penfever commited on
Commit
8fb4e5f
·
verified ·
1 Parent(s): 9873734

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 sha256:2914fb9d49accbcfafb4870dc35d216b7a8f711183e68341cc84e74325ea42a8
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b360ed5e34a02e66df60d5e9c2273673464dbc7d0d6bf86467e8cbeee95636
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96b02b53ab9ebfbaecb88e51e0eaff1001de930cb6414b014fac30683057365a
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92a1de97f13e0d9ad430f74143fae0f8cb01971c27c9165910ab313c9d806e4
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:fd0974dddae5d4891e0be7b994ef5a4ab3d61fe305ed5cd8c9616cee2398b1fe
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2089fd10e827d0b708ed83125beaac859cab9dc8160ce2efdc1824d29261321e
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:e3c52e4f3556fd9c8b4eb9de924f4d3d34a217f92d91c865ae3712d9b75ddb7c
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc493238756b0935f95d0ec97a528b48c7902f739501a012063f1b9cf04ee8ca
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1902,3 +1902,40 @@
1902
  {"current_steps": 9410, "total_steps": 9625, "loss": 0.0729, "lr": 6.13407052051529e-08, "epoch": 6.844670789377956, "percentage": 97.77, "elapsed_time": "17:32:57", "remaining_time": "0:24:03"}
1903
  {"current_steps": 9415, "total_steps": 9625, "loss": 0.0799, "lr": 5.853509639138777e-08, "epoch": 6.848308475809385, "percentage": 97.82, "elapsed_time": "17:34:45", "remaining_time": "0:23:31"}
1904
  {"current_steps": 9420, "total_steps": 9625, "loss": 0.0598, "lr": 5.5795065904888926e-08, "epoch": 6.851946162240814, "percentage": 97.87, "elapsed_time": "17:36:21", "remaining_time": "0:22:59"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1902
  {"current_steps": 9410, "total_steps": 9625, "loss": 0.0729, "lr": 6.13407052051529e-08, "epoch": 6.844670789377956, "percentage": 97.77, "elapsed_time": "17:32:57", "remaining_time": "0:24:03"}
1903
  {"current_steps": 9415, "total_steps": 9625, "loss": 0.0799, "lr": 5.853509639138777e-08, "epoch": 6.848308475809385, "percentage": 97.82, "elapsed_time": "17:34:45", "remaining_time": "0:23:31"}
1904
  {"current_steps": 9420, "total_steps": 9625, "loss": 0.0598, "lr": 5.5795065904888926e-08, "epoch": 6.851946162240814, "percentage": 97.87, "elapsed_time": "17:36:21", "remaining_time": "0:22:59"}
1905
+ {"current_steps": 9425, "total_steps": 9625, "loss": 0.0777, "lr": 5.312062275636187e-08, "epoch": 6.855583848672245, "percentage": 97.92, "elapsed_time": "17:37:57", "remaining_time": "0:22:26"}
1906
+ {"current_steps": 9430, "total_steps": 9625, "loss": 0.0756, "lr": 5.051177574082244e-08, "epoch": 6.859221535103674, "percentage": 97.97, "elapsed_time": "17:39:34", "remaining_time": "0:21:54"}
1907
+ {"current_steps": 9435, "total_steps": 9625, "loss": 0.0828, "lr": 4.796853343757013e-08, "epoch": 6.862859221535103, "percentage": 98.03, "elapsed_time": "17:41:22", "remaining_time": "0:21:22"}
1908
+ {"current_steps": 9440, "total_steps": 9625, "loss": 0.0786, "lr": 4.5490904210161443e-08, "epoch": 6.866496907966534, "percentage": 98.08, "elapsed_time": "17:43:05", "remaining_time": "0:20:50"}
1909
+ {"current_steps": 9445, "total_steps": 9625, "loss": 0.082, "lr": 4.30788962063855e-08, "epoch": 6.870134594397963, "percentage": 98.13, "elapsed_time": "17:44:35", "remaining_time": "0:20:17"}
