penfever commited on
Commit
5aeb277
·
verified ·
1 Parent(s): ab0cdc6

Training in progress, step 9600

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:098c66a66fcc14deabc66f12753bff071d233722893c0c17f511a49e6e717fd0
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ed496a0d512c055a1701e27ef8914242bc8007a781a9907a08a6ade389e9cd
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:eb67372fcdbbaf294b0722aff8d566efb15a7c96c679f80eb5e6871e84dc7c20
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9b2aefc04e03dc16b5a7b4e6708424dcb4dcad4a5ce2ae386a231b902d0a3b
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bbb6742468e75881577517d19dc58eaac8d938d0ae84351bd8f0ac8ffd2b1fa
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ebe1635d6057f894ee88687ae70a700788d2dda1275e998b275ad8ad2fa43f
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:f8676e4fcdc1daafc8b713f5f82f9295a64707eddee55386857a392f4ba8900b
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa22c7dde35b88cfc4258517540773eb2bb4936a7fe43c2756384eda9994a91
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1892,3 +1892,43 @@
1892
  {"current_steps": 9390, "total_steps": 9625, "loss": 0.1898, "lr": 7.32187359714831e-08, "epoch": 6.830120043652237, "percentage": 97.56, "elapsed_time": "14:58:21", "remaining_time": "0:22:28"}
1893
  {"current_steps": 9395, "total_steps": 9625, "loss": 0.1931, "lr": 7.015090826835603e-08, "epoch": 6.833757730083667, "percentage": 97.61, "elapsed_time": "15:00:01", "remaining_time": "0:22:02"}
1894
  {"current_steps": 9400, "total_steps": 9625, "loss": 0.1869, "lr": 6.714862069342021e-08, "epoch": 6.837395416515096, "percentage": 97.66, "elapsed_time": "15:01:42", "remaining_time": "0:21:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1892
  {"current_steps": 9390, "total_steps": 9625, "loss": 0.1898, "lr": 7.32187359714831e-08, "epoch": 6.830120043652237, "percentage": 97.56, "elapsed_time": "14:58:21", "remaining_time": "0:22:28"}
1893
  {"current_steps": 9395, "total_steps": 9625, "loss": 0.1931, "lr": 7.015090826835603e-08, "epoch": 6.833757730083667, "percentage": 97.61, "elapsed_time": "15:00:01", "remaining_time": "0:22:02"}
1894
  {"current_steps": 9400, "total_steps": 9625, "loss": 0.1869, "lr": 6.714862069342021e-08, "epoch": 6.837395416515096, "percentage": 97.66, "elapsed_time": "15:01:42", "remaining_time": "0:21:35"}
1895
+ {"current_steps": 9405, "total_steps": 9625, "loss": 0.1922, "lr": 6.421188311982684e-08, "epoch": 6.841033102946526, "percentage": 97.71, "elapsed_time": "15:04:56", "remaining_time": "0:21:10"}
1896
+ {"current_steps": 9410, "total_steps": 9625, "loss": 0.1855, "lr": 6.13407052051529e-08, "epoch": 6.844670789377956, "percentage": 97.77, "elapsed_time": "15:06:37", "remaining_time": "0:20:42"}
1897
+ {"current_steps": 9415, "total_steps": 9625, "loss": 0.1773, "lr": 5.853509639138777e-08, "epoch": 6.848308475809385, "percentage": 97.82, "elapsed_time": "15:08:22", "remaining_time": "0:20:15"}
1898
+ {"current_steps": 9420, "total_steps": 9625, "loss": 0.1935, "lr": 5.5795065904888926e-08, "epoch": 6.851946162240814, "percentage": 97.87, "elapsed_time": "15:09:58", "remaining_time": "0:19:48"}
1899
+ {"current_steps": 9425, "total_steps": 9625, "loss": 0.1805, "lr": 5.312062275636187e-08, "epoch": 6.855583848672245, "percentage": 97.92, "elapsed_time": "15:11:39", "remaining_time": "0:19:20"}
1900
+ {"current_steps": 9430, "total_steps": 9625, "loss": 0.1889, "lr": 5.051177574082244e-08, "epoch": 6.859221535103674, "percentage": 97.97, "elapsed_time": "15:13:21", "remaining_time": "0:18:53"}
