Hugging Face's logo

chanchan7
/
llama-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
chanchan7 commited on
Commit
c3e185c
•
1 Parent(s): 57a84fc

Training in progress, step 1900

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Mar05_01-38-10_SYS-4029GP-TRT/events.out.tfevents.1709574193.SYS-4029GP-TRT.1942121.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b38f92fab0054405253c966fbdb84aa43d9546c34ebbb9f70a9090c7118392f
3
  size 639692768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25118f501537916a9b89de85ab7c31d16a0786bc7d89771d3b1c7bbedaabf31
3
  size 639692768
runs/Mar05_01-38-10_SYS-4029GP-TRT/events.out.tfevents.1709574193.SYS-4029GP-TRT.1942121.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d46e42970fe3c7051a3018acd58fc5bd4280f66c7c5f69704d348cc12abfb86
3
- size 132902
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d703d4e50b6102b23c0007085f8f86c7cb562619f8ceffa080d0ead04152084
3
+ size 139982