|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: xlnet-large-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: CS221-xlnet-large-cased-finetuned-semeval-NT |
|
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. --> |
|
|
|
# CS221-xlnet-large-cased-finetuned-semeval-NT |
|
|
|
This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co./xlnet-large-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3954 |
|
- F1: 0.7622 |
|
- Roc Auc: 0.8208 |
|
- Accuracy: 0.4657 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.5664 | 1.0 | 139 | 0.5827 | 0.4593 | 0.6262 | 0.1516 | |
|
| 0.5686 | 2.0 | 278 | 0.5801 | 0.4593 | 0.6262 | 0.1516 | |
|
| 0.478 | 3.0 | 417 | 0.4532 | 0.6704 | 0.7544 | 0.3249 | |
|
| 0.3799 | 4.0 | 556 | 0.3867 | 0.7262 | 0.7929 | 0.4079 | |
|
| 0.2727 | 5.0 | 695 | 0.3954 | 0.7622 | 0.8208 | 0.4657 | |
|
| 0.1747 | 6.0 | 834 | 0.3805 | 0.7403 | 0.8009 | 0.4603 | |
|
| 0.11 | 7.0 | 973 | 0.4434 | 0.7565 | 0.8164 | 0.4386 | |
|
| 0.0705 | 8.0 | 1112 | 0.4957 | 0.7619 | 0.8196 | 0.4549 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
