Commit
•
497e812
1
Parent(s):
ddd15c3
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: Finetuned_FLAN-T5_VALUE_adapterfusion_lr5e-4_bs32
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# Finetuned_FLAN-T5_VALUE_adapterfusion_lr5e-4_bs32
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4](https://huggingface.co/liuyanchen1015/FLAN-T5_GLUE_finetuning_lr3e-4) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.0870
|
20 |
+
- Accuracy: 0.8692
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0005
|
40 |
+
- train_batch_size: 32
|
41 |
+
- eval_batch_size: 32
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 3.0
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
51 |
+
| 0.0862 | 0.08 | 2500 | 0.1059 | 0.8526 |
|
52 |
+
| 0.092 | 0.17 | 5000 | 0.1025 | 0.856 |
|
53 |
+
| 0.0943 | 0.25 | 7500 | 0.1126 | 0.8516 |
|
54 |
+
| 0.0899 | 0.34 | 10000 | 0.0955 | 0.8578 |
|
55 |
+
| 0.0896 | 0.42 | 12500 | 0.1046 | 0.8564 |
|
56 |
+
| 0.0952 | 0.51 | 15000 | 0.0978 | 0.851 |
|
57 |
+
| 0.0901 | 0.59 | 17500 | 0.0958 | 0.8498 |
|
58 |
+
| 0.095 | 0.68 | 20000 | 0.0974 | 0.8532 |
|
59 |
+
| 0.0955 | 0.76 | 22500 | 0.0982 | 0.853 |
|
60 |
+
| 0.0912 | 0.85 | 25000 | 0.0980 | 0.853 |
|
61 |
+
| 0.0913 | 0.93 | 27500 | 0.0944 | 0.8528 |
|
62 |
+
| 0.0889 | 1.02 | 30000 | 0.0907 | 0.8592 |
|
63 |
+
| 0.0871 | 1.1 | 32500 | 0.0933 | 0.855 |
|
64 |
+
| 0.0872 | 1.18 | 35000 | 0.0904 | 0.861 |
|
65 |
+
| 0.0859 | 1.27 | 37500 | 0.0879 | 0.8594 |
|
66 |
+
| 0.0847 | 1.35 | 40000 | 0.0950 | 0.8584 |
|
67 |
+
| 0.0827 | 1.44 | 42500 | 0.0909 | 0.8622 |
|
68 |
+
| 0.0836 | 1.52 | 45000 | 0.0933 | 0.8552 |
|
69 |
+
| 0.0805 | 1.61 | 47500 | 0.0928 | 0.8646 |
|
70 |
+
| 0.0799 | 1.69 | 50000 | 0.0905 | 0.8648 |
|
71 |
+
| 0.0789 | 1.78 | 52500 | 0.0863 | 0.87 |
|
72 |
+
| 0.0786 | 1.86 | 55000 | 0.0907 | 0.8612 |
|
73 |
+
| 0.0772 | 1.95 | 57500 | 0.0883 | 0.8672 |
|
74 |
+
| 0.075 | 2.03 | 60000 | 0.0886 | 0.8664 |
|
75 |
+
| 0.0727 | 2.12 | 62500 | 0.0878 | 0.8688 |
|
76 |
+
| 0.0724 | 2.2 | 65000 | 0.0881 | 0.8708 |
|
77 |
+
| 0.0729 | 2.28 | 67500 | 0.0879 | 0.8664 |
|
78 |
+
| 0.0714 | 2.37 | 70000 | 0.0883 | 0.8694 |
|
79 |
+
| 0.0694 | 2.45 | 72500 | 0.0876 | 0.8724 |
|
80 |
+
| 0.0698 | 2.54 | 75000 | 0.0869 | 0.8698 |
|
81 |
+
| 0.0706 | 2.62 | 77500 | 0.0872 | 0.8712 |
|
82 |
+
| 0.0685 | 2.71 | 80000 | 0.0874 | 0.8692 |
|
83 |
+
| 0.068 | 2.79 | 82500 | 0.0873 | 0.869 |
|
84 |
+
| 0.0685 | 2.88 | 85000 | 0.0863 | 0.8688 |
|
85 |
+
| 0.068 | 2.96 | 87500 | 0.0870 | 0.8692 |
|
86 |
+
|
87 |
+
|
88 |
+
### Framework versions
|
89 |
+
|
90 |
+
- Transformers 4.26.1
|
91 |
+
- Pytorch 1.13.0+cu117
|
92 |
+
- Datasets 2.10.1
|
93 |
+
- Tokenizers 0.12.1
|