Edit model card

entailed_after_rte-t5-base

This model is a fine-tuned version of kennethge123/superglue_rte-t5-base on the bigbench dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0000
  • Accuracy: 1.0

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 30 0.7892 0.5714
No log 2.0 60 1.0497 0.7143
No log 3.0 90 1.5272 0.7857
No log 4.0 120 0.0498 1.0
No log 5.0 150 0.0000 1.0
No log 6.0 180 0.0000 1.0
No log 7.0 210 0.0000 1.0
No log 8.0 240 0.0000 1.0
No log 9.0 270 0.0000 1.0
No log 10.0 300 0.0000 1.0
No log 11.0 330 0.0000 1.0
No log 12.0 360 0.0000 1.0
No log 13.0 390 0.0000 1.0
No log 14.0 420 0.0000 1.0
No log 15.0 450 0.0000 1.0
No log 16.0 480 0.0000 1.0
0.1757 17.0 510 0.0000 1.0
0.1757 18.0 540 0.0000 1.0
0.1757 19.0 570 0.0000 1.0
0.1757 20.0 600 0.0000 1.0

Framework versions

  • Transformers 4.37.0
  • Pytorch 1.13.1+cu117
  • Datasets 2.15.0
  • Tokenizers 0.15.2
Downloads last month
2
Safetensors
Model size
223M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for kennethge123/entailed_after_rte-t5-base

Base model

google-t5/t5-base
Finetuned
(1)
this model

Dataset used to train kennethge123/entailed_after_rte-t5-base

Evaluation results