Hugging Face's logo

martimfasantos
/
tinyllama-1.1b-sum-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
ea15fdd
·
verified ·
1 Parent(s): 38cc1b8

Training in progress, step 5600

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. runs/May10_18-01-31_poseidon/events.out.tfevents.1715364109.poseidon.2827305.0 +2 -2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:861fcd0f7cf2dec33514028dff3f9399fab40a5383245df30f264266c40d1b47
3
  size 201892728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af0a03d27d57e1d92b5674f083a4b0d0aae2091ce0149f7807f5f190b11f7c9
3
  size 201892728
runs/May10_18-01-31_poseidon/events.out.tfevents.1715364109.poseidon.2827305.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e6da98454742ca6ad452bd7008a70b7803a3d1b5bc39da1a3b308b1e1467211
3
- size 424994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4b4467d886aca515dfdf313f30d93cb1b6d463d6f52716c36c6289cb5059f1
3
+ size 432614