Hugging Face's logo

GauravGrow
/
vit-base-hate-meme

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GauravGrow commited on
Commit
31d0112
•
1 Parent(s): 4cbc492

Yayyy Lets Share hateful Memes!!!

Browse files
Files changed (10) hide show
  1. README.md +11 -14
  2. all_results.json +8 -8
  3. config.json +0 -8
  4. eval_results.json +4 -5
  5. model.safetensors +1 -1
  6. runs/Apr10_12-00-17_decc3680cd07/events.out.tfevents.1712750428.decc3680cd07.703.4 +3 -0
  7. runs/Apr10_12-00-17_decc3680cd07/events.out.tfevents.1712752527.decc3680cd07.703.5 +3 -0
  8. train_results.json +4 -4
  9. trainer_state.json +0 -0
  10. training_args.bin +1 -1
README.md CHANGED
@@ -4,8 +4,6 @@ base_model: google/vit-base-patch16-224
4
  tags:
5
  - image-classification
6
  - generated_from_trainer
7
- metrics:
8
- - accuracy
9
  model-index:
10
  - name: vit-base-hate-meme
11
  results: []
@@ -18,8 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the emily49/hateful_memes_train_dev dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.7461
22
- - Accuracy: 0.498
23
 
24
  ## Model description
25
 
@@ -50,16 +47,16 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.6483 | 1.0 | 532 | 0.7933 | 0.5 |
56
- | 0.6203 | 2.0 | 1064 | 0.7461 | 0.498 |
57
- | 0.5955 | 3.0 | 1596 | 0.7539 | 0.518 |
58
- | 0.4796 | 4.0 | 2128 | 0.9387 | 0.536 |
59
- | 0.425 | 5.0 | 2660 | 0.9824 | 0.538 |
60
- | 0.2869 | 6.0 | 3192 | 1.6186 | 0.542 |
61
- | 0.0337 | 7.0 | 3724 | 2.5670 | 0.538 |
62
- | 0.0166 | 8.0 | 4256 | 2.8061 | 0.538 |
63
 
64
 
65
  ### Framework versions
 
4
  tags:
5
  - image-classification
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: vit-base-hate-meme
9
  results: []
 
16
 
17
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the emily49/hateful_memes_train_dev dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6966
 
20
 
21
  ## Model description
22
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.6407 | 1.0 | 532 | 0.6966 |
53
+ | 0.5847 | 2.0 | 1064 | 0.7980 |
54
+ | 0.6144 | 3.0 | 1596 | 0.7764 |
55
+ | 0.5307 | 4.0 | 2128 | 0.9913 |
56
+ | 0.5545 | 5.0 | 2660 | 0.9512 |
57
+ | 0.3243 | 6.0 | 3192 | 1.5071 |
58
+ | 0.1371 | 7.0 | 3724 | 2.0203 |
59
+ | 0.0571 | 8.0 | 4256 | 2.9499 |
60
 
61
 
62
  ### Framework versions
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 8.0,
3
  "eval_accuracy": 0.498,
4
- "eval_loss": 0.746105968952179,
5
- "eval_runtime": 5.5949,
6
- "eval_samples_per_second": 89.367,
7
- "eval_steps_per_second": 2.86,
8
  "total_flos": 5.269455293792256e+18,
9
- "train_loss": 0.40350076897398923,
10
- "train_runtime": 1386.2467,
11
- "train_samples_per_second": 49.053,
12
- "train_steps_per_second": 3.07
13
  }
 
1
  {
2
  "epoch": 8.0,
3
  "eval_accuracy": 0.498,
4
+ "eval_loss": 0.6965588331222534,
5
+ "eval_runtime": 6.8942,
6
+ "eval_samples_per_second": 72.524,
7
+ "eval_steps_per_second": 2.321,
8
  "total_flos": 5.269455293792256e+18,
9
+ "train_loss": 0.4405817036390921,
10
+ "train_runtime": 1400.9279,
11
+ "train_samples_per_second": 48.539,
12
+ "train_steps_per_second": 3.038
13
  }
config.json CHANGED
@@ -8,17 +8,9 @@
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
11
- "id2label": {
12
- "0": 0,
13
- "1": 1
14
- },
15
  "image_size": 224,
16
  "initializer_range": 0.02,
17
  "intermediate_size": 3072,
18
- "label2id": {
19
- "0": "0",
20
- "1": "1"
21
- },
22
  "layer_norm_eps": 1e-12,
23
  "model_type": "vit",
24
  "num_attention_heads": 12,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.0,
10
  "hidden_size": 768,
 
 
 
 
11
  "image_size": 224,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
 
 
 
 
14
  "layer_norm_eps": 1e-12,
15
  "model_type": "vit",
16
  "num_attention_heads": 12,
eval_results.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
  "epoch": 8.0,
3
- "eval_accuracy": 0.498,
4
- "eval_loss": 0.746105968952179,
5
- "eval_runtime": 5.5949,
6
- "eval_samples_per_second": 89.367,
7
- "eval_steps_per_second": 2.86
8
  }
 
1
  {
2
  "epoch": 8.0,
3
+ "eval_loss": 0.6965588331222534,
4
+ "eval_runtime": 6.8942,
5
+ "eval_samples_per_second": 72.524,
6
+ "eval_steps_per_second": 2.321
 
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8710ba864bae83388e22f3b5e1f0c884776b615f25c94f15cc3b917142ee7cd
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6918b6ac855c979220f8ba97528da52a8ef76e9dec15d76bb85871fff1e13183
3
  size 343223968
runs/Apr10_12-00-17_decc3680cd07/events.out.tfevents.1712750428.decc3680cd07.703.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33e82c52daca615e977225e4a38bb7824ec1776801d122d50ae7fabc17aeb75e
3
+ size 96651
runs/Apr10_12-00-17_decc3680cd07/events.out.tfevents.1712752527.decc3680cd07.703.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e851efcaecd2f8e1fdbf8c092b651960ccb109e7bc917403f57878536b900d
3
+ size 359
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 8.0,
3
  "total_flos": 5.269455293792256e+18,
4
- "train_loss": 0.40350076897398923,
5
- "train_runtime": 1386.2467,
6
- "train_samples_per_second": 49.053,
7
- "train_steps_per_second": 3.07
8
  }
 
1
  {
2
  "epoch": 8.0,
3
  "total_flos": 5.269455293792256e+18,
4
+ "train_loss": 0.4405817036390921,
5
+ "train_runtime": 1400.9279,
6
+ "train_samples_per_second": 48.539,
7
+ "train_steps_per_second": 3.038
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b19ba6bc19f5ba61d85c29b1ba40f80a59d96fadc9cd9b34010a076d641e735
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcf2383e609537e3804ed5eba77860e24322dad9bd0fcbda980eecb841355fdb
3
  size 4920