randomization_model / README.md
jvalline's picture
Training in progress, step 500
84116c6 verified
|
raw
history blame
1.56 kB
metadata
license: apache-2.0
base_model: t5-base
tags:
  - generated_from_trainer
metrics:
  - bleu
  - accuracy
model-index:
  - name: randomization_model
    results: []

randomization_model

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

  • Loss: 0.1397
  • Bleu: 0.0001
  • Accuracy: 0.0
  • Gen Len: 18.9987

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu Accuracy Gen Len
0.2127 1.0 6250 0.1517 0.0001 0.0 18.9987
0.1844 2.0 12500 0.1397 0.0001 0.0 18.9987

Framework versions

  • Transformers 4.37.1
  • Pytorch 2.3.0.dev20240122+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1