yuzhounie commited on
Commit
ee68de7
·
verified ·
1 Parent(s): 234207a

Training in progress, step 40

Browse files
model-00001-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfc739692e04c2868b12eeb5686732c3963ae21aee96903d5dd35a1857d03b09
3
  size 4932307584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b4d005053283735004cf0f9302a3c8c5a7801c957c7abe0aff7bf80f2ad1ba
3
  size 4932307584
model-00002-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fbb2a957d3fc50a35c5c7e8d07f0395373fce2b1c90475fdfd88796681036d6
3
  size 4875989696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e8f3864b98de6f370aa6251156cbd100d57101b02243f243774f1532b6676c
3
  size 4875989696
model-00003-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80a75386266b5728d6fe41bada1e7acc4236f9da4acaad3b8e42c39d9717e5ee
3
  size 4875989720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b67ab8b02cf67bdf3bbe395abfaf95ab955292290be30249475b389c2850029a
3
  size 4875989720
model-00004-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9ccf58c3898cd3c828d35e93d14c43b88c81db85a7c03db6a7852c1fe1e7c00
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b2493ed2d8e155e412a72882622c232985901982569a7566f86e98e6ce6950
3
  size 4875989752
model-00005-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c97c992ba415564f2aa5047603e632db84b9771d0ca1a255be520e68bdb60188
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:387acf317d672a34763537fe16c44f0388bbd5db77b759746991ef991bc8f006
3
  size 4875989752
model-00006-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:002fa9cfda02c00ec86f0986b0d053a141d30d10524d951e89cefb70bf830806
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b148ff262feb4f9aefb5d77748de5152a2efb4afa5ecabd7bb07d5f153b965
3
  size 4875989752
model-00007-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dea2c872ff75e3f804686036dbf07bc8eff3afa16e99145e485782d385172e1
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a76891ed5faedfd6c3e1a67115e4b7246f7f5d7b6b742f2a69783c7230f568
3
  size 4875989752
model-00008-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f7ce4deacf2752fa50de85f6d7edcf5f7bd56a01bee760aebe19d9e392d86b0
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b7dcb9b2fa711d94c5c4356632a35ac0e944eba0b2c4e5620ab27a5c06f17c4
3
  size 4875989752
model-00009-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eef13121763dbc8957f679d47f7463f066dc6ae6fd724eafcc57bfc3506c001c
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e64d2406ef97b6a92aa335d87ef30c8cd4c63648a8f864511459d5057916f0
3
  size 4875989752
model-00010-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2f4717f41487805f0dc3517d9a7f1999edf77e969edda7046e4b9b47c5c8e8f
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e344ca4111b3c73a7dd04a559d14237aeca3d096e89153ae85c5ae3246d99fda
3
  size 4875989752
model-00011-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:781539b09c85548af22dd05cde69c599afe3ea9652e7dbd9fe1851e9c1868994
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bebdbb8460e32bd71dd706e6abe57ae03416151195bbc7ef48c5d3911cf77d
3
  size 4875989752
model-00012-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78d21a566a0720b000d8ea24270d5c804cdd7dc268d1480684ce4305e714bee0
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ae903814cf1f327217f8526b10c362e4b22e9610664627d36d37d3e70d2839
3
  size 4875989752
model-00013-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e8fe36d4c640b3d3157e01b0424d63fe32b3fc3e16638f43c961b483fc9921b
3
  size 4875989752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08e672e4715988b4068ebad474d7a9e47f6c41c022b2f7115c491e22592d15e
3
  size 4875989752
model-00014-of-00014.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14d06429a356df7279d4b01e6a80543a35762ffeb39e1cc1d8632ff1c2cc3866
3
  size 2080144040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40c9d7b02e00a3992bae3fcd8ec7592eed320b1c8e266cfa1906c5ed5ec111b
3
  size 2080144040
trainer_log.jsonl CHANGED
@@ -22,3 +22,27 @@
22
  {"current_steps": 19, "total_steps": 200, "loss": 1.1176, "lr": 2.7e-06, "epoch": 0.9620253164556962, "percentage": 9.5, "elapsed_time": "3:45:43", "remaining_time": "1 day, 11:50:19"}
23
  {"current_steps": 20, "total_steps": 200, "loss": 1.1047, "lr": 2.85e-06, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "3:55:54", "remaining_time": "1 day, 11:23:10"}
24
  {"current_steps": 20, "total_steps": 200, "eval_loss": 1.0604734420776367, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "4:00:28", "remaining_time": "1 day, 12:04:14"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  {"current_steps": 19, "total_steps": 200, "loss": 1.1176, "lr": 2.7e-06, "epoch": 0.9620253164556962, "percentage": 9.5, "elapsed_time": "3:45:43", "remaining_time": "1 day, 11:50:19"}
23
  {"current_steps": 20, "total_steps": 200, "loss": 1.1047, "lr": 2.85e-06, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "3:55:54", "remaining_time": "1 day, 11:23:10"}
24
