Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,28 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
- Model is directly from pytorch. Refer to the python file. To reuse, use .load_state_dict() from the .pth file. Good luck.
|
| 5 |
+
|
| 6 |
+
Training steps:
|
| 7 |
+
- step 0: train loss 4.2221, val loss 4.2306
|
| 8 |
+
- step 500: train loss 1.7526, val loss 1.9053
|
| 9 |
+
- step 1000: train loss 1.3949, val loss 1.6050
|
| 10 |
+
- step 1500: train loss 1.2625, val loss 1.5219
|
| 11 |
+
- step 2000: train loss 1.1860, val loss 1.5046
|
| 12 |
+
- step 2500: train loss 1.1254, val loss 1.4972
|
| 13 |
+
- step 3000: train loss 1.0694, val loss 1.4849
|
| 14 |
+
- step 3500: train loss 1.0211, val loss 1.5048
|
| 15 |
+
- step 4000: train loss 0.9643, val loss 1.5160
|
| 16 |
+
- step 4500: train loss 0.9121, val loss 1.5396
|
| 17 |
+
- step 5000: train loss 0.8673, val loss 1.5552
|
| 18 |
+
- step 5500: train loss 0.8052, val loss 1.5988
|
| 19 |
+
- step 6000: train loss 0.7611, val loss 1.6231
|
| 20 |
+
- step 6500: train loss 0.7087, val loss 1.6706
|
| 21 |
+
- step 7000: train loss 0.6644, val loss 1.7000
|
| 22 |
+
- step 7500: train loss 0.6187, val loss 1.7484
|
| 23 |
+
- step 8000: train loss 0.5818, val loss 1.7882
|
| 24 |
+
- step 8500: train loss 0.5350, val loss 1.8304
|
| 25 |
+
- step 9000: train loss 0.4973, val loss 1.8688
|
| 26 |
+
- step 9500: train loss 0.4638, val loss 1.9050
|
| 27 |
+
- step 9999: train loss 0.4333, val loss 1.9475
|
| 28 |
+
---
|