update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- sentiment140
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: Sentiment140_ELECTRA_5E
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: sentiment140
|
17 |
+
type: sentiment140
|
18 |
+
config: sentiment140
|
19 |
+
split: train
|
20 |
+
args: sentiment140
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.84
|
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 |
+
# Sentiment140_ELECTRA_5E
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the sentiment140 dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.5410
|
35 |
+
- Accuracy: 0.84
|
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: 1e-05
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 5
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| 0.6896 | 0.08 | 50 | 0.6605 | 0.7133 |
|
67 |
+
| 0.6664 | 0.16 | 100 | 0.6054 | 0.7133 |
|
68 |
+
| 0.5915 | 0.24 | 150 | 0.4777 | 0.8333 |
|
69 |
+
| 0.5053 | 0.32 | 200 | 0.4735 | 0.7733 |
|
70 |
+
| 0.4946 | 0.4 | 250 | 0.3847 | 0.8267 |
|
71 |
+
| 0.4578 | 0.48 | 300 | 0.4025 | 0.8067 |
|
72 |
+
| 0.4724 | 0.56 | 350 | 0.3642 | 0.8333 |
|
73 |
+
| 0.4309 | 0.64 | 400 | 0.3762 | 0.86 |
|
74 |
+
| 0.4818 | 0.72 | 450 | 0.3829 | 0.84 |
|
75 |
+
| 0.416 | 0.8 | 500 | 0.3599 | 0.8467 |
|
76 |
+
| 0.4201 | 0.88 | 550 | 0.3469 | 0.8533 |
|
77 |
+
| 0.3664 | 0.96 | 600 | 0.3462 | 0.8467 |
|
78 |
+
| 0.4289 | 1.04 | 650 | 0.3470 | 0.86 |
|
79 |
+
| 0.3859 | 1.12 | 700 | 0.3440 | 0.8533 |
|
80 |
+
| 0.3599 | 1.2 | 750 | 0.3475 | 0.8533 |
|
81 |
+
| 0.3287 | 1.28 | 800 | 0.3524 | 0.8467 |
|
82 |
+
| 0.3331 | 1.36 | 850 | 0.3475 | 0.8733 |
|
83 |
+
| 0.3236 | 1.44 | 900 | 0.3657 | 0.8467 |
|
84 |
+
| 0.3502 | 1.52 | 950 | 0.3525 | 0.84 |
|
85 |
+
| 0.3702 | 1.6 | 1000 | 0.3655 | 0.8333 |
|
86 |
+
| 0.3323 | 1.68 | 1050 | 0.3405 | 0.84 |
|
87 |
+
| 0.3452 | 1.76 | 1100 | 0.3376 | 0.8533 |
|
88 |
+
| 0.3742 | 1.84 | 1150 | 0.3481 | 0.8533 |
|
89 |
+
| 0.3145 | 1.92 | 1200 | 0.3472 | 0.86 |
|
90 |
+
| 0.3657 | 2.0 | 1250 | 0.3302 | 0.8733 |
|
91 |
+
| 0.2601 | 2.08 | 1300 | 0.3612 | 0.86 |
|
92 |
+
| 0.2954 | 2.16 | 1350 | 0.3640 | 0.8533 |
|
93 |
+
| 0.2888 | 2.24 | 1400 | 0.3670 | 0.8467 |
|
94 |
+
| 0.2572 | 2.32 | 1450 | 0.4118 | 0.84 |
|
95 |
+
| 0.2955 | 2.4 | 1500 | 0.3811 | 0.86 |
|
96 |
+
| 0.2431 | 2.48 | 1550 | 0.4221 | 0.84 |
|
97 |
+
| 0.318 | 2.56 | 1600 | 0.3844 | 0.8467 |
|
98 |
+
| 0.2615 | 2.64 | 1650 | 0.4109 | 0.8333 |
|
99 |
+
| 0.2389 | 2.72 | 1700 | 0.4420 | 0.8467 |
|
100 |
+
| 0.2983 | 2.8 | 1750 | 0.4203 | 0.8467 |
|
101 |
+
| 0.2828 | 2.88 | 1800 | 0.3629 | 0.8733 |
|
102 |
+
| 0.2897 | 2.96 | 1850 | 0.3916 | 0.8733 |
|
103 |
+
| 0.2239 | 3.04 | 1900 | 0.4143 | 0.86 |
|
104 |
+
| 0.2093 | 3.12 | 1950 | 0.4521 | 0.84 |
|
105 |
+
| 0.2438 | 3.2 | 2000 | 0.4271 | 0.8467 |
|
106 |
+
| 0.2282 | 3.28 | 2050 | 0.4548 | 0.8333 |
|
107 |
+
| 0.1918 | 3.36 | 2100 | 0.4533 | 0.86 |
|
108 |
+
| 0.1698 | 3.44 | 2150 | 0.5177 | 0.84 |
|
109 |
+
| 0.2765 | 3.52 | 2200 | 0.4884 | 0.84 |
|
110 |
+
| 0.2282 | 3.6 | 2250 | 0.4697 | 0.8533 |
|
111 |
+
| 0.239 | 3.68 | 2300 | 0.4766 | 0.8533 |
|
112 |
+
| 0.2219 | 3.76 | 2350 | 0.4628 | 0.8533 |
|
113 |
+
| 0.2375 | 3.84 | 2400 | 0.4704 | 0.8533 |
|
114 |
+
| 0.1883 | 3.92 | 2450 | 0.4744 | 0.84 |
|
115 |
+
| 0.2049 | 4.0 | 2500 | 0.4977 | 0.84 |
|
116 |
+
| 0.1958 | 4.08 | 2550 | 0.4906 | 0.84 |
|
117 |
+
| 0.1656 | 4.16 | 2600 | 0.5219 | 0.8333 |
|
118 |
+
| 0.1543 | 4.24 | 2650 | 0.5379 | 0.8333 |
|
119 |
+
| 0.2082 | 4.32 | 2700 | 0.5107 | 0.84 |
|
120 |
+
| 0.1724 | 4.4 | 2750 | 0.5208 | 0.84 |
|
121 |
+
| 0.1778 | 4.48 | 2800 | 0.5238 | 0.84 |
|
122 |
+
| 0.1914 | 4.56 | 2850 | 0.5325 | 0.84 |
|
123 |
+
| 0.2436 | 4.64 | 2900 | 0.5279 | 0.84 |
|
124 |
+
| 0.1662 | 4.72 | 2950 | 0.5295 | 0.84 |
|
125 |
+
| 0.1288 | 4.8 | 3000 | 0.5392 | 0.84 |
|
126 |
+
| 0.2087 | 4.88 | 3050 | 0.5409 | 0.84 |
|
127 |
+
| 0.1612 | 4.96 | 3100 | 0.5410 | 0.84 |
|
128 |
+
|
129 |
+
|
130 |
+
### Framework versions
|
131 |
+
|
132 |
+
- Transformers 4.24.0
|
133 |
+
- Pytorch 1.13.0
|
134 |
+
- Datasets 2.3.2
|
135 |
+
- Tokenizers 0.13.1
|