Hugging Face's logo

JulesGo
/
vit_focus

Transformers
Safetensors
importance_model
Generated from Trainer
Model card Files
xet
Community
JulesGo commited on
Commit
f9d4c4b
·
verified ·
1 Parent(s): 7aaa910

Model save

Browse files
Files changed (2) hide show
  1. README.md +32 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0859
18
- - Mse: 0.1291
19
- - Mae: 0.3120
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
@@ -43,30 +43,39 @@ The following hyperparameters were used during training:
43
  - total_train_batch_size: 32
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
- - num_epochs: 20
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Mse | Mae |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
52
- | No log | 1.0 | 10 | 0.1177 | 0.1614 | 0.3476 |
53
- | No log | 2.0 | 20 | 0.0932 | 0.1411 | 0.3288 |
54
- | No log | 3.0 | 30 | 0.0914 | 0.1478 | 0.3351 |
55
- | 0.3379 | 4.0 | 40 | 0.0799 | 0.1369 | 0.3216 |
56
- | 0.3379 | 5.0 | 50 | 0.0773 | 0.1365 | 0.3211 |
57
- | 0.3379 | 6.0 | 60 | 0.0842 | 0.1413 | 0.3251 |
58
- | 0.3379 | 7.0 | 70 | 0.0877 | 0.1329 | 0.3170 |
59
- | 0.2829 | 8.0 | 80 | 0.0830 | 0.1370 | 0.3192 |
60
- | 0.2829 | 9.0 | 90 | 0.0827 | 0.1408 | 0.3254 |
61
- | 0.2829 | 10.0 | 100 | 0.0859 | 0.1291 | 0.3120 |
62
- | 0.2829 | 11.0 | 110 | 0.1009 | 0.1478 | 0.3309 |
63
- | 0.2461 | 12.0 | 120 | 0.0810 | 0.1352 | 0.3174 |
64
- | 0.2461 | 13.0 | 130 | 0.0837 | 0.1368 | 0.3189 |
65
- | 0.2461 | 14.0 | 140 | 0.0887 | 0.1410 | 0.3230 |
66
- | 0.2461 | 15.0 | 150 | 0.0837 | 0.1321 | 0.3139 |
67
- | 0.2104 | 16.0 | 160 | 0.0908 | 0.1404 | 0.3226 |
68
- | 0.2104 | 17.0 | 170 | 0.0857 | 0.1367 | 0.3183 |
69
- | 0.2104 | 18.0 | 180 | 0.0834 | 0.1351 | 0.3171 |
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0609
18
+ - Mse: 0.1301
19
+ - Mae: 0.3117
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
 
43
  - total_train_batch_size: 32
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 30
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Mse | Mae |
51
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
52
+ | No log | 1.0 | 10 | 0.0993 | 0.1529 | 0.3380 |
53
+ | No log | 2.0 | 20 | 0.1050 | 0.1554 | 0.3409 |
54
+ | No log | 3.0 | 30 | 0.0997 | 0.1493 | 0.3352 |
55
+ | 0.313 | 4.0 | 40 | 0.0656 | 0.1345 | 0.3157 |
56
+ | 0.313 | 5.0 | 50 | 0.0659 | 0.1366 | 0.3203 |
57
+ | 0.313 | 6.0 | 60 | 0.0639 | 0.1296 | 0.3119 |
58
+ | 0.313 | 7.0 | 70 | 0.0639 | 0.1351 | 0.3178 |
59
+ | 0.1742 | 8.0 | 80 | 0.0639 | 0.1274 | 0.3086 |
60
+ | 0.1742 | 9.0 | 90 | 0.0728 | 0.1294 | 0.3096 |
61
+ | 0.1742 | 10.0 | 100 | 0.0671 | 0.1330 | 0.3150 |
62
+ | 0.1742 | 11.0 | 110 | 0.0670 | 0.1260 | 0.3067 |
63
+ | 0.1284 | 12.0 | 120 | 0.0658 | 0.1253 | 0.3059 |
64
+ | 0.1284 | 13.0 | 130 | 0.0641 | 0.1281 | 0.3104 |
65
+ | 0.1284 | 14.0 | 140 | 0.0643 | 0.1289 | 0.3105 |
66
+ | 0.1284 | 15.0 | 150 | 0.0649 | 0.1342 | 0.3172 |
67
+ | 0.0981 | 16.0 | 160 | 0.0656 | 0.1276 | 0.3085 |
68
+ | 0.0981 | 17.0 | 170 | 0.0627 | 0.1316 | 0.3136 |
69
+ | 0.0981 | 18.0 | 180 | 0.0620 | 0.1343 | 0.3169 |
70
+ | 0.0981 | 19.0 | 190 | 0.0632 | 0.1311 | 0.3129 |
71
+ | 0.0767 | 20.0 | 200 | 0.0630 | 0.1326 | 0.3143 |
72
+ | 0.0767 | 21.0 | 210 | 0.0641 | 0.1299 | 0.3117 |
73
+ | 0.0767 | 22.0 | 220 | 0.0634 | 0.1294 | 0.3114 |
74
+ | 0.0767 | 23.0 | 230 | 0.0629 | 0.1315 | 0.3130 |
75
+ | 0.0615 | 24.0 | 240 | 0.0612 | 0.1308 | 0.3124 |
76
+ | 0.0615 | 25.0 | 250 | 0.0599 | 0.1302 | 0.3118 |
77
+ | 0.0615 | 26.0 | 260 | 0.0609 | 0.1313 | 0.3132 |
78
+ | 0.0615 | 27.0 | 270 | 0.0609 | 0.1301 | 0.3117 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35efaeb9a773fd405b498a9b43bd438766510ce0d0c48f6192a6aada07e8f650
3
  size 97176156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f7c5a7f684c08ba478f32613b8b76b519776c876a398fe247ef8ae047246d8
3
  size 97176156