franac1 commited on
Commit
9be8257
·
verified ·
1 Parent(s): 91413ad

End of training

Browse files
Files changed (2) hide show
  1. README.md +83 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: franac1/mlm_hate
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: hate_speech
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # hate_speech
20
+
21
+ This model is a fine-tuned version of [franac1/mlm_hate](https://huggingface.co/franac1/mlm_hate) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6490
24
+ - Accuracy: 0.7294
25
+ - Auc Score: 0.7950
26
+ - F1: 0.7694
27
+ - Precision: 0.7318
28
+ - Recall: 0.8110
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 16
50
+ - seed: 42
51
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 3
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc Score | F1 | Precision | Recall |
58
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:---------:|:------:|
59
+ | 0.7015 | 0.1736 | 100 | 0.6727 | 0.6095 | 0.6569 | 0.6584 | 0.6415 | 0.6762 |
60
+ | 0.6507 | 0.3472 | 200 | 0.6320 | 0.6476 | 0.7127 | 0.7422 | 0.6259 | 0.9116 |
61
+ | 0.6477 | 0.5208 | 300 | 0.6226 | 0.6667 | 0.7306 | 0.7067 | 0.6925 | 0.7215 |
62
+ | 0.6693 | 0.6944 | 400 | 0.6237 | 0.6753 | 0.7412 | 0.7230 | 0.6883 | 0.7613 |
63
+ | 0.5823 | 0.8681 | 500 | 0.5898 | 0.6796 | 0.7597 | 0.7479 | 0.6652 | 0.8541 |
64
+ | 0.5678 | 1.0417 | 600 | 0.6616 | 0.6876 | 0.7775 | 0.7581 | 0.6661 | 0.8796 |
65
+ | 0.4947 | 1.2153 | 700 | 0.6208 | 0.7054 | 0.7812 | 0.7113 | 0.7825 | 0.6519 |
66
+ | 0.5419 | 1.3889 | 800 | 0.6291 | 0.6728 | 0.7815 | 0.7616 | 0.6405 | 0.9392 |
67
+ | 0.4772 | 1.5625 | 900 | 0.6225 | 0.7060 | 0.7863 | 0.7677 | 0.6852 | 0.8729 |
68
+ | 0.485 | 1.7361 | 1000 | 0.5864 | 0.7263 | 0.7969 | 0.7570 | 0.7484 | 0.7657 |
69
+ | 0.48 | 1.9097 | 1100 | 0.5785 | 0.7220 | 0.7943 | 0.7738 | 0.7072 | 0.8541 |
70
+ | 0.4273 | 2.0833 | 1200 | 0.6733 | 0.7165 | 0.7853 | 0.7696 | 0.7026 | 0.8508 |
71
+ | 0.3691 | 2.2569 | 1300 | 0.6891 | 0.7122 | 0.7942 | 0.7685 | 0.6956 | 0.8586 |
72
+ | 0.3806 | 2.4306 | 1400 | 0.6315 | 0.7171 | 0.7908 | 0.7459 | 0.7459 | 0.7459 |
73
+ | 0.3762 | 2.6042 | 1500 | 0.6407 | 0.7183 | 0.7913 | 0.7677 | 0.7095 | 0.8365 |
74
+ | 0.3665 | 2.7778 | 1600 | 0.6385 | 0.7263 | 0.7919 | 0.7639 | 0.7347 | 0.7956 |
75
+ | 0.3496 | 2.9514 | 1700 | 0.6490 | 0.7294 | 0.7950 | 0.7694 | 0.7318 | 0.8110 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.52.4
81
+ - Pytorch 2.6.0+cu124
82
+ - Datasets 3.6.0
83
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91515220d6c48e48db1dfcb7c8b0203afa11c2a6e554ecb07782cab8e2f3b027
3
  size 442499064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57922207194c8be4fe5697ced3c78ed9e98da6a51458df9417b2592043fe0bc8
3
  size 442499064