Training in progress epoch 0
Browse files- README.md +4 -35
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [madatnlp/ke-t5-math-py](https://huggingface.co/madatnlp/ke-t5-math-py) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Train Loss:
|
| 17 |
-
- Validation Loss:
|
| 18 |
-
- Epoch:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -41,38 +41,7 @@ The following hyperparameters were used during training:
|
|
| 41 |
|
| 42 |
| Train Loss | Validation Loss | Epoch |
|
| 43 |
|:----------:|:---------------:|:-----:|
|
| 44 |
-
|
|
| 45 |
-
| 1.9923 | 1.5399 | 1 |
|
| 46 |
-
| 1.5972 | 1.2482 | 2 |
|
| 47 |
-
| 1.4318 | 1.1416 | 3 |
|
| 48 |
-
| 1.2938 | 1.0979 | 4 |
|
| 49 |
-
| 1.1901 | 1.0205 | 5 |
|
| 50 |
-
| 1.1353 | 0.9546 | 6 |
|
| 51 |
-
| 1.0667 | 0.9118 | 7 |
|
| 52 |
-
| 1.0332 | 0.9256 | 8 |
|
| 53 |
-
| 0.9526 | 0.8136 | 9 |
|
| 54 |
-
| 0.8977 | 0.8164 | 10 |
|
| 55 |
-
| 0.8556 | 0.7733 | 11 |
|
| 56 |
-
| 0.7916 | 0.7578 | 12 |
|
| 57 |
-
| 0.7446 | 0.7172 | 13 |
|
| 58 |
-
| 0.7004 | 0.6962 | 14 |
|
| 59 |
-
| 0.6532 | 0.6611 | 15 |
|
| 60 |
-
| 0.6171 | 0.6897 | 16 |
|
| 61 |
-
| 0.5716 | 0.7145 | 17 |
|
| 62 |
-
| 0.5272 | 0.6789 | 18 |
|
| 63 |
-
| 0.4969 | 0.6006 | 19 |
|
| 64 |
-
| 0.4483 | 0.6339 | 20 |
|
| 65 |
-
| 0.4104 | 0.5614 | 21 |
|
| 66 |
-
| 0.3901 | 0.6786 | 22 |
|
| 67 |
-
| 0.3567 | 0.6617 | 23 |
|
| 68 |
-
| 0.3142 | 0.6668 | 24 |
|
| 69 |
-
| 0.3042 | 0.6578 | 25 |
|
| 70 |
-
| 0.2796 | 0.6587 | 26 |
|
| 71 |
-
| 0.2529 | 0.6606 | 27 |
|
| 72 |
-
| 0.2303 | 0.7759 | 28 |
|
| 73 |
-
| 0.2047 | 0.6297 | 29 |
|
| 74 |
-
| 0.2037 | 0.7410 | 30 |
|
| 75 |
-
| 0.1796 | 0.7374 | 31 |
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [madatnlp/ke-t5-math-py](https://huggingface.co/madatnlp/ke-t5-math-py) on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Train Loss: 3.9330
|
| 17 |
+
- Validation Loss: 1.9960
|
| 18 |
+
- Epoch: 0
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 41 |
|
| 42 |
| Train Loss | Validation Loss | Epoch |
|
| 43 |
|:----------:|:---------------:|:-----:|
|
| 44 |
+
| 3.9330 | 1.9960 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
|
| 47 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 831509840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ca9917d460a2e7078c924ac6d175a2a347dddbd8e506608c5611c6517c2947
|
| 3 |
size 831509840
|