Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
llama-duo
/
mistral_7b_0_3-closedqa-gpt4o-100k
like
0
Follow
llama-duo
14
PEFT
TensorBoard
Safetensors
llama-duo/synth_closed_qa_dataset_dedup
mistral
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
c5b2e26
mistral_7b_0_3-closedqa-gpt4o-100k
/
eval_results.json
chansung
End of training
c5b2e26
verified
5 months ago
raw
Copy download link
history
blame
Safe
184 Bytes
{
"epoch"
:
10.0
,
"eval_loss"
:
1.7579952478408813
,
"eval_runtime"
:
0.6389
,
"eval_samples"
:
15
,
"eval_samples_per_second"
:
9.391
,
"eval_steps_per_second"
:
1.565
}