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
64e681b
·
verified ·
1 Parent(s): 4a3776f

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. interrupted_76560/checkpoint.pt +3 -0
  2. interrupted_76560/model.safetensors +3 -0
  3. interrupted_76560/optimizer_rank0.pt +3 -0
  4. interrupted_76560/optimizer_rank1.pt +3 -0
  5. interrupted_76560/optimizer_rank2.pt +3 -0
  6. interrupted_76560/optimizer_rank3.pt +3 -0
  7. interrupted_76560/optimizer_rank4.pt +3 -0
  8. interrupted_76560/optimizer_rank5.pt +3 -0
  9. interrupted_76560/optimizer_rank6.pt +3 -0
  10. interrupted_76560/optimizer_rank7.pt +3 -0
  11. interrupted_76560/training_state.json +7 -0
interrupted_76560/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1784ff1529da65c8255d187b8949e1dd0c4f6e78379da41d06613c17d0fad10
3
+ size 813577195
interrupted_76560/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbf5f6dbdb08eabb4bfd0f4456343907aa7d814c2da4e160a3be9d6be4caa89
3
+ size 813515200
interrupted_76560/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:202d4a402e39bc1ab3e6f831657b2e4ade7499a19ed57b40148ec40091ca4bc8
3
+ size 1609755607
interrupted_76560/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b2328a97be94533c2e3cd0d6090627b6cb14ed5ce38e7b745da2e8f568b38b
3
+ size 1609755607
interrupted_76560/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde57f487110b31e4caf088a898009a7a4208605e0ed5bb91d0ca23866d19316
3
+ size 1609755607
interrupted_76560/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d9ab4d2e2aea34d27f80bd3ea3d8cbde5d7ed7454e753cf25183f56c9dc079
3
+ size 1609755607
interrupted_76560/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b0e8ca92f693f56d4493455304951a27082cc19371600dd6a5dca31bf461566
3
+ size 1609755607
interrupted_76560/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a10d7b84d3911e0dca5e4f4d162ec2ebf939b4946fdcf4ad0c51db90f28bb72
3
+ size 1609755607
interrupted_76560/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a013224ababb816baac1594e73ef3132c56d9a667769d335ab8e784330dd5d7
3
+ size 1609755607
interrupted_76560/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2304070512c4728a2a0791713f238c6b1f58384b1eead3696cb616d4bd5f6a3
3
+ size 1609755607
interrupted_76560/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 76560,
3
+ "epoch": 2,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.0003
7
+ }