Commit
•
31d0112
1
Parent(s):
4cbc492
Yayyy Lets Share hateful Memes!!!
Browse files- README.md +11 -14
- all_results.json +8 -8
- config.json +0 -8
- eval_results.json +4 -5
- model.safetensors +1 -1
- runs/Apr10_12-00-17_decc3680cd07/events.out.tfevents.1712750428.decc3680cd07.703.4 +3 -0
- runs/Apr10_12-00-17_decc3680cd07/events.out.tfevents.1712752527.decc3680cd07.703.5 +3 -0
- train_results.json +4 -4
- trainer_state.json +0 -0
- 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.
|
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 |
|
54 |
-
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
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.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 2.
|
8 |
"total_flos": 5.269455293792256e+18,
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime":
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 3.
|
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 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
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:
|
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.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 3.
|
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:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcf2383e609537e3804ed5eba77860e24322dad9bd0fcbda980eecb841355fdb
|
3 |
size 4920
|