1910
+ {"current_steps": 9450, "total_steps": 9625, "loss": 0.0755, "lr": 4.073251735822403e-08, "epoch": 6.873772280829392, "percentage": 98.18, "elapsed_time": "17:46:16", "remaining_time": "0:19:44"}
1911
+ {"current_steps": 9455, "total_steps": 9625, "loss": 0.082, "lr": 3.845177538184697e-08, "epoch": 6.877409967260822, "percentage": 98.23, "elapsed_time": "17:48:05", "remaining_time": "0:19:12"}
1912
+ {"current_steps": 9460, "total_steps": 9625, "loss": 0.0764, "lr": 3.6236677777561345e-08, "epoch": 6.881047653692252, "percentage": 98.29, "elapsed_time": "17:49:41", "remaining_time": "0:18:39"}
1913
+ {"current_steps": 9465, "total_steps": 9625, "loss": 0.0661, "lr": 3.408723182981355e-08, "epoch": 6.884685340123681, "percentage": 98.34, "elapsed_time": "17:51:14", "remaining_time": "0:18:06"}
1914
+ {"current_steps": 9470, "total_steps": 9625, "loss": 0.0847, "lr": 3.200344460713822e-08, "epoch": 6.888323026555111, "percentage": 98.39, "elapsed_time": "17:53:10", "remaining_time": "0:17:33"}
1915
+ {"current_steps": 9475, "total_steps": 9625, "loss": 0.075, "lr": 2.9985322962160504e-08, "epoch": 6.89196071298654, "percentage": 98.44, "elapsed_time": "17:54:51", "remaining_time": "0:17:00"}
1916
+ {"current_steps": 9480, "total_steps": 9625, "loss": 0.067, "lr": 2.8032873531553818e-08, "epoch": 6.89559839941797, "percentage": 98.49, "elapsed_time": "17:56:34", "remaining_time": "0:16:27"}
1917
+ {"current_steps": 9485, "total_steps": 9625, "loss": 0.0704, "lr": 2.61461027360288e-08, "epoch": 6.8992360858494, "percentage": 98.55, "elapsed_time": "17:58:36", "remaining_time": "0:15:55"}
1918
+ {"current_steps": 9490, "total_steps": 9625, "loss": 0.065, "lr": 2.4325016780308853e-08, "epoch": 6.902873772280829, "percentage": 98.6, "elapsed_time": "18:00:16", "remaining_time": "0:15:22"}
1919
+ {"current_steps": 9495, "total_steps": 9625, "loss": 0.0602, "lr": 2.256962165311016e-08, "epoch": 6.906511458712259, "percentage": 98.65, "elapsed_time": "18:01:52", "remaining_time": "0:14:48"}
1920
+ {"current_steps": 9500, "total_steps": 9625, "loss": 0.0811, "lr": 2.0879923127123946e-08, "epoch": 6.910149145143689, "percentage": 98.7, "elapsed_time": "18:03:33", "remaining_time": "0:14:15"}
1921
+ {"current_steps": 9505, "total_steps": 9625, "loss": 0.0919, "lr": 1.9255926758989795e-08, "epoch": 6.913786831575118, "percentage": 98.75, "elapsed_time": "18:05:26", "remaining_time": "0:13:42"}
1922
+ {"current_steps": 9510, "total_steps": 9625, "loss": 0.0707, "lr": 1.76976378892868e-08, "epoch": 6.9174245180065475, "percentage": 98.81, "elapsed_time": "18:07:02", "remaining_time": "0:13:08"}
1923
+ {"current_steps": 9515, "total_steps": 9625, "loss": 0.0798, "lr": 1.6205061642513565e-08, "epoch": 6.921062204437978, "percentage": 98.86, "elapsed_time": "18:08:42", "remaining_time": "0:12:35"}
1924
+ {"current_steps": 9520, "total_steps": 9625, "loss": 0.0967, "lr": 1.4778202927068219e-08, "epoch": 6.924699890869407, "percentage": 98.91, "elapsed_time": "18:10:20", "remaining_time": "0:12:01"}
1925
+ {"current_steps": 9525, "total_steps": 9625, "loss": 0.0682, "lr": 1.3417066435232885e-08, "epoch": 6.928337577300836, "percentage": 98.96, "elapsed_time": "18:11:52", "remaining_time": "0:11:27"}
