Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
terry69
/
preference_p0.1_seed42_level2_styledirtybatch16_reverse
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
83694c4
preference_p0.1_seed42_level2_styledirtybatch16_reverse
/
eval_results.json
terry69
End of training
83694c4
verified
about 2 months ago
raw
Copy download link
history
blame
146 Bytes
{
"epoch"
:
1.0
,
"eval_runtime"
:
3.2449
,
"eval_samples"
:
10
,
"eval_samples_per_second"
:
3.082
,
"eval_steps_per_second"
:
0.925
}