ft-vilt-b32-mlm
Browse files- README.md +55 -0
- config.json +79 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: dandelin/vilt-b32-mlm
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- vqa
|
8 |
+
model-index:
|
9 |
+
- name: ft-vilt-b32-mlm
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# ft-vilt-b32-mlm
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on the vqa dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 20
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.35.2
|
53 |
+
- Pytorch 2.0.0
|
54 |
+
- Datasets 2.15.0
|
55 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dandelin/vilt-b32-mlm",
|
3 |
+
"architectures": [
|
4 |
+
"ViltForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.0,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "chopsticks",
|
12 |
+
"1": "picnic table",
|
13 |
+
"2": "yes",
|
14 |
+
"3": "boy",
|
15 |
+
"4": "crossing",
|
16 |
+
"5": "resting",
|
17 |
+
"6": "gray",
|
18 |
+
"7": "table",
|
19 |
+
"8": "4",
|
20 |
+
"9": "skateboard",
|
21 |
+
"10": "1",
|
22 |
+
"11": "at table",
|
23 |
+
"12": "green",
|
24 |
+
"13": "brown",
|
25 |
+
"14": "tired",
|
26 |
+
"15": "down",
|
27 |
+
"16": "watching",
|
28 |
+
"17": "walking",
|
29 |
+
"18": "10",
|
30 |
+
"19": "ice cream",
|
31 |
+
"20": "air",
|
32 |
+
"21": "shrimp",
|
33 |
+
"22": "no"
|
34 |
+
},
|
35 |
+
"image_size": 384,
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"label2id": {
|
39 |
+
"1": 10,
|
40 |
+
"10": 18,
|
41 |
+
"4": 8,
|
42 |
+
"air": 20,
|
43 |
+
"at table": 11,
|
44 |
+
"boy": 3,
|
45 |
+
"brown": 13,
|
46 |
+
"chopsticks": 0,
|
47 |
+
"crossing": 4,
|
48 |
+
"down": 15,
|
49 |
+
"gray": 6,
|
50 |
+
"green": 12,
|
51 |
+
"ice cream": 19,
|
52 |
+
"no": 22,
|
53 |
+
"picnic table": 1,
|
54 |
+
"resting": 5,
|
55 |
+
"shrimp": 21,
|
56 |
+
"skateboard": 9,
|
57 |
+
"table": 7,
|
58 |
+
"tired": 14,
|
59 |
+
"walking": 17,
|
60 |
+
"watching": 16,
|
61 |
+
"yes": 2
|
62 |
+
},
|
63 |
+
"layer_norm_eps": 1e-12,
|
64 |
+
"max_image_length": -1,
|
65 |
+
"max_position_embeddings": 40,
|
66 |
+
"modality_type_vocab_size": 2,
|
67 |
+
"model_type": "vilt",
|
68 |
+
"num_attention_heads": 12,
|
69 |
+
"num_channels": 3,
|
70 |
+
"num_hidden_layers": 12,
|
71 |
+
"num_images": -1,
|
72 |
+
"patch_size": 32,
|
73 |
+
"qkv_bias": true,
|
74 |
+
"tie_word_embeddings": false,
|
75 |
+
"torch_dtype": "float32",
|
76 |
+
"transformers_version": "4.35.2",
|
77 |
+
"type_vocab_size": 2,
|
78 |
+
"vocab_size": 30522
|
79 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8452601832466d911ad0081c723e70caf78bc575be2bbebc0d2fd46c4b122e0
|
3 |
+
size 451283276
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee30d3fef0442816d77578e30edae42b09d1ce8f779d3d001b8c7bfe5cbc7c70
|
3 |
+
size 4155
|