Training in progress, epoch 0
Browse files- config.json +55 -0
- model.safetensors +3 -0
- preprocessor_config.json +27 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-large-patch14",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"id2label": {
|
| 7 |
+
"0": "0",
|
| 8 |
+
"1": "1",
|
| 9 |
+
"2": "2",
|
| 10 |
+
"3": "3",
|
| 11 |
+
"4": "4",
|
| 12 |
+
"5": "5",
|
| 13 |
+
"6": "6",
|
| 14 |
+
"7": "7",
|
| 15 |
+
"8": "8",
|
| 16 |
+
"9": "9"
|
| 17 |
+
},
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"0": 0,
|
| 21 |
+
"1": 1,
|
| 22 |
+
"2": 2,
|
| 23 |
+
"3": 3,
|
| 24 |
+
"4": 4,
|
| 25 |
+
"5": 5,
|
| 26 |
+
"6": 6,
|
| 27 |
+
"7": 7,
|
| 28 |
+
"8": 8,
|
| 29 |
+
"9": 9
|
| 30 |
+
},
|
| 31 |
+
"logit_scale_init_value": 2.6592,
|
| 32 |
+
"model_type": "clip",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"projection_dim": 768,
|
| 35 |
+
"text_config": {
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"hidden_size": 768,
|
| 38 |
+
"intermediate_size": 3072,
|
| 39 |
+
"model_type": "clip_text_model",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"projection_dim": 768
|
| 42 |
+
},
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.44.2",
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"dropout": 0.0,
|
| 47 |
+
"hidden_size": 1024,
|
| 48 |
+
"intermediate_size": 4096,
|
| 49 |
+
"model_type": "clip_vision_model",
|
| 50 |
+
"num_attention_heads": 16,
|
| 51 |
+
"num_hidden_layers": 24,
|
| 52 |
+
"patch_size": 14,
|
| 53 |
+
"projection_dim": 768
|
| 54 |
+
}
|
| 55 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b0f5664c62ceff0e716b1ae920add04ccc3d3eb00db8c2048b5746b4aa75ff2
|
| 3 |
+
size 1212808056
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 224
|
| 26 |
+
}
|
| 27 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e70f226bb79a1ad7e11fbafee3ed866b95dba8361fcc753e31eae69dbded1193
|
| 3 |
+
size 5240
|