Initial Commit
Browse files- README.md +32 -18
- eval_results_cardiff.json +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 4.
|
22 |
-
- Accuracy: 0.
|
23 |
-
- F1: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -40,8 +40,8 @@ More information needed
|
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 5e-05
|
43 |
-
- train_batch_size:
|
44 |
-
- eval_batch_size:
|
45 |
- seed: 66
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
@@ -51,19 +51,33 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
54 |
-
| No log |
|
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
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 4.7992
|
22 |
+
- Accuracy: 0.5154
|
23 |
+
- F1: 0.5146
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
- learning_rate: 5e-05
|
43 |
+
- train_batch_size: 32
|
44 |
+
- eval_batch_size: 64
|
45 |
- seed: 66
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
54 |
+
| No log | 1.09 | 250 | 1.2801 | 0.5069 | 0.5029 |
|
55 |
+
| 0.7278 | 2.17 | 500 | 1.6260 | 0.5077 | 0.5080 |
|
56 |
+
| 0.7278 | 3.26 | 750 | 1.6500 | 0.5193 | 0.5209 |
|
57 |
+
| 0.3512 | 4.35 | 1000 | 2.1813 | 0.5123 | 0.5144 |
|
58 |
+
| 0.3512 | 5.43 | 1250 | 2.5133 | 0.5154 | 0.5167 |
|
59 |
+
| 0.1838 | 6.52 | 1500 | 2.6502 | 0.5093 | 0.5093 |
|
60 |
+
| 0.1838 | 7.61 | 1750 | 3.0408 | 0.5015 | 0.5021 |
|
61 |
+
| 0.118 | 8.7 | 2000 | 3.3486 | 0.4877 | 0.4822 |
|
62 |
+
| 0.118 | 9.78 | 2250 | 3.5117 | 0.4923 | 0.4906 |
|
63 |
+
| 0.072 | 10.87 | 2500 | 3.5966 | 0.5046 | 0.5027 |
|
64 |
+
| 0.072 | 11.96 | 2750 | 3.3823 | 0.5100 | 0.5121 |
|
65 |
+
| 0.0545 | 13.04 | 3000 | 3.7627 | 0.5085 | 0.5053 |
|
66 |
+
| 0.0545 | 14.13 | 3250 | 3.9342 | 0.5108 | 0.5124 |
|
67 |
+
| 0.0336 | 15.22 | 3500 | 4.2215 | 0.5093 | 0.5061 |
|
68 |
+
| 0.0336 | 16.3 | 3750 | 4.2219 | 0.5046 | 0.5021 |
|
69 |
+
| 0.0272 | 17.39 | 4000 | 4.0061 | 0.5208 | 0.5227 |
|
70 |
+
| 0.0272 | 18.48 | 4250 | 4.3214 | 0.5116 | 0.5074 |
|
71 |
+
| 0.0198 | 19.57 | 4500 | 4.5333 | 0.5093 | 0.5075 |
|
72 |
+
| 0.0198 | 20.65 | 4750 | 4.3535 | 0.5247 | 0.5256 |
|
73 |
+
| 0.0161 | 21.74 | 5000 | 4.5169 | 0.5239 | 0.5238 |
|
74 |
+
| 0.0161 | 22.83 | 5250 | 4.4982 | 0.5285 | 0.5298 |
|
75 |
+
| 0.012 | 23.91 | 5500 | 4.5591 | 0.5170 | 0.5186 |
|
76 |
+
| 0.012 | 25.0 | 5750 | 4.7615 | 0.5085 | 0.5069 |
|
77 |
+
| 0.0066 | 26.09 | 6000 | 4.8457 | 0.5100 | 0.5079 |
|
78 |
+
| 0.0066 | 27.17 | 6250 | 4.7872 | 0.5131 | 0.5118 |
|
79 |
+
| 0.0069 | 28.26 | 6500 | 4.6257 | 0.5301 | 0.5303 |
|
80 |
+
| 0.0069 | 29.35 | 6750 | 4.7992 | 0.5154 | 0.5146 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
eval_results_cardiff.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"arabic": {"f1": 0.
|
|
|
1 |
+
{"arabic": {"f1": 0.5940991842458893, "accuracy": 0.593103448275862, "confusion_matrix": [[146, 113, 31], [48, 215, 27], [20, 115, 155]]}, "english": {"f1": 0.6767487000243078, "accuracy": 0.6793103448275862, "confusion_matrix": [[235, 47, 8], [85, 156, 49], [27, 63, 200]]}, "french": {"f1": 0.5091797893031121, "accuracy": 0.539080459770115, "confusion_matrix": [[147, 134, 9], [23, 259, 8], [33, 194, 63]]}, "german": {"f1": 0.7221885493493773, "accuracy": 0.7229885057471265, "confusion_matrix": [[222, 40, 28], [62, 187, 41], [36, 34, 220]]}, "hindi": {"f1": 0.5148790318312105, "accuracy": 0.5172413793103449, "confusion_matrix": [[155, 64, 71], [88, 123, 79], [65, 53, 172]]}, "italian": {"f1": 0.7147248790960297, "accuracy": 0.7160919540229885, "confusion_matrix": [[183, 63, 44], [19, 242, 29], [28, 64, 198]]}, "portuguese": {"f1": 0.6633915248733473, "accuracy": 0.6632183908045977, "confusion_matrix": [[200, 59, 31], [60, 177, 53], [33, 57, 200]]}, "spanish": {"f1": 0.6573314978575006, "accuracy": 0.6609195402298851, "confusion_matrix": [[218, 46, 26], [80, 147, 63], [18, 62, 210]]}, "all": {"f1": 0.6383252563181864, "accuracy": 0.6364942528735632, "confusion_matrix": [[1526, 562, 232], [471, 1494, 355], [245, 665, 1410]]}}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1115316658
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e316b4306d445aae1da6157e80f941444e965b505c69661a1294aab3a5af6d4a
|
3 |
size 1115316658
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7941163c8fd184d99820f8db753da01c36d7b29d24920d212b3f00f614ef85cd
|
3 |
size 4536
|