metadata
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: []
finetuned_ieroberta-base_on_shEMO_transcripts
This model is a fine-tuned version of 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