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
91c9554
·
verified ·
1 Parent(s): 5d421fc

End of training

Browse files
Files changed (3) hide show
  1. README.md +19 -18
  2. all_results.json +6 -6
  3. eval_results.json +6 -6
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  library_name: transformers
3
- base_model: motheecreator/vit-Facial-Expression-Recognition
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
@@ -22,7 +23,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7822344637631262
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  # trainer_output
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: 0.6649
36
- - Accuracy: 0.7822
37
 
38
  ## Model description
39
 
@@ -53,11 +54,11 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 3e-05
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 8
60
- - total_train_batch_size: 256
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
@@ -67,16 +68,16 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:------:|:----:|:---------------:|:--------:|
70
- | 2.0497 | 0.9904 | 90 | 1.9228 | 0.4772 |
71
- | 1.7528 | 1.9904 | 180 | 1.4622 | 0.6034 |
72
- | 1.2398 | 2.9904 | 270 | 1.0978 | 0.6984 |
73
- | 1.0084 | 3.9904 | 360 | 0.9290 | 0.7383 |
74
- | 0.8878 | 4.9904 | 450 | 0.8286 | 0.7576 |
75
- | 0.8291 | 5.9904 | 540 | 0.7620 | 0.7712 |
76
- | 0.773 | 6.9904 | 630 | 0.7269 | 0.7740 |
77
- | 0.718 | 7.9904 | 720 | 0.6918 | 0.7814 |
78
- | 0.6805 | 8.9904 | 810 | 0.6808 | 0.7800 |
79
- | 0.6581 | 9.9904 | 900 | 0.6649 | 0.7822 |
80
 
81
 
82
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
  - generated_from_trainer
7
  datasets:
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.6099156481322087
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # trainer_output
33
 
34
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.1080
37
+ - Accuracy: 0.6099
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 3e-05
57
+ - train_batch_size: 64
58
+ - eval_batch_size: 64
59
  - seed: 42
60
  - gradient_accumulation_steps: 8
61
+ - total_train_batch_size: 512
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: cosine
64
  - lr_scheduler_warmup_steps: 1000
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.9890 | 45 | 2.0759 | 0.1400 |
72
+ | 2.0912 | 1.9890 | 90 | 2.0549 | 0.1852 |
73
+ | 2.0576 | 2.9890 | 135 | 1.9888 | 0.2307 |
74
+ | 1.9515 | 3.9890 | 180 | 1.7330 | 0.3922 |
75
+ | 1.7027 | 4.9890 | 225 | 1.5496 | 0.4882 |
76
+ | 1.5105 | 5.9890 | 270 | 1.3937 | 0.5400 |
77
+ | 1.3426 | 6.9890 | 315 | 1.2821 | 0.5590 |
78
+ | 1.2216 | 7.9890 | 360 | 1.2052 | 0.5820 |
79
+ | 1.1407 | 8.9890 | 405 | 1.1482 | 0.5965 |
80
+ | 1.0803 | 9.9890 | 450 | 1.1080 | 0.6099 |
81
 
82
 
83
  ### Framework versions
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 9.990371389270976,
3
- "eval_accuracy": 0.7822344637631262,
4
- "eval_loss": 0.6649115681648254,
5
- "eval_runtime": 59.5489,
6
- "eval_samples_per_second": 97.55,
7
- "eval_steps_per_second": 3.056
8
  }
 
1
  {
2
+ "epoch": 9.989010989010989,
3
+ "eval_accuracy": 0.6099156481322087,
4
+ "eval_loss": 1.1079732179641724,
5
+ "eval_runtime": 57.5807,
6
+ "eval_samples_per_second": 100.885,
7
+ "eval_steps_per_second": 1.58
8
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 9.990371389270976,
3
- "eval_accuracy": 0.7822344637631262,
4
- "eval_loss": 0.6649115681648254,
5
- "eval_runtime": 59.5489,
6
- "eval_samples_per_second": 97.55,
7
- "eval_steps_per_second": 3.056
8
  }
 
1
  {
2
+ "epoch": 9.989010989010989,
3
+ "eval_accuracy": 0.6099156481322087,
4
+ "eval_loss": 1.1079732179641724,
5
+ "eval_runtime": 57.5807,
6
+ "eval_samples_per_second": 100.885,
7
+ "eval_steps_per_second": 1.58
8
  }