ArafatBHossain commited on
Commit
e67255d
1 Parent(s): f7235a0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - emotion
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: distiled_flip_model_emotion_alpha_0.8_epoch7_v1
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: emotion
17
+ type: emotion
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9435
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
+ # distiled_flip_model_emotion_alpha_0.8_epoch7_v1
31
+
32
+ This model is a fine-tuned version of [ArafatBHossain/distill_bert_fine_tuned_emotion_dataset](https://huggingface.co/ArafatBHossain/distill_bert_fine_tuned_emotion_dataset) on the emotion dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1583
35
+ - Accuracy: 0.9435
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: 8
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: 7
61
+ - mixed_precision_training: Native AMP
62
+
63
+ ### Training results
64
+
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | 0.2013 | 1.0 | 2000 | 0.2653 | 0.9355 |
68
+ | 0.1625 | 2.0 | 4000 | 0.2537 | 0.9365 |
69
+ | 0.1262 | 3.0 | 6000 | 0.1934 | 0.935 |
70
+ | 0.1048 | 4.0 | 8000 | 0.1813 | 0.9435 |
71
+ | 0.0777 | 5.0 | 10000 | 0.1500 | 0.941 |
72
+ | 0.0614 | 6.0 | 12000 | 0.1591 | 0.944 |
73
+ | 0.0465 | 7.0 | 14000 | 0.1583 | 0.9435 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.23.1
79
+ - Pytorch 1.11.0
80
+ - Datasets 2.6.1
81
+ - Tokenizers 0.12.1