t5-small-laShootKP / README.md
rizvi-rahil786's picture
End of training
bb68b3a verified
|
raw
history blame
2.26 kB
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: t5-small-laShootKP
    results: []

t5-small-laShootKP

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

  • Loss: 1.1739
  • Rouge1: 49.6859
  • Rouge2: 37.2276
  • Rougel: 49.5085
  • Rougelsum: 49.5531
  • Gen Len: 6.5138

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: 8

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
1.1796 1.0 6223 1.1739 49.6859 37.2276 49.5085 49.5531 6.5138
1.0232 2.0 12446 1.1820 49.7748 37.0118 49.5941 49.6469 6.8708
0.9315 3.0 18669 1.2301 48.0881 35.58 48.0004 48.0227 6.6295
0.8268 4.0 24892 1.2825 44.9333 32.8997 44.8001 44.8274 6.3620
0.8217 5.0 31115 1.3131 45.5074 32.864 45.3445 45.3414 6.3456
0.7738 6.0 37338 1.3544 44.6476 32.7547 44.4945 44.5461 6.5479
0.7336 7.0 43561 1.3442 45.3053 33.1408 45.155 45.1848 6.5295
0.7086 8.0 49784 1.3590 45.3277 33.0743 45.2083 45.2695 6.5869

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2