metadata
base_model: techthiyanes/chinese_sentiment
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ASAP_SENT
results: []
ASAP_SENT
This model is a fine-tuned version of techthiyanes/chinese_sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8509
- Accuracy: 0.5615
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: 32
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.9289 | 1.0 | 1152 | 0.8937 | 0.5879 |
| 0.8395 | 2.0 | 2304 | 0.9166 | 0.5913 |
| 0.7698 | 3.0 | 3456 | 0.9561 | 0.5879 |
| 0.6523 | 4.0 | 4608 | 1.0678 | 0.5787 |
| 0.4581 | 5.0 | 5760 | 1.2595 | 0.5648 |
| 0.3461 | 6.0 | 6912 | 1.4034 | 0.5595 |
| 0.2374 | 7.0 | 8064 | 1.5402 | 0.5630 |
| 0.2438 | 8.0 | 9216 | 1.7174 | 0.5607 |
| 0.2324 | 9.0 | 10368 | 1.7918 | 0.5640 |
| 0.1555 | 10.0 | 11520 | 1.8509 | 0.5615 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2