Text Classification
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
text-embeddings-inference
Instructions to use ltuzova/citation_intent_classification_roberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ltuzova/citation_intent_classification_roberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ltuzova/citation_intent_classification_roberta")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ltuzova/citation_intent_classification_roberta") model = AutoModelForSequenceClassification.from_pretrained("ltuzova/citation_intent_classification_roberta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
-
- Accuracy: 0.
|
| 21 |
-
- F1 Macro: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -52,14 +52,16 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
|
|
|
|
|
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0731
|
| 20 |
+
- Accuracy: 0.7842
|
| 21 |
+
- F1 Macro: 0.6927
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
| 55 |
+
| 1.3931 | 1.0 | 105 | 1.0457 | 0.6842 | 0.3071 |
|
| 56 |
+
| 1.0487 | 2.0 | 211 | 0.8936 | 0.6842 | 0.3201 |
|
| 57 |
+
| 0.8369 | 3.0 | 316 | 0.7841 | 0.7281 | 0.4126 |
|
| 58 |
+
| 0.5949 | 4.0 | 422 | 0.6737 | 0.7807 | 0.6027 |
|
| 59 |
+
| 0.431 | 5.0 | 527 | 0.7379 | 0.7632 | 0.6569 |
|
| 60 |
+
| 0.3456 | 6.0 | 633 | 0.7826 | 0.7719 | 0.6541 |
|
| 61 |
+
| 0.2285 | 7.0 | 738 | 0.7410 | 0.8158 | 0.7300 |
|
| 62 |
+
| 0.1757 | 8.0 | 844 | 0.8297 | 0.7982 | 0.7306 |
|
| 63 |
+
| 0.1577 | 9.0 | 949 | 0.8780 | 0.7982 | 0.7212 |
|
| 64 |
+
| 0.0973 | 9.95 | 1050 | 0.9575 | 0.8158 | 0.7410 |
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|