Hugging Face's logo

vxbrandon
/
t5-base_cola_dense

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
vxbrandon commited on
Commit
2d95e61
•
1 Parent(s): 27f44a4

Training in progress, step 500

Browse files
Files changed (3) hide show
  1. README.md +17 -71
  2. pytorch_model.bin +2 -2
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8360498561840843
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 [t5-base](https://huggingface.co/t5-base) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5247
36
- - Accuracy: 0.8360
37
 
38
  ## Model description
39
 
@@ -61,79 +61,25 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 200
64
- - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.6253 | 0.07 | 10 | 0.6218 | 0.6913 |
71
- | 0.6283 | 0.15 | 20 | 0.6207 | 0.6913 |
72
- | 0.6297 | 0.22 | 30 | 0.6193 | 0.6913 |
73
- | 0.5936 | 0.3 | 40 | 0.6200 | 0.6913 |
74
- | 0.609 | 0.37 | 50 | 0.6216 | 0.6913 |
75
- | 0.5818 | 0.45 | 60 | 0.6182 | 0.6913 |
76
- | 0.5984 | 0.52 | 70 | 0.6139 | 0.6913 |
77
- | 0.5961 | 0.6 | 80 | 0.6089 | 0.6913 |
78
- | 0.5594 | 0.67 | 90 | 0.6168 | 0.6913 |
79
- | 0.597 | 0.75 | 100 | 0.6022 | 0.6913 |
80
- | 0.6092 | 0.82 | 110 | 0.5537 | 0.6903 |
81
- | 0.5454 | 0.9 | 120 | 0.5120 | 0.7296 |
82
- | 0.5368 | 0.97 | 130 | 0.5120 | 0.7584 |
83
- | 0.5185 | 1.04 | 140 | 0.4615 | 0.7987 |
84
- | 0.4664 | 1.12 | 150 | 0.4893 | 0.7977 |
85
- | 0.4938 | 1.19 | 160 | 0.4793 | 0.8044 |
86
- | 0.3994 | 1.27 | 170 | 0.4912 | 0.8025 |
87
- | 0.4989 | 1.34 | 180 | 0.5515 | 0.8092 |
88
- | 0.4709 | 1.42 | 190 | 0.4909 | 0.8054 |
89
- | 0.4099 | 1.49 | 200 | 0.5397 | 0.8121 |
90
- | 0.4671 | 1.57 | 210 | 0.4736 | 0.8102 |
91
- | 0.3893 | 1.64 | 220 | 0.4803 | 0.8178 |
92
- | 0.4027 | 1.72 | 230 | 0.5195 | 0.8159 |
93
- | 0.4208 | 1.79 | 240 | 0.4521 | 0.8188 |
94
- | 0.4506 | 1.87 | 250 | 0.4943 | 0.8188 |
95
- | 0.3647 | 1.94 | 260 | 0.4650 | 0.8255 |
96
- | 0.4223 | 2.01 | 270 | 0.4865 | 0.8284 |
97
- | 0.3584 | 2.09 | 280 | 0.4639 | 0.8284 |
98
- | 0.3555 | 2.16 | 290 | 0.5321 | 0.8236 |
99
- | 0.3433 | 2.24 | 300 | 0.5174 | 0.8303 |
100
- | 0.3904 | 2.31 | 310 | 0.4811 | 0.8274 |
101
- | 0.3418 | 2.39 | 320 | 0.5135 | 0.8265 |
102
- | 0.3397 | 2.46 | 330 | 0.4854 | 0.8322 |
103
- | 0.3336 | 2.54 | 340 | 0.5008 | 0.8332 |
104
- | 0.3471 | 2.61 | 350 | 0.5065 | 0.8293 |
105
- | 0.382 | 2.69 | 360 | 0.4708 | 0.8274 |
106
- | 0.3533 | 2.76 | 370 | 0.4862 | 0.8265 |
107
- | 0.3199 | 2.84 | 380 | 0.4904 | 0.8293 |
108
- | 0.3757 | 2.91 | 390 | 0.4970 | 0.8332 |
109
- | 0.3726 | 2.99 | 400 | 0.4965 | 0.8322 |
110
- | 0.2957 | 3.06 | 410 | 0.4628 | 0.8303 |
111
- | 0.3232 | 3.13 | 420 | 0.5174 | 0.8322 |
112
- | 0.2836 | 3.21 | 430 | 0.5038 | 0.8351 |
113
- | 0.2919 | 3.28 | 440 | 0.4987 | 0.8341 |
114
- | 0.3578 | 3.36 | 450 | 0.5187 | 0.8313 |
115
- | 0.398 | 3.43 | 460 | 0.5285 | 0.8380 |
116
- | 0.3024 | 3.51 | 470 | 0.4971 | 0.8351 |
117
- | 0.3153 | 3.58 | 480 | 0.5084 | 0.8351 |
118
- | 0.307 | 3.66 | 490 | 0.5371 | 0.8332 |
119
- | 0.2753 | 3.73 | 500 | 0.5247 | 0.8360 |
120
- | 0.3515 | 3.81 | 510 | 0.4782 | 0.8360 |
121
- | 0.2881 | 3.88 | 520 | 0.4784 | 0.8389 |
122
- | 0.3203 | 3.96 | 530 | 0.5115 | 0.8351 |
123
- | 0.2791 | 4.03 | 540 | 0.5294 | 0.8360 |
124
- | 0.301 | 4.1 | 550 | 0.5218 | 0.8322 |
125
- | 0.2652 | 4.18 | 560 | 0.4956 | 0.8360 |
126
- | 0.2954 | 4.25 | 570 | 0.4878 | 0.8332 |
127
- | 0.2345 | 4.33 | 580 | 0.5190 | 0.8313 |
128
- | 0.3762 | 4.4 | 590 | 0.5315 | 0.8351 |
129
- | 0.3614 | 4.48 | 600 | 0.5200 | 0.8341 |
130
- | 0.3178 | 4.55 | 610 | 0.5237 | 0.8341 |
131
- | 0.306 | 4.63 | 620 | 0.5232 | 0.8341 |
132
- | 0.2828 | 4.7 | 630 | 0.5278 | 0.8360 |
133
- | 0.3442 | 4.78 | 640 | 0.5270 | 0.8360 |
134
- | 0.3268 | 4.85 | 650 | 0.5252 | 0.8351 |
135
- | 0.2959 | 4.93 | 660 | 0.5284 | 0.8370 |
136
- | 0.2861 | 5.0 | 670 | 0.5277 | 0.8351 |
137
 
