Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
sfulay
/
zephyr-7b-dpo-full
like
0
Text Generation
Transformers
Safetensors
hh
oasst
shp
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
d684950
zephyr-7b-dpo-full
/
all_results.json
sfulay
Model save
d684950
verified
4 months ago
raw
Copy download link
history
blame
Safe
213 Bytes
{
"epoch"
:
1.0
,
"total_flos"
:
0.0
,
"train_loss"
:
0.6931471824645996
,
"train_runtime"
:
29.6161
,
"train_samples"
:
100
,
"train_samples_per_second"
:
3.377
,
"train_steps_per_second"
:
0.034
}