|
--- |
|
library_name: transformers |
|
base_model: michellejieli/emotion_text_classifier |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: sentiment_analysis_for_emotion_chat_bot |
|
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. --> |
|
|
|
# sentiment_analysis_for_emotion_chat_bot |
|
|
|
This model is a fine-tuned version of [michellejieli/emotion_text_classifier](https://huggingface.co/michellejieli/emotion_text_classifier) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4012 |
|
- Accuracy: 0.8653 |
|
- F1-score: 0.8582 |
|
- Num Input Tokens Seen: 130810880 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Input Tokens Seen | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:| |
|
| No log | 1.0 | 6388 | 0.3932 | 0.8715 | 0.8678 | 26162176 | |
|
| 0.6659 | 2.0 | 12776 | 0.3770 | 0.8724 | 0.8680 | 52324352 | |
|
| 0.6659 | 3.0 | 19164 | 0.3531 | 0.8776 | 0.8749 | 78486528 | |
|
| 0.643 | 4.0 | 25552 | 0.3735 | 0.8726 | 0.8696 | 104648704 | |
|
| 0.643 | 5.0 | 31940 | 0.4012 | 0.8653 | 0.8582 | 130810880 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 3.0.0 |
|
- Tokenizers 0.19.1 |
|
|
