Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
vwxyzjn
/
mistral-7b-dpo-constitutional-ai
like
1
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrafeedback_binarized
HuggingFaceH4/cai-conversation-harmless
mistral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
c219d95
mistral-7b-dpo-constitutional-ai
/
train_results.json
vwxyzjn
Model save
c219d95
verified
9 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
3.0
,
"train_loss"
:
0.2455477410652717
,
"train_runtime"
:
50581.1093
,
"train_samples"
:
82404
,
"train_samples_per_second"
:
4.887
,
"train_steps_per_second"
:
0.306
}