Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
alexredna
/
Tukan-1.1B-Chat-reasoning-sft-COLA
like
0
Text Generation
Transformers
TensorBoard
Safetensors
generator
llama
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
0e86e1d
Tukan-1.1B-Chat-reasoning-sft-COLA
/
train_results.json
alexredna
Model save
0e86e1d
verified
10 months ago
raw
Copy download link
history
blame
Safe
190 Bytes
{
"epoch"
:
0.95
,
"train_loss"
:
1.555079698562622
,
"train_runtime"
:
77.9815
,
"train_samples"
:
682
,
"train_samples_per_second"
:
1.564
,
"train_steps_per_second"
:
0.013
}