Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TTTXXX01
/
DPO-Zephyr-7B-baseline
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
mit
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
4ea962b
DPO-Zephyr-7B-baseline
/
all_results.json
TTTXXX01
Model save
4ea962b
verified
5 months ago
raw
Copy download link
history
blame
Safe
219 Bytes
{
"epoch"
:
1.0
,
"total_flos"
:
0.0
,
"train_loss"
:
0.44209186683851615
,
"train_runtime"
:
28094.4071
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
2.176
,
"train_steps_per_second"
:
0.242
}