Update README.md
Browse files
README.md
CHANGED
@@ -250,19 +250,6 @@ The LLM will make another call
|
|
250 |
[{'id': '2ffc3de4', 'function': {'name': 'addition', 'arguments': '{"a": "10", "b": "2"}'}, 'type': 'function'}]
|
251 |
```
|
252 |
|
253 |
-
## Training Hyperparameters
|
254 |
-
|
255 |
-
The following hyperparameters were used during training:
|
256 |
-
- learning_rate: 2e-05
|
257 |
-
- train_batch_size: 2
|
258 |
-
- eval_batch_size: 8
|
259 |
-
- seed: 42
|
260 |
-
- gradient_accumulation_steps: 12
|
261 |
-
- total_train_batch_size: 24
|
262 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
263 |
-
- lr_scheduler_type: cosine
|
264 |
-
- num_epochs: 1.0
|
265 |
-
|
266 |
## Framework Versions
|
267 |
|
268 |
- Transformers 4.41.2
|
|
|
250 |
[{'id': '2ffc3de4', 'function': {'name': 'addition', 'arguments': '{"a": "10", "b": "2"}'}, 'type': 'function'}]
|
251 |
```
|
252 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
253 |
## Framework Versions
|
254 |
|
255 |
- Transformers 4.41.2
|