Commit
•
70159a2
1
Parent(s):
16aca3f
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,33 @@ tags:
|
|
| 12 |
- sft
|
| 13 |
---
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
# Uploaded model
|
| 16 |
|
| 17 |
- **Developed by:** tamang0000
|
|
|
|
| 12 |
- sft
|
| 13 |
---
|
| 14 |
|
| 15 |
+
Before:
|
| 16 |
+
কম্পিউটাৰ এন্ড এন্ডিং এন্ডিং এন্ডিং
|
| 17 |
+
কম্পিউটাৰ এন্ড এন্ডিং এন্ডিং এন্ডিং
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
After:
|
| 21 |
+
কম্পিউটাৰ অভিযান অভিযান অভিযান অভিযান
|
| 22 |
+
কম্পিউটাৰ অভিযান অভিযান অভিযান অভিযান
|
| 23 |
+
|
| 24 |
+
```
|
| 25 |
+
max_seq_length = 512
|
| 26 |
+
per_device_train_batch_size = 2,
|
| 27 |
+
gradient_accumulation_steps = 4,
|
| 28 |
+
warmup_steps = 2,
|
| 29 |
+
max_steps = 10,
|
| 30 |
+
learning_rate = 0.0010,
|
| 31 |
+
fp16 = not torch.cuda.is_bf16_supported(),
|
| 32 |
+
bf16 = torch.cuda.is_bf16_supported(),
|
| 33 |
+
logging_steps = 1,
|
| 34 |
+
optim = "adamw_8bit",
|
| 35 |
+
weight_decay = 0.01,
|
| 36 |
+
lr_scheduler_type = "linear",
|
| 37 |
+
seed = 3407,
|
| 38 |
+
output_dir = "outputs",
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
---
|
| 42 |
# Uploaded model
|
| 43 |
|
| 44 |
- **Developed by:** tamang0000
|