metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: twiiter_try15_fold0
results: []
twiiter_try15_fold0
This model is a fine-tuned version of ProsusAI/finbert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2122
- F1: 0.9766
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.2209 | 1.0 | 500 | 0.1609 | 0.9642 |
| 0.0596 | 2.0 | 1000 | 0.1312 | 0.9705 |
| 0.0274 | 3.0 | 1500 | 0.1583 | 0.9746 |
| 0.0128 | 4.0 | 2000 | 0.1524 | 0.9784 |
| 0.0098 | 5.0 | 2500 | 0.1748 | 0.9784 |
| 0.0101 | 6.0 | 3000 | 0.1385 | 0.9826 |
| 0.0047 | 7.0 | 3500 | 0.1709 | 0.9779 |
| 0.0032 | 8.0 | 4000 | 0.2081 | 0.9739 |
| 0.0018 | 9.0 | 4500 | 0.1727 | 0.9776 |
| 0.0013 | 10.0 | 5000 | 0.2054 | 0.9767 |
| 0.002 | 11.0 | 5500 | 0.1938 | 0.9762 |
| 0.0029 | 12.0 | 6000 | 0.2310 | 0.9743 |
| 0.0 | 13.0 | 6500 | 0.1994 | 0.9774 |
| 0.0 | 14.0 | 7000 | 0.2111 | 0.9761 |
| 0.0 | 15.0 | 7500 | 0.2122 | 0.9766 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3