Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
llama-duo
/
gemma2b-summarize-gpt4o-32k
like
0
Follow
llama-duo
15
PEFT
TensorBoard
Safetensors
llama-duo/synth_summarize_dataset_dedup
gemma
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
gemma
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
b8c6249
gemma2b-summarize-gpt4o-32k
/
eval_results.json
chansung
End of training
cfb882f
verified
7 months ago
raw
Copy download link
history
blame
Safe
183 Bytes
{
"epoch"
:
10.0
,
"eval_loss"
:
2.5617620944976807
,
"eval_runtime"
:
0.5264
,
"eval_samples"
:
25
,
"eval_samples_per_second"
:
18.996
,
"eval_steps_per_second"
:
1.9
}