penfever commited on
Commit
c7a8a04
·
verified ·
1 Parent(s): ff690d3

Training in progress, step 4200

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b1bf5647ba0bdb40aa0eb688d7ab15d76b1e3783facc7ee3092512540b2386
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a019bed817cd4ad63b8ab9ee0c88c5b17228f5bbf6955712e2ea9684a500f9f4
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:721f043ecb9035ea61171024da4fa407d2cb37d3ecf9847d61868ba38f8edf88
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:915ad499882a980067b2dc1d394fd0111dfbadfa613461d855f025609b33aa99
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:373b6435a895496f9b6aea8d0071ed9abb01e96b746f0f4fba7ae666b6ce5d40
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f2ebd0b3a358e8b5a6f440dc67d2d66cae84bbaaf5c3015246514a2d7c7bfb
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a93c7ee9827ad2246a12a2c9b214f41a619e7df94a96b320d0ab537b2661e9f
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a0422fe27c384079adc03eaff66171a437b0fb53e2c0816541b5a831151202
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -799,3 +799,45 @@
799
  {"current_steps": 3995, "total_steps": 9128, "loss": 0.1847, "lr": 2.765101873310765e-05, "epoch": 3.06367472190257, "percentage": 43.77, "elapsed_time": "1 day, 0:58:28", "remaining_time": "1 day, 8:05:19"}
800
  {"current_steps": 4000, "total_steps": 9128, "loss": 0.1901, "lr": 2.761567152961115e-05, "epoch": 3.067510548523207, "percentage": 43.82, "elapsed_time": "1 day, 1:01:24", "remaining_time": "1 day, 8:04:47"}
801
  {"current_steps": 4005, "total_steps": 9128, "loss": 0.2044, "lr": 2.758029648204635e-05, "epoch": 3.0713463751438437, "percentage": 43.88, "elapsed_time": "1 day, 1:05:22", "remaining_time": "1 day, 8:05:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
799
  {"current_steps": 3995, "total_steps": 9128, "loss": 0.1847, "lr": 2.765101873310765e-05, "epoch": 3.06367472190257, "percentage": 43.77, "elapsed_time": "1 day, 0:58:28", "remaining_time": "1 day, 8:05:19"}
800
  {"current_steps": 4000, "total_steps": 9128, "loss": 0.1901, "lr": 2.761567152961115e-05, "epoch": 3.067510548523207, "percentage": 43.82, "elapsed_time": "1 day, 1:01:24", "remaining_time": "1 day, 8:04:47"}
801
  {"current_steps": 4005, "total_steps": 9128, "loss": 0.2044, "lr": 2.758029648204635e-05, "epoch": 3.0713463751438437, "percentage": 43.88, "elapsed_time": "1 day, 1:05:22", "remaining_time": "1 day, 8:05:36"}
802
+ {"current_steps": 4010, "total_steps": 9128, "loss": 0.2014, "lr": 2.754489371974986e-05, "epoch": 3.07518220176448, "percentage": 43.93, "elapsed_time": "1 day, 1:07:54", "remaining_time": "1 day, 8:04:33"}
803
+ {"current_steps": 4015, "total_steps": 9128, "loss": 0.1687, "lr": 2.7509463372159636e-05, "epoch": 3.079018028385117, "percentage": 43.99, "elapsed_time": "1 day, 1:10:37", "remaining_time": "1 day, 8:03:44"}
804
+ {"current_steps": 4020, "total_steps": 9128, "loss": 0.184, "lr": 2.7474005568814495e-05, "epoch": 3.082853855005754, "percentage": 44.04, "elapsed_time": "1 day, 1:13:31", "remaining_time": "1 day, 8:03:08"}
805
+ {"current_steps": 4025, "total_steps": 9128, "loss": 0.1874, "lr": 2.743852043935363e-05, "epoch": 3.0866896816263907, "percentage": 44.1, "elapsed_time": "1 day, 1:16:22", "remaining_time": "1 day, 8:02:30"}
806
+ {"current_steps": 4030, "total_steps": 9128, "loss": 0.1928, "lr": 2.7403008113516127e-05, "epoch": 3.090525508247027, "percentage": 44.15, "elapsed_time": "1 day, 1:19:09", "remaining_time": "1 day, 8:01:44"}
807
+ {"current_steps": 4035, "total_steps": 9128, "loss": 0.1866, "lr": 2.736746872114053e-05, "epoch": 3.094361334867664, "percentage": 44.2, "elapsed_time": "1 day, 1:22:11", "remaining_time": "1 day, 8:01:19"}
808