  {"current_steps": 20, "total_steps": 200, "eval_loss": 1.0604734420776367, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "4:00:28", "remaining_time": "1 day, 12:04:14"}
25
+ {"current_steps": 21, "total_steps": 200, "loss": 1.0932, "lr": 3e-06, "epoch": 1.0506329113924051, "percentage": 10.5, "elapsed_time": "4:20:57", "remaining_time": "1 day, 13:04:22"}
26
+ {"current_steps": 22, "total_steps": 200, "loss": 1.0784, "lr": 2.999771542734587e-06, "epoch": 1.1012658227848102, "percentage": 11.0, "elapsed_time": "4:33:04", "remaining_time": "1 day, 12:49:28"}
27
+ {"current_steps": 23, "total_steps": 200, "loss": 1.0516, "lr": 2.9990862405286437e-06, "epoch": 1.1518987341772151, "percentage": 11.5, "elapsed_time": "4:47:18", "remaining_time": "1 day, 12:50:58"}
28
+ {"current_steps": 24, "total_steps": 200, "loss": 1.032, "lr": 2.9979443021318607e-06, "epoch": 1.2025316455696202, "percentage": 12.0, "elapsed_time": "4:59:14", "remaining_time": "1 day, 12:34:26"}
29
+ {"current_steps": 25, "total_steps": 200, "loss": 0.9672, "lr": 2.9963460753897363e-06, "epoch": 1.2531645569620253, "percentage": 12.5, "elapsed_time": "5:09:14", "remaining_time": "1 day, 12:04:44"}
30
+ {"current_steps": 25, "total_steps": 200, "eval_loss": 0.9851410388946533, "epoch": 1.2531645569620253, "percentage": 12.5, "elapsed_time": "5:13:49", "remaining_time": "1 day, 12:36:49"}
31
+ {"current_steps": 26, "total_steps": 200, "loss": 1.0263, "lr": 2.994292047137618e-06, "epoch": 1.3037974683544304, "percentage": 13.0, "elapsed_time": "5:19:10", "remaining_time": "1 day, 11:36:00"}
32
+ {"current_steps": 27, "total_steps": 200, "loss": 0.9972, "lr": 2.99178284305241e-06, "epoch": 1.3544303797468356, "percentage": 13.5, "elapsed_time": "5:31:58", "remaining_time": "1 day, 11:27:03"}
33
+ {"current_steps": 28, "total_steps": 200, "loss": 0.9812, "lr": 2.9888192274619833e-06, "epoch": 1.4050632911392404, "percentage": 14.0, "elapsed_time": "5:43:24", "remaining_time": "1 day, 11:09:28"}
34
+ {"current_steps": 29, "total_steps": 200, "loss": 1.0132, "lr": 2.9854021031123555e-06, "epoch": 1.4556962025316456, "percentage": 14.5, "elapsed_time": "5:59:53", "remaining_time": "1 day, 11:22:08"}
35
+ {"current_steps": 30, "total_steps": 200, "loss": 0.9552, "lr": 2.981532510892707e-06, "epoch": 1.5063291139240507, "percentage": 15.0, "elapsed_time": "6:07:08", "remaining_time": "1 day, 10:40:29"}
36
+ {"current_steps": 30, "total_steps": 200, "eval_loss": 0.9442359805107117, "epoch": 1.5063291139240507, "percentage": 15.0, "elapsed_time": "6:11:44", "remaining_time": "1 day, 11:06:31"}
37
+ {"current_steps": 31, "total_steps": 200, "loss": 0.977, "lr": 2.9772116295183124e-06, "epoch": 1.5569620253164556, "percentage": 15.5, "elapsed_time": "6:19:25", "remaining_time": "1 day, 10:28:27"}
38
+ {"current_steps": 32, "total_steps": 200, "loss": 0.9326, "lr": 2.972440775171496e-06, "epoch": 1.6075949367088609, "percentage": 16.0, "elapsed_time": "6:32:33", "remaining_time": "1 day, 10:20:53"}
39
+ {"current_steps": 33, "total_steps": 200, "loss": 0.9584, "lr": 2.9672214011007086e-06, "epoch": 1.6582278481012658, "percentage": 16.5, "elapsed_time": "6:40:42", "remaining_time": "1 day, 9:47:50"}
40
+ {"current_steps": 34, "total_steps": 200, "loss": 0.9386, "lr": 2.961555097177853e-06, "epoch": 1.7088607594936709, "percentage": 17.0, "elapsed_time": "6:53:00", "remaining_time": "1 day, 9:36:26"}
41
+ {"current_steps": 35, "total_steps": 200, "loss": 0.9453, "lr": 2.9554435894139947e-06, "epoch": 1.759493670886076, "percentage": 17.5, "elapsed_time": "6:59:38", "remaining_time": "1 day, 8:58:19"}
42
+ {"current_steps": 35, "total_steps": 200, "eval_loss": 0.914239227771759, "epoch": 1.759493670886076, "percentage": 17.5, "elapsed_time": "7:04:14", "remaining_time": "1 day, 9:19:58"}
43
+ {"current_steps": 36, "total_steps": 200, "loss": 0.9473, "lr": 2.9488887394336023e-06, "epoch": 1.810126582278481, "percentage": 18.0, "elapsed_time": "7:12:36", "remaining_time": "1 day, 8:50:44"}
44
+ {"current_steps": 37, "total_steps": 200, "loss": 0.9009, "lr": 2.9418925439074784e-06, "epoch": 1.8607594936708862, "percentage": 18.5, "elapsed_time": "7:26:17", "remaining_time": "1 day, 8:46:04"}
45
+ {"current_steps": 38, "total_steps": 200, "loss": 0.9074, "lr": 2.9344571339445534e-06, "epoch": 1.9113924050632911, "percentage": 19.0, "elapsed_time": "7:40:20", "remaining_time": "1 day, 8:42:31"}
46
+ {"current_steps": 39, "total_steps": 200, "loss": 0.9064, "lr": 2.9265847744427307e-06, "epoch": 1.9620253164556962, "percentage": 19.5, "elapsed_time": "7:55:05", "remaining_time": "1 day, 8:41:16"}
47
+ {"current_steps": 40, "total_steps": 200, "loss": 0.9201, "lr": 2.9182778633989753e-06, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "8:00:58", "remaining_time": "1 day, 8:03:53"}
48
+ {"current_steps": 40, "total_steps": 200, "eval_loss": 0.8951823115348816, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "8:05:34", "remaining_time": "1 day, 8:22:19"}