henryscheible
commited on
Commit
•
5864493
1
Parent(s):
1fbef7d
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- stereoset
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: xlnet-base-cased_stereoset_finetuned
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: stereoset
|
17 |
+
type: stereoset
|
18 |
+
config: intersentence
|
19 |
+
split: validation
|
20 |
+
args: intersentence
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.7441130298273155
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# xlnet-base-cased_stereoset_finetuned
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the stereoset dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.0332
|
35 |
+
- Accuracy: 0.7441
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 5e-05
|
55 |
+
- train_batch_size: 128
|
56 |
+
- eval_batch_size: 64
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 10
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| No log | 0.21 | 5 | 0.7165 | 0.5055 |
|
67 |
+
| No log | 0.42 | 10 | 0.6932 | 0.5 |
|
68 |
+
| No log | 0.62 | 15 | 0.6971 | 0.5047 |
|
69 |
+
| No log | 0.83 | 20 | 0.7107 | 0.4953 |
|
70 |
+
| No log | 1.04 | 25 | 0.6895 | 0.5047 |
|
71 |
+
| No log | 1.25 | 30 | 0.6715 | 0.5840 |
|
72 |
+
| No log | 1.46 | 35 | 0.6476 | 0.6476 |
|
73 |
+
| No log | 1.67 | 40 | 0.6150 | 0.6970 |
|
74 |
+
| No log | 1.88 | 45 | 0.6170 | 0.6884 |
|
75 |
+
| No log | 2.08 | 50 | 0.6065 | 0.6797 |
|
76 |
+
| No log | 2.29 | 55 | 0.5865 | 0.7033 |
|
77 |
+
| No log | 2.5 | 60 | 0.5899 | 0.7064 |
|
78 |
+
| No log | 2.71 | 65 | 0.5980 | 0.7151 |
|
79 |
+
| No log | 2.92 | 70 | 0.5890 | 0.7229 |
|
80 |
+
| No log | 3.12 | 75 | 0.5930 | 0.7190 |
|
81 |
+
| No log | 3.33 | 80 | 0.6430 | 0.7049 |
|
82 |
+
| No log | 3.54 | 85 | 0.6677 | 0.7198 |
|
83 |
+
| No log | 3.75 | 90 | 0.6076 | 0.7370 |
|
84 |
+
| No log | 3.96 | 95 | 0.6041 | 0.7339 |
|
85 |
+
| No log | 4.17 | 100 | 0.6324 | 0.7323 |
|
86 |
+
| No log | 4.38 | 105 | 0.6990 | 0.7308 |
|
87 |
+
| No log | 4.58 | 110 | 0.7081 | 0.7433 |
|
88 |
+
| No log | 4.79 | 115 | 0.6549 | 0.7237 |
|
89 |
+
| No log | 5.0 | 120 | 0.6868 | 0.7072 |
|
90 |
+
| No log | 5.21 | 125 | 0.6525 | 0.7363 |
|
91 |
+
| No log | 5.42 | 130 | 0.7622 | 0.7418 |
|
92 |
+
| No log | 5.62 | 135 | 0.7730 | 0.7402 |
|
93 |
+
| No log | 5.83 | 140 | 0.7788 | 0.7449 |
|
94 |
+
| No log | 6.04 | 145 | 0.7609 | 0.7347 |
|
95 |
+
| No log | 6.25 | 150 | 0.8058 | 0.7323 |
|
96 |
+
| No log | 6.46 | 155 | 0.8525 | 0.7331 |
|
97 |
+
| No log | 6.67 | 160 | 0.8504 | 0.7339 |
|
98 |
+
| No log | 6.88 | 165 | 0.8424 | 0.7300 |
|
99 |
+
| No log | 7.08 | 170 | 0.8413 | 0.7394 |
|
100 |
+
| No log | 7.29 | 175 | 0.8808 | 0.7268 |
|
101 |
+
| No log | 7.5 | 180 | 0.9058 | 0.7292 |
|
102 |
+
| No log | 7.71 | 185 | 0.9338 | 0.7363 |
|
103 |
+
| No log | 7.92 | 190 | 0.9412 | 0.7370 |
|
104 |
+
| No log | 8.12 | 195 | 0.9453 | 0.7339 |
|
105 |
+
| No log | 8.33 | 200 | 0.9544 | 0.7394 |
|
106 |
+
| No log | 8.54 | 205 | 0.9664 | 0.7402 |
|
107 |
+
| No log | 8.75 | 210 | 0.9840 | 0.7339 |
|
108 |
+
| No log | 8.96 | 215 | 0.9896 | 0.7370 |
|
109 |
+
| No log | 9.17 | 220 | 1.0239 | 0.7410 |
|
110 |
+
| No log | 9.38 | 225 | 1.0306 | 0.7418 |
|
111 |
+
| No log | 9.58 | 230 | 1.0358 | 0.7402 |
|
112 |
+
| No log | 9.79 | 235 | 1.0351 | 0.7410 |
|
113 |
+
| No log | 10.0 | 240 | 1.0332 | 0.7441 |
|
114 |
+
|
115 |
+
|
116 |
+
### Framework versions
|
117 |
+
|
118 |
+
- Transformers 4.26.1
|
119 |
+
- Pytorch 1.13.1
|
120 |
+
- Datasets 2.9.0
|
121 |
+
- Tokenizers 0.13.2
|