|
--- |
|
library_name: transformers |
|
base_model: microsoft/infoxlm-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: vp-infoxlm-large-dsc |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# vp-infoxlm-large-dsc |
|
|
|
This model is a fine-tuned version of [microsoft/infoxlm-large](https://huggingface.co/microsoft/infoxlm-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6113 |
|
- Accuracy: 0.8706 |
|
- F1: 0.8705 |
|
- Precision: 0.8713 |
|
- Recall: 0.8706 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.8771 | 1.0 | 3180 | 0.8099 | 0.6890 | 0.6914 | 0.7003 | 0.6890 | |
|
| 0.5911 | 2.0 | 6360 | 0.5717 | 0.8014 | 0.8007 | 0.8107 | 0.8014 | |
|
| 0.4608 | 3.0 | 9540 | 0.5323 | 0.8442 | 0.8442 | 0.8449 | 0.8442 | |
|
| 0.407 | 4.0 | 12720 | 0.5047 | 0.8680 | 0.8679 | 0.8683 | 0.8680 | |
|
| 0.3372 | 5.0 | 15900 | 0.6113 | 0.8706 | 0.8705 | 0.8713 | 0.8706 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
