finetuning-emotion-model
This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.1719
- Accuracy: 0.943
- F1: 0.9430
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 250 | 0.2690 | 0.916 | 0.9163 |
0.5073 | 2.0 | 500 | 0.1674 | 0.927 | 0.9268 |
0.5073 | 3.0 | 750 | 0.1478 | 0.939 | 0.9399 |
0.1212 | 4.0 | 1000 | 0.1471 | 0.94 | 0.9402 |
0.1212 | 5.0 | 1250 | 0.1472 | 0.938 | 0.9376 |
0.0776 | 6.0 | 1500 | 0.1502 | 0.9385 | 0.9388 |
0.0776 | 7.0 | 1750 | 0.1620 | 0.935 | 0.9348 |
0.053 | 8.0 | 2000 | 0.1697 | 0.9375 | 0.9376 |
0.053 | 9.0 | 2250 | 0.1712 | 0.939 | 0.9392 |
0.0381 | 10.0 | 2500 | 0.1719 | 0.943 | 0.9430 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 17
Finetuned from
Dataset used to train DeekshithaKumariPrabhakar/finetuning-emotion-model
Evaluation results
- Accuracy on emotionvalidation set self-reported0.943
- F1 on emotionvalidation set self-reported0.943