Hugging Face's logo

thrunlab
/
t5-3b_rte_sp0_ar0

Text Classification
Transformers
Safetensors
t5
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
lukeleeai commited on
Commit
5571dfe
·
1 Parent(s): 6aa2c7a

End of training

Browse files
Files changed (3) hide show
  1. README.md +40 -6
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.5140562248995983
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 [t5-3b](https://huggingface.co/t5-3b) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.6984
36
- - Accuracy: 0.5141
37
 
38
  ## Model description
39
 
@@ -53,19 +53,53 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 8
57
- - eval_batch_size: 16
58
  - seed: 1
59
  - distributed_type: multi-GPU
 
60
  - gradient_accumulation_steps: 2
61
  - total_train_batch_size: 16
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 20
65
- - training_steps: 10
66
 
67
  ### Training results
68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8875502008032129
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 [t5-3b](https://huggingface.co/t5-3b) on the glue dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 3.4268
36
+ - Accuracy: 0.8876
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 4
57
+ - eval_batch_size: 8
58
  - seed: 1
59
  - distributed_type: multi-GPU
60
+ - num_devices: 2
61
  - gradient_accumulation_steps: 2
62
  - total_train_batch_size: 16
63
+ - total_eval_batch_size: 16
64
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
65
  - lr_scheduler_type: linear
66
  - lr_scheduler_warmup_steps: 20
67
+ - training_steps: 750
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
72
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
73
+ | 0.7306 | 0.18 | 25 | 0.6913 | 0.5921 |
74
+ | 0.6717 | 0.36 | 50 | 0.4976 | 0.8339 |
75
+ | 0.3978 | 0.53 | 75 | 0.5226 | 0.8628 |
76
+ | 0.322 | 0.71 | 100 | 0.3902 | 0.8484 |
77
+ | 0.2958 | 0.89 | 125 | 0.3803 | 0.8881 |
78
+ | 0.2604 | 1.07 | 150 | 0.8628 | 0.8736 |
79
+ | 0.2011 | 1.25 | 175 | 0.7780 | 0.8953 |
80
+ | 0.263 | 1.42 | 200 | 2.1533 | 0.8881 |
81
+ | 0.2032 | 1.6 | 225 | 4.7955 | 0.8917 |
82
+ | 0.2536 | 1.78 | 250 | 1.7810 | 0.8989 |
83
+ | 0.1984 | 1.96 | 275 | 0.5119 | 0.8845 |
84
+ | 0.1495 | 2.14 | 300 | 0.5128 | 0.8845 |
85
+ | 0.1275 | 2.31 | 325 | 0.8602 | 0.8628 |
86
+ | 0.0955 | 2.49 | 350 | 1.3642 | 0.8773 |
87
+ | 0.3912 | 2.67 | 375 | 1.0186 | 0.8664 |
88
+ | 0.1108 | 2.85 | 400 | 2.1450 | 0.8592 |
89
+ | 0.0726 | 3.02 | 425 | 2.6801 | 0.8809 |
90
+ | 0.0937 | 3.2 | 450 | 5.2053 | 0.8736 |
91
+ | 1.0143 | 3.38 | 475 | 3.3979 | 0.8845 |
92
+ | 0.5754 | 3.56 | 500 | 4.2786 | 0.8989 |
93
+ | 0.2928 | 3.74 | 525 | 5.6543 | 0.8917 |
94
+ | 0.5633 | 3.91 | 550 | 6.7064 | 0.8845 |
95
+ | 1.0431 | 4.09 | 575 | 4.9205 | 0.8953 |
96
+ | 0.2839 | 4.27 | 600 | 4.2344 | 0.8809 |
97
+ | 0.5464 | 4.45 | 625 | 4.9598 | 0.8809 |
98
+ | 0.0031 | 4.63 | 650 | 5.3705 | 0.8881 |
99
+ | 0.5149 | 4.8 | 675 | 4.8105 | 0.8845 |
100
+ | 0.2702 | 4.98 | 700 | 6.9958 | 0.8953 |
101
+ | 0.7503 | 5.16 | 725 | 5.4360 | 0.8881 |
102
+ | 0.2639 | 5.34 | 750 | 5.4420 | 0.8917 |
103
 
104
 
105
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc997526ec5af386ad44532e723d8c6872ec73f950f9ce2bccbf3caad559a42a
3
  size 4998578592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:828e62612b4cffa2467ca73ca6cc096e04e92145b3652c804148eef0a1e4c8f2
3
  size 4998578592
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b20323baec700a9f33a51031b0b313c9dd3afb791decfbb0c1c279165726d797
3
  size 706803048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0414a11f91dce242ced67dc4b0f38bf29f82a8d60bf8c48d3eb98d4f58ee24df
3
  size 706803048