Edit model card

my_summarization_model

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: 2.1956
  • Rouge1: 0.2007
  • Rouge2: 0.1006
  • Rougel: 0.1699
  • Rougelsum: 0.1695
  • 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: 3e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 62 2.3847 0.1952 0.0958 0.1639 0.1635 19.0
No log 2.0 124 2.3171 0.1997 0.0994 0.1688 0.1685 19.0
No log 3.0 186 2.2786 0.1985 0.0992 0.1688 0.1685 19.0
No log 4.0 248 2.2493 0.2004 0.1005 0.1695 0.1693 19.0
No log 5.0 310 2.2326 0.1995 0.1018 0.1703 0.17 19.0
No log 6.0 372 2.2189 0.1994 0.1001 0.1692 0.1688 19.0
No log 7.0 434 2.2074 0.1999 0.1009 0.1692 0.1689 19.0
No log 8.0 496 2.2018 0.1995 0.1003 0.1689 0.1685 19.0
2.4776 9.0 558 2.1969 0.2007 0.1003 0.1696 0.1693 19.0
2.4776 10.0 620 2.1956 0.2007 0.1006 0.1699 0.1695 19.0

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for manu2501sharma/my_summarization_model

Base model

google-t5/t5-small
Finetuned
(1532)
this model