sagorsarker
commited on
Commit
•
54dbf4f
1
Parent(s):
099969d
Update README.md
Browse files
README.md
CHANGED
@@ -22,6 +22,14 @@ Notable training configs:
|
|
22 |
- vocab_size: 72000
|
23 |
- attn_impl: flash
|
24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
## Datasets
|
26 |
We add Bangla text datasets from several sources including
|
27 |
|
|
|
22 |
- vocab_size: 72000
|
23 |
- attn_impl: flash
|
24 |
|
25 |
+
__Training status__
|
26 |
+
|
27 |
+
- Evaluation CrossEntropy Loss
|
28 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/5f40b34279c1ba4c353d0c7a/Mr0yAg9AfXTm15GATgSTN.png" alt="alt text" width="620" height="620">
|
29 |
+
|
30 |
+
- Language Perplexity
|
31 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/5f40b34279c1ba4c353d0c7a/B-ZC1LfFZdCTO25Twcyth.png" alt="alt text" width="620" height="620">
|
32 |
+
|
33 |
## Datasets
|
34 |
We add Bangla text datasets from several sources including
|
35 |
|