Instructions to use dusersad12/BestCheckpoint-ExpRepo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dusersad12/BestCheckpoint-ExpRepo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="dusersad12/BestCheckpoint-ExpRepo")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dusersad12/BestCheckpoint-ExpRepo") model = AutoModelForCausalLM.from_pretrained("dusersad12/BestCheckpoint-ExpRepo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- text-classification
|
| 6 |
+
- experiment
|
| 7 |
+
---
|
| 8 |
+
# BestCheckpoint Model
|
| 9 |
+
|
| 10 |
+
This model was selected as the best checkpoint from a series of hyperparameter search experiments. It achieved the highest validation F1 score across all runs.
|
| 11 |
+
|
| 12 |
+
## Training Details
|
| 13 |
+
|
| 14 |
+
| Hyperparameter | Value |
|
| 15 |
+
|---|---|
|
| 16 |
+
| Best Run | run_swift_hawk |
|
| 17 |
+
| Validation F1 | 0.891 |
|
| 18 |
+
| Validation Loss | 0.287 |
|
| 19 |
+
| Epoch | 7 |
|
| 20 |
+
| Learning Rate | 2e-05 |
|
| 21 |
+
|
| 22 |
+
## Evaluation
|
| 23 |
+
|
| 24 |
+
The model was evaluated on a held-out validation set. The primary selection criterion was `val_f1`.
|
| 25 |
+
|
| 26 |
+
## Usage
|
| 27 |
+
|
| 28 |
+
```python
|
| 29 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
| 30 |
+
|
| 31 |
+
model = AutoModelForSequenceClassification.from_pretrained("BestCheckpoint-ExpRepo")
|
| 32 |
+
tokenizer = AutoTokenizer.from_pretrained("BestCheckpoint-ExpRepo")
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
+
## Limitations
|
| 36 |
+
|
| 37 |
+
This model was trained for research purposes and may not generalize well to all domains.
|
| 38 |
+
|
| 39 |
+
## License
|
| 40 |
+
|
| 41 |
+
This model is released under the Apache 2.0 license.
|