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-cased-sigir-support-no-label-40
|
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-cased-sigir-support-no-label-40
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.1107
|
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: 4e-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 |
+
| 2.7638 | 1.0 | 246 | 2.2805 |
|
50 |
+
| 2.1924 | 2.0 | 492 | 1.9602 |
|
51 |
+
| 1.8921 | 3.0 | 738 | 1.7992 |
|
52 |
+
| 1.7412 | 4.0 | 984 | 1.7229 |
|
53 |
+
| 1.6311 | 5.0 | 1230 | 1.6165 |
|
54 |
+
| 1.5421 | 6.0 | 1476 | 1.5400 |
|
55 |
+
| 1.4619 | 7.0 | 1722 | 1.5001 |
|
56 |
+
| 1.3846 | 8.0 | 1968 | 1.4381 |
|
57 |
+
| 1.3414 | 9.0 | 2214 | 1.4285 |
|
58 |
+
| 1.2894 | 10.0 | 2460 | 1.4108 |
|
59 |
+
| 1.2467 | 11.0 | 2706 | 1.3460 |
|
60 |
+
| 1.1992 | 12.0 | 2952 | 1.3434 |
|
61 |
+
| 1.1612 | 13.0 | 3198 | 1.2951 |
|
62 |
+
| 1.1266 | 14.0 | 3444 | 1.2518 |
|
63 |
+
| 1.0933 | 15.0 | 3690 | 1.2825 |
|
64 |
+
| 1.0625 | 16.0 | 3936 | 1.2523 |
|
65 |
+
| 1.0386 | 17.0 | 4182 | 1.2251 |
|
66 |
+
| 1.0066 | 18.0 | 4428 | 1.2339 |
|
67 |
+
| 0.9755 | 19.0 | 4674 | 1.1887 |
|
68 |
+
| 0.9656 | 20.0 | 4920 | 1.2288 |
|
69 |
+
| 0.9517 | 21.0 | 5166 | 1.1391 |
|
70 |
+
| 0.9207 | 22.0 | 5412 | 1.1718 |
|
71 |
+
| 0.8964 | 23.0 | 5658 | 1.1850 |
|
72 |
+
| 0.8891 | 24.0 | 5904 | 1.1306 |
|
73 |
+
| 0.8564 | 25.0 | 6150 | 1.1956 |
|
74 |
+
| 0.851 | 26.0 | 6396 | 1.1263 |
|
75 |
+
| 0.8331 | 27.0 | 6642 | 1.1060 |
|
76 |
+
| 0.8143 | 28.0 | 6888 | 1.0689 |
|
77 |
+
| 0.7972 | 29.0 | 7134 | 1.0772 |
|
78 |
+
| 0.7857 | 30.0 | 7380 | 1.1103 |
|
79 |
+
| 0.7687 | 31.0 | 7626 | 1.1635 |
|
80 |
+
| 0.7653 | 32.0 | 7872 | 1.0736 |
|
81 |
+
| 0.777 | 33.0 | 8118 | 1.1103 |
|
82 |
+
| 0.741 | 34.0 | 8364 | 1.0830 |
|
83 |
+
| 0.7408 | 35.0 | 8610 | 1.0809 |
|
84 |
+
| 0.736 | 36.0 | 8856 | 1.0894 |
|
85 |
+
| 0.7362 | 37.0 | 9102 | 1.0691 |
|
86 |
+
| 0.727 | 38.0 | 9348 | 1.0519 |
|
87 |
+
| 0.715 | 39.0 | 9594 | 1.0919 |
|
88 |
+
| 0.7286 | 40.0 | 9840 | 1.1107 |
|
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
|