|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: distilrubert-tiny-cased-conversational-v1_single_finetuned_empathy_classifier |
|
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. --> |
|
|
|
# distilrubert-tiny-cased-conversational-v1_single_finetuned_empathy_classifier |
|
|
|
This model is a fine-tuned version of [DeepPavlov/distilrubert-tiny-cased-conversational-v1](https://huggingface.co/DeepPavlov/distilrubert-tiny-cased-conversational-v1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0183 |
|
- Accuracy: 0.6218 |
|
- F1: 0.6262 |
|
- Precision: 0.6318 |
|
- Recall: 0.6218 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 1.0456 | 1.0 | 9 | 0.9718 | 0.4958 | 0.4197 | 0.6526 | 0.4958 | |
|
| 0.9042 | 2.0 | 18 | 0.8920 | 0.5882 | 0.5769 | 0.5784 | 0.5882 | |
|
| 0.7923 | 3.0 | 27 | 0.8427 | 0.6134 | 0.5861 | 0.5935 | 0.6134 | |
|
| 0.7544 | 4.0 | 36 | 0.8400 | 0.6387 | 0.6234 | 0.6344 | 0.6387 | |
|
| 0.6675 | 5.0 | 45 | 0.8410 | 0.6303 | 0.6095 | 0.6184 | 0.6303 | |
|
| 0.6091 | 6.0 | 54 | 0.9095 | 0.6050 | 0.6041 | 0.6396 | 0.6050 | |
|
| 0.6279 | 7.0 | 63 | 0.8596 | 0.6723 | 0.6692 | 0.6725 | 0.6723 | |
|
| 0.4968 | 8.0 | 72 | 0.8725 | 0.6303 | 0.6274 | 0.6253 | 0.6303 | |
|
| 0.4459 | 9.0 | 81 | 0.9120 | 0.6387 | 0.6395 | 0.6426 | 0.6387 | |
|
| 0.4122 | 10.0 | 90 | 0.9478 | 0.6303 | 0.6262 | 0.6248 | 0.6303 | |
|
| 0.3244 | 11.0 | 99 | 0.9746 | 0.6387 | 0.6375 | 0.6381 | 0.6387 | |
|
| 0.3535 | 12.0 | 108 | 1.0183 | 0.6218 | 0.6262 | 0.6318 | 0.6218 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