+ {"current_steps": 4040, "total_steps": 9128, "loss": 0.177, "lr": 2.7331902392164332e-05, "epoch": 3.098197161488301, "percentage": 44.26, "elapsed_time": "1 day, 1:25:10", "remaining_time": "1 day, 8:00:48"}
809
+ {"current_steps": 4045, "total_steps": 9128, "loss": 0.1647, "lr": 2.7296309256623508e-05, "epoch": 3.1020329881089377, "percentage": 44.31, "elapsed_time": "1 day, 1:28:12", "remaining_time": "1 day, 8:00:21"}
810
+ {"current_steps": 4050, "total_steps": 9128, "loss": 0.1678, "lr": 2.7260689444652048e-05, "epoch": 3.105868814729574, "percentage": 44.37, "elapsed_time": "1 day, 1:31:04", "remaining_time": "1 day, 7:59:42"}
811
+ {"current_steps": 4055, "total_steps": 9128, "loss": 0.1879, "lr": 2.7225043086481463e-05, "epoch": 3.109704641350211, "percentage": 44.42, "elapsed_time": "1 day, 1:33:57", "remaining_time": "1 day, 7:59:03"}
812
+ {"current_steps": 4060, "total_steps": 9128, "loss": 0.1787, "lr": 2.7189370312440343e-05, "epoch": 3.113540467970848, "percentage": 44.48, "elapsed_time": "1 day, 1:36:08", "remaining_time": "1 day, 7:57:31"}
813
+ {"current_steps": 4065, "total_steps": 9128, "loss": 0.1976, "lr": 2.715367125295383e-05, "epoch": 3.1173762945914847, "percentage": 44.53, "elapsed_time": "1 day, 1:38:56", "remaining_time": "1 day, 7:56:45"}
814
+ {"current_steps": 4070, "total_steps": 9128, "loss": 0.2004, "lr": 2.7117946038543203e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "1 day, 1:41:54", "remaining_time": "1 day, 7:56:13"}
815
+ {"current_steps": 4075, "total_steps": 9128, "loss": 0.1989, "lr": 2.7082194799825338e-05, "epoch": 3.125047947832758, "percentage": 44.64, "elapsed_time": "1 day, 1:44:45", "remaining_time": "1 day, 7:55:30"}
816
+ {"current_steps": 4080, "total_steps": 9128, "loss": 0.1847, "lr": 2.704641766751227e-05, "epoch": 3.128883774453395, "percentage": 44.7, "elapsed_time": "1 day, 1:47:36", "remaining_time": "1 day, 7:54:47"}
817
+ {"current_steps": 4085, "total_steps": 9128, "loss": 0.1913, "lr": 2.701061477241071e-05, "epoch": 3.1327196010740312, "percentage": 44.75, "elapsed_time": "1 day, 1:50:38", "remaining_time": "1 day, 7:54:17"}
818
+ {"current_steps": 4090, "total_steps": 9128, "loss": 0.1923, "lr": 2.6974786245421555e-05, "epoch": 3.136555427694668, "percentage": 44.81, "elapsed_time": "1 day, 1:53:37", "remaining_time": "1 day, 7:53:44"}
819
+ {"current_steps": 4095, "total_steps": 9128, "loss": 0.1904, "lr": 2.693893221753942e-05, "epoch": 3.140391254315305, "percentage": 44.86, "elapsed_time": "1 day, 1:56:35", "remaining_time": "1 day, 7:53:08"}
820
+ {"current_steps": 4100, "total_steps": 9128, "loss": 0.1931, "lr": 2.6903052819852163e-05, "epoch": 3.144227080935942, "percentage": 44.92, "elapsed_time": "1 day, 1:59:39", "remaining_time": "1 day, 7:52:40"}
821
+ {"current_steps": 4105, "total_steps": 9128, "loss": 0.1933, "lr": 2.6867148183540375e-05, "epoch": 3.1480629075565782, "percentage": 44.97, "elapsed_time": "1 day, 2:02:37", "remaining_time": "1 day, 7:52:04"}
822
+ {"current_steps": 4110, "total_steps": 9128, "loss": 0.1943, "lr": 2.683121843987695e-05, "epoch": 3.151898734177215, "percentage": 45.03, "elapsed_time": "1 day, 2:05:22", "remaining_time": "1 day, 7:51:12"}
823
+ {"current_steps": 4115, "total_steps": 9128, "loss": 0.1903, "lr": 2.6795263720226548e-05, "epoch": 3.155734560797852, "percentage": 45.08, "elapsed_time": "1 day, 2:08:15", "remaining_time": "1 day, 7:50:29"}
824
+ {"current_steps": 4120, "total_steps": 9128, "loss": 0.163, "lr": 2.675928415604519e-05, "epoch": 3.159570387418489, "percentage": 45.14, "elapsed_time": "1 day, 2:10:21", "remaining_time": "1 day, 7:48:48"}
825
+ {"current_steps": 4125, "total_steps": 9128, "loss": 0.193, "lr": 2.6723279878879683e-05, "epoch": 3.1634062140391253, "percentage": 45.19, "elapsed_time": "1 day, 2:13:07", "remaining_time": "1 day, 7:47:57"}
826
