ppak10 commited on
Commit
6fa464e
·
verified ·
1 Parent(s): d16e460

Trained model with classification head weights

Browse files
Files changed (1) hide show
  1. README.md +79 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: allenai/scibert_scivocab_uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: defect-classification-scibert-baseline-20-epochs
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
+ # defect-classification-scibert-baseline-20-epochs
17
+
18
+ This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2422
21
+ - Accuracy: 0.9124
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 256
42
+ - eval_batch_size: 256
43
+ - seed: 42
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 20
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 1.3805 | 1.0 | 2124 | 0.7077 | 0.8454 |
53
+ | 0.9347 | 2.0 | 4248 | 0.4424 | 0.8740 |
54
+ | 0.782 | 3.0 | 6372 | 0.3730 | 0.8907 |
55
+ | 0.6677 | 4.0 | 8496 | 0.3447 | 0.8957 |
56
+ | 0.6018 | 5.0 | 10620 | 0.3021 | 0.9057 |
57
+ | 0.5746 | 6.0 | 12744 | 0.3155 | 0.8961 |
58
+ | 0.5257 | 7.0 | 14868 | 0.2747 | 0.9100 |
59
+ | 0.5162 | 8.0 | 16992 | 0.2639 | 0.9104 |
60
+ | 0.4955 | 9.0 | 19116 | 0.2921 | 0.8975 |
61
+ | 0.4763 | 10.0 | 21240 | 0.2684 | 0.9036 |
62
+ | 0.4579 | 11.0 | 23364 | 0.2657 | 0.9069 |
63
+ | 0.454 | 12.0 | 25488 | 0.2535 | 0.9114 |
64
+ | 0.4384 | 13.0 | 27612 | 0.2626 | 0.9039 |
65
+ | 0.428 | 14.0 | 29736 | 0.2620 | 0.9011 |
66
+ | 0.4262 | 15.0 | 31860 | 0.2411 | 0.9141 |
67
+ | 0.425 | 16.0 | 33984 | 0.2586 | 0.9035 |
68
+ | 0.4141 | 17.0 | 36108 | 0.2446 | 0.9117 |
69
+ | 0.4129 | 18.0 | 38232 | 0.2506 | 0.9073 |
70
+ | 0.4105 | 19.0 | 40356 | 0.2424 | 0.9132 |
71
+ | 0.4099 | 20.0 | 42480 | 0.2422 | 0.9124 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.47.0
77
+ - Pytorch 2.5.1+cu124
78
+ - Datasets 3.2.0
79
+ - Tokenizers 0.21.0