|
--- |
|
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment |
|
metrics: |
|
- accuracy |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: unfortified_xlm |
|
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. --> |
|
|
|
# unfortified_xlm |
|
|
|
This model is a fine-tuned version of [cardiffnlp/twitter-xlm-roberta-base-sentiment](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-base-sentiment) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4579 |
|
- Accuracy: 0.86 |
|
|
|
## 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: 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| No log | 0.0546 | 50 | 0.4420 | 0.85 | |
|
| No log | 0.1092 | 100 | 0.3343 | 0.87 | |
|
| No log | 0.1638 | 150 | 0.4337 | 0.8 | |
|
| No log | 0.2183 | 200 | 0.3168 | 0.89 | |
|
| No log | 0.2729 | 250 | 0.3471 | 0.86 | |
|
| No log | 0.3275 | 300 | 0.3396 | 0.86 | |
|
| No log | 0.3821 | 350 | 0.4050 | 0.86 | |
|
| No log | 0.4367 | 400 | 0.3182 | 0.84 | |
|
| No log | 0.4913 | 450 | 0.4252 | 0.88 | |
|
| 0.315 | 0.5459 | 500 | 0.3432 | 0.87 | |
|
| 0.315 | 0.6004 | 550 | 0.3081 | 0.89 | |
|
| 0.315 | 0.6550 | 600 | 0.2650 | 0.9 | |
|
| 0.315 | 0.7096 | 650 | 0.4030 | 0.88 | |
|
| 0.315 | 0.7642 | 700 | 0.3755 | 0.89 | |
|
| 0.315 | 0.8188 | 750 | 0.4085 | 0.86 | |
|
| 0.315 | 0.8734 | 800 | 0.3329 | 0.91 | |
|
| 0.315 | 0.9279 | 850 | 0.2862 | 0.9 | |
|
| 0.315 | 0.9825 | 900 | 0.4816 | 0.88 | |
|
| 0.315 | 1.0371 | 950 | 0.3559 | 0.87 | |
|
| 0.2576 | 1.0917 | 1000 | 0.4644 | 0.89 | |
|
| 0.2576 | 1.1463 | 1050 | 0.3396 | 0.88 | |
|
| 0.2576 | 1.2009 | 1100 | 0.3641 | 0.89 | |
|
| 0.2576 | 1.2555 | 1150 | 0.3362 | 0.88 | |
|
| 0.2576 | 1.3100 | 1200 | 0.3626 | 0.89 | |
|
| 0.2576 | 1.3646 | 1250 | 0.4579 | 0.86 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
