Augusto777
commited on
Commit
•
290ba76
1
Parent(s):
3091b97
Model save
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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.
|
20 |
- Accuracy: 0.8165
|
21 |
|
22 |
## Model description
|
@@ -45,49 +45,85 @@ The following hyperparameters were used during training:
|
|
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:
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
-
| No log | 0.9 | 7 | 1.
|
55 |
-
| 1.
|
56 |
-
| 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
64 |
-
| 1.
|
65 |
-
|
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
|
92 |
|
93 |
### Framework versions
|
|
|
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: 0.4359
|
20 |
- Accuracy: 0.8165
|
21 |
|
22 |
## Model description
|
|
|
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: 80
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
54 |
+
| No log | 0.9 | 7 | 1.3863 | 0.2844 |
|
55 |
+
| 1.4158 | 1.94 | 15 | 1.3760 | 0.3119 |
|
56 |
+
| 1.3853 | 2.97 | 23 | 1.3548 | 0.3853 |
|
57 |
+
| 1.3745 | 4.0 | 31 | 1.3327 | 0.3394 |
|
58 |
+
| 1.3745 | 4.9 | 38 | 1.2938 | 0.4220 |
|
59 |
+
| 1.3435 | 5.94 | 46 | 1.2450 | 0.4679 |
|
60 |
+
| 1.2681 | 6.97 | 54 | 1.1933 | 0.5596 |
|
61 |
+
| 1.1803 | 8.0 | 62 | 1.1410 | 0.4771 |
|
62 |
+
| 1.1803 | 8.9 | 69 | 1.1014 | 0.5046 |
|
63 |
+
| 1.1277 | 9.94 | 77 | 1.0785 | 0.5321 |
|
64 |
+
| 1.0674 | 10.97 | 85 | 1.0440 | 0.5596 |
|
65 |
+
| 1.0353 | 12.0 | 93 | 0.9962 | 0.5780 |
|
66 |
+
| 0.9859 | 12.9 | 100 | 0.9700 | 0.5872 |
|
67 |
+
| 0.9859 | 13.94 | 108 | 0.9402 | 0.6422 |
|
68 |
+
| 0.9397 | 14.97 | 116 | 0.9215 | 0.6239 |
|
69 |
+
| 0.8959 | 16.0 | 124 | 0.8745 | 0.6606 |
|
70 |
+
| 0.8663 | 16.9 | 131 | 0.8561 | 0.6697 |
|
71 |
+
| 0.8663 | 17.94 | 139 | 0.8182 | 0.6789 |
|
72 |
+
| 0.8405 | 18.97 | 147 | 0.8168 | 0.6514 |
|
73 |
+
| 0.8093 | 20.0 | 155 | 0.8039 | 0.6789 |
|
74 |
+
| 0.7396 | 20.9 | 162 | 0.7478 | 0.7064 |
|
75 |
+
| 0.7588 | 21.94 | 170 | 0.7237 | 0.6972 |
|
76 |
+
| 0.7588 | 22.97 | 178 | 0.7031 | 0.7156 |
|
77 |
+
| 0.7189 | 24.0 | 186 | 0.6956 | 0.6972 |
|
78 |
+
| 0.7111 | 24.9 | 193 | 0.6749 | 0.7248 |
|
79 |
+
| 0.6577 | 25.94 | 201 | 0.6758 | 0.6972 |
|
80 |
+
| 0.6577 | 26.97 | 209 | 0.6429 | 0.7339 |
|
81 |
+
| 0.6681 | 28.0 | 217 | 0.6451 | 0.7064 |
|
82 |
+
| 0.6238 | 28.9 | 224 | 0.6368 | 0.7339 |
|
83 |
+
| 0.6136 | 29.94 | 232 | 0.6233 | 0.7706 |
|
84 |
+
| 0.5934 | 30.97 | 240 | 0.6161 | 0.7706 |
|
85 |
+
| 0.5934 | 32.0 | 248 | 0.6268 | 0.7431 |
|
86 |
+
