Instructions to use SMG0/Model3_Marabertv2_T2_WOS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SMG0/Model3_Marabertv2_T2_WOS with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SMG0/Model3_Marabertv2_T2_WOS")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("SMG0/Model3_Marabertv2_T2_WOS") model = AutoModelForSequenceClassification.from_pretrained("SMG0/Model3_Marabertv2_T2_WOS") - Notebooks
- Google Colab
- Kaggle
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,9 @@
|
|
| 2 |
base_model: UBC-NLP/MARBERTv2
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: Model3_Marabertv2_T2_WOS
|
| 7 |
results: []
|
|
@@ -12,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# Model3_Marabertv2_T2_WOS
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [UBC-NLP/MARBERTv2](https://huggingface.co/UBC-NLP/MARBERTv2) on
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -39,6 +47,23 @@ The following hyperparameters were used during training:
|
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
- num_epochs: 15
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
- Transformers 4.31.0
|
|
|
|
| 2 |
base_model: UBC-NLP/MARBERTv2
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: Model3_Marabertv2_T2_WOS
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# Model3_Marabertv2_T2_WOS
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [UBC-NLP/MARBERTv2](https://huggingface.co/UBC-NLP/MARBERTv2) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0816
|
| 21 |
+
- F1: 0.8297
|
| 22 |
+
- Roc Auc: 0.9146
|
| 23 |
+
- Accuracy: 0.7412
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- num_epochs: 15
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
| 54 |
+
| No log | 1.0 | 193 | 0.1523 | 0.5204 | 0.6899 | 0.3743 |
|
| 55 |
+
| No log | 2.0 | 386 | 0.1084 | 0.7070 | 0.7979 | 0.5940 |
|
| 56 |
+
| 0.162 | 3.0 | 579 | 0.0896 | 0.7799 | 0.8517 | 0.6872 |
|
| 57 |
+
| 0.162 | 4.0 | 772 | 0.0814 | 0.8089 | 0.8834 | 0.7281 |
|
| 58 |
+
| 0.162 | 5.0 | 965 | 0.0845 | 0.8037 | 0.8866 | 0.7244 |
|
| 59 |
+
| 0.0569 | 6.0 | 1158 | 0.0814 | 0.8112 | 0.8968 | 0.7095 |
|
| 60 |
+
| 0.0569 | 7.0 | 1351 | 0.0744 | 0.8253 | 0.9009 | 0.7225 |
|
| 61 |
+
| 0.0258 | 8.0 | 1544 | 0.0754 | 0.8313 | 0.9081 | 0.7207 |
|
| 62 |
+
| 0.0258 | 9.0 | 1737 | 0.0754 | 0.8418 | 0.9171 | 0.7579 |
|
| 63 |
+
| 0.0258 | 10.0 | 1930 | 0.0813 | 0.8264 | 0.9143 | 0.7356 |
|
| 64 |
+
| 0.0145 | 11.0 | 2123 | 0.0816 | 0.8297 | 0.9146 | 0.7412 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
### Framework versions
|
| 68 |
|
| 69 |
- Transformers 4.31.0
|