Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
chanchan7
/
llama-7b-dpo-qlora
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
llama
alignment-handbook
Generated from Trainer
trl
dpo
4-bit precision
bitsandbytes
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
aef4b53
llama-7b-dpo-qlora
/
train_results.json
chanchan7
Model save
aef4b53
verified
4 months ago
raw
history
blame
No virus
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.598351346759896
,
"train_runtime"
:
27817.4474
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
2.198
,
"train_steps_per_second"
:
0.069
}