Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
AlignmentResearch
/
robust_llm_r2d2_tom-debug_pythia-14m_lora
like
0
Follow
FAR AI
33
PEFT
TensorBoard
Safetensors
gpt_neox
Generated from Trainer
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
50d43ea
robust_llm_r2d2_tom-debug_pythia-14m_lora
/
train_results.json
tomtseng
Model save
42f5374
verified
6 months ago
raw
Copy download link
history
blame
Safe
179 Bytes
{
"epoch"
:
0.0
,
"train_loss"
:
9.125
,
"train_runtime"
:
57.0654
,
"train_samples"
:
207865
,
"train_samples_per_second"
:
0.07
,
"train_steps_per_second"
:
0.018
}