Hugging Face's logo

martimfasantos
/
tinyllama-1.1b-mt-dpo-qlora

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
martimfasantos commited on
Commit
7174143
•
1 Parent(s): 757a047

Training in progress, step 2700

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/May29_13-52-00_poseidon/events.out.tfevents.1716990749.poseidon.1872531.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d380eb45549f1f03b51dcf789c6d9c2942c7918566266913d48827b4de58143a
3
  size 201892728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9946e9dd22039c51de13844f02c015a4b4c800dfd15812b7bc9ba119ab59f8cd
3
  size 201892728
runs/May29_13-52-00_poseidon/events.out.tfevents.1716990749.poseidon.1872531.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45e2bfeb9b62854672ac7f22e212b54e4750bcb8f57a5f3bc63913b71b3ac8a0
3
- size 184780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091e1b35641af3605c1094029ff6abef957d5ec57cc3d1ca5eba7fc7dd0f17d5
3
+ size 191660