+ {"current_steps": 4130, "total_steps": 9128, "loss": 0.1853, "lr": 2.668725102036721e-05, "epoch": 3.167242040659762, "percentage": 45.25, "elapsed_time": "1 day, 2:15:55", "remaining_time": "1 day, 7:47:08"}
827
+ {"current_steps": 4135, "total_steps": 9128, "loss": 0.1915, "lr": 2.665119771223484e-05, "epoch": 3.171077867280399, "percentage": 45.3, "elapsed_time": "1 day, 2:18:51", "remaining_time": "1 day, 7:46:27"}
828
+ {"current_steps": 4140, "total_steps": 9128, "loss": 0.1838, "lr": 2.661512008629903e-05, "epoch": 3.174913693901036, "percentage": 45.35, "elapsed_time": "1 day, 2:21:49", "remaining_time": "1 day, 7:45:49"}
829
+ {"current_steps": 4145, "total_steps": 9128, "loss": 0.1842, "lr": 2.6579018274465113e-05, "epoch": 3.1787495205216723, "percentage": 45.41, "elapsed_time": "1 day, 2:24:44", "remaining_time": "1 day, 7:45:07"}
830
+ {"current_steps": 4150, "total_steps": 9128, "loss": 0.1936, "lr": 2.6542892408726886e-05, "epoch": 3.182585347142309, "percentage": 45.46, "elapsed_time": "1 day, 2:27:45", "remaining_time": "1 day, 7:44:33"}
831
+ {"current_steps": 4155, "total_steps": 9128, "loss": 0.193, "lr": 2.6506742621166086e-05, "epoch": 3.186421173762946, "percentage": 45.52, "elapsed_time": "1 day, 2:30:28", "remaining_time": "1 day, 7:43:36"}
832
+ {"current_steps": 4160, "total_steps": 9128, "loss": 0.1577, "lr": 2.64705690439519e-05, "epoch": 3.190257000383583, "percentage": 45.57, "elapsed_time": "1 day, 2:32:37", "remaining_time": "1 day, 7:41:57"}
833
+ {"current_steps": 4165, "total_steps": 9128, "loss": 0.1856, "lr": 2.64343718093405e-05, "epoch": 3.1940928270042193, "percentage": 45.63, "elapsed_time": "1 day, 2:35:21", "remaining_time": "1 day, 7:41:01"}
834
+ {"current_steps": 4170, "total_steps": 9128, "loss": 0.1864, "lr": 2.6398151049674542e-05, "epoch": 3.197928653624856, "percentage": 45.68, "elapsed_time": "1 day, 2:38:16", "remaining_time": "1 day, 7:40:17"}
835
+ {"current_steps": 4175, "total_steps": 9128, "loss": 0.1881, "lr": 2.6361906897382716e-05, "epoch": 3.201764480245493, "percentage": 45.74, "elapsed_time": "1 day, 2:41:00", "remaining_time": "1 day, 7:39:21"}
836
+ {"current_steps": 4180, "total_steps": 9128, "loss": 0.1791, "lr": 2.6325639484979225e-05, "epoch": 3.20560030686613, "percentage": 45.79, "elapsed_time": "1 day, 2:43:45", "remaining_time": "1 day, 7:38:25"}
837
+ {"current_steps": 4185, "total_steps": 9128, "loss": 0.1858, "lr": 2.6289348945063306e-05, "epoch": 3.2094361334867663, "percentage": 45.85, "elapsed_time": "1 day, 2:46:39", "remaining_time": "1 day, 7:37:39"}
838
+ {"current_steps": 4190, "total_steps": 9128, "loss": 0.1835, "lr": 2.6253035410318775e-05, "epoch": 3.213271960107403, "percentage": 45.9, "elapsed_time": "1 day, 2:49:35", "remaining_time": "1 day, 7:36:56"}
839
+ {"current_steps": 4195, "total_steps": 9128, "loss": 0.1949, "lr": 2.62166990135135e-05, "epoch": 3.21710778672804, "percentage": 45.96, "elapsed_time": "1 day, 2:50:51", "remaining_time": "1 day, 7:34:14"}
840
+ {"current_steps": 4200, "total_steps": 9128, "loss": 0.175, "lr": 2.618033988749895e-05, "epoch": 3.220943613348677, "percentage": 46.01, "elapsed_time": "1 day, 2:52:05", "remaining_time": "1 day, 7:31:31"}
841
+ {"current_steps": 4205, "total_steps": 9128, "loss": 0.1714, "lr": 2.6143958165209695e-05, "epoch": 3.2247794399693133, "percentage": 46.07, "elapsed_time": "1 day, 2:54:37", "remaining_time": "1 day, 7:30:18"}
842
+ {"current_steps": 4210, "total_steps": 9128, "loss": 0.1685, "lr": 2.6107553979662906e-05, "epoch": 3.22861526658995, "percentage": 46.12, "elapsed_time": "1 day, 2:55:52", "remaining_time": "1 day, 7:27:36"}
843
+ {"current_steps": 4215, "total_steps": 9128, "loss": 0.1774, "lr": 2.60711274639579e-05, "epoch": 3.232451093210587, "percentage": 46.18, "elapsed_time": "1 day, 2:57:12", "remaining_time": "1 day, 7:25:00"}