138
 
139
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.6912751677852349
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 [t5-base](https://huggingface.co/t5-base) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6351
36
+ - Accuracy: 0.6913
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 200
64
+ - num_epochs: 1
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.6331 | 0.07 | 10 | 0.6263 | 0.6855 |
71
+ | 0.626 | 0.15 | 20 | 0.6247 | 0.6826 |
72
+ | 0.6412 | 0.22 | 30 | 0.6240 | 0.6865 |
73
+ | 0.6497 | 0.3 | 40 | 0.6210 | 0.6874 |
74
+ | 0.6226 | 0.37 | 50 | 0.6213 | 0.6874 |
75
+ | 0.6183 | 0.45 | 60 | 0.6198 | 0.6894 |
76
+ | 0.6034 | 0.52 | 70 | 0.6202 | 0.6894 |
77
+ | 0.5802 | 0.6 | 80 | 0.6219 | 0.6913 |
78
+ | 0.6005 | 0.67 | 90 | 0.6261 | 0.6913 |
79
+ | 0.6178 | 0.75 | 100 | 0.6331 | 0.6922 |
80
+ | 0.5887 | 0.82 | 110 | 0.6344 | 0.6913 |
81
+ | 0.6492 | 0.9 | 120 | 0.6371 | 0.6913 |
82
+ | 0.6333 | 0.97 | 130 | 0.6376 | 0.6913 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c54c92135503700f82ecb30917670911c470d56c3e92757e99520a1f58e7cecf
3
- size 1120899297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd29d552a4be38f2581f4bf0b8b23da49e91b3e0aded86906e80030422e7fd4
3
+ size 923798945
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da90a3f5b82968cc8a63bbc22dd6182cd86026eab5ecde3967bcf3e86b9a605e
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6593fee8449e954b030a437babad128f5960da9a083a5b2d4965ef1b2da5b6eb
3
  size 4027