|
--- |
|
library_name: transformers |
|
base_model: microsoft/infoxlm-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: vp-infoxlm-base-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-base-dsc |
|
|
|
This model is a fine-tuned version of [microsoft/infoxlm-base](https://huggingface.co/microsoft/infoxlm-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4642 |
|
- Accuracy: 0.8251 |
|
- F1: 0.8249 |
|
- Precision: 0.8259 |
|
- Recall: 0.8251 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.9971 | 1.0 | 1590 | 0.8708 | 0.5664 | 0.5565 | 0.6042 | 0.5664 | |
|
| 0.7175 | 2.0 | 3180 | 0.5943 | 0.7631 | 0.7626 | 0.7713 | 0.7631 | |
|
| 0.5942 | 3.0 | 4770 | 0.5007 | 0.8069 | 0.8069 | 0.8075 | 0.8069 | |
|
| 0.4981 | 4.0 | 6360 | 0.4676 | 0.8188 | 0.8182 | 0.8218 | 0.8188 | |
|
| 0.4669 | 5.0 | 7950 | 0.4642 | 0.8251 | 0.8249 | 0.8259 | 0.8251 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
