fhyfhy commited on
Commit
fe8d1b4
·
verified ·
1 Parent(s): 9c7e45b

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +0 -0
  2. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/.metadata +3 -0
  3. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__0_0.distcp +3 -0
  4. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__1_0.distcp +3 -0
  5. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__2_0.distcp +3 -0
  6. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__3_0.distcp +3 -0
  7. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__4_0.distcp +3 -0
  8. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__5_0.distcp +3 -0
  9. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__6_0.distcp +3 -0
  10. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__7_0.distcp +3 -0
  11. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/.metadata +3 -0
  12. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__0_0.distcp +3 -0
  13. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__1_0.distcp +3 -0
  14. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__2_0.distcp +3 -0
  15. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__3_0.distcp +3 -0
  16. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__4_0.distcp +3 -0
  17. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__5_0.distcp +3 -0
  18. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__6_0.distcp +3 -0
  19. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__7_0.distcp +3 -0
  20. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/launcher.log +0 -0
  21. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/launcher_model_config.json +23 -0
  22. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank0_trace.json +3 -0
  23. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank1_trace.json +3 -0
  24. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank2_trace.json +3 -0
  25. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank3_trace.json +3 -0
  26. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank4_trace.json +3 -0
  27. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank5_trace.json +3 -0
  28. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank6_trace.json +3 -0
  29. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank7_trace.json +3 -0
  30. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank0_trace.json +3 -0
  31. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank1_trace.json +3 -0
  32. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank2_trace.json +3 -0
  33. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank3_trace.json +3 -0
  34. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank4_trace.json +3 -0
  35. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank5_trace.json +3 -0
  36. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank6_trace.json +3 -0
  37. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank7_trace.json +3 -0
  38. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank0_trace.json +3 -0
  39. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank1_trace.json +3 -0
  40. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank2_trace.json +3 -0
  41. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank3_trace.json +3 -0
  42. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank4_trace.json +3 -0
  43. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank5_trace.json +3 -0
  44. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank6_trace.json +3 -0
  45. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank7_trace.json +3 -0
  46. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank0_trace.json +3 -0
  47. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank1_trace.json +3 -0
  48. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank2_trace.json +3 -0
  49. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank3_trace.json +3 -0
  50. LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank4_trace.json +3 -0
.gitattributes CHANGED
The diff for this file is too large to render. See raw diff
 
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653681c100ce7e35a8bafddd7dd2418ac116281d5c4d7f6a8a56447f042ba655
3
+ size 1012198
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dbf6b8557712f899d0d9341156a2e87633df3e835d27fa0ddf7f17bbf986f2f
3
+ size 419487917
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6f1c5e214c6bd219566f49db72f3bcbdf7b2516945de76ac2d67c9d4d44814
3
+ size 419796904
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f247ce7764abb32d92b67e971ff303e72dbcce106d13564b47dcdfc861bf1b
3
+ size 419794066
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0633f811955c858b9ba3c91bf141341aeb56299c61cba584373ab05df472efd
3
+ size 419795643
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2344128c0f6c7981bcb04f29109d31146620d5d62e7ec821459e971129a26c02
3
+ size 419803846
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625981ff73794c18bdfcb74ba5ee8e2d7ae9702b097c35b0cdff9b37cb0de192
3
+ size 419800454
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bce6c338f33345c8d5fbb61f557dfbac90af48161ba95ce4a8ba1afe42ccdac
3
+ size 419800454
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-1/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac67ab4cddd46d1171e997c16235ca5d347eb8aeec8323ccc21d79fad080c12d
3
+ size 419792251
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc144a7edac7627623175232d57eaa62bb80bc6c7bfcd9102b058e3c1c562245
3
+ size 1012213
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f66f7420af1f62ea4810f084b85b681daf41c7d2b1e4470ca8738f828337b6
3
+ size 419491245
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206a71a94e0e9159a479423c12cb01c7ab712620edfd1d28a2894c980880af65
3
+ size 419826408
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80b48d7a1a35c986796aaca9267b39d6bb5e14d54dceea1b074ddd219bbdd8c2
3
+ size 419800722
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda6df8c8ab99a8250f9bec1626ce922c2626bd1dfa5024ca87ad2f1366bc5bd
3
+ size 419811387
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c34b7ebb54748a5ef05f16b84ff15beda242d7e7107836a59ca3122e3da10c8
3
+ size 419832902
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17976bd529982794bcea52eb117074af710be85b6fc98bdd323d6c91869122de
3
+ size 419809030
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f73baf1e114d542a99d22c892b290e171367a4d10255c214ce4f5cb58eb585b
3
+ size 419809286
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/checkpoint/step-5000/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12012d9d1aa7c74a2d220f65fee065a23019afbfe83158db49d10ceb08cb21f8
3
+ size 419797179
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/launcher.log ADDED
The diff for this file is too large to render. See raw diff
 
