Hugging Face's logo

thrunlab
/
t5-large_rte_sp0_ar0

Text Classification
Transformers
PyTorch
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
lukeleeai commited on
Commit
5ce9fd3
•
1 Parent(s): 4337a4d

End of training

Browse files
Files changed (1) hide show
  1. README.md +37 -18
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.853515625
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: 53.5781
36
- - Accuracy: 0.8535
37
 
38
  ## Model description
39
 
@@ -56,31 +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: multi-GPU
60
- - num_devices: 2
61
- - total_train_batch_size: 32
62
- - total_eval_batch_size: 64
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
  - lr_scheduler_warmup_steps: 20
66
- - num_epochs: 8
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
72
- | 21.7037 | 1.09 | 50 | 50.2626 | 0.7365 |
73
- | 19.7544 | 2.17 | 100 | 48.4847 | 0.8375 |
74
- | 18.2538 | 3.26 | 150 | 48.2347 | 0.8484 |
75
- | 18.8494 | 4.35 | 200 | 48.5903 | 0.8195 |
76
- | 18.9237 | 5.43 | 250 | 48.2256 | 0.8520 |
77
- | 19.01 | 6.52 | 300 | 48.6390 | 0.8375 |
78
- | 18.8412 | 7.61 | 350 | 48.3700 | 0.8412 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
82
 
83
- - Transformers 4.33.2
84
  - Pytorch 2.0.1+cu117
85
- - Datasets 2.14.5
86
- - Tokenizers 0.11.6
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.859375
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: 3.5699
36
+ - Accuracy: 0.8594
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
+ - training_steps: 750
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.6946 | 0.27 | 25 | 0.6855 | 0.5271 |
69
+ | 0.6855 | 0.54 | 50 | 0.6477 | 0.6354 |
70
+ | 0.5931 | 0.82 | 75 | 0.4711 | 0.7942 |
71
+ | 0.4206 | 1.09 | 100 | 0.5129 | 0.8159 |
72
+ | 0.4076 | 1.36 | 125 | 0.4682 | 0.8375 |
73
+ | 0.2787 | 1.63 | 150 | 0.4392 | 0.8484 |
74
+ | 0.2772 | 1.9 | 175 | 0.4809 | 0.8520 |
75
+ | 0.2214 | 2.17 | 200 | 0.8655 | 0.8448 |
76
+ | 0.1505 | 2.45 | 225 | 0.9392 | 0.8628 |
77
+ | 0.1502 | 2.72 | 250 | 1.2747 | 0.8664 |
78
+ | 0.1149 | 2.99 | 275 | 3.4780 | 0.8448 |
79
+ | 0.1074 | 3.26 | 300 | 2.8125 | 0.8484 |
80
+ | 0.1359 | 3.53 | 325 | 3.0765 | 0.8448 |
81
+ | 0.0577 | 3.8 | 350 | 3.1358 | 0.8592 |
82
+ | 0.0212 | 4.08 | 375 | 3.3075 | 0.8520 |
83
+ | 0.0251 | 4.35 | 400 | 5.9088 | 0.8736 |
84
+ | 0.0532 | 4.62 | 425 | 5.5508 | 0.8700 |
85
+ | 0.0229 | 4.89 | 450 | 4.6194 | 0.8700 |
86
+ | 0.0517 | 5.16 | 475 | 3.2927 | 0.8592 |
87
+ | 0.0182 | 5.43 | 500 | 4.5065 | 0.8773 |
88
+ | 0.2538 | 5.71 | 525 | 4.5460 | 0.8809 |
89
+ | 0.0162 | 5.98 | 550 | 4.2678 | 0.8700 |
90
+ | 0.0221 | 6.25 | 575 | 4.6268 | 0.8664 |
91
+ | 0.007 | 6.52 | 600 | 4.3411 | 0.8664 |
92
+ | 0.0038 | 6.79 | 625 | 5.0136 | 0.8664 |
93
+ | 0.036 | 7.07 | 650 | 5.6308 | 0.8736 |
94
+ | 0.0064 | 7.34 | 675 | 5.9644 | 0.8736 |
95
+ | 0.0037 | 7.61 | 700 | 5.3223 | 0.8736 |
96
+ | 0.0121 | 7.88 | 725 | 5.3345 | 0.8736 |
97
+ | 0.0251 | 8.15 | 750 | 4.9899 | 0.8736 |
98
 
99
 
100
  ### Framework versions
101
 
102
+ - Transformers 4.34.1
103
  - Pytorch 2.0.1+cu117
104
+ - Datasets 2.9.0
105
+ - Tokenizers 0.14.1