update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: bert-large-uncased-finetuned-lowR100-4-uncased-DA-20
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# bert-large-uncased-finetuned-lowR100-4-uncased-DA-20
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 2.2624
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 2e-05
|
37 |
+
- train_batch_size: 30
|
38 |
+
- eval_batch_size: 30
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 40.0
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 1 | 5.4063 |
|
50 |
+
| 5.9654 | 2.0 | 2 | 6.1913 |
|
51 |
+
| 5.9654 | 3.0 | 3 | 5.8608 |
|
52 |
+
| 5.5864 | 4.0 | 4 | 4.4613 |
|
53 |
+
| 5.5864 | 5.0 | 5 | 5.0257 |
|
54 |
+
| 5.1093 | 6.0 | 6 | 4.7405 |
|
55 |
+
| 5.1093 | 7.0 | 7 | 4.7516 |
|
56 |
+
| 4.3965 | 8.0 | 8 | 3.1646 |
|
57 |
+
| 4.3965 | 9.0 | 9 | 3.7378 |
|
58 |
+
| 3.7825 | 10.0 | 10 | 2.0073 |
|
59 |
+
| 3.7825 | 11.0 | 11 | 5.5725 |
|
60 |
+
| 3.009 | 12.0 | 12 | 3.0077 |
|
61 |
+
| 3.009 | 13.0 | 13 | 2.6288 |
|
62 |
+
| 2.7427 | 14.0 | 14 | 2.8630 |
|
63 |
+
| 2.7427 | 15.0 | 15 | 2.3270 |
|
64 |
+
| 2.4122 | 16.0 | 16 | 3.3092 |
|
65 |
+
| 2.4122 | 17.0 | 17 | 2.7499 |
|
66 |
+
| 2.3707 | 18.0 | 18 | 3.2892 |
|
67 |
+
| 2.3707 | 19.0 | 19 | 2.9385 |
|
68 |
+
| 2.6243 | 20.0 | 20 | 1.5626 |
|
69 |
+
| 2.6243 | 21.0 | 21 | 1.0104 |
|
70 |
+
| 2.1606 | 22.0 | 22 | 3.3464 |
|
71 |
+
| 2.1606 | 23.0 | 23 | 3.9334 |
|
72 |
+
| 2.1419 | 24.0 | 24 | 1.7512 |
|
73 |
+
| 2.1419 | 25.0 | 25 | 2.5855 |
|
74 |
+
| 2.2265 | 26.0 | 26 | 2.2896 |
|
75 |
+
| 2.2265 | 27.0 | 27 | 2.3118 |
|
76 |
+
| 2.2539 | 28.0 | 28 | 2.9997 |
|
77 |
+
| 2.2539 | 29.0 | 29 | 3.0682 |
|
78 |
+
| 2.3866 | 30.0 | 30 | 3.3435 |
|
79 |
+
| 2.3866 | 31.0 | 31 | 3.5848 |
|
80 |
+
| 2.1788 | 32.0 | 32 | 2.4658 |
|
81 |
+
| 2.1788 | 33.0 | 33 | 2.4060 |
|
82 |
+
| 2.0932 | 34.0 | 34 | 2.8497 |
|
83 |
+
| 2.0932 | 35.0 | 35 | 3.8500 |
|
84 |
+
| 1.9799 | 36.0 | 36 | 1.9458 |
|
85 |
+
| 1.9799 | 37.0 | 37 | 2.4557 |
|
86 |
+
| 2.0164 | 38.0 | 38 | 3.3370 |
|
87 |
+
| 2.0164 | 39.0 | 39 | 3.6850 |
|
88 |
+
| 2.1732 | 40.0 | 40 | 1.7986 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.26.0
|
94 |
+
- Pytorch 1.13.1+cu116
|
95 |
+
- Datasets 2.9.0
|
96 |
+
- Tokenizers 0.13.2
|