Commit
•
f661e6f
1
Parent(s):
87c8c50
End of training
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
- Accuracy: 0.32
|
| 22 |
|
| 23 |
## Model description
|
|
@@ -43,29 +43,32 @@ The following hyperparameters were used during training:
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
-
| 6.
|
| 53 |
-
| 1.
|
| 54 |
-
| 1.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.35.2
|
| 69 |
-
- Pytorch 2.1.0+
|
| 70 |
- Datasets 2.15.0
|
| 71 |
- Tokenizers 0.15.0
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.4462
|
| 21 |
- Accuracy: 0.32
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 15
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| 6.6376 | 1.0 | 250 | 1.2577 | 0.004 |
|
| 53 |
+
| 1.6709 | 2.0 | 500 | 0.8265 | 0.088 |
|
| 54 |
+
| 1.0413 | 3.0 | 750 | 0.6782 | 0.144 |
|
| 55 |
+
| 0.8324 | 4.0 | 1000 | 0.5901 | 0.222 |
|
| 56 |
+
| 0.7187 | 5.0 | 1250 | 0.5476 | 0.246 |
|
| 57 |
+
| 0.6556 | 6.0 | 1500 | 0.5215 | 0.276 |
|
| 58 |
+
| 0.6089 | 7.0 | 1750 | 0.5028 | 0.274 |
|
| 59 |
+
| 0.5736 | 8.0 | 2000 | 0.4930 | 0.304 |
|
| 60 |
+
| 0.5385 | 9.0 | 2250 | 0.4695 | 0.296 |
|
| 61 |
+
| 0.5195 | 10.0 | 2500 | 0.4650 | 0.304 |
|
| 62 |
+
| 0.5073 | 11.0 | 2750 | 0.4571 | 0.304 |
|
| 63 |
+
| 0.4895 | 12.0 | 3000 | 0.4491 | 0.306 |
|
| 64 |
+
| 0.4836 | 13.0 | 3250 | 0.4495 | 0.316 |
|
| 65 |
+
| 0.4745 | 14.0 | 3500 | 0.4460 | 0.318 |
|
| 66 |
+
| 0.4736 | 15.0 | 3750 | 0.4462 | 0.32 |
|
| 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
|