Hugging Face's logo

Vishnou
/
distilbert_base_SST2

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Vishnou commited on
Commit
240862b
·
1 Parent(s): ba0d891

Vishnou/distilbert_base_SST2

Browse files
Files changed (1) hide show
  1. README.md +23 -40
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8979357798165137
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the sst2 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4747
36
- - Accuracy: 0.8979
37
 
38
  ## Model description
39
 
@@ -58,50 +58,33 @@ The following hyperparameters were used during training:
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 2
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
- | 0.1303 | 0.06 | 500 | 0.6599 | 0.8784 |
68
- | 0.1781 | 0.12 | 1000 | 0.5644 | 0.8716 |
69
- | 0.1856 | 0.18 | 1500 | 0.5357 | 0.8716 |
70
- | 0.1833 | 0.24 | 2000 | 0.6749 | 0.8727 |
71
- | 0.1887 | 0.3 | 2500 | 0.4967 | 0.8945 |
72
- | 0.1873 | 0.36 | 3000 | 0.6415 | 0.8658 |
73
- | 0.1787 | 0.42 | 3500 | 0.4886 | 0.9014 |
74
- | 0.1979 | 0.48 | 4000 | 0.4122 | 0.8865 |
75
- | 0.1662 | 0.53 | 4500 | 0.5310 | 0.8888 |
76
- | 0.1718 | 0.59 | 5000 | 0.5415 | 0.8945 |
77
- | 0.1808 | 0.65 | 5500 | 0.4059 | 0.8956 |
78
- | 0.1666 | 0.71 | 6000 | 0.4731 | 0.8876 |
79
- | 0.1762 | 0.77 | 6500 | 0.3817 | 0.8807 |
80
- | 0.1782 | 0.83 | 7000 | 0.4583 | 0.8956 |
81
- | 0.1739 | 0.89 | 7500 | 0.4756 | 0.8888 |
82
- | 0.1715 | 0.95 | 8000 | 0.4871 | 0.8911 |
83
- | 0.1682 | 1.01 | 8500 | 0.4936 | 0.8922 |
84
- | 0.095 | 1.07 | 9000 | 0.4956 | 0.8899 |
85
- | 0.0928 | 1.13 | 9500 | 0.6543 | 0.8716 |
86
- | 0.0855 | 1.19 | 10000 | 0.5812 | 0.8956 |
87
- | 0.1032 | 1.25 | 10500 | 0.6683 | 0.8716 |
88
- | 0.0982 | 1.31 | 11000 | 0.6076 | 0.8842 |
89
- | 0.0907 | 1.37 | 11500 | 0.5826 | 0.8956 |
90
- | 0.1085 | 1.43 | 12000 | 0.4708 | 0.8922 |
91
- | 0.0785 | 1.48 | 12500 | 0.5486 | 0.8956 |
92
- | 0.0903 | 1.54 | 13000 | 0.6104 | 0.875 |
93
- | 0.0764 | 1.6 | 13500 | 0.5576 | 0.8888 |
94
- | 0.0982 | 1.66 | 14000 | 0.5447 | 0.8888 |
95
- | 0.0864 | 1.72 | 14500 | 0.4833 | 0.8922 |
96
- | 0.0888 | 1.78 | 15000 | 0.4737 | 0.8945 |
97
- | 0.0775 | 1.84 | 15500 | 0.4818 | 0.8991 |
98
- | 0.0958 | 1.9 | 16000 | 0.4674 | 0.8991 |
99
- | 0.0805 | 1.96 | 16500 | 0.4747 | 0.8979 |
100
 
101
 
102
  ### Framework versions
103
 
104
  - Transformers 4.35.2
105
  - Pytorch 2.1.0+cu118
106
- - Datasets 2.14.7
107
  - Tokenizers 0.15.0
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9151376146788991
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the sst2 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3690
36
+ - Accuracy: 0.9151
37
 
38
  ## Model description
39
 
 
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 1
62
 
63
  ### Training results
64
 
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.1335 | 0.06 | 500 | 0.5579 | 0.8911 |
68
+ | 0.1666 | 0.12 | 1000 | 0.5413 | 0.8876 |
69
+ | 0.1778 | 0.18 | 1500 | 0.7077 | 0.8544 |
70
+ | 0.1746 | 0.24 | 2000 | 0.5727 | 0.875 |
71
+ | 0.1632 | 0.3 | 2500 | 0.4972 | 0.8979 |
72
+ | 0.1675 | 0.36 | 3000 | 0.4742 | 0.8991 |
73
+ | 0.1573 | 0.42 | 3500 | 0.4943 | 0.8956 |
74
+ | 0.1525 | 0.48 | 4000 | 0.4907 | 0.8819 |
75
+ | 0.1394 | 0.53 | 4500 | 0.5010 | 0.8899 |
76
+ | 0.1458 | 0.59 | 5000 | 0.5461 | 0.8876 |
77
+ | 0.1588 | 0.65 | 5500 | 0.3364 | 0.9094 |
78
+ | 0.1373 | 0.71 | 6000 | 0.4198 | 0.9163 |
79
+ | 0.138 | 0.77 | 6500 | 0.3466 | 0.9128 |
80
+ | 0.1383 | 0.83 | 7000 | 0.4064 | 0.9094 |
81
+ | 0.1371 | 0.89 | 7500 | 0.4083 | 0.9002 |
82
+ | 0.1373 | 0.95 | 8000 | 0.3690 | 0.9151 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
86
 
87
  - Transformers 4.35.2
88
  - Pytorch 2.1.0+cu118
89
+ - Datasets 2.15.0
90
  - Tokenizers 0.15.0