754659e-07, "epoch": 2.392101551480959, "percentage": 79.76, "elapsed_time": "1 day, 2:46:56", "remaining_time": "6:47:47"}
+{"current_steps": 1070, "total_steps": 1329, "loss": 0.4983, "learning_rate": 6.454525092801745e-07, "epoch": 2.414668547249647, "percentage": 80.51, "elapsed_time": "1 day, 3:01:53", "remaining_time": "6:32:35"}
+{"current_steps": 1080, "total_steps": 1329, "loss": 0.5016, "learning_rate": 6.056315514795699e-07, "epoch": 2.4372355430183354, "percentage": 81.26, "elapsed_time": "1 day, 3:16:52", "remaining_time": "6:17:23"}
+{"current_steps": 1090, "total_steps": 1329, "loss": 0.4997, "learning_rate": 5.671520946142526e-07, "epoch": 2.459802538787024, "percentage": 82.02, "elapsed_time": "1 day, 3:31:50", "remaining_time": "6:02:11"}
+{"current_steps": 1100, "total_steps": 1329, "loss": 0.5022, "learning_rate": 5.300406872673434e-07, "epoch": 2.4823695345557124, "percentage": 82.77, "elapsed_time": "1 day, 3:46:46", "remaining_time": "5:46:59"}
+{"current_steps": 1110, "total_steps": 1329, "loss": 0.5054, "learning_rate": 4.943229341475108e-07, "epoch": 2.5049365303244007, "percentage": 83.52, "elapsed_time": "1 day, 4:01:43", "remaining_time": "5:31:47"}
+{"current_steps": 1120, "total_steps": 1329, "loss": 0.495, "learning_rate": 4.600234784232087e-07, "epoch": 2.527503526093089, "percentage": 84.27, "elapsed_time": "1 day, 4:16:40", "remaining_time": "5:16:36"}
+{"current_steps": 1130, "total_steps": 1329, "loss": 0.4999, "learning_rate": 4.2716598472033066e-07, "epoch": 2.550070521861777, "percentage": 85.03, "elapsed_time": "1 day, 4:31:36", "remaining_time": "5:01:25"}
+{"current_steps": 1140, "total_steps": 1329, "loss": 0.4982, "learning_rate": 3.957731227949975e-07, "epoch": 2.5726375176304654, "percentage": 85.78, "elapsed_time": "1 day, 4:46:34", "remaining_time": "4:46:14"}
+{"current_steps": 1150, "total_steps": 1329, "loss": 0.4986, "learning_rate": 3.6586655189274235e-07, "epoch": 2.5952045133991537, "percentage": 86.53, "elapsed_time": "1 day, 5:01:27", "remaining_time": "4:31:03"}
+{"current_steps": 1160, "total_steps": 1329, "loss": 0.5019, "learning_rate": 3.374669058048948e-07, "epoch": 2.617771509167842, "percentage": 87.28, "elapsed_time": "1 day, 5:16:24", "remaining_time": "4:15:53"}
+{"current_steps": 1170, "total_steps": 1329, "loss": 0.4904, "learning_rate": 3.1059377863246947e-07, "epoch": 2.64033850493653, "percentage": 88.04, "elapsed_time": "1 day, 5:31:20", "remaining_time": "4:00:43"}
+{"current_steps": 1180, "total_steps": 1329, "loss": 0.5015, "learning_rate": 2.8526571126737587e-07, "epoch": 2.6629055007052185, "percentage": 88.79, "elapsed_time": "1 day, 5:46:17", "remaining_time": "3:45:33"}
+{"current_steps": 1190, "total_steps": 1329, "loss": 0.502, "learning_rate": 2.615001786002833e-07, "epoch": 2.685472496473907, "percentage": 89.54, "elapsed_time": "1 day, 6:01:09", "remaining_time": "3:30:23"}
+{"current_steps": 1200, "total_steps": 1329, "loss": 0.5001, "learning_rate": 2.3931357746396515e-07, "epoch": 2.7080394922425954, "percentage": 90.29, "elapsed_time": "1 day, 6:16:02", "remaining_time": "3:15:13"}
+{"current_steps": 1210, "total_steps": 1329, "loss": 0.5009, "learning_rate": 2.1872121532043977e-07, "epoch": 2.7306064880112837, "percentage": 91.05, "elapsed_time": "1 day, 6:31:00", "remaining_time": "3:00:04"}
+{"current_steps": 1220, "total_steps": 1329, "loss": 0.4973, "learning_rate": 1.9973729969971315e-07, "epoch": 2.753173483779972, "percentage": 91.8, "elapsed_time": "1 day, 6:45:52", "remaining_time": "2:44:55"}
+{"current_steps": 1230, "total_steps": 1329, "loss": 0.5041, "learning_rate": 1.823749283974119e-07, "epoch": 2.77574047954866, "percentage": 92.55, "elapsed_time": "1 day, 7:00:47", "remaining_time": "2:29:46"}
+{"current_steps": 1240, "total_steps": 1329, "loss": 0.5023, "learning_rate": 1.6664608043806614e-07, "epoch": 2.7983074753173485, "percentage": 93.3, "elapsed_time": "1 day, 7:15:44", "remaining_time": "2:14:37"}
+{"current_steps": 1250, "total_steps": 1329, "loss": 0.5021, "learning_rate": 1.5256160781028118e-07, "epoch": 2.8208744710860367, "percentage": 94.06, "elapsed_time": "1 day, 7:30:37", "remaining_time": "1:59:29"}
+{"current_steps": 1260, "total_steps": 1329, "loss": 0.5036, "learning_rate": 1.401312279794984e-07, "epoch": 2.843441466854725, "percentage": 94.81, "elapsed_time": "1 day, 7:45:35", "remaining_time": "1:44:21"}
+{"current_steps": 1270, "total_steps": 1329, "loss": 0.5009, "learning_rate": 1.2936351718350923e-07, "epoch": 2.8660084626234132, "percentage": 95.56, "elapsed_time": "1 day, 8:00:33", "remaining_time": "1:29:13"}
+{"current_steps": 1280, "total_steps": 1329, "loss": 0.4983, "learning_rate": 1.202659045153513e-07, "epoch": 2.8885754583921015, "percentage": 96.31, "elapsed_time": "1 day, 8:15:28", "remaining_time": "1:14:05"}
+{"current_steps": 1290, "total_steps": 1329, "loss": 0.5021, "learning_rate": 1.1284466679766762e-07, "epoch": 2.9111424541607898, "percentage": 97.07, "elapsed_time": "1 day, 8:30:27", "remaining_time": "0:58:58"}
+{"current_steps": 1300, "total_steps": 1329, "loss": 0.4973, "learning_rate": 1.0710492425206354e-07, "epoch": 2.933709449929478, "percentage": 97.82, "elapsed_time": "1 day, 8:45:25", "remaining_time": "0:43:50"}
+{"current_steps": 1310, "total_steps": 1329, "loss": 0.5012, "learning_rate": 1.0305063696645283e-07, "epoch": 2.9562764456981663, "percentage": 98.57, "elapsed_time": "1 day, 9:00:21", "remaining_time": "0:28:43"}
+{"current_steps": 1320, "total_steps": 1329, "loss": 0.4967, "learning_rate": 1.006846021628281e-07, "epoch": 2.9788434414668545, "percentage": 99.32, "elapsed_time": "1 day, 9:15:17", "remaining_time": "0:13:36"}