update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
model-index:
|
7 |
+
- name: dit_base
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# dit_base
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/dit-base](https://huggingface.co/microsoft/dit-base) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4527
|
19 |
+
- Accuracy: 0.8190
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 16
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 64
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
47 |
+
- num_epochs: 50
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| No log | 0.89 | 6 | 1.7452 | 0.4095 |
|
54 |
+
| 1.8958 | 1.89 | 12 | 1.6185 | 0.4286 |
|
55 |
+
| 1.8958 | 2.89 | 18 | 1.4731 | 0.4857 |
|
56 |
+
| 1.8466 | 3.89 | 24 | 1.3459 | 0.5524 |
|
57 |
+
| 1.445 | 4.89 | 30 | 1.1766 | 0.5810 |
|
58 |
+
| 1.445 | 5.89 | 36 | 1.0902 | 0.6381 |
|
59 |
+
| 1.2077 | 6.89 | 42 | 0.9331 | 0.6762 |
|
60 |
+
| 1.2077 | 7.89 | 48 | 0.8431 | 0.6762 |
|
61 |
+
| 1.0254 | 8.89 | 54 | 0.8657 | 0.6857 |
|
62 |
+
| 0.8275 | 9.89 | 60 | 0.6801 | 0.7429 |
|
63 |
+
| 0.8275 | 10.89 | 66 | 0.6699 | 0.7810 |
|
64 |
+
| 0.8063 | 11.89 | 72 | 0.6296 | 0.7524 |
|
65 |
+
| 0.8063 | 12.89 | 78 | 0.5498 | 0.7905 |
|
66 |
+
| 0.7127 | 13.89 | 84 | 0.4974 | 0.8381 |
|
67 |
+
| 0.6356 | 14.89 | 90 | 0.6715 | 0.7619 |
|
68 |
+
| 0.6356 | 15.89 | 96 | 0.4602 | 0.8095 |
|
69 |
+
| 0.6438 | 16.89 | 102 | 0.4886 | 0.8095 |
|
70 |
+
| 0.6438 | 17.89 | 108 | 0.4332 | 0.8 |
|
71 |
+
| 0.5329 | 18.89 | 114 | 0.4197 | 0.8095 |
|
72 |
+
| 0.4932 | 19.89 | 120 | 0.4168 | 0.8190 |
|
73 |
+
| 0.4932 | 20.89 | 126 | 0.4691 | 0.8 |
|
74 |
+
| 0.4861 | 21.89 | 132 | 0.4263 | 0.8476 |
|
75 |
+
| 0.4861 | 22.89 | 138 | 0.4464 | 0.8190 |
|
76 |
+
| 0.4935 | 23.89 | 144 | 0.4857 | 0.7905 |
|
77 |
+
| 0.433 | 24.89 | 150 | 0.4873 | 0.7810 |
|
78 |
+
| 0.433 | 25.89 | 156 | 0.4641 | 0.8095 |
|
79 |
+
| 0.4289 | 26.89 | 162 | 0.5316 | 0.8 |
|
80 |
+
| 0.4289 | 27.89 | 168 | 0.3389 | 0.8571 |
|
81 |
+
| 0.4204 | 28.89 | 174 | 0.4272 | 0.8 |
|
82 |
+
| 0.3668 | 29.89 | 180 | 0.3493 | 0.8667 |
|
83 |
+
| 0.3668 | 30.89 | 186 | 0.3861 | 0.8571 |
|
84 |
+
| 0.4101 | 31.89 | 192 | 0.4216 | 0.8381 |
|
85 |
+
| 0.4101 | 32.89 | 198 | 0.4258 | 0.8190 |
|
86 |
+
| 0.3614 | 33.89 | 204 | 0.4409 | 0.8571 |
|
87 |
+
| 0.3267 | 34.89 | 210 | 0.4475 | 0.8190 |
|
88 |
+
| 0.3267 | 35.89 | 216 | 0.4316 | 0.8190 |
|
89 |
+
| 0.3423 | 36.89 | 222 | 0.4095 | 0.8381 |
|
90 |
+
| 0.3423 | 37.89 | 228 | 0.4671 | 0.8286 |
|
91 |
+
| 0.3325 | 38.89 | 234 | 0.3994 | 0.8286 |
|
92 |
+
| 0.3326 | 39.89 | 240 | 0.5004 | 0.8190 |
|
93 |
+
| 0.3326 | 40.89 | 246 | 0.4103 | 0.8381 |
|
94 |
+
| 0.2964 | 41.89 | 252 | 0.4469 | 0.8286 |
|
95 |
+
| 0.2964 | 42.89 | 258 | 0.4774 | 0.8286 |
|
96 |
+
| 0.3435 | 43.89 | 264 | 0.3843 | 0.8381 |
|
97 |
+
| 0.3146 | 44.89 | 270 | 0.3710 | 0.8667 |
|
98 |
+
| 0.3146 | 45.89 | 276 | 0.3392 | 0.8667 |
|
99 |
+
| 0.3168 | 46.89 | 282 | 0.3597 | 0.8667 |
|
100 |
+
| 0.3168 | 47.89 | 288 | 0.4143 | 0.8381 |
|
101 |
+
| 0.3081 | 48.89 | 294 | 0.3579 | 0.8571 |
|
102 |
+
| 0.3103 | 49.89 | 300 | 0.4527 | 0.8190 |
|
103 |
+
|
104 |
+
|
105 |
+
### Framework versions
|
106 |
+
|
107 |
+
- Transformers 4.25.1
|
108 |
+
- Pytorch 1.12.1
|
109 |
+
- Datasets 2.7.1
|
110 |
+
- Tokenizers 0.13.1
|