| 0.5807 | 32.9 | 255 | 0.5879 | 0.7982 |
|
87 |
+
| 0.575 | 33.94 | 263 | 0.5772 | 0.7706 |
|
88 |
+
| 0.5409 | 34.97 | 271 | 0.5703 | 0.7798 |
|
89 |
+
| 0.5409 | 36.0 | 279 | 0.5603 | 0.7890 |
|
90 |
+
| 0.553 | 36.9 | 286 | 0.5560 | 0.8073 |
|
91 |
+
| 0.515 | 37.94 | 294 | 0.5639 | 0.7706 |
|
92 |
+
| 0.5424 | 38.97 | 302 | 0.5483 | 0.7890 |
|
93 |
+
| 0.5193 | 40.0 | 310 | 0.5505 | 0.7798 |
|
94 |
+
| 0.5193 | 40.9 | 317 | 0.5323 | 0.8073 |
|
95 |
+
| 0.5123 | 41.94 | 325 | 0.5257 | 0.7982 |
|
96 |
+
| 0.4719 | 42.97 | 333 | 0.5270 | 0.7798 |
|
97 |
+
| 0.4583 | 44.0 | 341 | 0.5305 | 0.7706 |
|
98 |
+
| 0.4583 | 44.9 | 348 | 0.5282 | 0.7798 |
|
99 |
+
| 0.4568 | 45.94 | 356 | 0.5178 | 0.7890 |
|
100 |
+
| 0.4717 | 46.97 | 364 | 0.4945 | 0.7982 |
|
101 |
+
| 0.4587 | 48.0 | 372 | 0.4978 | 0.7982 |
|
102 |
+
| 0.4587 | 48.9 | 379 | 0.4888 | 0.7890 |
|
103 |
+
| 0.4314 | 49.94 | 387 | 0.4867 | 0.7982 |
|
104 |
+
| 0.4389 | 50.97 | 395 | 0.4739 | 0.7890 |
|
105 |
+
| 0.4115 | 52.0 | 403 | 0.4844 | 0.7982 |
|
106 |
+
| 0.4323 | 52.9 | 410 | 0.4819 | 0.7982 |
|
107 |
+
| 0.4323 | 53.94 | 418 | 0.4562 | 0.7982 |
|
108 |
+
| 0.3855 | 54.97 | 426 | 0.4640 | 0.8073 |
|
109 |
+
| 0.4113 | 56.0 | 434 | 0.4474 | 0.8165 |
|
110 |
+
| 0.4282 | 56.9 | 441 | 0.4540 | 0.7982 |
|
111 |
+
| 0.4282 | 57.94 | 449 | 0.4450 | 0.8165 |
|
112 |
+
| 0.4499 | 58.97 | 457 | 0.4497 | 0.8165 |
|
113 |
+
| 0.4179 | 60.0 | 465 | 0.4400 | 0.8073 |
|
114 |
+
| 0.4213 | 60.9 | 472 | 0.4392 | 0.8073 |
|
115 |
+
| 0.4176 | 61.94 | 480 | 0.4325 | 0.8257 |
|
116 |
+
| 0.4176 | 62.97 | 488 | 0.4296 | 0.8165 |
|
117 |
+
| 0.4083 | 64.0 | 496 | 0.4388 | 0.8165 |
|
118 |
+
| 0.3853 | 64.9 | 503 | 0.4392 | 0.8073 |
|
119 |
+
| 0.3647 | 65.94 | 511 | 0.4349 | 0.8073 |
|
120 |
+
| 0.3647 | 66.97 | 519 | 0.4344 | 0.8257 |
|
121 |
+
| 0.3927 | 68.0 | 527 | 0.4348 | 0.8073 |
|
122 |
+
| 0.3833 | 68.9 | 534 | 0.4352 | 0.8073 |
|
123 |
+
| 0.3932 | 69.94 | 542 | 0.4294 | 0.8165 |
|
124 |
+
| 0.4085 | 70.97 | 550 | 0.4276 | 0.8073 |
|
125 |
+
| 0.4085 | 72.0 | 558 | 0.4232 | 0.8073 |
|
126 |
+
| 0.4029 | 72.26 | 560 | 0.4359 | 0.8165 |
|
127 |
|
128 |
|
129 |
### Framework versions
|
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 sha256:2975e1daa5151f020c7e969d82f9e24e3e3d168dba3c3758833ceea78d267479
|
3 |
size 12203648
|
runs/Feb01_19-27-47_b2db6ba6b423/events.out.tfevents.1706815678.b2db6ba6b423.7182.0
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 sha256:084aff1bdf867f4359dee9ed19187e50d52c92edaa05598b1f18552a6d5f98cc
|
3 |
+
size 37012
|