Commit
•
2a87a9f
1
Parent(s):
38c23cb
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,7 +38,7 @@ The model will continue the conversation between the user and itself. If you wan
|
|
| 38 |
Trained for 4 epochs with a sequence length of 2048 on 8 A6000s with an effective batch size of 120.
|
| 39 |
|
| 40 |
Training settings:
|
| 41 |
-
|
| 42 |
lr: 2.0e-04
|
| 43 |
lr_scheduler_type: linear
|
| 44 |
warmup_ratio: 0.06
|
|
@@ -51,4 +51,5 @@ r: 64
|
|
| 51 |
lora_alpha: 32
|
| 52 |
lora_dropout: 0.05
|
| 53 |
bias: "none"
|
| 54 |
-
task_type: "CAUSAL_LM"
|
|
|
|
|
|
| 38 |
Trained for 4 epochs with a sequence length of 2048 on 8 A6000s with an effective batch size of 120.
|
| 39 |
|
| 40 |
Training settings:
|
| 41 |
+
```json
|
| 42 |
lr: 2.0e-04
|
| 43 |
lr_scheduler_type: linear
|
| 44 |
warmup_ratio: 0.06
|
|
|
|
| 51 |
lora_alpha: 32
|
| 52 |
lora_dropout: 0.05
|
| 53 |
bias: "none"
|
| 54 |
+
task_type: "CAUSAL_LM"
|
| 55 |
+
```
|