philschmid HF staff commited on
Commit
874eb28
1 Parent(s): 4450086

End of training

Browse files
Files changed (2) hide show
  1. README.md +79 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: tiny-bert-sst2-distilled
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: glue
17
+ type: glue
18
+ args: sst2
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.8325688073394495
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # tiny-bert-sst2-distilled
29
+
30
+ This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the glue dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 1.7305
33
+ - Accuracy: 0.8326
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 0.0007199555649276667
53
+ - train_batch_size: 1024
54
+ - eval_batch_size: 1024
55
+ - seed: 33
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 7
59
+ - mixed_precision_training: Native AMP
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
65
+ | 1.77 | 1.0 | 66 | 1.6939 | 0.8165 |
66
+ | 0.729 | 2.0 | 132 | 1.5090 | 0.8326 |
67
+ | 0.5242 | 3.0 | 198 | 1.5369 | 0.8257 |
68
+ | 0.4017 | 4.0 | 264 | 1.7025 | 0.8326 |
69
+ | 0.327 | 5.0 | 330 | 1.6743 | 0.8245 |
70
+ | 0.2749 | 6.0 | 396 | 1.7305 | 0.8337 |
71
+ | 0.2521 | 7.0 | 462 | 1.7305 | 0.8326 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 4.12.3
77
+ - Pytorch 1.9.1
78
+ - Datasets 1.15.1
79
+ - Tokenizers 0.10.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75d65dd3e98959998afadca5d750c56fa5a0dabb3a963ffcdfb81e334aa22310
3
  size 17564583
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76203837509647859ac1f01a7cce7b48d09999ccae518040ec47f17cc31d58b
3
  size 17564583