Hugging Face's logo

aiface
/
velectra-base_v2

Text Classification
Transformers
Safetensors
electra
Generated from Trainer
Model card Files
xet
 Community
aiface commited on
Commit
f056406
·
verified ·
1 Parent(s): 5b46fa6

Model save

Browse files
Files changed (4) hide show
  1. README.md +86 -0
  2. classification_report_test.txt +14 -0
  3. confusion_matrix_test.csv +4 -0
  4. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: FPTAI/velectra-base-discriminator-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: velectra-base_v2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # velectra-base_v2
17
+
18
+ This model is a fine-tuned version of [FPTAI/velectra-base-discriminator-cased](https://huggingface.co/FPTAI/velectra-base-discriminator-cased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5503
21
+ - Accuracy: 0.9242
22
+ - Precision Macro: 0.8370
23
+ - Recall Macro: 0.7946
24
+ - F1 Macro: 0.8125
25
+ - F1 Weighted: 0.9222
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 3e-05
45
+ - train_batch_size: 64
46
+ - eval_batch_size: 64
47
+ - seed: 42
48
+ - gradient_accumulation_steps: 2
49
+ - total_train_batch_size: 128
50
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 20
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | F1 Weighted |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:-----------:|
59
+ | 0.5452 | 1.0 | 90 | 0.2734 | 0.9071 | 0.8647 | 0.6926 | 0.7190 | 0.8965 |
60
+ | 0.2546 | 2.0 | 180 | 0.2530 | 0.9198 | 0.8318 | 0.7882 | 0.8059 | 0.9176 |
61
+ | 0.1788 | 3.0 | 270 | 0.2528 | 0.9223 | 0.8241 | 0.7732 | 0.7929 | 0.9193 |
62
+ | 0.1323 | 4.0 | 360 | 0.2605 | 0.9261 | 0.8473 | 0.8000 | 0.8197 | 0.9241 |
63
+ | 0.0901 | 5.0 | 450 | 0.2840 | 0.9305 | 0.8839 | 0.7986 | 0.8303 | 0.9276 |
64
+ | 0.0682 | 6.0 | 540 | 0.3434 | 0.9210 | 0.8458 | 0.8007 | 0.8197 | 0.9192 |
65
+ | 0.0482 | 7.0 | 630 | 0.3689 | 0.9191 | 0.7970 | 0.8197 | 0.8073 | 0.9206 |
66
+ | 0.0443 | 8.0 | 720 | 0.3906 | 0.9223 | 0.8315 | 0.7728 | 0.7952 | 0.9191 |
67
+ | 0.0275 | 9.0 | 810 | 0.4178 | 0.9210 | 0.8717 | 0.7504 | 0.7861 | 0.9155 |
68
+ | 0.028 | 10.0 | 900 | 0.4642 | 0.9103 | 0.7837 | 0.7837 | 0.7835 | 0.9103 |
69
+ | 0.02 | 11.0 | 990 | 0.4823 | 0.9179 | 0.8459 | 0.7694 | 0.7971 | 0.9143 |
70
+ | 0.0122 | 12.0 | 1080 | 0.5070 | 0.9179 | 0.8594 | 0.7853 | 0.8136 | 0.9151 |
71
+ | 0.0098 | 13.0 | 1170 | 0.5093 | 0.9248 | 0.8387 | 0.7911 | 0.8106 | 0.9225 |
72
+ | 0.0108 | 14.0 | 1260 | 0.5309 | 0.9248 | 0.8678 | 0.7783 | 0.8098 | 0.9212 |
73
+ | 0.0101 | 15.0 | 1350 | 0.5214 | 0.9261 | 0.8623 | 0.7669 | 0.7986 | 0.9216 |
74
+ | 0.0076 | 16.0 | 1440 | 0.5352 | 0.9242 | 0.8653 | 0.7737 | 0.8054 | 0.9203 |
75
+ | 0.0042 | 17.0 | 1530 | 0.5533 | 0.9198 | 0.8163 | 0.7870 | 0.8000 | 0.9181 |
76
+ | 0.0058 | 18.0 | 1620 | 0.5503 | 0.9255 | 0.8574 | 0.7871 | 0.8138 | 0.9225 |
77
+ | 0.0034 | 19.0 | 1710 | 0.5590 | 0.9248 | 0.8349 | 0.8035 | 0.8173 | 0.9233 |
78
+ | 0.0029 | 20.0 | 1800 | 0.5503 | 0.9242 | 0.8370 | 0.7946 | 0.8125 | 0.9222 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.55.0
84
+ - Pytorch 2.7.0+cu126
85
+ - Datasets 4.0.0
86
+ - Tokenizers 0.21.4
classification_report_test.txt ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ negative 0.91 0.95 0.93 1409
4
+ neutral 0.64 0.35 0.46 167
5
+ positive 0.93 0.94 0.93 1590
6
+
7
+ accuracy 0.91 3166
8
+ macro avg 0.83 0.75 0.77 3166
9
+ weighted avg 0.90 0.91 0.91 3166
10
+
11
+ Confusion matrix:
12
+ [[1339 14 56]
13
+ [ 52 59 56]
14
+ [ 84 19 1487]]
confusion_matrix_test.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ ,negative,neutral,positive
2
+ negative,1339,14,56
3
+ neutral,52,59,56
4
+ positive,84,19,1487
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4185f792719ee181d83a62e30c4e26666b317a0b92310490d5dc0780a5e2d1a
3
  size 442668636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b031fff2a96a14d327611c8035a8a2036191620849a67e52541ebb29d12afed
3
  size 442668636