Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb916bc0b450690c5e1afe6c478d1f897fd1dc2540cccd22b8199c13e8660d5e
+oid sha256:6c5166d4b3ceb3ce285a4b81e6c214fd5afcbfeb0165f31bfa3b5f07d3e9994b
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205275e417a966a8cd58a598695091a241244a6cebc379faddd50b03106eeb79
+oid sha256:400a5013a855a2b7c21573674197edb192923c4fb1cab9d1a5689d5a4a6554e7
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afaa6cb5402a003f3641db27c880ade415548dfbf5ae9acb41e6ce09266e08e0
+oid sha256:dc56cb2b43619143dff59a17de086d7f6e3f6a8c4e4dcd7c1be66b7f1817d499
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c7698e8de6d3d99fe6e5ba20dc8dd518071a276ca7e9acc72343f32321d607
+oid sha256:5e54cee87252872159dc0ba97cfd98da8ad6a6192d7f102265c462106e0ff9de
 size 1089994880

trainer_log.jsonl

@@ -87,3 +87,47 @@
 {"current_steps": 860, "total_steps": 1314, "loss": 0.6048, "learning_rate": 1.9204737732656517e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:43:59", "remaining_time": "6:43:18"}
 {"current_steps": 870, "total_steps": 1314, "loss": 0.6024, "learning_rate": 1.8781725888324874e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:52:48", "remaining_time": "6:34:23"}
 {"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6210305690765381, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:06:18", "remaining_time": "6:31:48"}
+{"current_steps": 880, "total_steps": 1314, "loss": 0.6254, "learning_rate": 1.8358714043993234e-06, "epoch": 2.006837606837607, "percentage": 66.97, "elapsed_time": "13:10:06", "remaining_time": "6:29:39"}
+{"current_steps": 890, "total_steps": 1314, "loss": 0.5721, "learning_rate": 1.7935702199661592e-06, "epoch": 2.0296296296296297, "percentage": 67.73, "elapsed_time": "13:18:54", "remaining_time": "6:20:36"}
+{"current_steps": 900, "total_steps": 1314, "loss": 0.5881, "learning_rate": 1.7512690355329951e-06, "epoch": 2.0524216524216525, "percentage": 68.49, "elapsed_time": "13:27:42", "remaining_time": "6:11:32"}
+{"current_steps": 910, "total_steps": 1314, "loss": 0.586, "learning_rate": 1.708967851099831e-06, "epoch": 2.0752136752136754, "percentage": 69.25, "elapsed_time": "13:36:29", "remaining_time": "6:02:29"}
+{"current_steps": 920, "total_steps": 1314, "loss": 0.589, "learning_rate": 1.6666666666666667e-06, "epoch": 2.098005698005698, "percentage": 70.02, "elapsed_time": "13:45:18", "remaining_time": "5:53:27"}
+{"current_steps": 930, "total_steps": 1314, "loss": 0.5866, "learning_rate": 1.6243654822335026e-06, "epoch": 2.1207977207977207, "percentage": 70.78, "elapsed_time": "13:54:05", "remaining_time": "5:44:24"}
+{"current_steps": 940, "total_steps": 1314, "loss": 0.5812, "learning_rate": 1.5820642978003386e-06, "epoch": 2.1435897435897435, "percentage": 71.54, "elapsed_time": "14:02:52", "remaining_time": "5:35:21"}
+{"current_steps": 950, "total_steps": 1314, "loss": 0.5822, "learning_rate": 1.5397631133671746e-06, "epoch": 2.1663817663817664, "percentage": 72.3, "elapsed_time": "14:11:39", "remaining_time": "5:26:19"}
+{"current_steps": 960, "total_steps": 1314, "loss": 0.5871, "learning_rate": 1.4974619289340103e-06, "epoch": 2.1891737891737892, "percentage": 73.06, "elapsed_time": "14:20:27", "remaining_time": "5:17:17"}
+{"current_steps": 970, "total_steps": 1314, "loss": 0.5859, "learning_rate": 1.455160744500846e-06, "epoch": 2.211965811965812, "percentage": 73.82, "elapsed_time": "14:29:14", "remaining_time": "5:08:16"}
