Augusto777
commited on
Commit
•
0605b70
1
Parent(s):
d5ecc96
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: MBZUAI/swiftformer-xs
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: swiftformer-xs-dmae-va-U-40
|
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 |
+
# swiftformer-xs-dmae-va-U-40
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.6736
|
20 |
+
- Accuracy: 0.7523
|
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: 5e-05
|
40 |
+
- train_batch_size: 32
|
41 |
+
- eval_batch_size: 32
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 128
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 40
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| No log | 0.9 | 7 | 1.3578 | 0.2936 |
|
55 |
+
| 1.3702 | 1.94 | 15 | 1.3703 | 0.2936 |
|
56 |
+
| 1.3497 | 2.97 | 23 | 1.3361 | 0.3394 |
|
57 |
+
| 1.3004 | 4.0 | 31 | 1.2852 | 0.3670 |
|
58 |
+
| 1.3004 | 4.9 | 38 | 1.2317 | 0.4312 |
|
59 |
+
| 1.2248 | 5.94 | 46 | 1.1786 | 0.4587 |
|
60 |
+
| 1.1485 | 6.97 | 54 | 1.1240 | 0.5046 |
|
61 |
+
| 1.0759 | 8.0 | 62 | 1.0727 | 0.5505 |
|
62 |
+
| 1.0759 | 8.9 | 69 | 1.0404 | 0.5596 |
|
63 |
+
| 1.0244 | 9.94 | 77 | 0.9742 | 0.6239 |
|
64 |
+
| 0.9782 | 10.97 | 85 | 0.9374 | 0.6422 |
|
65 |
+
| 0.9359 | 12.0 | 93 | 0.9197 | 0.6789 |
|
66 |
+
| 0.9051 | 12.9 | 100 | 0.8753 | 0.6881 |
|
67 |
+
| 0.9051 | 13.94 | 108 | 0.8679 | 0.6972 |
|
68 |
+
| 0.8652 | 14.97 | 116 | 0.8316 | 0.7156 |
|
69 |
+
| 0.8336 | 16.0 | 124 | 0.8222 | 0.6972 |
|
70 |
+
| 0.8177 | 16.9 | 131 | 0.8178 | 0.6972 |
|
71 |
+
| 0.8177 | 17.94 | 139 | 0.7818 | 0.7339 |
|
72 |
+
| 0.8077 | 18.97 | 147 | 0.7627 | 0.7339 |
|
73 |
+
| 0.7796 | 20.0 | 155 | 0.7478 | 0.7339 |
|
74 |
+
| 0.7673 | 20.9 | 162 | 0.7415 | 0.7431 |
|
75 |
+
| 0.7445 | 21.94 | 170 | 0.7414 | 0.7156 |
|
76 |
+
| 0.7445 | 22.97 | 178 | 0.7375 | 0.7156 |
|
77 |
+
| 0.7413 | 24.0 | 186 | 0.7354 | 0.7156 |
|
78 |
+
| 0.739 | 24.9 | 193 | 0.7110 | 0.7431 |
|
79 |
+
| 0.6992 | 25.94 | 201 | 0.7121 | 0.7339 |
|
80 |
+
| 0.6992 | 26.97 | 209 | 0.7044 | 0.7431 |
|
81 |
+
| 0.7111 | 28.0 | 217 | 0.6947 | 0.7339 |
|
82 |
+
| 0.7013 | 28.9 | 224 | 0.7007 | 0.7523 |
|
83 |
+
| 0.712 | 29.94 | 232 | 0.6793 | 0.7431 |
|
84 |
+
| 0.671 | 30.97 | 240 | 0.6808 | 0.7431 |
|
85 |
+
| 0.671 | 32.0 | 248 | 0.6821 | 0.7339 |
|
86 |
+
| 0.6862 | 32.9 | 255 | 0.6705 | 0.7339 |
|
87 |
+
| 0.6606 | 33.94 | 263 | 0.6784 | 0.7431 |
|
88 |
+
| 0.6667 | 34.97 | 271 | 0.6764 | 0.7523 |
|
89 |
+
| 0.6667 | 36.0 | 279 | 0.6717 | 0.7523 |
|
90 |
+
| 0.6687 | 36.13 | 280 | 0.6736 | 0.7523 |
|
91 |
+
|
92 |
+
|
93 |
+
### Framework versions
|
94 |
+
|
95 |
+
- Transformers 4.35.2
|
96 |
+
- Pytorch 2.1.0+cu121
|
97 |
+
- Datasets 2.16.1
|
98 |
+
- Tokenizers 0.15.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12203648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cdf22794ce831a58aa55da647b52558ef1db28c7463cecbae217511e0d62c09
|
3 |
size 12203648
|
runs/Feb01_15-59-58_56aa26a8524f/events.out.tfevents.1706803208.56aa26a8524f.1432.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27d41ed4d8a9b377cb9f57fdd4a2e6d4e9ee40c5589ae2c9f08a2af1af651aeb
|
3 |
+
size 20988
|