|
--- |
|
license: mit |
|
base_model: microsoft/mdeberta-v3-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- tweet_sentiment_multilingual |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: scenario-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: tweet_sentiment_multilingual |
|
type: tweet_sentiment_multilingual |
|
config: all |
|
split: validation |
|
args: all |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.6361882716049383 |
|
- name: F1 |
|
type: f1 |
|
value: 0.6387023843949189 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# scenario-TCR_data-cardiffnlp_tweet_sentiment_multilingual_all |
|
|
|
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the tweet_sentiment_multilingual dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0269 |
|
- Accuracy: 0.6362 |
|
- F1: 0.6387 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 66 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.8991 | 1.09 | 500 | 0.8258 | 0.6265 | 0.6117 | |
|
| 0.6873 | 2.17 | 1000 | 0.8627 | 0.6481 | 0.6502 | |
|
| 0.5102 | 3.26 | 1500 | 0.9726 | 0.6516 | 0.6440 | |
|
| 0.3825 | 4.35 | 2000 | 1.1881 | 0.6578 | 0.6540 | |
|
| 0.2946 | 5.43 | 2500 | 1.2475 | 0.6532 | 0.6554 | |
|
| 0.228 | 6.52 | 3000 | 1.5294 | 0.6435 | 0.6458 | |
|
| 0.2006 | 7.61 | 3500 | 1.6058 | 0.6389 | 0.6342 | |
|
| 0.159 | 8.7 | 4000 | 1.5956 | 0.6528 | 0.6510 | |
|
| 0.1334 | 9.78 | 4500 | 1.8463 | 0.6478 | 0.6409 | |
|
| 0.1052 | 10.87 | 5000 | 2.0269 | 0.6362 | 0.6387 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.3 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|