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
1d0d577
·
verified ·
1 Parent(s): bfae78c

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. token_pack_017_70252/checkpoint.pt +3 -0
  2. token_pack_017_70252/model.safetensors +3 -0
  3. token_pack_017_70252/optimizer_rank0.pt +3 -0
  4. token_pack_017_70252/optimizer_rank1.pt +3 -0
  5. token_pack_017_70252/optimizer_rank2.pt +3 -0
  6. token_pack_017_70252/optimizer_rank3.pt +3 -0
  7. token_pack_017_70252/optimizer_rank4.pt +3 -0
  8. token_pack_017_70252/optimizer_rank5.pt +3 -0
  9. token_pack_017_70252/optimizer_rank6.pt +3 -0
  10. token_pack_017_70252/optimizer_rank7.pt +3 -0
  11. token_pack_017_70252/training_state.json +7 -0
token_pack_017_70252/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bfd2f6458bf7d758fa9e4fd1d327ec9bfa470274c870a6d96cb54b08d0d29e8
3
+ size 813577195
token_pack_017_70252/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6e55553cf2e76e6d841725d8f2f4f2024706acdcb206697118a1fe670110d2
3
+ size 813515200
token_pack_017_70252/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d93d67a064b78d69ec675a7c3a7d946d8e00e8d696fe2dc0fa4ad68ba9ba63
3
+ size 1609755607
token_pack_017_70252/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76cdc24e1c987964f8241f49f45e2609f9a732f47fcd9a074f2695a30656a4cf
3
+ size 1609755607
token_pack_017_70252/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143c4247733104aaa4085410dbbbd5f81c25da35c0ffbc079e901b08f69170c3
3
+ size 1609755607
token_pack_017_70252/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87b1ecd0589b39faac8c5f3c92ca53023e1334c1f5cea1889f5f9fc06a1cde8
3
+ size 1609755607
token_pack_017_70252/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d392dd69fafc89fc510405f832266916241abf30df527a50ebdf0cf2e665d50
3
+ size 1609755607
token_pack_017_70252/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec39a5f0a8bad0995171b1ade4938352e552d94cf64072f17014f229a911963c
3
+ size 1609755607
token_pack_017_70252/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a83b0cbd5d621166ee27bd72f0f8cc4c3dadccadd087c07d47c79b78176f82a6
3
+ size 1609755607
token_pack_017_70252/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eaff93d606d261acafd0a0ccdfd27fc9d909a562c7c8b3b5ca0aa58d2f91c09
3
+ size 1609755607
token_pack_017_70252/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 70252,
3
+ "epoch": 2,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.0003
7
+ }