nicholasKluge
commited on
Commit
•
c84cc3a
1
Parent(s):
2d3efeb
Update README.md
Browse files
README.md
CHANGED
@@ -25,21 +25,22 @@ The model was trained with a dataset composed of `prompt`, `completions`, and an
|
|
25 |
|
26 |
## Details
|
27 |
|
28 |
-
**Number of Epochs:** 5
|
29 |
-
**Batch size:** 64
|
30 |
-
**Optimizer:** `torch.optim.Adam`
|
31 |
-
**Learning Rate:** 1e-4
|
32 |
-
**Loss Function:** `torch.nn.MSELoss()`
|
33 |
-
**GPU:** 1 NVIDIA A100-SXM4-40GB
|
34 |
-
**RMSE in testing:** 0.1190
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
|
40 |
-
|
|
41 |
-
|
|
42 |
-
|
|
|
|
43 |
|
44 |
## Usage
|
45 |
|
|
|
25 |
|
26 |
## Details
|
27 |
|
28 |
+
- **Number of Epochs:** 5
|
29 |
+
- **Batch size:** 64
|
30 |
+
- **Optimizer:** `torch.optim.Adam`
|
31 |
+
- **Learning Rate:** 1e-4
|
32 |
+
- **Loss Function:** `torch.nn.MSELoss()`
|
33 |
+
- **GPU:** 1 NVIDIA A100-SXM4-40GB
|
34 |
+
- **RMSE in testing:** 0.1190
|
35 |
+
|
36 |
+
|
37 |
+
| Epoch/Loss|Training|Validation|
|
38 |
+
|---|---|---|
|
39 |
+
| 1 |0.06136|0.031815|
|
40 |
+
| 2 |0.030398|0.02459|
|
41 |
+
| 3 |0.02389|0.026569|
|
42 |
+
| 4 |0.024755|0.02109|
|
43 |
+
| 5 |0.019445|0.01416|
|
44 |
|
45 |
## Usage
|
46 |
|