Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
wzhouad
/
zephyr-7b-dpo-full
like
0
Text Generation
Transformers
Safetensors
llama
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
a71d566
zephyr-7b-dpo-full
/
train_results.json
wzhouad
Model save
a71d566
verified
about 1 month ago
raw
Copy download link
history
blame
No virus
195 Bytes
{
"epoch"
:
2.0
,
"train_loss"
:
0.5407548575334146
,
"train_runtime"
:
10382.7821
,
"train_samples"
:
45548
,
"train_samples_per_second"
:
8.774
,
"train_steps_per_second"
:
0.068
}