Update README.md
Browse files
README.md
CHANGED
|
@@ -57,6 +57,7 @@ This model is fine-tuned to answer questions from the DSPFirst textbook. I'm not
|
|
| 57 |
## Training and evaluation data
|
| 58 |
|
| 59 |
- `batch_size` of 6 results in 14.82 GB VRAM
|
|
|
|
| 60 |
- 4.52 GB RAM
|
| 61 |
- 30% of the total questions is dedicated for evaluating.
|
| 62 |
|
|
|
|
| 57 |
## Training and evaluation data
|
| 58 |
|
| 59 |
- `batch_size` of 6 results in 14.82 GB VRAM
|
| 60 |
+
- Utilizes `gradient_accumulation_steps` to get total batch size to 514 (batch size should be at least 256)
|
| 61 |
- 4.52 GB RAM
|
| 62 |
- 30% of the total questions is dedicated for evaluating.
|
| 63 |
|