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/launcher_model_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "fuse_cross_entropy": true,
5
+ "fuse_norm": true,
6
+ "fuse_swiglu": true,
7
+ "gradient_checkpointing": true,
8
+ "hidden_act": "swish",
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "max_position_embeddings": 16384,
12
+ "model_type": "loop_transformer",
13
+ "norm_eps": 1e-06,
14
+ "num_heads": 16,
15
+ "num_hidden_layers": 12,
16
+ "qkv_bias": false,
17
+ "rope_theta": 1000000.0,
18
+ "tie_word_embeddings": true,
19
+ "use_cache": true,
20
+ "ut_steps": 3,
21
+ "vocab_size": 129280,
22
+ "window_size": 2048
23
+ }
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank0_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32404df91ca5f7fd93aa87a116cfcdac91871fd62968c6399871c923815fa251
3
+ size 25271006
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank1_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aada29b14ce1bcc89ce65e497142a0785bb7e2183ee70a66115a84c48828fefb
3
+ size 25225484
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank2_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d681609ff704bd6ac2cd7e6c95a791f0b33b34ae44b0f8a5390fa677e8b64ff2
3
+ size 25188131
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank3_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97988523bd7c0380d47e910493860eaadba9cf3a5e59f74d94b0ca0ebf0aa2a6
3
+ size 25197160
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank4_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474df7d0d65404dc98ac19e4d7be3eb107a23f769b8820857e0547dace08fc44
3
+ size 25030432
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank5_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca9ca2c58292c8d36e12fbd88f37c3b7a61ad633089775ce348e3cb59a38664
3
+ size 25011598
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank6_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dfeda636e5f0444cc3a9f130009c3d300a80755cf05839539ba2e3c056df4a
3
+ size 24949317
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1024/rank7_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621cece5b487bd226f578cfae31710328c7952fb2c87b9bebbb3380cc27ec235
3
+ size 25033558
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank0_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382e72d461ab3b4d39ed673ec0ee0aa7f8893ad9d533473e4a64237f07f7b036
3
+ size 25224047
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank1_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6616940661c1d42385836ac9b1e9dd2015487b2a5fbedf10de4a5e597b629d80
3
+ size 25222556
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank2_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8ab6fc240288a6aaeca37ffdf90eebeb525fd638cda282d9b45ae3f564e292
3
+ size 25212178
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank3_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85caee07ef34d8b1a55f5ecf35be9104b24381409f56e9e8790e05339d73633c
3
+ size 25204531
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank4_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c51afee9e2ee299c187ab9bf507916c4c0df477e633371e84e053e049d1fc7
3
+ size 24989342
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank5_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041b0824ede562c1961bb03ebf901ddc6d2112b9affd477200fd1279cfbf89f8
3
+ size 24974791
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank6_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f97fefc490ab3fb97e67e75f412bc3622453d13935bd7d59643332a0137c40e
3
+ size 24981540
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_1536/rank7_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5af83f501e429f1b57a1b96d736be1f034fd74ed61b6c20027b3c1ded5c439
3
+ size 24982083
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank0_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d0941d541d8945769ec23dff7225046a32bbd5a6a502ff3055154d5daa2472d
3
+ size 25545902
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank1_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5b50c79655a001a208b1e26e70a850c4cce3263fd27d99f71c437116c82c68
3
+ size 25561984
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank2_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:846daccdeb16ada79b73c6aceaeea2c728238ae6ebb871865c0011cd920f852b
3
+ size 25304185
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank3_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98547991185beae08df848a97e043af4e71f8ed96627f17798ac59a6a50b1aee
3
+ size 25549258
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank4_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb0a68be7cb8e51dc914827cef4ef5354a742bd2794f765b781337154834f1e
3
+ size 25309661
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank5_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd25666fe152f18c7bc7feffc2acf8850a247bf95d8ef50dd6950247c4604f5
3
+ size 25306934
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank6_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f4ba55d5a7c7ab010ba9fd3fa792cac91cd8f2ad722b237d7b49681ba4a80c
3
+ size 25030449
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2048/rank7_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01bdc0fc93214db151be1866775bc44748c8b678cfacf715b6ad928443668c6
3
+ size 24671754
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank0_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841496c1ff9cdb6b6c3388c50a2b22de2a2ff527e74cd694cd78c92e39af80ac
3
+ size 25649302
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank1_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec87db7c5b076db518181154758cc54d1e0210850f7a8a55bb79e46d39c4171e
3
+ size 25333377
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank2_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6749c1b597c00824bc6393bc06a92eb45eff3e2bf0bddc432c267d37f53e07bf
3
+ size 25646196
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank3_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c82489f226dce1732b6e3ac2370884bdd7ec62e2d7287faf87f73081215b6a
3
+ size 25645980
LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192/LoopTransformer_FW20B_h1024_l12_ut3_v129280_seq8192-loop_transformer_h1024_l12_ut3_v129280-bs8-sl8192-20260415-040118/profile_trace/iteration_2560/rank4_trace.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ddeadfcfd918512355eb28939cc4cead70e11c1c72d54e02177a2cb43a82be0
3
+ size 25408511