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
a21f263
·
verified ·
1 Parent(s): 4dc2d44

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. token_pack_007_28928/checkpoint.pt +3 -0
  2. token_pack_007_28928/model.safetensors +3 -0
  3. token_pack_007_28928/optimizer_rank0.pt +3 -0
  4. token_pack_007_28928/optimizer_rank1.pt +3 -0
  5. token_pack_007_28928/optimizer_rank2.pt +3 -0
  6. token_pack_007_28928/optimizer_rank3.pt +3 -0
  7. token_pack_007_28928/optimizer_rank4.pt +3 -0
  8. token_pack_007_28928/optimizer_rank5.pt +3 -0
  9. token_pack_007_28928/optimizer_rank6.pt +3 -0
  10. token_pack_007_28928/optimizer_rank7.pt +3 -0
  11. token_pack_007_28928/training_state.json +7 -0
token_pack_007_28928/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24ce57f2815a45831b633a2609a2cfba29c51c45a63d55949d3a2379c3df6c6
3
+ size 813577195
token_pack_007_28928/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a20720050e4b93a80cba9eba969f2c6f66b44edce9c2eb00e42a102f93071e8f
3
+ size 813515200
token_pack_007_28928/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606faf1cb36fb615baf20bd4a9f928cf20a2914f0a535518c8988194929ec001
3
+ size 1609755607
token_pack_007_28928/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ea7d2cb8ba7280cffb13897d9bbb61e8033209c0542ed8a2a3bd4fad897db8
3
+ size 1609755607
token_pack_007_28928/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aed9813484946129e0e03099e185b80e8de4e278d038d154259d600a4660f91a
3
+ size 1609755607
token_pack_007_28928/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04bde5a87842de4daa7b64557f77d7e913682e7e0e424b6b641fb7da839ba435
3
+ size 1609755607
token_pack_007_28928/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94796cd025c8a59fa56f813bf44a8e22acaa6e1bb1a3633c4f42df4471e67b19
3
+ size 1609755607
token_pack_007_28928/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064bf2e33b402ecda534d938bd5ffdfa56dbc78a460f2f3864b82b19e60b854d
3
+ size 1609755607
token_pack_007_28928/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88dc6554630f5b9e3c482dac335a1c6e5c6077592761cf02b1e8ed7aec01f6f
3
+ size 1609755607
token_pack_007_28928/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886dc36919c5f5367ff3fabc5cc61870d13d7afbbfc0946a6e2152cbd84efb31
3
+ size 1609755607
token_pack_007_28928/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 28928,
3
+ "epoch": 1,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.0003
7
+ }