Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
terry69
/
feedback_p0.1_seed42_level2_rare
like
0
TensorBoard
Safetensors
preference-data
mistral
alignment-handbook
trl
sft
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
94f2c0b
feedback_p0.1_seed42_level2_rare
/
eval_results.json
terry69
End of training
94f2c0b
verified
4 months ago
raw
Copy download link
history
blame
198 Bytes
{
"epoch"
:
0.9988193624557261
,
"eval_loss"
:
0.8673050403594971
,
"eval_runtime"
:
2.0994
,
"eval_samples"
:
10
,
"eval_samples_per_second"
:
0.953
,
"eval_steps_per_second"
:
0.476
}