1901
+ {"current_steps": 9435, "total_steps": 9625, "loss": 0.1973, "lr": 4.796853343757013e-08, "epoch": 6.862859221535103, "percentage": 98.03, "elapsed_time": "15:15:01", "remaining_time": "0:18:25"}
1902
+ {"current_steps": 9440, "total_steps": 9625, "loss": 0.1899, "lr": 4.5490904210161443e-08, "epoch": 6.866496907966534, "percentage": 98.08, "elapsed_time": "15:16:42", "remaining_time": "0:17:57"}
1903
+ {"current_steps": 9445, "total_steps": 9625, "loss": 0.2055, "lr": 4.30788962063855e-08, "epoch": 6.870134594397963, "percentage": 98.13, "elapsed_time": "15:18:18", "remaining_time": "0:17:30"}
1904
+ {"current_steps": 9450, "total_steps": 9625, "loss": 0.1872, "lr": 4.073251735822403e-08, "epoch": 6.873772280829392, "percentage": 98.18, "elapsed_time": "15:19:53", "remaining_time": "0:17:02"}
1905
+ {"current_steps": 9455, "total_steps": 9625, "loss": 0.2017, "lr": 3.845177538184697e-08, "epoch": 6.877409967260822, "percentage": 98.23, "elapsed_time": "15:21:34", "remaining_time": "0:16:34"}
1906
+ {"current_steps": 9460, "total_steps": 9625, "loss": 0.2011, "lr": 3.6236677777561345e-08, "epoch": 6.881047653692252, "percentage": 98.29, "elapsed_time": "15:23:14", "remaining_time": "0:16:06"}
1907
+ {"current_steps": 9465, "total_steps": 9625, "loss": 0.1963, "lr": 3.408723182981355e-08, "epoch": 6.884685340123681, "percentage": 98.34, "elapsed_time": "15:24:52", "remaining_time": "0:15:38"}
1908
+ {"current_steps": 9470, "total_steps": 9625, "loss": 0.2002, "lr": 3.200344460713822e-08, "epoch": 6.888323026555111, "percentage": 98.39, "elapsed_time": "15:26:39", "remaining_time": "0:15:10"}
1909
+ {"current_steps": 9475, "total_steps": 9625, "loss": 0.1913, "lr": 2.9985322962160504e-08, "epoch": 6.89196071298654, "percentage": 98.44, "elapsed_time": "15:28:17", "remaining_time": "0:14:41"}
1910
+ {"current_steps": 9480, "total_steps": 9625, "loss": 0.193, "lr": 2.8032873531553818e-08, "epoch": 6.89559839941797, "percentage": 98.49, "elapsed_time": "15:29:51", "remaining_time": "0:14:13"}
1911
+ {"current_steps": 9485, "total_steps": 9625, "loss": 0.1947, "lr": 2.61461027360288e-08, "epoch": 6.8992360858494, "percentage": 98.55, "elapsed_time": "15:31:30", "remaining_time": "0:13:44"}
1912
+ {"current_steps": 9490, "total_steps": 9625, "loss": 0.1833, "lr": 2.4325016780308853e-08, "epoch": 6.902873772280829, "percentage": 98.6, "elapsed_time": "15:33:10", "remaining_time": "0:13:16"}
1913
+ {"current_steps": 9495, "total_steps": 9625, "loss": 0.1833, "lr": 2.256962165311016e-08, "epoch": 6.906511458712259, "percentage": 98.65, "elapsed_time": "15:34:55", "remaining_time": "0:12:48"}
1914
+ {"current_steps": 9500, "total_steps": 9625, "loss": 0.1898, "lr": 2.0879923127123946e-08, "epoch": 6.910149145143689, "percentage": 98.7, "elapsed_time": "15:36:36", "remaining_time": "0:12:19"}
1915
+ {"current_steps": 9505, "total_steps": 9625, "loss": 0.1875, "lr": 1.9255926758989795e-08, "epoch": 6.913786831575118, "percentage": 98.75, "elapsed_time": "15:38:18", "remaining_time": "0:11:50"}
1916
+ {"current_steps": 9510, "total_steps": 9625, "loss": 0.1995, "lr": 1.76976378892868e-08, "epoch": 6.9174245180065475, "percentage": 98.81, "elapsed_time": "15:39:54", "remaining_time": "0:11:21"}
1917
+ {"current_steps": 9515, "total_steps": 9625, "loss": 0.1906, "lr": 1.6205061642513565e-08, "epoch": 6.921062204437978, "percentage": 98.86, "elapsed_time": "15:41:33", "remaining_time": "0:10:53"}
