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
517076f
·
verified ·
1 Parent(s): 3258170

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. token_pack_030_123974/checkpoint.pt +3 -0
  2. token_pack_030_123974/model.safetensors +3 -0
  3. token_pack_030_123974/optimizer_rank0.pt +3 -0
  4. token_pack_030_123974/optimizer_rank1.pt +3 -0
  5. token_pack_030_123974/optimizer_rank2.pt +3 -0
  6. token_pack_030_123974/optimizer_rank3.pt +3 -0
  7. token_pack_030_123974/optimizer_rank4.pt +3 -0
  8. token_pack_030_123974/optimizer_rank5.pt +3 -0
  9. token_pack_030_123974/optimizer_rank6.pt +3 -0
  10. token_pack_030_123974/optimizer_rank7.pt +3 -0
  11. token_pack_030_123974/training_state.json +7 -0
token_pack_030_123974/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12bf38cfb3341fdfa98660943d60e1aca1495befb1c784b2b35d608ac8ab5f9e
3
+ size 813577195
token_pack_030_123974/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbb346c759eb35cc575cd63aecad668f2fcbc4d8d1b954704780ffa425776f31
3
+ size 813515200
token_pack_030_123974/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6432dcd30e85c97805895efe1c6565f5037df4a1d068c15d3032fc2ca8a59048
3
+ size 1609755607
token_pack_030_123974/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08452fdce22f113eb12f293087a706716f9e1d693bfac8ee46713ed68747c8d7
3
+ size 1609755607
token_pack_030_123974/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:341bfd56912f432d3894eb416921fd6f8be3d70103f37e4d73d7089e7ba7ba0f
3
+ size 1609755607
token_pack_030_123974/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4650260abee9ef7aa4cc820c58b59f63eca791d45d51ccc5081a30ffe049b0
3
+ size 1609755607
token_pack_030_123974/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ae6fe50ac893ef56a81587a4853768034529d79985bd9c3e41b6da5356dde2
3
+ size 1609755607
token_pack_030_123974/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4803d98794fbb742fa87d54a66ed19e4864a4694d25c1146cda3ec0a9216315
3
+ size 1609755607
token_pack_030_123974/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb4811f15333750aaadd91135ae94c5ec6dd26db741d14187979cd35b70267a
3
+ size 1609755607
token_pack_030_123974/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d853d3e0b75a0dc1d7d981281567dc0fbf476695b86b51b5fbd5256992cd0992
3
+ size 1609755607
token_pack_030_123974/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 123974,
3
+ "epoch": 3,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.0003
7
+ }