Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
pkarypis
/
gpt2-sft-port
like
0
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
9cbeb37
gpt2-sft-port
/
eval_results.json
pkarypis
End of training
9cbeb37
verified
about 1 year ago
raw
Copy download link
history
blame
190 Bytes
{
"epoch"
:
2.0
,
"eval_loss"
:
2.073899507522583
,
"eval_runtime"
:
26.2955
,
"eval_samples"
:
23110
,
"eval_samples_per_second"
:
1216.139
,
"eval_steps_per_second"
:
38.029
}