Hugging Face's logo

lukeleeai
/
t5-base_cola_dense_mare_mlp_einsum

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
lukeleeai commited on
Commit
eb886c3
•
1 Parent(s): 81d9bf2

End of training

Browse files
Files changed (2) hide show
  1. README.md +45 -28
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7526366251198466
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 [lukeleeai/t5-base_cola_densedense_baseline](https://huggingface.co/lukeleeai/t5-base_cola_densedense_baseline) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6369
36
- - Accuracy: 0.7526
37
 
38
  ## Model description
39
 
@@ -70,31 +70,48 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
72
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
73
- | 0.5857 | 0.19 | 50 | 0.6136 | 0.6913 |
74
- | 0.5918 | 0.37 | 100 | 0.6222 | 0.6913 |
75
- | 0.5688 | 0.56 | 150 | 0.6246 | 0.6913 |
76
- | 0.685 | 0.75 | 200 | 0.6150 | 0.6913 |
77
- | 0.565 | 0.93 | 250 | 0.6197 | 0.6913 |
78
- | 0.5892 | 1.12 | 300 | 0.6066 | 0.6922 |
79
- | 0.5444 | 1.31 | 350 | 0.5988 | 0.7009 |
80
- | 0.6097 | 1.5 | 400 | 0.5796 | 0.7076 |
81
- | 0.5904 | 1.68 | 450 | 0.5916 | 0.6884 |
82
- | 0.5898 | 1.87 | 500 | 0.5815 | 0.7057 |
83
- | 0.5569 | 2.06 | 550 | 0.5771 | 0.6999 |
84
- | 0.4553 | 2.24 | 600 | 0.6217 | 0.7210 |
85
- | 0.4796 | 2.43 | 650 | 0.6323 | 0.7229 |
86
- | 0.5362 | 2.62 | 700 | 0.6491 | 0.7229 |
87
- | 0.5756 | 2.8 | 750 | 0.5745 | 0.7018 |
88
- | 0.5731 | 2.99 | 800 | 0.6104 | 0.7315 |
89
- | 0.4573 | 3.18 | 850 | 0.6087 | 0.7248 |
90
- | 0.5395 | 3.36 | 900 | 0.6768 | 0.7459 |
91
- | 0.4447 | 3.55 | 950 | 0.6372 | 0.7383 |
92
- | 0.3891 | 3.74 | 1000 | 0.6589 | 0.7402 |
93
- | 0.3923 | 3.93 | 1050 | 0.6273 | 0.7344 |
94
- | 0.3855 | 4.11 | 1100 | 0.7189 | 0.7344 |
95
- | 0.4015 | 4.3 | 1150 | 0.6456 | 0.7469 |
96
- | 0.33 | 4.49 | 1200 | 0.7179 | 0.7450 |
97
- | 0.354 | 4.67 | 1250 | 0.6369 | 0.7526 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
 
99
 
100
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.7516778523489933
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 [lukeleeai/t5-base_cola_densedense_baseline](https://huggingface.co/lukeleeai/t5-base_cola_densedense_baseline) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7682
36
+ - Accuracy: 0.7517
37
 
38
  ## Model description
39
 
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
72
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
73
+ | 0.5856 | 0.19 | 50 | 0.6260 | 0.6913 |
74
+ | 0.5836 | 0.37 | 100 | 0.6029 | 0.6913 |
75
+ | 0.5724 | 0.56 | 150 | 0.6055 | 0.6932 |
76
+ | 0.6635 | 0.75 | 200 | 0.6171 | 0.6922 |
77
+ | 0.5634 | 0.93 | 250 | 0.6162 | 0.6999 |
78
+ | 0.5361 | 1.12 | 300 | 0.6142 | 0.6932 |
79
+ | 0.5426 | 1.31 | 350 | 0.5920 | 0.7057 |
80
+ | 0.6255 | 1.5 | 400 | 0.5884 | 0.7095 |
81
+ | 0.6312 | 1.68 | 450 | 0.5723 | 0.7095 |
82
+ | 0.5686 | 1.87 | 500 | 0.5894 | 0.7057 |
83
+ | 0.5486 | 2.06 | 550 | 0.5590 | 0.7124 |
84
+ | 0.4436 | 2.24 | 600 | 0.5838 | 0.7220 |
85
+ | 0.4405 | 2.43 | 650 | 0.6176 | 0.7315 |
86
+ | 0.4785 | 2.62 | 700 | 0.6236 | 0.7296 |
87
+ | 0.5759 | 2.8 | 750 | 0.6233 | 0.7191 |
88
+ | 0.6156 | 2.99 | 800 | 0.6807 | 0.7392 |
89
+ | 0.4843 | 3.18 | 850 | 0.6337 | 0.7373 |
90
+ | 0.5408 | 3.36 | 900 | 0.7107 | 0.7392 |
91
+ | 0.4327 | 3.55 | 950 | 0.6256 | 0.7239 |
92
+ | 0.4318 | 3.74 | 1000 | 0.6951 | 0.7478 |
93
+ | 0.4047 | 3.93 | 1050 | 0.6566 | 0.7430 |
94
+ | 0.423 | 4.11 | 1100 | 0.6731 | 0.7440 |
95
+ | 0.3919 | 4.3 | 1150 | 0.6750 | 0.7392 |
96
+ | 0.4041 | 4.49 | 1200 | 0.6464 | 0.7421 |
97
+ | 0.3941 | 4.67 | 1250 | 0.6580 | 0.7517 |
98
+ | 0.3834 | 4.86 | 1300 | 0.6257 | 0.7459 |
99
+ | 0.2678 | 5.05 | 1350 | 0.6464 | 0.7555 |
100
+ | 0.3202 | 5.23 | 1400 | 0.7048 | 0.7507 |
101
+ | 0.2869 | 5.42 | 1450 | 0.7405 | 0.7565 |
102
+ | 0.3359 | 5.61 | 1500 | 0.6393 | 0.7593 |
103
+ | 0.3528 | 5.79 | 1550 | 0.6249 | 0.7555 |
104
+ | 0.3304 | 5.98 | 1600 | 0.6349 | 0.7565 |
105
+ | 0.2862 | 6.17 | 1650 | 0.7497 | 0.7670 |
106
+ | 0.2315 | 6.36 | 1700 | 0.7787 | 0.7622 |
107
+ | 0.3251 | 6.54 | 1750 | 0.7038 | 0.7555 |
108
+ | 0.3584 | 6.73 | 1800 | 0.7732 | 0.7603 |
109
+ | 0.1804 | 6.92 | 1850 | 0.8226 | 0.7584 |
110
+ | 0.2264 | 7.1 | 1900 | 0.7420 | 0.7613 |
111
+ | 0.2374 | 7.29 | 1950 | 0.7825 | 0.7507 |
112
+ | 0.203 | 7.48 | 2000 | 0.7575 | 0.7641 |
113
+ | 0.238 | 7.66 | 2050 | 1.9945 | 0.7603 |
114
+ | 0.2328 | 7.85 | 2100 | 0.7682 | 0.7517 |
115
 
116
 
117
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65e2d8976187f22fd908d81b24bf2e44927311bce5d01250872a8a8db411cc1e
3
  size 557791593
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97bbdef145e0d10cddf68bd64951144b657ace00f5cc4791aa1760fa99872f0f
3
  size 557791593