Edit model card

my_billsum_model

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

  • Loss: 2.5803
  • Rouge1: 0.1414
  • Rouge2: 0.0501
  • Rougel: 0.1176
  • Rougelsum: 0.1176
  • 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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 200
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.9137 0.65 40 3.0404 0.1351 0.044 0.1138 0.114 19.0
3.0852 1.29 80 2.7349 0.1363 0.0453 0.1143 0.1144 19.0
2.9298 1.94 120 2.6341 0.1405 0.0471 0.1162 0.1164 19.0
2.8389 2.58 160 2.5929 0.1413 0.049 0.1176 0.118 19.0
2.8414 3.23 200 2.5803 0.1414 0.0501 0.1176 0.1176 19.0

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.1
Downloads last month
0
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from