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
eba96d9
·
verified ·
1 Parent(s): 6ec7600

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. token_pack_035_144636/checkpoint.pt +3 -0
  2. token_pack_035_144636/model.safetensors +3 -0
  3. token_pack_035_144636/optimizer_rank0.pt +3 -0
  4. token_pack_035_144636/optimizer_rank1.pt +3 -0
  5. token_pack_035_144636/optimizer_rank2.pt +3 -0
  6. token_pack_035_144636/optimizer_rank3.pt +3 -0
  7. token_pack_035_144636/optimizer_rank4.pt +3 -0
  8. token_pack_035_144636/optimizer_rank5.pt +3 -0
  9. token_pack_035_144636/optimizer_rank6.pt +3 -0
  10. token_pack_035_144636/optimizer_rank7.pt +3 -0
  11. token_pack_035_144636/training_state.json +7 -0
token_pack_035_144636/checkpoint.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774e27cb48ae2a974620641f27d41191a3ee7ab33d59e8aad338efe85f13ab52
3
+ size 813577195
token_pack_035_144636/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a342388ef433a1e1f7043d49b18405fae3db496bbc99fce43234a91b2e58d606
3
+ size 813515200
token_pack_035_144636/optimizer_rank0.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d051c6d59d9a7593067bafe3a6d837971ff7fda935758d50a92483535727c232
3
+ size 1609755607
token_pack_035_144636/optimizer_rank1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd35f8a06813514c1a35ce21f50063872401a0a550a8c5083ec978610db9a3e1
3
+ size 1609755607
token_pack_035_144636/optimizer_rank2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b622005ba66c9c1753c396a9b5d301765f720b20669ac046018bdddd8acd1a6d
3
+ size 1609755607
token_pack_035_144636/optimizer_rank3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212dc56e2ae160524fa8c9ae38dccd22bb89fc0bfac6c2533c27f646f04e919c
3
+ size 1609755607
token_pack_035_144636/optimizer_rank4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0f04a268a1574d3e0dac4954fecf3fdb1c96f37e9fae9ff703ccf5052b35bf
3
+ size 1609755607
token_pack_035_144636/optimizer_rank5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd33ff2818ce9f3902af30ac73cd23ad276012455aba4aa8c1f900f1d337787
3
+ size 1609755607
token_pack_035_144636/optimizer_rank6.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d6db244528902c44b0b38ce511807deaa2852d907ff6cf9d1f4e8d033d032c
3
+ size 1609755607
token_pack_035_144636/optimizer_rank7.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c77fbb73f9452776a0973236dedfbf125744c4894385a5ac0ed0641aae6604c
3
+ size 1609755607
token_pack_035_144636/training_state.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 144636,
3
+ "epoch": 3,
4
+ "best_loss": Infinity,
5
+ "total_tokens": 0,
6
+ "learning_rate": 0.00021854637903164756
7
+ }