Hugging Face's logo

Vishnou
/
TinyBERT_SST2

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Vishnou commited on
Commit
84977da
•
1 Parent(s): 0acb971

Vishnou/TinyBERT_SST2

Browse files
Files changed (2) hide show
  1. README.md +36 -36
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.8795871559633027
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on the sst2 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.5289
35
- - Accuracy: 0.8796
36
 
37
  ## Model description
38
 
@@ -63,39 +63,39 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
66
- | 0.4655 | 0.06 | 500 | 0.4229 | 0.8234 |
67
- | 0.3869 | 0.12 | 1000 | 0.3870 | 0.8383 |
68
- | 0.3786 | 0.18 | 1500 | 0.4844 | 0.8234 |
69
- | 0.3573 | 0.24 | 2000 | 0.4276 | 0.8532 |
70
- | 0.3502 | 0.3 | 2500 | 0.4048 | 0.8372 |
71
- | 0.3473 | 0.36 | 3000 | 0.3623 | 0.8658 |
72
- | 0.3283 | 0.42 | 3500 | 0.4937 | 0.8681 |
73
- | 0.3198 | 0.48 | 4000 | 0.4020 | 0.8532 |
74
- | 0.3006 | 0.53 | 4500 | 0.4514 | 0.8612 |
75
- | 0.3254 | 0.59 | 5000 | 0.4370 | 0.8624 |
76
- | 0.2923 | 0.65 | 5500 | 0.5068 | 0.8544 |
77
- | 0.2959 | 0.71 | 6000 | 0.4557 | 0.8704 |
78
- | 0.3003 | 0.77 | 6500 | 0.4536 | 0.8647 |
79
- | 0.3049 | 0.83 | 7000 | 0.4810 | 0.8704 |
80
- | 0.3008 | 0.89 | 7500 | 0.4431 | 0.8681 |
81
- | 0.2937 | 0.95 | 8000 | 0.5207 | 0.8693 |
82
- | 0.2805 | 1.01 | 8500 | 0.4972 | 0.8784 |
83
- | 0.2176 | 1.07 | 9000 | 0.5370 | 0.8773 |
84
- | 0.2379 | 1.13 | 9500 | 0.5453 | 0.8807 |
85
- | 0.2639 | 1.19 | 10000 | 0.5117 | 0.8693 |
86
- | 0.2555 | 1.25 | 10500 | 0.6062 | 0.8670 |
87
- | 0.2324 | 1.31 | 11000 | 0.5623 | 0.8704 |
88
- | 0.2225 | 1.37 | 11500 | 0.5804 | 0.8773 |
89
- | 0.2332 | 1.43 | 12000 | 0.5089 | 0.8807 |
90
- | 0.2214 | 1.48 | 12500 | 0.5565 | 0.8796 |
91
- | 0.2105 | 1.54 | 13000 | 0.5614 | 0.8739 |
92
- | 0.2174 | 1.6 | 13500 | 0.5561 | 0.875 |
93
- | 0.2196 | 1.66 | 14000 | 0.5165 | 0.8819 |
94
- | 0.2067 | 1.72 | 14500 | 0.5249 | 0.8796 |
95
- | 0.1986 | 1.78 | 15000 | 0.5121 | 0.875 |
96
- | 0.2103 | 1.84 | 15500 | 0.5044 | 0.875 |
97
- | 0.2115 | 1.9 | 16000 | 0.5241 | 0.8784 |
98
- | 0.2011 | 1.96 | 16500 | 0.5289 | 0.8796 |
99
 
100
 
101
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.8864678899082569
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on the sst2 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.5142
35
+ - Accuracy: 0.8865
36
 
37
  ## Model description
38
 
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
66
+ | 0.4686 | 0.06 | 500 | 0.4020 | 0.8337 |
67
+ | 0.384 | 0.12 | 1000 | 0.3666 | 0.8360 |
68
+ | 0.381 | 0.18 | 1500 | 0.3951 | 0.8337 |
69
+ | 0.3609 | 0.24 | 2000 | 0.4378 | 0.8555 |
70
+ | 0.3616 | 0.3 | 2500 | 0.3743 | 0.8475 |
71
+ | 0.3521 | 0.36 | 3000 | 0.3692 | 0.8589 |
72
+ | 0.3113 | 0.42 | 3500 | 0.5072 | 0.8486 |
73
+ | 0.319 | 0.48 | 4000 | 0.4212 | 0.8612 |
74
+ | 0.3034 | 0.53 | 4500 | 0.4555 | 0.8647 |
75
+ | 0.3098 | 0.59 | 5000 | 0.4163 | 0.8635 |
76
+ | 0.3113 | 0.65 | 5500 | 0.5226 | 0.8440 |
77
+ | 0.2949 | 0.71 | 6000 | 0.4137 | 0.875 |
78
+ | 0.2977 | 0.77 | 6500 | 0.4775 | 0.8486 |
79
+ | 0.3077 | 0.83 | 7000 | 0.4774 | 0.8693 |
80
+ | 0.2953 | 0.89 | 7500 | 0.4491 | 0.8589 |
81
+ | 0.2846 | 0.95 | 8000 | 0.5228 | 0.8784 |
82
+ | 0.292 | 1.01 | 8500 | 0.4801 | 0.8865 |
83
+ | 0.2185 | 1.07 | 9000 | 0.4889 | 0.8933 |
84
+ | 0.2343 | 1.13 | 9500 | 0.5862 | 0.8716 |
85
+ | 0.2667 | 1.19 | 10000 | 0.4796 | 0.8842 |
86
+ | 0.252 | 1.25 | 10500 | 0.5181 | 0.8842 |
87
+ | 0.2385 | 1.31 | 11000 | 0.5148 | 0.875 |
88
+ | 0.2144 | 1.37 | 11500 | 0.5345 | 0.8704 |
89
+ | 0.2348 | 1.43 | 12000 | 0.5073 | 0.8807 |
90
+ | 0.2166 | 1.48 | 12500 | 0.4885 | 0.8865 |
91
+ | 0.2104 | 1.54 | 13000 | 0.6118 | 0.8658 |
92
+ | 0.2145 | 1.6 | 13500 | 0.5091 | 0.8865 |
93
+ | 0.2098 | 1.66 | 14000 | 0.5221 | 0.8876 |
94
+ | 0.2111 | 1.72 | 14500 | 0.5031 | 0.8888 |
95
+ | 0.2042 | 1.78 | 15000 | 0.5257 | 0.8796 |
96
+ | 0.2091 | 1.84 | 15500 | 0.5175 | 0.8819 |
97
+ | 0.2027 | 1.9 | 16000 | 0.5528 | 0.8784 |
98
+ | 0.2173 | 1.96 | 16500 | 0.5142 | 0.8865 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f2fcf145623300854efdb61deef8b3126ff092fb8b2970f857701451300a7fe
3
  size 57411808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b15f95bae36f14f3124420e8341531a6f4dc312b3d1fe5bf3e849480e39dcc4
3
  size 57411808