Hugging Face's logo

thrunlab
/
t5-large_sst2_sp0_ar0

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
lukeleeai commited on
Commit
ea437e5
·
1 Parent(s): 3c11cc1

End of training

Browse files
Files changed (1) hide show
  1. README.md +35 -36
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9560546875
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-large](https://huggingface.co/t5-large) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3456
36
- - Accuracy: 0.9561
37
 
38
  ## Model description
39
 
@@ -56,51 +56,50 @@ The following hyperparameters were used during training:
56
  - train_batch_size: 16
57
  - eval_batch_size: 32
58
  - seed: 1
59
- - distributed_type: tpu
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 20
63
- - training_steps: 750
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.6852 | 0.01 | 25 | 0.6952 | 0.5092 |
70
- | 0.6751 | 0.01 | 50 | 0.6331 | 0.7546 |
71
- | 0.603 | 0.02 | 75 | 0.4811 | 0.8899 |
72
- | 0.3459 | 0.02 | 100 | 0.2048 | 0.9335 |
73
- | 0.1808 | 0.03 | 125 | 0.2377 | 0.9300 |
74
- | 0.1933 | 0.04 | 150 | 0.3369 | 0.9323 |
75
- | 0.527 | 0.04 | 175 | 0.6582 | 0.9404 |
76
- | 0.2241 | 0.05 | 200 | 0.1874 | 0.9507 |
77
- | 0.1997 | 0.05 | 225 | 0.5160 | 0.9472 |
78
- | 0.2192 | 0.06 | 250 | 0.5193 | 0.9461 |
79
- | 0.168 | 0.07 | 275 | 0.4091 | 0.9484 |
80
- | 0.1879 | 0.07 | 300 | 0.3114 | 0.9427 |
81
- | 0.1653 | 0.08 | 325 | 0.5526 | 0.9484 |
82
- | 0.1847 | 0.08 | 350 | 0.6536 | 0.9450 |
83
- | 0.1449 | 0.09 | 375 | 0.6520 | 0.9438 |
84
- | 0.2485 | 0.1 | 400 | 0.4093 | 0.9518 |
85
- | 0.1604 | 0.1 | 425 | 0.2821 | 0.9461 |
86
- | 0.1316 | 0.11 | 450 | 0.8609 | 0.9461 |
87
- | 0.1754 | 0.11 | 475 | 0.4047 | 0.9472 |
88
- | 0.1524 | 0.12 | 500 | 0.4034 | 0.9495 |
89
- | 0.4571 | 0.13 | 525 | 0.2895 | 0.9495 |
90
- | 0.1448 | 0.13 | 550 | 0.5239 | 0.9484 |
91
- | 0.1459 | 0.14 | 575 | 0.2996 | 0.9518 |
92
- | 0.2131 | 0.14 | 600 | 0.2983 | 0.9495 |
93
- | 0.1298 | 0.15 | 625 | 0.5322 | 0.9484 |
94
- | 0.1519 | 0.16 | 650 | 0.5311 | 0.9518 |
95
- | 0.1809 | 0.16 | 675 | 0.5271 | 0.9495 |
96
- | 0.1495 | 0.17 | 700 | 0.5282 | 0.9495 |
97
- | 0.1665 | 0.17 | 725 | 0.5307 | 0.9507 |
98
- | 0.1978 | 0.18 | 750 | 0.5295 | 0.9507 |
99
 
100
 
101
  ### Framework versions
102
 
103
  - Transformers 4.33.2
104
- - Pytorch 2.0.0+cu118
105
  - Datasets 2.14.5
106
  - Tokenizers 0.11.6
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9453125
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-large](https://huggingface.co/t5-large) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1944
36
+ - Accuracy: 0.9453
37
 
38
  ## Model description
39
 
 
56
  - train_batch_size: 16
57
  - eval_batch_size: 32
58
  - seed: 1
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - lr_scheduler_warmup_steps: 20
62
+ - num_epochs: 6
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.6815 | 0.01 | 25 | 0.6999 | 0.5092 |
69
+ | 0.6592 | 0.01 | 50 | 0.6221 | 0.6445 |
70
+ | 0.5832 | 0.02 | 75 | 0.4570 | 0.7993 |
71
+ | 0.2882 | 0.02 | 100 | 0.2076 | 0.9358 |
72
+ | 0.1894 | 0.03 | 125 | 0.3499 | 0.9404 |
73
+ | 0.1864 | 0.04 | 150 | 0.2963 | 0.9461 |
74
+ | 0.2553 | 0.04 | 175 | 0.6929 | 0.9289 |
75
+ | 0.245 | 0.05 | 200 | 0.4761 | 0.9323 |
76
+ | 0.2042 | 0.05 | 225 | 0.5294 | 0.9461 |
77
+ | 0.2002 | 0.06 | 250 | 0.8441 | 0.9472 |
78
+ | 0.1633 | 0.07 | 275 | 0.8560 | 0.9495 |
79
+ | 0.1939 | 0.07 | 300 | 0.3197 | 0.9450 |
80
+ | 0.1928 | 0.08 | 325 | 0.4214 | 0.9472 |
81
+ | 0.2201 | 0.08 | 350 | 0.5266 | 0.9484 |
82
+ | 0.143 | 0.09 | 375 | 0.8642 | 0.9450 |
83
+ | 0.2354 | 0.1 | 400 | 1.2116 | 0.9335 |
84
+ | 0.1692 | 0.1 | 425 | 0.1807 | 0.9472 |
85
+ | 0.1531 | 0.11 | 450 | 0.6431 | 0.9484 |
86
+ | 0.152 | 0.11 | 475 | 1.4046 | 0.9553 |
87
+ | 0.1948 | 0.12 | 500 | 0.1596 | 0.9553 |
88
+ | 0.2007 | 0.13 | 525 | 0.1779 | 0.9438 |
89
+ | 0.1338 | 0.13 | 550 | 0.6476 | 0.9495 |
90
+ | 0.3812 | 0.14 | 575 | 0.3901 | 0.9484 |
91
+ | 0.7052 | 0.14 | 600 | 0.1740 | 0.9507 |
92
+ | 0.8601 | 0.15 | 625 | 1.5226 | 0.9484 |
93
+ | 1.384 | 0.16 | 650 | 0.6605 | 0.9427 |
94
+ | 0.6833 | 0.16 | 675 | 0.7313 | 0.9484 |
95
+ | 0.1833 | 0.17 | 700 | 0.4110 | 0.9438 |
96
+ | 0.1968 | 0.17 | 725 | 0.2914 | 0.9450 |
97
+ | 0.2001 | 0.18 | 750 | 0.1947 | 0.9335 |
98
 
99
 
100
  ### Framework versions
101
 
102
  - Transformers 4.33.2
103
+ - Pytorch 2.0.1+cu117
104
  - Datasets 2.14.5
105
  - Tokenizers 0.11.6