penfever commited on
Commit
7e8f27c
·
verified ·
1 Parent(s): db67f17

Training in progress, step 5000

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fab000089051e4ffa40af8197890cca19f2c950621c26b4ded2c8fddffec104e
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7ecd029ab63fcc6fd6044d1de87203515dea3ecf5a04b973ee12316eabcb53
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f1535dba425e038a893bb52445edbf7cee5a92ebcea160690cb0b1ed500053b
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217cac45c2657050e0d04569b1e1146df6aec7e743fcbd9eff43fbdf72c3faa6
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ddadccd39bfc3eb0924270514a04fc33497a20b116bd99486c59811fd0c7070
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83995bd453db15fec113d606f4e3bf1f2def5db6f655477a2736d04627fce565
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5841577ed2dcb4b2ffa655bb5f450c3c90012fcd90a141608034ce26685f17c5
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb426af840c5279940ecf4825f879f0c5b877ab3a05a24526e7e06f683396ca
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -962,3 +962,43 @@
962
  {"current_steps": 4810, "total_steps": 9128, "loss": 0.2391, "lr": 2.1615879788855763e-05, "epoch": 3.68891446106636, "percentage": 52.7, "elapsed_time": "1 day, 5:54:20", "remaining_time": "1 day, 2:50:48"}
963
  {"current_steps": 4815, "total_steps": 9128, "loss": 0.2257, "lr": 2.157775972815319e-05, "epoch": 3.6927502876869966, "percentage": 52.75, "elapsed_time": "1 day, 5:56:07", "remaining_time": "1 day, 2:48:52"}
964
  {"current_steps": 4820, "total_steps": 9128, "loss": 0.2274, "lr": 2.1539633898918004e-05, "epoch": 3.6965861143076335, "percentage": 52.8, "elapsed_time": "1 day, 5:57:45", "remaining_time": "1 day, 2:46:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
962
  {"current_steps": 4810, "total_steps": 9128, "loss": 0.2391, "lr": 2.1615879788855763e-05, "epoch": 3.68891446106636, "percentage": 52.7, "elapsed_time": "1 day, 5:54:20", "remaining_time": "1 day, 2:50:48"}
963
  {"current_steps": 4815, "total_steps": 9128, "loss": 0.2257, "lr": 2.157775972815319e-05, "epoch": 3.6927502876869966, "percentage": 52.75, "elapsed_time": "1 day, 5:56:07", "remaining_time": "1 day, 2:48:52"}
964
  {"current_steps": 4820, "total_steps": 9128, "loss": 0.2274, "lr": 2.1539633898918004e-05, "epoch": 3.6965861143076335, "percentage": 52.8, "elapsed_time": "1 day, 5:57:45", "remaining_time": "1 day, 2:46:47"}
965
+ {"current_steps": 4825, "total_steps": 9128, "loss": 0.2285, "lr": 2.15015024405441e-05, "epoch": 3.70042194092827, "percentage": 52.86, "elapsed_time": "1 day, 5:59:33", "remaining_time": "1 day, 2:44:52"}
966
+ {"current_steps": 4830, "total_steps": 9128, "loss": 0.2365, "lr": 2.1463365492445964e-05, "epoch": 3.704257767548907, "percentage": 52.91, "elapsed_time": "1 day, 6:01:11", "remaining_time": "1 day, 2:42:47"}
967
+ {"current_steps": 4835, "total_steps": 9128, "loss": 0.227, "lr": 2.1425223194058158e-05, "epoch": 3.7080935941695436, "percentage": 52.97, "elapsed_time": "1 day, 6:02:47", "remaining_time": "1 day, 2:40:42"}
968
+ {"current_steps": 4840, "total_steps": 9128, "loss": 0.2308, "lr": 2.13870756848348e-05, "epoch": 3.71192942079018, "percentage": 53.02, "elapsed_time": "1 day, 6:04:29", "remaining_time": "1 day, 2:38:40"}
969
+ {"current_steps": 4845, "total_steps": 9128, "loss": 0.2276, "lr": 2.134892310424906e-05, "epoch": 3.715765247410817, "percentage": 53.08, "elapsed_time": "1 day, 6:06:09", "remaining_time": "1 day, 2:36:39"}
970
+ {"current_steps": 4850, "total_steps": 9128, "loss": 0.2181, "lr": 2.1310765591792647e-05, "epoch": 3.719601074031454, "percentage": 53.13, "elapsed_time": "1 day, 6:07:55", "remaining_time": "1 day, 2:34:41"}
