update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- glue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: bert-small-finetuned-glue-rte
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: glue
|
17 |
+
type: glue
|
18 |
+
config: rte
|
19 |
+
split: train
|
20 |
+
args: rte
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.631768953068592
|
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 |
+
# bert-small-finetuned-glue-rte
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the glue dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 2.8715
|
35 |
+
- Accuracy: 0.6318
|
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: 2e-05
|
55 |
+
- train_batch_size: 8
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 16
|
59 |
+
- total_train_batch_size: 128
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: linear
|
62 |
+
- num_epochs: 50
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| No log | 2.62 | 50 | 1.8285 | 0.6318 |
|
69 |
+
| No log | 5.26 | 100 | 2.0806 | 0.6462 |
|
70 |
+
| No log | 7.87 | 150 | 2.1598 | 0.6282 |
|
71 |
+
| No log | 10.51 | 200 | 2.2774 | 0.6318 |
|
72 |
+
| No log | 13.15 | 250 | 2.3676 | 0.6245 |
|
73 |
+
| No log | 15.77 | 300 | 2.4581 | 0.6462 |
|
74 |
+
| No log | 18.41 | 350 | 2.6175 | 0.6354 |
|
75 |
+
| No log | 21.05 | 400 | 2.6697 | 0.6354 |
|
76 |
+
| No log | 23.67 | 450 | 2.7717 | 0.6354 |
|
77 |
+
| 0.0101 | 26.31 | 500 | 2.7975 | 0.6462 |
|
78 |
+
| 0.0101 | 28.92 | 550 | 2.8532 | 0.6390 |
|
79 |
+
| 0.0101 | 31.56 | 600 | 2.9054 | 0.6209 |
|
80 |
+
| 0.0101 | 34.21 | 650 | 2.8715 | 0.6318 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.21.2
|
86 |
+
- Pytorch 1.12.1+cu113
|
87 |
+
- Datasets 2.4.0
|
88 |
+
- Tokenizers 0.12.1
|