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
11bb470
·
verified ·
1 Parent(s): 64e681b

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. token_pack_019_78517/checkpoint.pt +3 -0
  2. token_pack_019_78517/model.safetensors +3 -0
  3. token_pack_019_78517/optimizer_rank0.pt +3 -0
  4. token_pack_019_78517/optimizer_rank1.pt +3 -0
  5. token_pack_019_78517/optimizer_rank2.pt +3 -0
  6. token_pack_019_78517/optimizer_rank3.pt +3 -0
  7. token_pack_019_78517/optimizer_rank4.pt +3 -0
  8. token_pack_019_78517/optimizer_rank5.pt +3 -0
  9. token_pack_019_78517/optimizer_rank6.pt +3 -0
  10. token_pack_019_78517/optimizer_rank7.pt +3 -0
  11. token_pack_019_78517/training_state.json +7 -0
token_pack_019_78517/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f283362a0191e166ce91d4bf10dddf6faa517a1b32ab77290385659b955f2d
3
+ size 813577195
token_pack_019_78517/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef78c89c2f210e81d148af72a1fc4430b8a915ecc7774d1403e0c16b92b650f
3
+ size 813515200
token_pack_019_78517/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c68820396ab4eaa32c5c279f8537f712bbac37f08510340707d2148ba41b63
3
+ size 1609755607
token_pack_019_78517/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462db52c6299d083e1e2895c86c5692073f968f4515769a1aeab5ee44fe43054
3
+ size 1609755607
token_pack_019_78517/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6dde5be832094e4ffe8fdc121f0428a95e0a3d800dbb9ad2ec3590c00a703d4
3
+ size 1609755607
token_pack_019_78517/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815f164b7595d0ae53c40a4a38b7c4dfe3326412956dd1842bb1a29097921497
3
+ size 1609755607
token_pack_019_78517/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:513231ee76e3440bbe866bfc23cded8cf59af7bf02efbf51b84635b73fafe482
3
+ size 1609755607
token_pack_019_78517/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36e3292de55c41bdfc005610233c65d5d79693d947637abe28a20cd861945c5f
3
+ size 1609755607
token_pack_019_78517/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cbd3b19ee8683abf9a2e2f295f908dc3a0f92092bc8ce4c52822542290a6dbe
3
+ size 1609755607
token_pack_019_78517/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b6685f31a6b713afaf3ad01c045621df313e3591b0acce0704016a8d7bcd53
3
+ size 1609755607
token_pack_019_78517/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 78517,
3
+ "epoch": 3,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.0003
7
+ }