+{"current_steps": 980, "total_steps": 1314, "loss": 0.5755, "learning_rate": 1.412859560067682e-06, "epoch": 2.234757834757835, "percentage": 74.58, "elapsed_time": "14:38:02", "remaining_time": "4:59:14"}
+{"current_steps": 990, "total_steps": 1314, "loss": 0.5845, "learning_rate": 1.3705583756345178e-06, "epoch": 2.2575498575498574, "percentage": 75.34, "elapsed_time": "14:46:50", "remaining_time": "4:50:14"}
+{"current_steps": 1000, "total_steps": 1314, "loss": 0.5847, "learning_rate": 1.3282571912013536e-06, "epoch": 2.2803418803418802, "percentage": 76.1, "elapsed_time": "14:55:35", "remaining_time": "4:41:13"}
+{"current_steps": 1010, "total_steps": 1314, "loss": 0.5822, "learning_rate": 1.2859560067681896e-06, "epoch": 2.303133903133903, "percentage": 76.86, "elapsed_time": "15:04:22", "remaining_time": "4:32:12"}
+{"current_steps": 1020, "total_steps": 1314, "loss": 0.5851, "learning_rate": 1.2436548223350255e-06, "epoch": 2.325925925925926, "percentage": 77.63, "elapsed_time": "15:13:08", "remaining_time": "4:23:12"}
+{"current_steps": 1030, "total_steps": 1314, "loss": 0.5866, "learning_rate": 1.2013536379018613e-06, "epoch": 2.348717948717949, "percentage": 78.39, "elapsed_time": "15:21:56", "remaining_time": "4:14:12"}
+{"current_steps": 1040, "total_steps": 1314, "loss": 0.5841, "learning_rate": 1.1590524534686973e-06, "epoch": 2.3715099715099717, "percentage": 79.15, "elapsed_time": "15:30:43", "remaining_time": "4:05:12"}
+{"current_steps": 1050, "total_steps": 1314, "loss": 0.5834, "learning_rate": 1.116751269035533e-06, "epoch": 2.394301994301994, "percentage": 79.91, "elapsed_time": "15:39:30", "remaining_time": "3:56:13"}
+{"current_steps": 1060, "total_steps": 1314, "loss": 0.5917, "learning_rate": 1.074450084602369e-06, "epoch": 2.417094017094017, "percentage": 80.67, "elapsed_time": "15:48:16", "remaining_time": "3:47:13"}
+{"current_steps": 1070, "total_steps": 1314, "loss": 0.5948, "learning_rate": 1.0321489001692048e-06, "epoch": 2.43988603988604, "percentage": 81.43, "elapsed_time": "15:57:02", "remaining_time": "3:38:14"}
+{"current_steps": 1080, "total_steps": 1314, "loss": 0.59, "learning_rate": 9.898477157360407e-07, "epoch": 2.4626780626780627, "percentage": 82.19, "elapsed_time": "16:05:48", "remaining_time": "3:29:15"}
+{"current_steps": 1090, "total_steps": 1314, "loss": 0.5873, "learning_rate": 9.475465313028766e-07, "epoch": 2.4854700854700855, "percentage": 82.95, "elapsed_time": "16:14:36", "remaining_time": "3:20:17"}
+{"current_steps": 1100, "total_steps": 1314, "loss": 0.5941, "learning_rate": 9.052453468697125e-07, "epoch": 2.5082621082621084, "percentage": 83.71, "elapsed_time": "16:23:24", "remaining_time": "3:11:19"}
+{"current_steps": 1110, "total_steps": 1314, "loss": 0.587, "learning_rate": 8.629441624365482e-07, "epoch": 2.5310541310541312, "percentage": 84.47, "elapsed_time": "16:32:12", "remaining_time": "3:02:21"}
+{"current_steps": 1120, "total_steps": 1314, "loss": 0.5852, "learning_rate": 8.206429780033842e-07, "epoch": 2.5538461538461537, "percentage": 85.24, "elapsed_time": "16:41:00", "remaining_time": "2:53:23"}
+{"current_steps": 1130, "total_steps": 1314, "loss": 0.5845, "learning_rate": 7.7834179357022e-07, "epoch": 2.5766381766381765, "percentage": 86.0, "elapsed_time": "16:49:47", "remaining_time": "2:44:25"}
+{"current_steps": 1140, "total_steps": 1314, "loss": 0.5842, "learning_rate": 7.360406091370559e-07, "epoch": 2.5994301994301994, "percentage": 86.76, "elapsed_time": "16:58:35", "remaining_time": "2:35:28"}
