Hugging Face's logo

TerryLaw535
/
flan-t5-base-combined

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
flan-t5-base-combined / README.md
TerryLaw535's picture
TerryLaw535
End of training
578f226 verified
preview code
|
raw history blame contribute delete
No virus
1.78 kB
metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: flan-t5-base-combined
    results: []

flan-t5-base-combined

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

  • Loss: 1.9756
  • Rouge1: 41.6396
  • Rouge2: 16.2853
  • Rougel: 30.6526
  • Rougelsum: 38.3228
  • Gen Len: 96.9400

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
2.2075 1.0 5435 2.0439 39.7324 14.7723 29.4479 36.4427 93.9466
2.094 2.0 10870 2.0249 40.3667 15.3038 29.6423 37.1363 96.9290
2.0306 3.0 16305 2.0199 40.6314 15.4077 29.72 37.3677 97.4958

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2