Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
terry69
/
llama3-poison-50p
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
llama
alignment-handbook
trl
sft
Generated from Trainer
License:
other
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
1fe6821
llama3-poison-50p
/
train_results.json
terry69
Model save
fb70aa6
verified
7 months ago
raw
Copy download link
history
blame
Safe
195 Bytes
{
"epoch"
:
1.0
,
"train_loss"
:
0.6257000189696627
,
"train_runtime"
:
38581.5438
,
"train_samples"
:
51965
,
"train_samples_per_second"
:
1.347
,
"train_steps_per_second"
:
0.084
}