End of training
Browse files- README.md +54 -0
- config.json +27 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: bsd-3-clause
|
4 |
+
base_model: Salesforce/blip-vqa-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: blip-Visual-QuestionAnswering-coco
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# blip-Visual-QuestionAnswering-coco
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [Salesforce/blip-vqa-base](https://huggingface.co/Salesforce/blip-vqa-base) on an unknown dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.02
|
37 |
+
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 1
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.45.1
|
52 |
+
- Pytorch 2.4.0
|
53 |
+
- Datasets 3.0.1
|
54 |
+
- Tokenizers 0.20.0
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Salesforce/blip-vqa-base",
|
3 |
+
"architectures": [
|
4 |
+
"BlipForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"image_text_hidden_size": 256,
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"label_smoothing": 0.0,
|
10 |
+
"logit_scale_init_value": 2.6592,
|
11 |
+
"model_type": "blip",
|
12 |
+
"projection_dim": 512,
|
13 |
+
"text_config": {
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"model_type": "blip_text_model",
|
16 |
+
"num_attention_heads": 12
|
17 |
+
},
|
18 |
+
"torch_dtype": "float32",
|
19 |
+
"transformers_version": "4.45.1",
|
20 |
+
"vision_config": {
|
21 |
+
"dropout": 0.0,
|
22 |
+
"initializer_factor": 1.0,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"model_type": "blip_vision_model",
|
25 |
+
"num_channels": 3
|
26 |
+
}
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 30522,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.45.1"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7f747c0c0c9bc0255cc2f08ee721115bae47df31581427f31dadd3cb6e7594a
|
3 |
+
size 1538792184
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:892cae2877485cc80c016bc8b588aa5e52a404a4b86cf954165eccf1ef70100d
|
3 |
+
size 5432
|