update model card README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [VuongQuoc/my_awesome_swag_model](https://huggingface.co/VuongQuoc/my_awesome_swag_model) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 1.
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -32,26 +32,34 @@ More information needed
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
-
- learning_rate:
|
36 |
- train_batch_size: 2
|
37 |
- eval_batch_size: 4
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
-
- lr_scheduler_warmup_ratio: 0.
|
42 |
-
- num_epochs:
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
-
| Training Loss | Epoch | Step
|
47 |
-
|
48 |
-
| 0.
|
49 |
-
| 0.
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
|
|
53 |
-
|
|
54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [VuongQuoc/my_awesome_swag_model](https://huggingface.co/VuongQuoc/my_awesome_swag_model) on an unknown dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 1.6094
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
32 |
### Training hyperparameters
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 3e-05
|
36 |
- train_batch_size: 2
|
37 |
- eval_batch_size: 4
|
38 |
- seed: 42
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
+
- lr_scheduler_warmup_ratio: 0.6
|
42 |
+
- num_epochs: 2
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
+
| 0.8462 | 0.13 | 700 | 1.7281 |
|
49 |
+
| 0.4775 | 0.26 | 1400 | 1.6819 |
|
50 |
+
| 0.3949 | 0.38 | 2100 | 1.8476 |
|
51 |
+
| 0.3923 | 0.51 | 2800 | 2.2831 |
|
52 |
+
| 1.1178 | 0.64 | 3500 | 1.6094 |
|
53 |
+
| 1.6198 | 0.77 | 4200 | 1.6094 |
|
54 |
+
| 1.6156 | 0.89 | 4900 | 1.6094 |
|
55 |
+
| 1.6151 | 1.02 | 5600 | 1.6094 |
|
56 |
+
| 1.615 | 1.15 | 6300 | 1.6094 |
|
57 |
+
| 1.6113 | 1.28 | 7000 | 1.6094 |
|
58 |
+
| 1.6133 | 1.41 | 7700 | 1.6094 |
|
59 |
+
| 1.6114 | 1.53 | 8400 | 1.6094 |
|
60 |
+
| 1.6108 | 1.66 | 9100 | 1.6094 |
|
61 |
+
| 1.6155 | 1.79 | 9800 | 1.6094 |
|
62 |
+
| 1.6087 | 1.92 | 10500 | 1.6094 |
|
63 |
|
64 |
|
65 |
### Framework versions
|