Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TTTXXX01
/
IL_BrierAll-7b-sft-full
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrafeedback_binarized
mistral
alignment-handbook
trl
dpo
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
8afa53b
IL_BrierAll-7b-sft-full
/
train_results.json
TTTXXX01
Model save
8afa53b
verified
about 2 months ago
raw
Copy download link
history
blame
217 Bytes
{
"epoch"
:
1.0
,
"total_flos"
:
0.0
,
"train_loss"
:
0.4838377035206865
,
"train_runtime"
:
15889.6187
,
"train_samples"
:
61135
,
"train_samples_per_second"
:
3.847
,
"train_steps_per_second"
:
0.08
}