assignment3_model / README.md
shmagi's picture
End of training
09b1a73 verified
|
raw
history blame
1.62 kB
metadata
license: mit
base_model: prajjwal1/bert-small
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: assignment3_model
    results: []

Visualize in Weights & Biases

assignment3_model

This model is a fine-tuned version of prajjwal1/bert-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3004
  • Accuracy: 0.9115

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3227 1.0 4598 0.3143 0.9062
0.2899 2.0 9196 0.3004 0.9115

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.1.2
  • Datasets 2.19.1
  • Tokenizers 0.19.1