Visualize in Weights & Biases

t5-aramco-news

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

  • Loss: 4.1047
  • Rouge1: 13.0173
  • Rouge2: 6.3034
  • Rougel: 12.1769
  • Rougelsum: 13.0173

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: 2
  • eval_batch_size: 2
  • 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
No log 1.0 8 4.1414 12.0370 5.1987 8.9120 12.0370
No log 2.0 16 3.8934 12.0370 5.1987 8.9120 12.0370
No log 3.0 24 3.8055 12.0370 5.1987 8.9120 12.0370

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
108
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for zakiravian/t5-aramco-news

Base model

google-t5/t5-small
Finetuned
(1756)
this model