Hugging Face's logo

K-kiron
/
pythia-160m-v0-finetuned-squad

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
pythia-160m-v0-finetuned-squad / README.md
K-kiron's picture
K-kiron
End of training
b6cad8f verified
preview code
|
raw
history blame contribute delete
1.41 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: EleutherAI/pythia-160m-v0
model-index:
  - name: pythia-160m-v0-finetuned-squad
    results: []

pythia-160m-v0-finetuned-squad

This model is a fine-tuned version of EleutherAI/pythia-160m-v0 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 4.7825

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
4.7926 1.0 5539 4.7825

Framework versions

  • PEFT 0.7.2.dev0
  • Transformers 4.36.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.2