lukeleeai commited on
Commit
5dac4c4
1 Parent(s): 501d4dd

End of training

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: t5-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - glue
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: t5-base_rte_dense_sp0_ar0
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: glue
18
+ type: glue
19
+ config: rte
20
+ split: validation
21
+ args: rte
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.0
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # t5-base_rte_dense_sp0_ar0
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: 0.9086
36
+ - Accuracy: 0.0
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
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
+ - gradient_accumulation_steps: 2
60
+ - total_train_batch_size: 16
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_steps: 20
64
+ - num_epochs: 5
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.6787 | 0.16 | 25 | 0.6850 | 0.5307 |
71
+ | 0.7034 | 0.32 | 50 | 0.6689 | 0.5704 |
72
+ | 0.6478 | 0.48 | 75 | 0.6356 | 0.6570 |
73
+ | 0.6889 | 0.64 | 100 | 0.6188 | 0.6859 |
74
+ | 0.588 | 0.8 | 125 | 0.5892 | 0.6859 |
75
+ | 0.5989 | 0.96 | 150 | 0.6802 | 0.6606 |
76
+ | 0.5392 | 1.12 | 175 | 0.5836 | 0.7329 |
77
+ | 0.5497 | 1.28 | 200 | 0.6758 | 0.6715 |
78
+ | 0.5567 | 1.44 | 225 | 0.7056 | 0.6643 |
79
+ | 0.5063 | 1.6 | 250 | 0.5617 | 0.7401 |
80
+ | 0.5644 | 1.76 | 275 | 0.5737 | 0.7256 |
81
+ | 0.6018 | 1.92 | 300 | 0.6179 | 0.7112 |
82
+ | 0.4554 | 2.08 | 325 | 0.5339 | 0.7509 |
83
+ | 0.3778 | 2.24 | 350 | 0.5495 | 0.7726 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.34.1
89
+ - Pytorch 2.0.1+cu117
90
+ - Datasets 2.9.0
91
+ - Tokenizers 0.14.1