metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: SentimentT2
results: []
SentimentT2
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: 0.5309
- Accuracy: 0.875
- F1: 0.5098
- Auc Roc: 0.9113
- Log Loss: 0.5309
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: 5e-05
- train_batch_size: 40
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Auc Roc | Log Loss |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 13 | 0.4223 | 0.84 | 0.0 | 0.8263 | 0.4223 |
| No log | 2.0 | 26 | 0.3733 | 0.84 | 0.0 | 0.8826 | 0.3733 |
| No log | 3.0 | 39 | 0.3542 | 0.85 | 0.25 | 0.9012 | 0.3542 |
| No log | 4.0 | 52 | 0.2945 | 0.88 | 0.625 | 0.8955 | 0.2945 |
| No log | 5.0 | 65 | 0.3566 | 0.875 | 0.5283 | 0.9111 | 0.3566 |
| No log | 6.0 | 78 | 0.4393 | 0.865 | 0.4906 | 0.9049 | 0.4393 |
| No log | 7.0 | 91 | 0.4951 | 0.865 | 0.4706 | 0.9085 | 0.4951 |
| No log | 8.0 | 104 | 0.4460 | 0.885 | 0.6102 | 0.9057 | 0.4460 |
| No log | 9.0 | 117 | 0.5089 | 0.87 | 0.5000 | 0.9094 | 0.5089 |
| 0.1739 | 10.0 | 130 | 0.5309 | 0.875 | 0.5098 | 0.9113 | 0.5309 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0