|
--- |
|
license: mit |
|
base_model: microsoft/MiniLM-L12-H384-uncased |
|
tags: |
|
- Language |
|
- image-Emotion |
|
- miniLM |
|
- PyTorch |
|
- Trainer |
|
- SequenceClassification |
|
- WeightedLoss |
|
- CrossEntropyLoss |
|
- F1Score |
|
- HuggingFaceHub |
|
- generated_from_trainer |
|
datasets: |
|
- emotion |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: miniLM_finetuned_Emotion_2024_06_15 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: emotion |
|
type: emotion |
|
config: split |
|
split: validation |
|
args: split |
|
metrics: |
|
- name: F1 |
|
type: f1 |
|
value: 0.927424135409491 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# miniLM_finetuned_Emotion_2024_06_15 |
|
|
|
This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the emotion dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1881 |
|
- F1: 0.9274 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 1.1887 | 1.0 | 250 | 0.7672 | 0.7461 | |
|
| 0.5641 | 2.0 | 500 | 0.3698 | 0.9058 | |
|
| 0.3151 | 3.0 | 750 | 0.2783 | 0.9244 | |
|
| 0.2074 | 4.0 | 1000 | 0.2417 | 0.9273 | |
|
| 0.1586 | 5.0 | 1250 | 0.1749 | 0.9301 | |
|
| 0.1287 | 6.0 | 1500 | 0.1945 | 0.9344 | |
|
| 0.1112 | 7.0 | 1750 | 0.2054 | 0.9313 | |
|
| 0.1031 | 8.0 | 2000 | 0.1677 | 0.9308 | |
|
| 0.0819 | 9.0 | 2250 | 0.1862 | 0.9279 | |
|
| 0.0743 | 10.0 | 2500 | 0.1881 | 0.9274 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
