Instructions to use igor-im/test_trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use igor-im/test_trainer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="igor-im/test_trainer")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("igor-im/test_trainer") model = AutoModelForSequenceClassification.from_pretrained("igor-im/test_trainer") - Notebooks
- Google Colab
- Kaggle
igor commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,8 @@ More information needed
|
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
|
|
|
|
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
|
|
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
| 38 |
+
Still trying to figure out the overfitting, training loss is good, F1 is stable, but eval los seems to keep blowing up
|
| 39 |
+
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|