first_trial / README.md
vsamuel's picture
End of training
1fc2654
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: first_trial
    results: []

first_trial

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.6043
  • Rouge1: 0.1456
  • Rouge2: 0.0437
  • Rougel: 0.1267
  • Rougelsum: 0.1267
  • Gen Len: 18.4047

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
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 54 3.0826 0.1077 0.0244 0.092 0.0922 18.9059
No log 2.0 108 2.7618 0.1172 0.0267 0.101 0.1013 18.7259
No log 3.0 162 2.6393 0.1326 0.035 0.1159 0.116 18.4753
No log 4.0 216 2.6043 0.1456 0.0437 0.1267 0.1267 18.4047

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0