update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- imdb
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: bert_uncased_L-2_H-128_A-2-finetuned-emotion-finetuned-tweet
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: imdb
|
18 |
+
type: imdb
|
19 |
+
config: plain_text
|
20 |
+
split: train
|
21 |
+
args: plain_text
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.87168
|
26 |
+
- name: F1
|
27 |
+
type: f1
|
28 |
+
value: 0.8716747437975058
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# bert_uncased_L-2_H-128_A-2-finetuned-emotion-finetuned-tweet
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [muhtasham/bert_uncased_L-2_H-128_A-2-finetuned-emotion](https://huggingface.co/muhtasham/bert_uncased_L-2_H-128_A-2-finetuned-emotion) on the imdb dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.4004
|
39 |
+
- Accuracy: 0.8717
|
40 |
+
- F1: 0.8717
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 3e-05
|
60 |
+
- train_batch_size: 64
|
61 |
+
- eval_batch_size: 64
|
62 |
+
- seed: 42
|
63 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
+
- lr_scheduler_type: constant
|
65 |
+
- num_epochs: 200
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
71 |
+
| 0.4751 | 1.28 | 500 | 0.3880 | 0.828 | 0.8277 |
|
72 |
+
| 0.3453 | 2.56 | 1000 | 0.3282 | 0.8608 | 0.8607 |
|
73 |
+
| 0.2973 | 3.84 | 1500 | 0.3140 | 0.8695 | 0.8695 |
|
74 |
+
| 0.26 | 5.12 | 2000 | 0.3154 | 0.8736 | 0.8735 |
|
75 |
+
| 0.2218 | 6.39 | 2500 | 0.3144 | 0.8756 | 0.8756 |
|
76 |
+
| 0.1977 | 7.67 | 3000 | 0.3197 | 0.876 | 0.8760 |
|
77 |
+
| 0.1656 | 8.95 | 3500 | 0.3526 | 0.8737 | 0.8735 |
|
78 |
+
| 0.1404 | 10.23 | 4000 | 0.3865 | 0.8691 | 0.8689 |
|
79 |
+
| 0.121 | 11.51 | 4500 | 0.4004 | 0.8717 | 0.8717 |
|
80 |
+
|
81 |
+
|
82 |
+
### Framework versions
|
83 |
+
|
84 |
+
- Transformers 4.24.0
|
85 |
+
- Pytorch 1.12.1+cu113
|
86 |
+
- Datasets 2.7.0
|
87 |
+
- Tokenizers 0.13.2
|