971
+ {"current_steps": 4855, "total_steps": 9128, "loss": 0.225, "lr": 2.127260328697531e-05, "epoch": 3.7234369006520907, "percentage": 53.19, "elapsed_time": "1 day, 6:09:31", "remaining_time": "1 day, 2:32:36"}
972
+ {"current_steps": 4860, "total_steps": 9128, "loss": 0.2316, "lr": 2.1234436329324306e-05, "epoch": 3.7272727272727275, "percentage": 53.24, "elapsed_time": "1 day, 6:11:13", "remaining_time": "1 day, 2:30:36"}
973
+ {"current_steps": 4865, "total_steps": 9128, "loss": 0.2245, "lr": 2.1196264858383918e-05, "epoch": 3.731108553893364, "percentage": 53.3, "elapsed_time": "1 day, 6:12:55", "remaining_time": "1 day, 2:28:35"}
974
+ {"current_steps": 4870, "total_steps": 9128, "loss": 0.2364, "lr": 2.115808901371493e-05, "epoch": 3.734944380514001, "percentage": 53.35, "elapsed_time": "1 day, 6:14:32", "remaining_time": "1 day, 2:26:30"}
975
+ {"current_steps": 4875, "total_steps": 9128, "loss": 0.2263, "lr": 2.11199089348941e-05, "epoch": 3.7387802071346377, "percentage": 53.41, "elapsed_time": "1 day, 6:16:11", "remaining_time": "1 day, 2:24:28"}
976
+ {"current_steps": 4880, "total_steps": 9128, "loss": 0.2378, "lr": 2.108172476151368e-05, "epoch": 3.742616033755274, "percentage": 53.46, "elapsed_time": "1 day, 6:17:56", "remaining_time": "1 day, 2:22:29"}
977
+ {"current_steps": 4885, "total_steps": 9128, "loss": 0.2256, "lr": 2.1043536633180894e-05, "epoch": 3.746451860375911, "percentage": 53.52, "elapsed_time": "1 day, 6:19:32", "remaining_time": "1 day, 2:20:24"}
978
+ {"current_steps": 4890, "total_steps": 9128, "loss": 0.2331, "lr": 2.100534468951742e-05, "epoch": 3.750287686996548, "percentage": 53.57, "elapsed_time": "1 day, 6:21:14", "remaining_time": "1 day, 2:18:24"}
979
+ {"current_steps": 4895, "total_steps": 9128, "loss": 0.2192, "lr": 2.096714907015889e-05, "epoch": 3.7541235136171847, "percentage": 53.63, "elapsed_time": "1 day, 6:22:55", "remaining_time": "1 day, 2:16:23"}
980
+ {"current_steps": 4900, "total_steps": 9128, "loss": 0.2188, "lr": 2.0928949914754363e-05, "epoch": 3.7579593402378215, "percentage": 53.68, "elapsed_time": "1 day, 6:24:36", "remaining_time": "1 day, 2:14:22"}
981
+ {"current_steps": 4905, "total_steps": 9128, "loss": 0.2156, "lr": 2.0890747362965847e-05, "epoch": 3.761795166858458, "percentage": 53.74, "elapsed_time": "1 day, 6:26:14", "remaining_time": "1 day, 2:12:19"}
982
+ {"current_steps": 4910, "total_steps": 9128, "loss": 0.2351, "lr": 2.0852541554467763e-05, "epoch": 3.765630993479095, "percentage": 53.79, "elapsed_time": "1 day, 6:27:57", "remaining_time": "1 day, 2:10:20"}
983
+ {"current_steps": 4915, "total_steps": 9128, "loss": 0.2276, "lr": 2.0814332628946415e-05, "epoch": 3.7694668200997317, "percentage": 53.85, "elapsed_time": "1 day, 6:29:41", "remaining_time": "1 day, 2:08:21"}
984
+ {"current_steps": 4920, "total_steps": 9128, "loss": 0.2344, "lr": 2.0776120726099516e-05, "epoch": 3.773302646720368, "percentage": 53.9, "elapsed_time": "1 day, 6:31:32", "remaining_time": "1 day, 2:06:29"}
985
+ {"current_steps": 4925, "total_steps": 9128, "loss": 0.2256, "lr": 2.0737905985635693e-05, "epoch": 3.777138473341005, "percentage": 53.95, "elapsed_time": "1 day, 6:33:15", "remaining_time": "1 day, 2:04:29"}
986
+ {"current_steps": 4930, "total_steps": 9128, "loss": 0.2372, "lr": 2.0699688547273915e-05, "epoch": 3.780974299961642, "percentage": 54.01, "elapsed_time": "1 day, 6:34:57", "remaining_time": "1 day, 2:02:30"}
987
+ {"current_steps": 4935, "total_steps": 9128, "loss": 0.232, "lr": 2.0661468550743012e-05, "epoch": 3.7848101265822782, "percentage": 54.06, "elapsed_time": "1 day, 6:36:40", "remaining_time": "1 day, 2:00:31"}
