Hugging Face's logo

AETHORIA-AI
/
TR-HASH-MoE-200M-130B-Checkpoints

PyTorch
Safetensors
checkpoint
tr-hash
pretraining
work-in-progress
Model card Files
xet
 Community
Pacific-i64 commited on
Commit
ac3fc42
·
verified ·
1 Parent(s): 33fca1c

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. interrupted_35603/checkpoint.pt +3 -0
  2. interrupted_35603/model.safetensors +3 -0
  3. interrupted_35603/optimizer_rank0.pt +3 -0
  4. interrupted_35603/optimizer_rank1.pt +3 -0
  5. interrupted_35603/optimizer_rank2.pt +3 -0
  6. interrupted_35603/optimizer_rank3.pt +3 -0
  7. interrupted_35603/optimizer_rank4.pt +3 -0
  8. interrupted_35603/optimizer_rank5.pt +3 -0
  9. interrupted_35603/optimizer_rank6.pt +3 -0
  10. interrupted_35603/optimizer_rank7.pt +3 -0
  11. interrupted_35603/training_state.json +7 -0
interrupted_35603/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20f71262e8bdb61e55da55eb8efe404d7f9f292223f6efc507346d03d773429
3
+ size 813577195
interrupted_35603/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ef51cb86ba526ecf3b7ff089a23b1bd30d40180b67857e07392f4090ac7373
3
+ size 813515200
interrupted_35603/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6918f32bd023a7c1a5e6dbbcff132d2d1b027f17ee6141afa0a14c9c2ba1f013
3
+ size 1609755607
interrupted_35603/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc273c27fc48122e4f7334935efec98730764b8c3d66cd370ccbe2417efb7e05
3
+ size 1609755607
interrupted_35603/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022071ecd1db5a2bf37c7e29e013aabc6f9b4ee354647b95b07d6dc1fc58fc6b
3
+ size 1609755607
interrupted_35603/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457ddf6012e91ce83f6d151ef4f0e2231efd7631d8766204299272cd893f7abc
3
+ size 1609755607
interrupted_35603/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ed52a317fdcc83cd0b6773b2eb902b0f2c8d944bea6bbbb9bcb2cf378428e0
3
+ size 1609755607
interrupted_35603/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e292e246d0325754e68041ed439071894a26777e188bf3482d63d4ff43c9eaf0
3
+ size 1609755607
interrupted_35603/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73fb50131714abd78c6fc7f6f5eb60e1d23a81facdb124b4622478de4e23242b
3
+ size 1609755607
interrupted_35603/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98dbfe9f66ee93a20ce038bcf0fbc8004ce97bf685ec811da4dcb6d8a985ced9
3
+ size 1609755607
interrupted_35603/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 35603,
3
+ "epoch": 1,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.0003
7
+ }