Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
terry69
/
llama2-20p-POE
like
0
PEFT
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
llama
alignment-handbook
trl
sft
Generated from Trainer
License:
llama2
Model card
Files
Files and versions
Metrics
Training metrics
Community
Use this model
a1144ca
llama2-20p-POE
/
all_results.json
terry69
Model save
a1144ca
verified
about 1 year ago
raw
Copy download link
history
blame
Safe
187 Bytes
{
"epoch"
:
0.96
,
"train_loss"
:
0.0
,
"train_runtime"
:
0.0161
,
"train_samples"
:
27020
,
"train_samples_per_second"
:
1676083.975
,
"train_steps_per_second"
:
52354.363
}