Hugging Face's logo

NekoJar
/
trainer_output

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
NekoJar commited on
Commit
9ab7dfc
·
verified ·
1 Parent(s): d8f409c

End of training

Browse files
Files changed (4) hide show
  1. README.md +14 -9
  2. all_results.json +6 -6
  3. eval_results.json +6 -6
  4. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.6873816491650887
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.2060
36
- - Accuracy: 0.6874
37
 
38
  ## Model description
39
 
@@ -61,17 +61,22 @@ The following hyperparameters were used during training:
61
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: cosine
63
  - lr_scheduler_warmup_steps: 1000
64
- - num_epochs: 5
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
- | No log | 0.9890 | 45 | 2.0370 | 0.2152 |
71
- | 2.0662 | 1.9890 | 90 | 1.9128 | 0.3617 |
72
- | 1.9584 | 2.9890 | 135 | 1.6865 | 0.5517 |
73
- | 1.7286 | 3.9890 | 180 | 1.4094 | 0.6511 |
74
- | 1.4041 | 4.9890 | 225 | 1.2060 | 0.6874 |
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.755896023411947
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [motheecreator/vit-Facial-Expression-Recognition](https://huggingface.co/motheecreator/vit-Facial-Expression-Recognition) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.8323
36
+ - Accuracy: 0.7559
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
62
  - lr_scheduler_type: cosine
63
  - lr_scheduler_warmup_steps: 1000
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
+ | No log | 0.9890 | 45 | 2.0569 | 0.1918 |
71
+ | 2.0911 | 1.9890 | 90 | 1.9314 | 0.4433 |
72
+ | 1.9842 | 2.9890 | 135 | 1.6798 | 0.6192 |
73
+ | 1.7415 | 3.9890 | 180 | 1.3741 | 0.6504 |
74
+ | 1.413 | 4.9890 | 225 | 1.1637 | 0.6953 |
75
+ | 1.1803 | 5.9890 | 270 | 1.0347 | 0.7172 |
76
+ | 1.0364 | 6.9890 | 315 | 0.9433 | 0.7356 |
77
+ | 0.9529 | 7.9890 | 360 | 0.8781 | 0.7478 |
78
+ | 0.8837 | 8.9890 | 405 | 0.8323 | 0.7559 |
79
+ | 0.8339 | 9.9890 | 450 | 0.8072 | 0.7531 |
80
 
81
 
82
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.989010989010989,
3
- "eval_accuracy": 0.6873816491650887,
4
- "eval_loss": 1.2059834003448486,
5
- "eval_runtime": 55.6391,
6
- "eval_samples_per_second": 104.405,
7
- "eval_steps_per_second": 1.636
8
  }
 
1
  {
2
+ "epoch": 9.989010989010989,
3
+ "eval_accuracy": 0.755896023411947,
4
+ "eval_loss": 0.8322914838790894,
5
+ "eval_runtime": 53.712,
6
+ "eval_samples_per_second": 108.151,
7
+ "eval_steps_per_second": 1.694
8
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 4.989010989010989,
3
- "eval_accuracy": 0.6873816491650887,
4
- "eval_loss": 1.2059834003448486,
5
- "eval_runtime": 55.6391,
6
- "eval_samples_per_second": 104.405,
7
- "eval_steps_per_second": 1.636
8
  }
 
1
  {
2
+ "epoch": 9.989010989010989,
3
+ "eval_accuracy": 0.755896023411947,
4
+ "eval_loss": 0.8322914838790894,
5
+ "eval_runtime": 53.712,
6
+ "eval_samples_per_second": 108.151,
7
+ "eval_steps_per_second": 1.694
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4c2214d7857a1cb53b939097f09c0db5068420ebe58a6a193f0cac8025e6dcb
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c81ddd449b6039960b137608a59dd06e2491be145a7f26c85c7d00669a0ec4
3
  size 343242432