m-aliabbas1
commited on
Commit
•
85f5c2a
1
Parent(s):
e1bfa31
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: prajjwal1/bert-tiny
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: tinybert_29_med_intents
|
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 |
+
# tinybert_29_med_intents
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4559
|
21 |
+
- Accuracy: 0.9122
|
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: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 50
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 378 | 3.0359 | 0.3448 |
|
53 |
+
| 3.1662 | 2.0 | 756 | 2.7596 | 0.4953 |
|
54 |
+
| 2.7937 | 3.0 | 1134 | 2.4944 | 0.5141 |
|
55 |
+
| 2.4474 | 4.0 | 1512 | 2.2497 | 0.5674 |
|
56 |
+
| 2.4474 | 5.0 | 1890 | 2.0280 | 0.6207 |
|
57 |
+
| 2.1416 | 6.0 | 2268 | 1.8382 | 0.6646 |
|
58 |
+
| 1.8743 | 7.0 | 2646 | 1.6716 | 0.6740 |
|
59 |
+
| 1.6483 | 8.0 | 3024 | 1.5295 | 0.6959 |
|
60 |
+
| 1.6483 | 9.0 | 3402 | 1.4096 | 0.7304 |
|
61 |
+
| 1.4578 | 10.0 | 3780 | 1.3064 | 0.7304 |
|
62 |
+
| 1.3078 | 11.0 | 4158 | 1.2158 | 0.7524 |
|
63 |
+
| 1.1745 | 12.0 | 4536 | 1.1396 | 0.7555 |
|
64 |
+
| 1.1745 | 13.0 | 4914 | 1.0636 | 0.7837 |
|
65 |
+
| 1.0674 | 14.0 | 5292 | 1.0014 | 0.7931 |
|
66 |
+
| 0.9794 | 15.0 | 5670 | 0.9418 | 0.8119 |
|
67 |
+
| 0.8783 | 16.0 | 6048 | 0.8938 | 0.8307 |
|
68 |
+
| 0.8783 | 17.0 | 6426 | 0.8488 | 0.8401 |
|
69 |
+
| 0.8241 | 18.0 | 6804 | 0.8048 | 0.8370 |
|
70 |
+
| 0.7575 | 19.0 | 7182 | 0.7750 | 0.8401 |
|
71 |
+
| 0.7055 | 20.0 | 7560 | 0.7406 | 0.8433 |
|
72 |
+
| 0.7055 | 21.0 | 7938 | 0.7063 | 0.8589 |
|
73 |
+
| 0.6492 | 22.0 | 8316 | 0.6821 | 0.8527 |
|
74 |
+
| 0.6121 | 23.0 | 8694 | 0.6619 | 0.8589 |
|
75 |
+
| 0.5644 | 24.0 | 9072 | 0.6393 | 0.8683 |
|
76 |
+
| 0.5644 | 25.0 | 9450 | 0.6200 | 0.8683 |
|
77 |
+
| 0.5406 | 26.0 | 9828 | 0.5992 | 0.8746 |
|
78 |
+
| 0.5148 | 27.0 | 10206 | 0.5846 | 0.8809 |
|
79 |
+
| 0.4723 | 28.0 | 10584 | 0.5659 | 0.8934 |
|
80 |
+
| 0.4723 | 29.0 | 10962 | 0.5566 | 0.8934 |
|
81 |
+
| 0.4653 | 30.0 | 11340 | 0.5447 | 0.8966 |
|
82 |
+
| 0.4386 | 31.0 | 11718 | 0.5358 | 0.8997 |
|
83 |
+
| 0.4163 | 32.0 | 12096 | 0.5242 | 0.8997 |
|
84 |
+
| 0.4163 | 33.0 | 12474 | 0.5183 | 0.9028 |
|
85 |
+
| 0.404 | 34.0 | 12852 | 0.5113 | 0.9028 |
|
86 |
+
| 0.3849 | 35.0 | 13230 | 0.5005 | 0.9028 |
|
87 |
+
| 0.3677 | 36.0 | 13608 | 0.4966 | 0.9060 |
|
88 |
+
| 0.3677 | 37.0 | 13986 | 0.4908 | 0.9091 |
|
89 |
+
| 0.3652 | 38.0 | 14364 | 0.4843 | 0.9091 |
|
90 |
+
| 0.3533 | 39.0 | 14742 | 0.4784 | 0.9060 |
|
91 |
+
| 0.3362 | 40.0 | 15120 | 0.4733 | 0.9091 |
|
92 |
+
| 0.3362 | 41.0 | 15498 | 0.4703 | 0.9091 |
|
93 |
+
| 0.3403 | 42.0 | 15876 | 0.4668 | 0.9091 |
|
94 |
+
| 0.3268 | 43.0 | 16254 | 0.4642 | 0.9122 |
|
95 |
+
| 0.3229 | 44.0 | 16632 | 0.4642 | 0.9091 |
|
96 |
+
| 0.3177 | 45.0 | 17010 | 0.4606 | 0.9154 |
|
97 |
+
| 0.3177 | 46.0 | 17388 | 0.4575 | 0.9122 |
|
98 |
+
| 0.3137 | 47.0 | 17766 | 0.4574 | 0.9122 |
|
99 |
+
| 0.3067 | 48.0 | 18144 | 0.4562 | 0.9122 |
|
100 |
+
| 0.3054 | 49.0 | 18522 | 0.4561 | 0.9122 |
|
101 |
+
| 0.3054 | 50.0 | 18900 | 0.4559 | 0.9122 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- Transformers 4.34.1
|
107 |
+
- Pytorch 2.1.0+cu118
|
108 |
+
- Datasets 2.14.6
|
109 |
+
- Tokenizers 0.14.1
|