Hugging Face's logo

m-aliabbas1
/
tinybert_29_med_intents

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
m-aliabbas1 commited on
Commit
c1528e6
•
1 Parent(s): 42fbb6a

End of training

Browse files
Files changed (1) hide show
  1. README.md +55 -55
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
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
 
@@ -49,61 +49,61 @@ The following hyperparameters were used during training:
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
 
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: 0.3344
21
+ - Accuracy: 0.9199
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 430 | 2.8232 | 0.4144 |
53
+ | 3.1061 | 2.0 | 860 | 2.4220 | 0.4890 |
54
+ | 2.6532 | 3.0 | 1290 | 2.0921 | 0.5967 |
55
+ | 2.28 | 4.0 | 1720 | 1.8178 | 0.6878 |
56
+ | 1.9726 | 5.0 | 2150 | 1.5987 | 0.7431 |
57
+ | 1.7268 | 6.0 | 2580 | 1.4221 | 0.7569 |
58
+ | 1.5454 | 7.0 | 3010 | 1.2797 | 0.7762 |
59
+ | 1.5454 | 8.0 | 3440 | 1.1608 | 0.7818 |
60
+ | 1.3826 | 9.0 | 3870 | 1.0589 | 0.8039 |
61
+ | 1.2445 | 10.0 | 4300 | 0.9737 | 0.8177 |
62
+ | 1.1266 | 11.0 | 4730 | 0.8920 | 0.8343 |
63
+ | 1.0328 | 12.0 | 5160 | 0.8279 | 0.8398 |
64
+ | 0.9528 | 13.0 | 5590 | 0.7646 | 0.8453 |
65
+ | 0.8538 | 14.0 | 6020 | 0.7186 | 0.8564 |
66
+ | 0.8538 | 15.0 | 6450 | 0.6733 | 0.8619 |
67
+ | 0.7987 | 16.0 | 6880 | 0.6347 | 0.8812 |
68
+ | 0.7367 | 17.0 | 7310 | 0.5945 | 0.8840 |
69
+ | 0.6931 | 18.0 | 7740 | 0.5674 | 0.8950 |
70
+ | 0.6339 | 19.0 | 8170 | 0.5429 | 0.9061 |
71
+ | 0.606 | 20.0 | 8600 | 0.5132 | 0.9033 |
72
+ | 0.5647 | 21.0 | 9030 | 0.4991 | 0.9061 |
73
+ | 0.5647 | 22.0 | 9460 | 0.4709 | 0.9033 |
74
+ | 0.5375 | 23.0 | 9890 | 0.4642 | 0.9116 |
75
+ | 0.4961 | 24.0 | 10320 | 0.4421 | 0.9116 |
76
+ | 0.4695 | 25.0 | 10750 | 0.4390 | 0.9088 |
77
+ | 0.4499 | 26.0 | 11180 | 0.4126 | 0.9088 |
78
+ | 0.4315 | 27.0 | 11610 | 0.4149 | 0.9088 |
79
+ | 0.4005 | 28.0 | 12040 | 0.4036 | 0.9116 |
80
+ | 0.4005 | 29.0 | 12470 | 0.3938 | 0.9033 |
81
+ | 0.3929 | 30.0 | 12900 | 0.3846 | 0.9061 |
82
+ | 0.3707 | 31.0 | 13330 | 0.3856 | 0.9116 |
83
+ | 0.369 | 32.0 | 13760 | 0.3727 | 0.9088 |
84
+ | 0.3517 | 33.0 | 14190 | 0.3739 | 0.9088 |
85
+ | 0.3355 | 34.0 | 14620 | 0.3604 | 0.9088 |
86
+ | 0.3226 | 35.0 | 15050 | 0.3518 | 0.9144 |
87
+ | 0.3226 | 36.0 | 15480 | 0.3570 | 0.9116 |
88
+ | 0.3197 | 37.0 | 15910 | 0.3502 | 0.9144 |
89
+ | 0.3038 | 38.0 | 16340 | 0.3463 | 0.9144 |
90
+ | 0.3038 | 39.0 | 16770 | 0.3448 | 0.9116 |
91
+ | 0.2918 | 40.0 | 17200 | 0.3448 | 0.9144 |
92
+ | 0.2937 | 41.0 | 17630 | 0.3460 | 0.9144 |
93
+ | 0.2845 | 42.0 | 18060 | 0.3414 | 0.9199 |
94
+ | 0.2845 | 43.0 | 18490 | 0.3412 | 0.9199 |
95
+ | 0.2785 | 44.0 | 18920 | 0.3401 | 0.9227 |
96
+ | 0.2781 | 45.0 | 19350 | 0.3372 | 0.9199 |
97
+ | 0.2665 | 46.0 | 19780 | 0.3364 | 0.9199 |
98
+ | 0.2722 | 47.0 | 20210 | 0.3352 | 0.9199 |
99
+ | 0.2683 | 48.0 | 20640 | 0.3359 | 0.9199 |
100
+ | 0.267 | 49.0 | 21070 | 0.3345 | 0.9199 |
101
+ | 0.2641 | 50.0 | 21500 | 0.3344 | 0.9199 |
102
 
103
 
104
  ### Framework versions
105
 
106
+ - Transformers 4.35.2
107
  - Pytorch 2.1.0+cu118
108
+ - Datasets 2.15.0
109
+ - Tokenizers 0.15.0