Update README.md
Browse files
README.md
CHANGED
|
@@ -21,13 +21,21 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
## Model description
|
| 22 |
|
| 23 |
lora_alpha = 32
|
|
|
|
| 24 |
lora_dropout = 0.05
|
|
|
|
| 25 |
lora_r = 16
|
|
|
|
| 26 |
epochs = 9 <---------------
|
|
|
|
| 27 |
learning rate = 3e-4
|
|
|
|
| 28 |
warmup_steps=0.5
|
|
|
|
| 29 |
gradient_accumulation_steps = 8
|
|
|
|
| 30 |
train_batch = 1
|
|
|
|
| 31 |
eval_batch = 1
|
| 32 |
|
| 33 |
## Intended uses & limitations
|
|
|
|
| 21 |
## Model description
|
| 22 |
|
| 23 |
lora_alpha = 32
|
| 24 |
+
|
| 25 |
lora_dropout = 0.05
|
| 26 |
+
|
| 27 |
lora_r = 16
|
| 28 |
+
|
| 29 |
epochs = 9 <---------------
|
| 30 |
+
|
| 31 |
learning rate = 3e-4
|
| 32 |
+
|
| 33 |
warmup_steps=0.5
|
| 34 |
+
|
| 35 |
gradient_accumulation_steps = 8
|
| 36 |
+
|
| 37 |
train_batch = 1
|
| 38 |
+
|
| 39 |
eval_batch = 1
|
| 40 |
|
| 41 |
## Intended uses & limitations
|