|
--- |
|
license: mit |
|
base_model: minoosh/finetuned_roberta-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: finetuned_ieroberta-base_on_shEMO_transcripts |
|
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. --> |
|
|
|
# finetuned_ieroberta-base_on_shEMO_transcripts |
|
|
|
This model is a fine-tuned version of [minoosh/finetuned_roberta-base-uncased](https://huggingface.co/minoosh/finetuned_roberta-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1943 |
|
- Accuracy: 0.5933 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.3824 | 1.0 | 75 | 1.1850 | 0.5967 | |
|
| 1.1196 | 2.0 | 150 | 0.9580 | 0.6533 | |
|
| 1.0229 | 3.0 | 225 | 0.8937 | 0.6767 | |
|
| 0.8293 | 4.0 | 300 | 0.9288 | 0.6767 | |
|
| 0.7624 | 5.0 | 375 | 0.8706 | 0.6867 | |
|
| 0.6093 | 6.0 | 450 | 0.9811 | 0.68 | |
|
| 0.5163 | 7.0 | 525 | 1.0072 | 0.66 | |
|
| 0.4541 | 8.0 | 600 | 1.0485 | 0.6633 | |
|
| 0.3915 | 9.0 | 675 | 1.0788 | 0.66 | |
|
| 0.3513 | 10.0 | 750 | 1.2308 | 0.6633 | |
|
| 0.3011 | 11.0 | 825 | 1.2203 | 0.6767 | |
|
| 0.1669 | 12.0 | 900 | 1.2282 | 0.6567 | |
|
| 0.1987 | 13.0 | 975 | 1.2879 | 0.6467 | |
|
| 0.2169 | 14.0 | 1050 | 1.3021 | 0.6533 | |
|
| 0.1623 | 15.0 | 1125 | 1.3126 | 0.66 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
