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-LR100-0-prepend-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-LR100-0-prepend-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: 1.1764
|
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 |
+
| 2.6453 | 1.0 | 3 | 2.0522 |
|
50 |
+
| 2.0488 | 2.0 | 6 | 1.7600 |
|
51 |
+
| 1.9917 | 3.0 | 9 | 2.3036 |
|
52 |
+
| 1.6084 | 4.0 | 12 | 1.4050 |
|
53 |
+
| 1.856 | 5.0 | 15 | 1.3598 |
|
54 |
+
| 1.6471 | 6.0 | 18 | 1.5274 |
|
55 |
+
| 1.2358 | 7.0 | 21 | 1.6642 |
|
56 |
+
| 1.4355 | 8.0 | 24 | 1.6109 |
|
57 |
+
| 1.5753 | 9.0 | 27 | 1.8690 |
|
58 |
+
| 1.5374 | 10.0 | 30 | 1.7986 |
|
59 |
+
| 1.5063 | 11.0 | 33 | 1.4979 |
|
60 |
+
| 1.2185 | 12.0 | 36 | 0.7390 |
|
61 |
+
| 1.6042 | 13.0 | 39 | 1.1280 |
|
62 |
+
| 1.1938 | 14.0 | 42 | 1.1252 |
|
63 |
+
| 1.3215 | 15.0 | 45 | 1.6827 |
|
64 |
+
| 1.0789 | 16.0 | 48 | 1.6349 |
|
65 |
+
| 1.095 | 17.0 | 51 | 2.6303 |
|
66 |
+
| 1.0088 | 18.0 | 54 | 0.9429 |
|
67 |
+
| 1.015 | 19.0 | 57 | 1.4165 |
|
68 |
+
| 1.2432 | 20.0 | 60 | 2.1061 |
|
69 |
+
| 1.3365 | 21.0 | 63 | 1.5785 |
|
70 |
+
| 1.2704 | 22.0 | 66 | 2.1850 |
|
71 |
+
| 0.972 | 23.0 | 69 | 1.7769 |
|
72 |
+
| 0.9052 | 24.0 | 72 | 1.5376 |
|
73 |
+
| 0.976 | 25.0 | 75 | 2.1072 |
|
74 |
+
| 1.1134 | 26.0 | 78 | 2.4425 |
|
75 |
+
| 0.8328 | 27.0 | 81 | 1.5937 |
|
76 |
+
| 1.1662 | 28.0 | 84 | 1.3542 |
|
77 |
+
| 0.8575 | 29.0 | 87 | 1.2236 |
|
78 |
+
| 0.728 | 30.0 | 90 | 1.2229 |
|
79 |
+
| 1.1601 | 31.0 | 93 | 2.3723 |
|
80 |
+
| 0.9426 | 32.0 | 96 | 1.6974 |
|
81 |
+
| 0.8246 | 33.0 | 99 | 1.6610 |
|
82 |
+
| 0.9777 | 34.0 | 102 | 1.1179 |
|
83 |
+
| 0.7588 | 35.0 | 105 | 1.8809 |
|
84 |
+
| 0.6929 | 36.0 | 108 | 1.9128 |
|
85 |
+
| 0.6794 | 37.0 | 111 | 1.2689 |
|
86 |
+
| 0.811 | 38.0 | 114 | 1.6715 |
|
87 |
+
| 0.6805 | 39.0 | 117 | 2.0424 |
|
88 |
+
| 0.9157 | 40.0 | 120 | 1.4210 |
|
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
|