opt-1.3b-fp-sick / README.md
varun-v-rao's picture
End of training
eaf8927 verified
metadata
license: other
base_model: facebook/opt-1.3b
tags:
  - generated_from_trainer
datasets:
  - RobZamp/sick
metrics:
  - accuracy
model-index:
  - name: opt-1.3b-fp-sick
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: sick
          type: RobZamp/sick
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8888888888888888

opt-1.3b-fp-sick

This model is a fine-tuned version of facebook/opt-1.3b on the sick dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4505
  • Accuracy: 0.8889

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: 64
  • eval_batch_size: 32
  • seed: 6
  • 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 Accuracy
No log 1.0 70 0.3555 0.8828
No log 2.0 140 0.3348 0.8848
No log 3.0 210 0.4505 0.8889

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0