Hugging Face's logo

chanchan7
/
zephyr-7b-dpo-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card Files Metrics Community
chanchan7 commited on
Commit
a96bd39
•
1 Parent(s): 7dc2da4

Training in progress, step 5000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Mar06_15-34-32_SYS-4029GP-TRT/events.out.tfevents.1709710548.SYS-4029GP-TRT.2258942.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40614be77c04a57008aa01220f512dae31702ec7c0ccaeb2f3db329ef5c55594
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4fe548a8bdac626286cb58f24765c54c1fc7f4b669671c18cff67c51b7e0f8
3
  size 671150064
runs/Mar06_15-34-32_SYS-4029GP-TRT/events.out.tfevents.1709710548.SYS-4029GP-TRT.2258942.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a7b6c9f6b90428c7fca565bccfdae4fe305f0d89a9f268faa065cee8446c110
3
- size 352338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7050b61c3144c69fda83b8919ec33cece41e7a981d5f3168c9f694fe0eff9f12
3
+ size 359418