+{"current_steps": 1150, "total_steps": 1314, "loss": 0.5843, "learning_rate": 6.937394247038917e-07, "epoch": 2.6222222222222222, "percentage": 87.52, "elapsed_time": "17:07:24", "remaining_time": "2:26:30"}
+{"current_steps": 1160, "total_steps": 1314, "loss": 0.585, "learning_rate": 6.514382402707276e-07, "epoch": 2.645014245014245, "percentage": 88.28, "elapsed_time": "17:16:11", "remaining_time": "2:17:33"}
+{"current_steps": 1170, "total_steps": 1314, "loss": 0.5883, "learning_rate": 6.091370558375635e-07, "epoch": 2.667806267806268, "percentage": 89.04, "elapsed_time": "17:24:58", "remaining_time": "2:08:36"}
+{"current_steps": 1180, "total_steps": 1314, "loss": 0.5833, "learning_rate": 5.668358714043994e-07, "epoch": 2.690598290598291, "percentage": 89.8, "elapsed_time": "17:33:46", "remaining_time": "1:59:39"}
+{"current_steps": 1190, "total_steps": 1314, "loss": 0.5842, "learning_rate": 5.245346869712352e-07, "epoch": 2.7133903133903132, "percentage": 90.56, "elapsed_time": "17:42:33", "remaining_time": "1:50:43"}
+{"current_steps": 1200, "total_steps": 1314, "loss": 0.5874, "learning_rate": 4.822335025380711e-07, "epoch": 2.736182336182336, "percentage": 91.32, "elapsed_time": "17:51:21", "remaining_time": "1:41:46"}
+{"current_steps": 1210, "total_steps": 1314, "loss": 0.5906, "learning_rate": 4.39932318104907e-07, "epoch": 2.758974358974359, "percentage": 92.09, "elapsed_time": "18:00:08", "remaining_time": "1:32:50"}
+{"current_steps": 1220, "total_steps": 1314, "loss": 0.5803, "learning_rate": 3.9763113367174284e-07, "epoch": 2.781766381766382, "percentage": 92.85, "elapsed_time": "18:08:56", "remaining_time": "1:23:54"}
+{"current_steps": 1230, "total_steps": 1314, "loss": 0.5788, "learning_rate": 3.553299492385787e-07, "epoch": 2.8045584045584047, "percentage": 93.61, "elapsed_time": "18:17:45", "remaining_time": "1:14:58"}
+{"current_steps": 1240, "total_steps": 1314, "loss": 0.5938, "learning_rate": 3.1302876480541457e-07, "epoch": 2.827350427350427, "percentage": 94.37, "elapsed_time": "18:26:33", "remaining_time": "1:06:02"}
+{"current_steps": 1250, "total_steps": 1314, "loss": 0.5907, "learning_rate": 2.7072758037225044e-07, "epoch": 2.8501424501424504, "percentage": 95.13, "elapsed_time": "18:35:20", "remaining_time": "0:57:06"}
+{"current_steps": 1260, "total_steps": 1314, "loss": 0.5877, "learning_rate": 2.284263959390863e-07, "epoch": 2.872934472934473, "percentage": 95.89, "elapsed_time": "18:44:07", "remaining_time": "0:48:10"}
+{"current_steps": 1270, "total_steps": 1314, "loss": 0.5886, "learning_rate": 1.8612521150592217e-07, "epoch": 2.8957264957264957, "percentage": 96.65, "elapsed_time": "18:52:56", "remaining_time": "0:39:15"}
+{"current_steps": 1280, "total_steps": 1314, "loss": 0.5787, "learning_rate": 1.4382402707275804e-07, "epoch": 2.9185185185185185, "percentage": 97.41, "elapsed_time": "19:01:44", "remaining_time": "0:30:19"}
+{"current_steps": 1290, "total_steps": 1314, "loss": 0.5786, "learning_rate": 1.0152284263959391e-07, "epoch": 2.9413105413105414, "percentage": 98.17, "elapsed_time": "19:10:31", "remaining_time": "0:21:24"}
+{"current_steps": 1300, "total_steps": 1314, "loss": 0.58, "learning_rate": 5.922165820642979e-08, "epoch": 2.9641025641025642, "percentage": 98.93, "elapsed_time": "19:19:19", "remaining_time": "0:12:29"}
+{"current_steps": 1310, "total_steps": 1314, "loss": 0.5901, "learning_rate": 1.6920473773265652e-08, "epoch": 2.9868945868945866, "percentage": 99.7, "elapsed_time": "19:28:07", "remaining_time": "0:03:34"}