ZhiguangHan
commited on
Commit
•
e94a6be
1
Parent(s):
dafda31
End of training
Browse files
README.md
CHANGED
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# mt5-small-task2-dataset2
|
17 |
|
18 |
-
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -49,26 +49,25 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
|
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
|
68 |
|
69 |
### Framework versions
|
70 |
|
71 |
- Transformers 4.35.2
|
72 |
- Pytorch 2.1.0+cu121
|
73 |
-
- Datasets 2.15.0
|
74 |
- Tokenizers 0.15.0
|
|
|
15 |
|
16 |
# mt5-small-task2-dataset2
|
17 |
|
18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4320
|
21 |
+
- Accuracy: 0.37
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 7.018 | 1.0 | 250 | 1.2234 | 0.014 |
|
53 |
+
| 1.6684 | 2.0 | 500 | 0.8157 | 0.124 |
|
54 |
+
| 1.0289 | 3.0 | 750 | 0.6527 | 0.222 |
|
55 |
+
| 0.8021 | 4.0 | 1000 | 0.5877 | 0.282 |
|
56 |
+
| 0.6964 | 5.0 | 1250 | 0.5360 | 0.3 |
|
57 |
+
| 0.6252 | 6.0 | 1500 | 0.5118 | 0.32 |
|
58 |
+
| 0.5828 | 7.0 | 1750 | 0.4899 | 0.318 |
|
59 |
+
| 0.5436 | 8.0 | 2000 | 0.4718 | 0.35 |
|
60 |
+
| 0.5232 | 9.0 | 2250 | 0.4625 | 0.34 |
|
61 |
+
| 0.5005 | 10.0 | 2500 | 0.4556 | 0.342 |
|
62 |
+
| 0.4789 | 11.0 | 2750 | 0.4436 | 0.356 |
|
63 |
+
| 0.4733 | 12.0 | 3000 | 0.4379 | 0.356 |
|
64 |
+
| 0.4651 | 13.0 | 3250 | 0.4347 | 0.366 |
|
65 |
+
| 0.4591 | 14.0 | 3500 | 0.4320 | 0.37 |
|
66 |
+
| 0.4508 | 15.0 | 3750 | 0.4320 | 0.37 |
|
67 |
|
68 |
|
69 |
### Framework versions
|
70 |
|
71 |
- Transformers 4.35.2
|
72 |
- Pytorch 2.1.0+cu121
|
|
|
73 |
- Tokenizers 0.15.0
|