metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results: []
distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3852
- Accuracy: 0.9310
- F1: 0.9310
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: 256
- eval_batch_size: 256
- 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 | 2 | 0.6726 | 0.7759 | 0.7574 |
| No log | 2.0 | 4 | 0.6428 | 0.7931 | 0.7784 |
| No log | 3.0 | 6 | 0.6055 | 0.8448 | 0.8422 |
| 0.661 | 4.0 | 8 | 0.5613 | 0.8621 | 0.8614 |
| 0.661 | 5.0 | 10 | 0.5142 | 0.8966 | 0.8961 |
| 0.661 | 6.0 | 12 | 0.4709 | 0.9138 | 0.9136 |
| 0.5276 | 7.0 | 14 | 0.4350 | 0.9138 | 0.9136 |
| 0.5276 | 8.0 | 16 | 0.4093 | 0.9310 | 0.9310 |
| 0.5276 | 9.0 | 18 | 0.3924 | 0.9310 | 0.9310 |
| 0.5276 | 10.0 | 20 | 0.3852 | 0.9310 | 0.9310 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0