988
+ {"current_steps": 4940, "total_steps": 9128, "loss": 0.2211, "lr": 2.062324613578119e-05, "epoch": 3.788645953202915, "percentage": 54.12, "elapsed_time": "1 day, 6:38:17", "remaining_time": "1 day, 1:58:26"}
989
+ {"current_steps": 4945, "total_steps": 9128, "loss": 0.2228, "lr": 2.0585021442135485e-05, "epoch": 3.792481779823552, "percentage": 54.17, "elapsed_time": "1 day, 6:39:58", "remaining_time": "1 day, 1:56:26"}
990
+ {"current_steps": 4950, "total_steps": 9128, "loss": 0.2188, "lr": 2.054679460956127e-05, "epoch": 3.796317606444189, "percentage": 54.23, "elapsed_time": "1 day, 6:41:33", "remaining_time": "1 day, 1:54:21"}
991
+ {"current_steps": 4955, "total_steps": 9128, "loss": 0.2192, "lr": 2.0508565777821726e-05, "epoch": 3.8001534330648257, "percentage": 54.28, "elapsed_time": "1 day, 6:43:13", "remaining_time": "1 day, 1:52:19"}
992
+ {"current_steps": 4960, "total_steps": 9128, "loss": 0.2109, "lr": 2.0470335086687353e-05, "epoch": 3.803989259685462, "percentage": 54.34, "elapsed_time": "1 day, 6:44:54", "remaining_time": "1 day, 1:50:18"}
993
+ {"current_steps": 4965, "total_steps": 9128, "loss": 0.2081, "lr": 2.0432102675935445e-05, "epoch": 3.807825086306099, "percentage": 54.39, "elapsed_time": "1 day, 6:46:32", "remaining_time": "1 day, 1:48:16"}
994
+ {"current_steps": 4970, "total_steps": 9128, "loss": 0.2184, "lr": 2.039386868534959e-05, "epoch": 3.811660912926736, "percentage": 54.45, "elapsed_time": "1 day, 6:48:11", "remaining_time": "1 day, 1:46:14"}
995
+ {"current_steps": 4975, "total_steps": 9128, "loss": 0.246, "lr": 2.035563325471915e-05, "epoch": 3.8154967395473722, "percentage": 54.5, "elapsed_time": "1 day, 6:49:47", "remaining_time": "1 day, 1:44:09"}
996
+ {"current_steps": 4980, "total_steps": 9128, "loss": 0.2202, "lr": 2.0317396523838743e-05, "epoch": 3.819332566168009, "percentage": 54.56, "elapsed_time": "1 day, 6:51:26", "remaining_time": "1 day, 1:42:07"}
997
+ {"current_steps": 4985, "total_steps": 9128, "loss": 0.2316, "lr": 2.027915863250775e-05, "epoch": 3.823168392788646, "percentage": 54.61, "elapsed_time": "1 day, 6:53:05", "remaining_time": "1 day, 1:40:05"}
998
+ {"current_steps": 4990, "total_steps": 9128, "loss": 0.2187, "lr": 2.0240919720529796e-05, "epoch": 3.827004219409283, "percentage": 54.67, "elapsed_time": "1 day, 6:54:44", "remaining_time": "1 day, 1:38:03"}
999
+ {"current_steps": 4995, "total_steps": 9128, "loss": 0.2251, "lr": 2.0202679927712224e-05, "epoch": 3.8308400460299197, "percentage": 54.72, "elapsed_time": "1 day, 6:56:28", "remaining_time": "1 day, 1:36:06"}
1000
+ {"current_steps": 5000, "total_steps": 9128, "loss": 0.2202, "lr": 2.0164439393865614e-05, "epoch": 3.834675872650556, "percentage": 54.78, "elapsed_time": "1 day, 6:58:14", "remaining_time": "1 day, 1:34:09"}
1001
+ {"current_steps": 5005, "total_steps": 9128, "loss": 0.2204, "lr": 2.012619825880325e-05, "epoch": 3.838511699271193, "percentage": 54.83, "elapsed_time": "1 day, 7:01:22", "remaining_time": "1 day, 1:33:21"}
1002
+ {"current_steps": 5010, "total_steps": 9128, "loss": 0.2245, "lr": 2.008795666234061e-05, "epoch": 3.84234752589183, "percentage": 54.89, "elapsed_time": "1 day, 7:03:02", "remaining_time": "1 day, 1:31:20"}
1003
+ {"current_steps": 5015, "total_steps": 9128, "loss": 0.2201, "lr": 2.0049714744294865e-05, "epoch": 3.8461833525124662, "percentage": 54.94, "elapsed_time": "1 day, 7:04:45", "remaining_time": "1 day, 1:29:21"}
1004
+ {"current_steps": 5020, "total_steps": 9128, "loss": 0.2163, "lr": 2.001147264448435e-05, "epoch": 3.850019179133103, "percentage": 55.0, "elapsed_time": "1 day, 7:06:26", "remaining_time": "1 day, 1:27:21"}