Hugging Face's logo

Heather-Driver
/
distilbert-classn-LAlg-multihead-context-width-2

Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
Heather-Driver commited on
Commit
b554995
·
verified ·
1 Parent(s): 6936ba1

Classification Training

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: dslim/distilbert-NER
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ - precision
11
+ - recall
12
+ model-index:
13
+ - name: distilbert-classn-LAlg-multihead-context-width-2
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # distilbert-classn-LAlg-multihead-context-width-2
21
+
22
+ This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.8459
25
+ - Accuracy: 0.7698
26
+ - F1: 0.7717
27
+ - Precision: 0.8049
28
+ - Recall: 0.7698
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: 1e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
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
+ - lr_scheduler_warmup_steps: 500
54
+ - num_epochs: 25
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
60
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
61
+ | 2.4794 | 1.3514 | 50 | 2.4632 | 0.0952 | 0.0337 | 0.0269 | 0.0952 |
62
+ | 2.4695 | 2.7027 | 100 | 2.4386 | 0.0794 | 0.0395 | 0.0332 | 0.0794 |
63
+ | 2.4253 | 4.0541 | 150 | 2.4152 | 0.0556 | 0.0351 | 0.0299 | 0.0556 |
64
+ | 2.3921 | 5.4054 | 200 | 2.3838 | 0.0794 | 0.0818 | 0.1342 | 0.0794 |
65
+ | 2.3137 | 6.7568 | 250 | 2.3342 | 0.1349 | 0.1256 | 0.1343 | 0.1349 |
66
+ | 2.2091 | 8.1081 | 300 | 2.2389 | 0.2460 | 0.2390 | 0.2692 | 0.2460 |
67
+ | 2.0017 | 9.4595 | 350 | 2.0460 | 0.3889 | 0.3931 | 0.4582 | 0.3889 |
68
+ | 1.6241 | 10.8108 | 400 | 1.7016 | 0.5476 | 0.5285 | 0.5501 | 0.5476 |
69
+ | 1.1356 | 12.1622 | 450 | 1.3357 | 0.6825 | 0.6735 | 0.7118 | 0.6825 |
70
+ | 0.7122 | 13.5135 | 500 | 1.0433 | 0.7540 | 0.7501 | 0.7818 | 0.7540 |
71
+ | 0.4063 | 14.8649 | 550 | 0.9308 | 0.7540 | 0.7541 | 0.7860 | 0.7540 |
72
+ | 0.2025 | 16.2162 | 600 | 0.8688 | 0.7857 | 0.7838 | 0.8068 | 0.7857 |
73
+ | 0.1226 | 17.5676 | 650 | 0.8284 | 0.7698 | 0.7704 | 0.8092 | 0.7698 |
74
+ | 0.0677 | 18.9189 | 700 | 0.8517 | 0.7778 | 0.7784 | 0.8180 | 0.7778 |
75
+ | 0.0386 | 20.2703 | 750 | 0.8447 | 0.7857 | 0.7859 | 0.8250 | 0.7857 |
76
+ | 0.0299 | 21.6216 | 800 | 0.8531 | 0.7698 | 0.7693 | 0.7984 | 0.7698 |
77
+ | 0.0236 | 22.9730 | 850 | 0.8446 | 0.7698 | 0.7717 | 0.8049 | 0.7698 |
78
+ | 0.0182 | 24.3243 | 900 | 0.8459 | 0.7698 | 0.7717 | 0.8049 | 0.7698 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.48.3
84
+ - Pytorch 2.5.1+cu124
85
+ - Datasets 3.3.1
86
+ - Tokenizers 0.21.0