muhtasham commited on
Commit
426f389
1 Parent(s): 48615e4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: finetuned-base_mini
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: 0.9076
26
+ - name: F1
27
+ type: f1
28
+ value: 0.9515621723631789
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
+ # finetuned-base_mini
35
+
36
+ This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the imdb dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.3938
39
+ - Accuracy: 0.9076
40
+ - F1: 0.9516
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: 128
61
+ - eval_batch_size: 128
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
+ | 0.354 | 2.55 | 500 | 0.2300 | 0.9116 | 0.9538 |
72
+ | 0.2086 | 5.1 | 1000 | 0.3182 | 0.8815 | 0.9370 |
73
+ | 0.1401 | 7.65 | 1500 | 0.2160 | 0.9241 | 0.9605 |
74
+ | 0.0902 | 10.2 | 2000 | 0.4684 | 0.8722 | 0.9317 |
75
+ | 0.0654 | 12.76 | 2500 | 0.4885 | 0.8747 | 0.9332 |
76
+ | 0.043 | 15.31 | 3000 | 0.3938 | 0.9076 | 0.9516 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.25.0
82
+ - Pytorch 1.12.1+cu113
83
+ - Datasets 2.7.1
84
+ - Tokenizers 0.13.2