Hugging Face's logo

just1nseo
/
zephyr-dpo-qlora-gpt4-5e-6-epoch3

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
trl
dpo
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
just1nseo commited on
Commit
f544b0f
•
1 Parent(s): f78ea69

Training in progress, step 900

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/Jul29_11-56-09_node12/events.out.tfevents.1722222188.node12.2246976.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aad74ac338a7bcc79e97b0e043f8b635dc6cb8c1a1ade372bb724237b76e0a40
3
  size 671150064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1878c1d3605c435d28ff65d95397c696ac4d18cbd54e04f203f6398614dc28
3
  size 671150064
runs/Jul29_11-56-09_node12/events.out.tfevents.1722222188.node12.2246976.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df0907007ba6c20a9eef60b1a81b11f08a029f691ea25b850a036ce858fa3126
3
- size 83835
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3931643875c00751fcacafd1068a4d8cd8435f7622a17f73eceed33ee81a21
3
+ size 93564