Instructions to use dusersad12/BestCheckpoint-Demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dusersad12/BestCheckpoint-Demo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dusersad12/BestCheckpoint-Demo")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("dusersad12/BestCheckpoint-Demo") model = AutoModelForSequenceClassification.from_pretrained("dusersad12/BestCheckpoint-Demo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README with best run metrics
Browse files
README.md
CHANGED
|
@@ -10,9 +10,9 @@ This model checkpoint was selected from a hyperparameter sweep as the best-perfo
|
|
| 10 |
|
| 11 |
| Metric | Value |
|
| 12 |
|---|---|
|
| 13 |
-
| Validation Accuracy |
|
| 14 |
-
| Validation Loss |
|
| 15 |
-
| Validation F1 |
|
| 16 |
|
| 17 |
## Training Configuration
|
| 18 |
|
|
@@ -20,10 +20,10 @@ The best run used the following hyperparameters:
|
|
| 20 |
|
| 21 |
| Hyperparameter | Value |
|
| 22 |
|---|---|
|
| 23 |
-
| Learning Rate |
|
| 24 |
-
| Weight Decay |
|
| 25 |
-
| Epochs |
|
| 26 |
-
| Batch Size |
|
| 27 |
|
| 28 |
## How to Use
|
| 29 |
|
|
|
|
| 10 |
|
| 11 |
| Metric | Value |
|
| 12 |
|---|---|
|
| 13 |
+
| Validation Accuracy | 0.861 |
|
| 14 |
+
| Validation Loss | 0.412 |
|
| 15 |
+
| Validation F1 | 0.855 |
|
| 16 |
|
| 17 |
## Training Configuration
|
| 18 |
|
|
|
|
| 20 |
|
| 21 |
| Hyperparameter | Value |
|
| 22 |
|---|---|
|
| 23 |
+
| Learning Rate | 3e-05 |
|
| 24 |
+
| Weight Decay | 0.1 |
|
| 25 |
+
| Epochs | 10 |
|
| 26 |
+
| Batch Size | 32 |
|
| 27 |
|
| 28 |
## How to Use
|
| 29 |
|