metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: BERTicSENTNEG4
results: []
BERTicSENTNEG4
This model is a fine-tuned version of Tanor/BERTicSENTNEG4 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0501
- F1: 0.6
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: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 32
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 53 | 0.0846 | 0.0 |
| No log | 2.0 | 106 | 0.0477 | 0.1538 |
| No log | 3.0 | 159 | 0.0438 | 0.6087 |
| No log | 4.0 | 212 | 0.0421 | 0.5778 |
| No log | 5.0 | 265 | 0.0442 | 0.5778 |
| No log | 6.0 | 318 | 0.0477 | 0.5909 |
| No log | 7.0 | 371 | 0.0501 | 0.6 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3