DandinPower commited on
Commit
5da878c
1 Parent(s): 376345d

End of training

Browse files
Files changed (1) hide show
  1. README.md +84 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: mit
5
+ base_model: microsoft/deberta-v3-xsmall
6
+ tags:
7
+ - nycu-112-2-datamining-hw2
8
+ - generated_from_trainer
9
+ datasets:
10
+ - DandinPower/review_cleanonlytitleandtext
11
+ metrics:
12
+ - accuracy
13
+ model-index:
14
+ - name: deberta-v3-xsmall-cotat-recommened-hp
15
+ results:
16
+ - task:
17
+ name: Text Classification
18
+ type: text-classification
19
+ dataset:
20
+ name: DandinPower/review_cleanonlytitleandtext
21
+ type: DandinPower/review_cleanonlytitleandtext
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.6262857142857143
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # deberta-v3-xsmall-cotat-recommened-hp
32
+
33
+ This model is a fine-tuned version of [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) on the DandinPower/review_cleanonlytitleandtext dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8783
36
+ - Accuracy: 0.6263
37
+ - Macro F1: 0.6285
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 4.5e-05
57
+ - train_batch_size: 16
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 8
61
+ - total_train_batch_size: 128
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 1000
65
+ - num_epochs: 3
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
70
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|
71
+ | 1.61 | 0.4571 | 100 | 1.6076 | 0.22 | 0.1631 |
72
+ | 1.5063 | 0.9143 | 200 | 1.2854 | 0.4094 | 0.2942 |
73
+ | 1.2016 | 1.3714 | 300 | 1.0481 | 0.5529 | 0.5311 |
74
+ | 1.0219 | 1.8286 | 400 | 0.9338 | 0.6093 | 0.6020 |
75
+ | 0.9362 | 2.2857 | 500 | 0.8919 | 0.6261 | 0.6239 |
76
+ | 0.9097 | 2.7429 | 600 | 0.8783 | 0.6263 | 0.6285 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.40.2
82
+ - Pytorch 2.3.0+cu121
83
+ - Datasets 2.19.1
84
+ - Tokenizers 0.19.1