Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
terry69
/
preference_p0.1_seed42_level2_raremixbatch16
like
0
Text Generation
Transformers
TensorBoard
Safetensors
preference-data
mistral
alignment-handbook
trl
sft
Generated from Trainer
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
1a8a5b5
preference_p0.1_seed42_level2_raremixbatch16
/
eval_results.json
terry69
End of training
b30bca5
verified
3 months ago
raw
Copy download link
history
blame
Safe
184 Bytes
{
"epoch"
:
1.0
,
"eval_loss"
:
0.28806865215301514
,
"eval_runtime"
:
1.3149
,
"eval_samples"
:
10
,
"eval_samples_per_second"
:
2.282
,
"eval_steps_per_second"
:
0.761
}