<!-- 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. -->
emotion_classification_2_continue
This model is a fine-tuned version of raffel-22/emotion_classification_2 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8978
- Accuracy: 0.725
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: 4e-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
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 20 | 0.9714 | 0.7063 |
| No log | 2.0 | 40 | 0.9432 | 0.7188 |
| No log | 3.0 | 60 | 0.9633 | 0.7 |
| No log | 4.0 | 80 | 0.9322 | 0.7375 |
| No log | 5.0 | 100 | 0.8530 | 0.7063 |
| No log | 6.0 | 120 | 0.9063 | 0.7063 |
| No log | 7.0 | 140 | 0.8451 | 0.7125 |
| No log | 8.0 | 160 | 0.9672 | 0.6375 |
| No log | 9.0 | 180 | 0.9036 | 0.6937 |
| No log | 10.0 | 200 | 0.9261 | 0.6562 |
| No log | 11.0 | 220 | 0.8963 | 0.6937 |
| No log | 12.0 | 240 | 0.8852 | 0.7188 |
| No log | 13.0 | 260 | 0.8728 | 0.7063 |
| No log | 14.0 | 280 | 0.9559 | 0.6875 |
| No log | 15.0 | 300 | 0.9352 | 0.65 |
| No log | 16.0 | 320 | 0.8638 | 0.7 |
| No log | 17.0 | 340 | 0.9156 | 0.7 |
| No log | 18.0 | 360 | 1.0299 | 0.6687 |
| No log | 19.0 | 380 | 0.8983 | 0.675 |
| No log | 20.0 | 400 | 0.8858 | 0.7063 |
| No log | 21.0 | 420 | 0.9699 | 0.6937 |
| No log | 22.0 | 440 | 1.0603 | 0.625 |
| No log | 23.0 | 460 | 1.0404 | 0.6312 |
| No log | 24.0 | 480 | 0.8838 | 0.6937 |
| 0.4269 | 25.0 | 500 | 0.9280 | 0.6937 |
| 0.4269 | 26.0 | 520 | 0.9456 | 0.6937 |
| 0.4269 | 27.0 | 540 | 0.9640 | 0.6937 |
| 0.4269 | 28.0 | 560 | 0.9865 | 0.6937 |
| 0.4269 | 29.0 | 580 | 0.8900 | 0.7188 |
| 0.4269 | 30.0 | 600 | 0.9408 | 0.7063 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