1918
+ {"current_steps": 9520, "total_steps": 9625, "loss": 0.1927, "lr": 1.4778202927068219e-08, "epoch": 6.924699890869407, "percentage": 98.91, "elapsed_time": "15:43:15", "remaining_time": "0:10:24"}
1919
+ {"current_steps": 9525, "total_steps": 9625, "loss": 0.1927, "lr": 1.3417066435232885e-08, "epoch": 6.928337577300836, "percentage": 98.96, "elapsed_time": "15:44:49", "remaining_time": "0:09:55"}
1920
+ {"current_steps": 9530, "total_steps": 9625, "loss": 0.1956, "lr": 1.2121656643164781e-08, "epoch": 6.931975263732266, "percentage": 99.01, "elapsed_time": "15:46:33", "remaining_time": "0:09:26"}
1921
+ {"current_steps": 9535, "total_steps": 9625, "loss": 0.1874, "lr": 1.0891977810867372e-08, "epoch": 6.935612950163696, "percentage": 99.06, "elapsed_time": "15:48:23", "remaining_time": "0:08:57"}
1922
+ {"current_steps": 9540, "total_steps": 9625, "loss": 0.1781, "lr": 9.728033982192575e-09, "epoch": 6.939250636595125, "percentage": 99.12, "elapsed_time": "15:50:07", "remaining_time": "0:08:27"}
1923
+ {"current_steps": 9545, "total_steps": 9625, "loss": 0.1855, "lr": 8.629828984818568e-09, "epoch": 6.942888323026555, "percentage": 99.17, "elapsed_time": "15:51:50", "remaining_time": "0:07:58"}
1924
+ {"current_steps": 9550, "total_steps": 9625, "loss": 0.1848, "lr": 7.597366430234232e-09, "epoch": 6.946526009457985, "percentage": 99.22, "elapsed_time": "15:53:30", "remaining_time": "0:07:29"}
1925
+ {"current_steps": 9555, "total_steps": 9625, "loss": 0.1783, "lr": 6.630649713739168e-09, "epoch": 6.950163695889414, "percentage": 99.27, "elapsed_time": "15:55:11", "remaining_time": "0:06:59"}
1926
+ {"current_steps": 9560, "total_steps": 9625, "loss": 0.176, "lr": 5.729682014417037e-09, "epoch": 6.953801382320844, "percentage": 99.32, "elapsed_time": "15:56:54", "remaining_time": "0:06:30"}
1927
+ {"current_steps": 9565, "total_steps": 9625, "loss": 0.1824, "lr": 4.89446629514001e-09, "epoch": 6.957439068752274, "percentage": 99.38, "elapsed_time": "15:58:32", "remaining_time": "0:06:00"}
1928
+ {"current_steps": 9570, "total_steps": 9625, "loss": 0.1783, "lr": 4.125005302548779e-09, "epoch": 6.961076755183703, "percentage": 99.43, "elapsed_time": "16:00:14", "remaining_time": "0:05:31"}
1929
+ {"current_steps": 9575, "total_steps": 9625, "loss": 0.1977, "lr": 3.421301567045898e-09, "epoch": 6.964714441615133, "percentage": 99.48, "elapsed_time": "16:01:54", "remaining_time": "0:05:01"}
1930
+ {"current_steps": 9580, "total_steps": 9625, "loss": 0.1852, "lr": 2.783357402793563e-09, "epoch": 6.968352128046562, "percentage": 99.53, "elapsed_time": "16:03:28", "remaining_time": "0:04:31"}
1931
+ {"current_steps": 9585, "total_steps": 9625, "loss": 0.1858, "lr": 2.211174907693625e-09, "epoch": 6.971989814477992, "percentage": 99.58, "elapsed_time": "16:05:09", "remaining_time": "0:04:01"}
1932
+ {"current_steps": 9590, "total_steps": 9625, "loss": 0.1767, "lr": 1.7047559633920353e-09, "epoch": 6.975627500909422, "percentage": 99.64, "elapsed_time": "16:06:46", "remaining_time": "0:03:31"}
1933
+ {"current_steps": 9595, "total_steps": 9625, "loss": 0.187, "lr": 1.26410223527218e-09, "epoch": 6.979265187340851, "percentage": 99.69, "elapsed_time": "16:08:22", "remaining_time": "0:03:01"}
1934
+ {"current_steps": 9600, "total_steps": 9625, "loss": 0.1851, "lr": 8.89215172437119e-10, "epoch": 6.9829028737722805, "percentage": 99.74, "elapsed_time": "16:10:01", "remaining_time": "0:02:31"}