metadata
license: mit
base_model: SamLowe/roberta-base-go_emotions
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: bert-finetuned-sem_eval-english
results: []
bert-finetuned-sem_eval-english
This model is a fine-tuned version of SamLowe/roberta-base-go_emotions on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1189
- F1: 0.5833
- Roc Auc: 0.7555
- Accuracy: 0.3939
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 29 | 0.1381 | 0.5217 | 0.7178 | 0.3030 |
| No log | 2.0 | 58 | 0.1193 | 0.5532 | 0.7367 | 0.3636 |
| No log | 3.0 | 87 | 0.1220 | 0.5417 | 0.7355 | 0.3636 |
| No log | 4.0 | 116 | 0.1189 | 0.5833 | 0.7555 | 0.3939 |
| No log | 5.0 | 145 | 0.1186 | 0.5833 | 0.7555 | 0.3939 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2