Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
RikkiXu
/
zephyr-7b-dpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
44a6132
zephyr-7b-dpo-full
/
train_results.json
RikkiXu
Model save
2ab4618
verified
3 months ago
raw
Copy download link
history
blame
No virus
193 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.5566485422347293
,
"train_runtime"
:
6841.2124
,
"train_samples"
:
56236
,
"train_samples_per_second"
:
8.22
,
"train_steps_per_second"
:
0.064
}