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
6da8073
•
1 Parent(s): 48efc7b

Vishnou/distilbert_base_SST2

Browse files
Files changed (2) hide show
  1. README.md +39 -22
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8967889908256881
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](https://huggingface.co/distilbert-base-uncased) on the sst2 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3718
36
- - Accuracy: 0.8968
37
 
38
  ## Model description
39
 
@@ -58,28 +58,45 @@ 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: 1
62
 
63
  ### Training results
64
 
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 0.4401 | 0.06 | 500 | 0.3732 | 0.8417 |
68
- | 0.3465 | 0.12 | 1000 | 0.3451 | 0.8761 |
69
- | 0.3408 | 0.18 | 1500 | 0.3465 | 0.8612 |
70
- | 0.3059 | 0.24 | 2000 | 0.4580 | 0.8589 |
71
- | 0.2974 | 0.3 | 2500 | 0.3338 | 0.8830 |
72
- | 0.3023 | 0.36 | 3000 | 0.4487 | 0.8475 |
73
- | 0.2636 | 0.42 | 3500 | 0.4330 | 0.8888 |
74
- | 0.2558 | 0.48 | 4000 | 0.4193 | 0.8876 |
75
- | 0.2466 | 0.53 | 4500 | 0.4343 | 0.8945 |
76
- | 0.2393 | 0.59 | 5000 | 0.4935 | 0.875 |
77
- | 0.2279 | 0.65 | 5500 | 0.3818 | 0.8876 |
78
- | 0.2181 | 0.71 | 6000 | 0.4003 | 0.8968 |
79
- | 0.2245 | 0.77 | 6500 | 0.3496 | 0.9048 |
80
- | 0.2279 | 0.83 | 7000 | 0.3759 | 0.9014 |
81
- | 0.2152 | 0.89 | 7500 | 0.4037 | 0.8899 |
82
- | 0.2174 | 0.95 | 8000 | 0.3718 | 0.8968 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8990825688073395
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](https://huggingface.co/distilbert-base-uncased) on the sst2 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4181
36
+ - Accuracy: 0.8991
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: 2
62
 
63
  ### Training results
64
 
65
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
67
+ | 0.4378 | 0.06 | 500 | 0.3452 | 0.8601 |
68
+ | 0.343 | 0.12 | 1000 | 0.3483 | 0.8578 |
69
+ | 0.3342 | 0.18 | 1500 | 0.3373 | 0.8704 |
70
+ | 0.308 | 0.24 | 2000 | 0.4102 | 0.8819 |
71
+ | 0.2932 | 0.3 | 2500 | 0.3546 | 0.8830 |
72
+ | 0.3116 | 0.36 | 3000 | 0.3609 | 0.8716 |
73
+ | 0.2805 | 0.42 | 3500 | 0.3800 | 0.8945 |
74
+ | 0.2655 | 0.48 | 4000 | 0.4131 | 0.8842 |
75
+ | 0.2504 | 0.53 | 4500 | 0.4299 | 0.8830 |
76
+ | 0.2543 | 0.59 | 5000 | 0.5196 | 0.8727 |
77
+ | 0.2409 | 0.65 | 5500 | 0.4387 | 0.8807 |
78
+ | 0.2414 | 0.71 | 6000 | 0.4121 | 0.8922 |
79
+ | 0.2319 | 0.77 | 6500 | 0.3772 | 0.8830 |
80
+ | 0.247 | 0.83 | 7000 | 0.4179 | 0.8876 |
81
+ | 0.2233 | 0.89 | 7500 | 0.3544 | 0.8945 |
82
+ | 0.2202 | 0.95 | 8000 | 0.4160 | 0.8865 |
83
+ | 0.2242 | 1.01 | 8500 | 0.5125 | 0.8784 |
84
+ | 0.1296 | 1.07 | 9000 | 0.4212 | 0.8842 |
85
+ | 0.1429 | 1.13 | 9500 | 0.4675 | 0.8968 |
86
+ | 0.1466 | 1.19 | 10000 | 0.5034 | 0.8922 |
87
+ | 0.1626 | 1.25 | 10500 | 0.4431 | 0.8945 |
88
+ | 0.1459 | 1.31 | 11000 | 0.5001 | 0.8922 |
89
+ | 0.1489 | 1.37 | 11500 | 0.4739 | 0.8968 |
90
+ | 0.1591 | 1.43 | 12000 | 0.3852 | 0.8945 |
91
+ | 0.1211 | 1.48 | 12500 | 0.4648 | 0.8945 |
92
+ | 0.1275 | 1.54 | 13000 | 0.5281 | 0.8956 |
93
+ | 0.1302 | 1.6 | 13500 | 0.4411 | 0.8933 |
94
+ | 0.1313 | 1.66 | 14000 | 0.4914 | 0.8979 |
95
+ | 0.134 | 1.72 | 14500 | 0.3923 | 0.8979 |
96
+ | 0.1355 | 1.78 | 15000 | 0.4164 | 0.8956 |
97
+ | 0.1263 | 1.84 | 15500 | 0.4293 | 0.8945 |
98
+ | 0.1326 | 1.9 | 16000 | 0.4185 | 0.8933 |
99
+ | 0.1315 | 1.96 | 16500 | 0.4181 | 0.8991 |
100
 
101
 
102
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71800c81e9ed4dfa2a362921f332c40f36c2f8be9da06d83c8901d6cad86bb27
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcc59aace05879dd0138156289730cf5fff405afe418bfa1231991af7db4c37
3
  size 267832560