|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- sentiment140 |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Sentiment140_ELECTRA_5E |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: sentiment140 |
|
type: sentiment140 |
|
config: sentiment140 |
|
split: train |
|
args: sentiment140 |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.84 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Sentiment140_ELECTRA_5E |
|
|
|
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the sentiment140 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5410 |
|
- Accuracy: 0.84 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6896 | 0.08 | 50 | 0.6605 | 0.7133 | |
|
| 0.6664 | 0.16 | 100 | 0.6054 | 0.7133 | |
|
| 0.5915 | 0.24 | 150 | 0.4777 | 0.8333 | |
|
| 0.5053 | 0.32 | 200 | 0.4735 | 0.7733 | |
|
| 0.4946 | 0.4 | 250 | 0.3847 | 0.8267 | |
|
| 0.4578 | 0.48 | 300 | 0.4025 | 0.8067 | |
|
| 0.4724 | 0.56 | 350 | 0.3642 | 0.8333 | |
|
| 0.4309 | 0.64 | 400 | 0.3762 | 0.86 | |
|
| 0.4818 | 0.72 | 450 | 0.3829 | 0.84 | |
|
| 0.416 | 0.8 | 500 | 0.3599 | 0.8467 | |
|
| 0.4201 | 0.88 | 550 | 0.3469 | 0.8533 | |
|
| 0.3664 | 0.96 | 600 | 0.3462 | 0.8467 | |
|
| 0.4289 | 1.04 | 650 | 0.3470 | 0.86 | |
|
| 0.3859 | 1.12 | 700 | 0.3440 | 0.8533 | |
|
| 0.3599 | 1.2 | 750 | 0.3475 | 0.8533 | |
|
| 0.3287 | 1.28 | 800 | 0.3524 | 0.8467 | |
|
| 0.3331 | 1.36 | 850 | 0.3475 | 0.8733 | |
|
| 0.3236 | 1.44 | 900 | 0.3657 | 0.8467 | |
|
| 0.3502 | 1.52 | 950 | 0.3525 | 0.84 | |
|
| 0.3702 | 1.6 | 1000 | 0.3655 | 0.8333 | |
|
| 0.3323 | 1.68 | 1050 | 0.3405 | 0.84 | |
|
| 0.3452 | 1.76 | 1100 | 0.3376 | 0.8533 | |
|
| 0.3742 | 1.84 | 1150 | 0.3481 | 0.8533 | |
|
| 0.3145 | 1.92 | 1200 | 0.3472 | 0.86 | |
|
| 0.3657 | 2.0 | 1250 | 0.3302 | 0.8733 | |
|
| 0.2601 | 2.08 | 1300 | 0.3612 | 0.86 | |
|
| 0.2954 | 2.16 | 1350 | 0.3640 | 0.8533 | |
|
| 0.2888 | 2.24 | 1400 | 0.3670 | 0.8467 | |
|
| 0.2572 | 2.32 | 1450 | 0.4118 | 0.84 | |
|
| 0.2955 | 2.4 | 1500 | 0.3811 | 0.86 | |
|
| 0.2431 | 2.48 | 1550 | 0.4221 | 0.84 | |
|
| 0.318 | 2.56 | 1600 | 0.3844 | 0.8467 | |
|
| 0.2615 | 2.64 | 1650 | 0.4109 | 0.8333 | |
|
| 0.2389 | 2.72 | 1700 | 0.4420 | 0.8467 | |
|
| 0.2983 | 2.8 | 1750 | 0.4203 | 0.8467 | |
|
| 0.2828 | 2.88 | 1800 | 0.3629 | 0.8733 | |
|
| 0.2897 | 2.96 | 1850 | 0.3916 | 0.8733 | |
|
| 0.2239 | 3.04 | 1900 | 0.4143 | 0.86 | |
|
| 0.2093 | 3.12 | 1950 | 0.4521 | 0.84 | |
|
| 0.2438 | 3.2 | 2000 | 0.4271 | 0.8467 | |
|
| 0.2282 | 3.28 | 2050 | 0.4548 | 0.8333 | |
|
| 0.1918 | 3.36 | 2100 | 0.4533 | 0.86 | |
|
| 0.1698 | 3.44 | 2150 | 0.5177 | 0.84 | |
|
| 0.2765 | 3.52 | 2200 | 0.4884 | 0.84 | |
|
| 0.2282 | 3.6 | 2250 | 0.4697 | 0.8533 | |
|
| 0.239 | 3.68 | 2300 | 0.4766 | 0.8533 | |
|
| 0.2219 | 3.76 | 2350 | 0.4628 | 0.8533 | |
|
| 0.2375 | 3.84 | 2400 | 0.4704 | 0.8533 | |
|
| 0.1883 | 3.92 | 2450 | 0.4744 | 0.84 | |
|
| 0.2049 | 4.0 | 2500 | 0.4977 | 0.84 | |
|
| 0.1958 | 4.08 | 2550 | 0.4906 | 0.84 | |
|
| 0.1656 | 4.16 | 2600 | 0.5219 | 0.8333 | |
|
| 0.1543 | 4.24 | 2650 | 0.5379 | 0.8333 | |
|
| 0.2082 | 4.32 | 2700 | 0.5107 | 0.84 | |
|
| 0.1724 | 4.4 | 2750 | 0.5208 | 0.84 | |
|
| 0.1778 | 4.48 | 2800 | 0.5238 | 0.84 | |
|
| 0.1914 | 4.56 | 2850 | 0.5325 | 0.84 | |
|
| 0.2436 | 4.64 | 2900 | 0.5279 | 0.84 | |
|
| 0.1662 | 4.72 | 2950 | 0.5295 | 0.84 | |
|
| 0.1288 | 4.8 | 3000 | 0.5392 | 0.84 | |
|
| 0.2087 | 4.88 | 3050 | 0.5409 | 0.84 | |
|
| 0.1612 | 4.96 | 3100 | 0.5410 | 0.84 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.24.0 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.13.1 |
|
|
