Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Jerry46
/
zephyr-7b-dpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
llama3
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
ba512ef
zephyr-7b-dpo-full
/
train_results.json
Jerry46
Model save
98aa45a
verified
3 months ago
raw
Copy download link
history
blame
Safe
194 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5461576643349236
,
"train_runtime"
:
10580.1696
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
5.778
,
"train_steps_per_second"
:
0.09
}