Hugging Face's logo

mHossain
/
afrikans_sum_v2

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
afrikans_sum_v2 / README.md
mHossain's picture
mHossain
End of training
0de90ea verified
preview code
|
raw
history blame contribute delete
1.61 kB
metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: afrikans_sum_v2
    results: []

afrikans_sum_v2

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5721
  • Rouge1: 8.6374
  • Rouge2: 2.3685
  • Rougel: 7.6315
  • Rougelsum: 8.2247
  • Gen Len: 19.0

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5000
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
4.1394 1.0 625 2.5721 8.6374 2.3685 7.6315 8.2247 19.0

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2