Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
JW17
/
mistral-sft-simpo-cleaned-re
like
0
Text Generation
Transformers
Safetensors
argilla/ultrafeedback-binarized-preferences-cleaned
mistral
alignment-handbook
trl
simpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
cae349c
mistral-sft-simpo-cleaned-re
/
all_results.json
JW17
Model save
6b1122d
verified
5 months ago
raw
Copy download link
history
blame
Safe
218 Bytes
{
"epoch"
:
1.0
,
"total_flos"
:
0.0
,
"train_loss"
:
1.1419020675811447
,
"train_runtime"
:
10201.3152
,
"train_samples"
:
60917
,
"train_samples_per_second"
:
5.971
,
"train_steps_per_second"
:
0.047
}