Update README.md

README.md

@@ -1,3 +1,69 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- SkyWater21/lv_emotions
+language:
+- lv
+base_model:
+- AiLab-IMCS-UL/lvbert
+---
+Fine-tuned [LVBERT](https://huggingface.co/AiLab-IMCS-UL/lvbert) for multi-label emotion classification task.
+
+Model was trained on [lv_emotions](https://huggingface.co/datasets/SkyWater21/lv_emotions) dataset. This dataset is Latvian translation of [GoEmotions](https://huggingface.co/datasets/go_emotions) and [Twitter Emotions](https://huggingface.co/datasets/SkyWater21/lv_twitter_emotions) dataset. Google Translate was used to generate the machine translation.
+
+Original 26 emotions were mapped to 6 base emotions as per Dr. Ekman theory.
+
+Labels predicted by classifier:
+```yaml
+0: anger
+1: disgust
+2: fear
+3: joy
+4: sadness
+5: surprise
+6: neutral
+```
+
+Seed used for random number generator is 42:
+```python
+def set_seed(seed=42):
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed_all(seed)
+```
+
+Training parameters:
+```yaml
+max_length: null
+batch_size: 32
+shuffle: True
+num_workers: 4
+pin_memory: False
+drop_last: False
+optimizer: adam
+lr: 0.000005
+weight_decay: 0
+problem_type: multi_label_classification
+num_epochs: 3
+```
+
+
+Evaluation results on test split of [lv_go_emotions](https://huggingface.co/datasets/SkyWater21/lv_emotions/viewer/combined/lv_go_emotions_test)
+|              |Precision|Recall|F1-Score|Support|
+|--------------|---------|------|--------|-------|
+|anger         |     0.57|  0.36|    0.44|    726|
+|disgust       |     0.42|  0.29|    0.35|    123|
+|fear          |     0.59|  0.43|    0.50|     98|
+|joy           |     0.78|  0.80|    0.79|   2104|
+|sadness       |     0.65|  0.42|    0.51|    379|
+|surprise      |     0.62|  0.38|    0.47|    677|
+|neutral       |     0.66|  0.58|    0.62|   1787|
+|micro avg     |     0.70|  0.59|    0.64|   5894|
+|macro avg     |     0.61|  0.46|    0.52|   5894|
+|weighted avg  |     0.68|  0.59|    0.63|   5894|
+|samples avg   |     0.62|  0.61|    0.61|   5894|
+
+Evaluation results on test split of [lv_twitter_emotions](https://huggingface.co/datasets/SkyWater21/lv_emotions/viewer/combined/lv_twitter_emotions_test)
+TBD