Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
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
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
0fdc43f
gpt2-sft-port
/
eval_results.json
pkarypis
End of training
0fdc43f
verified
7 months ago
raw
Copy download link
history
blame
Safe
190 Bytes
{
"epoch"
:
2.0
,
"eval_loss"
:
2.105895519256592
,
"eval_runtime"
:
22.2286
,
"eval_samples"
:
23110
,
"eval_samples_per_second"
:
1438.643
,
"eval_steps_per_second"
:
22.494
}