metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
base_model: distilbert-base-uncased-finetuned-sst-2-english
model-index:
- name: twitter-data-distilbert-base-uncased-sentiment-finetuned-memes
results: []
twitter-data-distilbert-base-uncased-sentiment-finetuned-memes
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2474
- Accuracy: 0.9282
- Precision: 0.9290
- Recall: 0.9282
- F1: 0.9282
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: 1e-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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3623 | 1.0 | 1762 | 0.3171 | 0.8986 | 0.8995 | 0.8986 | 0.8981 |
| 0.271 | 2.0 | 3524 | 0.2665 | 0.9176 | 0.9182 | 0.9176 | 0.9173 |
| 0.2386 | 3.0 | 5286 | 0.2499 | 0.9237 | 0.9254 | 0.9237 | 0.9239 |
| 0.2136 | 4.0 | 7048 | 0.2494 | 0.9259 | 0.9263 | 0.9259 | 0.9257 |
| 0.1974 | 5.0 | 8810 | 0.2454 | 0.9278 | 0.9288 | 0.9278 | 0.9278 |
| 0.182 | 6.0 | 10572 | 0.2474 | 0.9282 | 0.9290 | 0.9282 | 0.9282 |
Framework versions
- Transformers 4.24.0.dev0
- Pytorch 1.11.0+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1