1926
+ {"current_steps": 9530, "total_steps": 9625, "loss": 0.0745, "lr": 1.2121656643164781e-08, "epoch": 6.931975263732266, "percentage": 99.01, "elapsed_time": "18:13:27", "remaining_time": "0:10:54"}
1927
+ {"current_steps": 9535, "total_steps": 9625, "loss": 0.0698, "lr": 1.0891977810867372e-08, "epoch": 6.935612950163696, "percentage": 99.06, "elapsed_time": "18:15:06", "remaining_time": "0:10:20"}
1928
+ {"current_steps": 9540, "total_steps": 9625, "loss": 0.1126, "lr": 9.728033982192575e-09, "epoch": 6.939250636595125, "percentage": 99.12, "elapsed_time": "18:16:56", "remaining_time": "0:09:46"}
1929
+ {"current_steps": 9545, "total_steps": 9625, "loss": 0.0887, "lr": 8.629828984818568e-09, "epoch": 6.942888323026555, "percentage": 99.17, "elapsed_time": "18:19:10", "remaining_time": "0:09:12"}
1930
+ {"current_steps": 9550, "total_steps": 9625, "loss": 0.0709, "lr": 7.597366430234232e-09, "epoch": 6.946526009457985, "percentage": 99.22, "elapsed_time": "18:20:49", "remaining_time": "0:08:38"}
1931
+ {"current_steps": 9555, "total_steps": 9625, "loss": 0.0705, "lr": 6.630649713739168e-09, "epoch": 6.950163695889414, "percentage": 99.27, "elapsed_time": "18:22:21", "remaining_time": "0:08:04"}
1932
+ {"current_steps": 9560, "total_steps": 9625, "loss": 0.0695, "lr": 5.729682014417037e-09, "epoch": 6.953801382320844, "percentage": 99.32, "elapsed_time": "18:23:55", "remaining_time": "0:07:30"}
1933
+ {"current_steps": 9565, "total_steps": 9625, "loss": 0.0621, "lr": 4.89446629514001e-09, "epoch": 6.957439068752274, "percentage": 99.38, "elapsed_time": "18:25:24", "remaining_time": "0:06:56"}
1934
+ {"current_steps": 9570, "total_steps": 9625, "loss": 0.089, "lr": 4.125005302548779e-09, "epoch": 6.961076755183703, "percentage": 99.43, "elapsed_time": "18:26:55", "remaining_time": "0:06:21"}
1935
+ {"current_steps": 9575, "total_steps": 9625, "loss": 0.063, "lr": 3.421301567045898e-09, "epoch": 6.964714441615133, "percentage": 99.48, "elapsed_time": "18:28:31", "remaining_time": "0:05:47"}
1936
+ {"current_steps": 9580, "total_steps": 9625, "loss": 0.0689, "lr": 2.783357402793563e-09, "epoch": 6.968352128046562, "percentage": 99.53, "elapsed_time": "18:30:01", "remaining_time": "0:05:12"}
1937
+ {"current_steps": 9585, "total_steps": 9625, "loss": 0.0697, "lr": 2.211174907693625e-09, "epoch": 6.971989814477992, "percentage": 99.58, "elapsed_time": "18:31:40", "remaining_time": "0:04:38"}
1938
+ {"current_steps": 9590, "total_steps": 9625, "loss": 0.0752, "lr": 1.7047559633920353e-09, "epoch": 6.975627500909422, "percentage": 99.64, "elapsed_time": "18:33:32", "remaining_time": "0:04:03"}
1939
+ {"current_steps": 9595, "total_steps": 9625, "loss": 0.0629, "lr": 1.26410223527218e-09, "epoch": 6.979265187340851, "percentage": 99.69, "elapsed_time": "18:35:18", "remaining_time": "0:03:29"}
1940
+ {"current_steps": 9600, "total_steps": 9625, "loss": 0.0703, "lr": 8.89215172437119e-10, "epoch": 6.9829028737722805, "percentage": 99.74, "elapsed_time": "18:37:05", "remaining_time": "0:02:54"}
1941
+ {"current_steps": 9605, "total_steps": 9625, "loss": 0.0963, "lr": 5.800960077206874e-10, "epoch": 6.986540560203711, "percentage": 99.79, "elapsed_time": "18:40:47", "remaining_time": "0:02:20"}