Training in progress, step 1000
Browse files- config.json +110 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/cvt-21-384-22k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CvtForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_drop_rate": [
|
| 7 |
+
0.0,
|
| 8 |
+
0.0,
|
| 9 |
+
0.0
|
| 10 |
+
],
|
| 11 |
+
"cls_token": [
|
| 12 |
+
false,
|
| 13 |
+
false,
|
| 14 |
+
true
|
| 15 |
+
],
|
| 16 |
+
"depth": [
|
| 17 |
+
1,
|
| 18 |
+
4,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": [
|
| 22 |
+
0.0,
|
| 23 |
+
0.0,
|
| 24 |
+
0.1
|
| 25 |
+
],
|
| 26 |
+
"drop_rate": [
|
| 27 |
+
0.0,
|
| 28 |
+
0.0,
|
| 29 |
+
0.0
|
| 30 |
+
],
|
| 31 |
+
"embed_dim": [
|
| 32 |
+
64,
|
| 33 |
+
192,
|
| 34 |
+
384
|
| 35 |
+
],
|
| 36 |
+
"image_size": 384,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"kernel_qkv": [
|
| 39 |
+
3,
|
| 40 |
+
3,
|
| 41 |
+
3
|
| 42 |
+
],
|
| 43 |
+
"layer_norm_eps": 1e-12,
|
| 44 |
+
"mlp_ratio": [
|
| 45 |
+
4.0,
|
| 46 |
+
4.0,
|
| 47 |
+
4.0
|
| 48 |
+
],
|
| 49 |
+
"model_type": "cvt",
|
| 50 |
+
"num_channels": 3,
|
| 51 |
+
"num_heads": [
|
| 52 |
+
1,
|
| 53 |
+
3,
|
| 54 |
+
6
|
| 55 |
+
],
|
| 56 |
+
"num_stages": 3,
|
| 57 |
+
"padding_kv": [
|
| 58 |
+
1,
|
| 59 |
+
1,
|
| 60 |
+
1
|
| 61 |
+
],
|
| 62 |
+
"padding_q": [
|
| 63 |
+
1,
|
| 64 |
+
1,
|
| 65 |
+
1
|
| 66 |
+
],
|
| 67 |
+
"patch_padding": [
|
| 68 |
+
2,
|
| 69 |
+
1,
|
| 70 |
+
1
|
| 71 |
+
],
|
| 72 |
+
"patch_sizes": [
|
| 73 |
+
7,
|
| 74 |
+
3,
|
| 75 |
+
3
|
| 76 |
+
],
|
| 77 |
+
"patch_stride": [
|
| 78 |
+
4,
|
| 79 |
+
2,
|
| 80 |
+
2
|
| 81 |
+
],
|
| 82 |
+
"pos_embed": [
|
| 83 |
+
false,
|
| 84 |
+
false,
|
| 85 |
+
false
|
| 86 |
+
],
|
| 87 |
+
"problem_type": "single_label_classification",
|
| 88 |
+
"qkv_bias": [
|
| 89 |
+
true,
|
| 90 |
+
true,
|
| 91 |
+
true
|
| 92 |
+
],
|
| 93 |
+
"qkv_projection_method": [
|
| 94 |
+
"dw_bn",
|
| 95 |
+
"dw_bn",
|
| 96 |
+
"dw_bn"
|
| 97 |
+
],
|
| 98 |
+
"stride_kv": [
|
| 99 |
+
2,
|
| 100 |
+
2,
|
| 101 |
+
2
|
| 102 |
+
],
|
| 103 |
+
"stride_q": [
|
| 104 |
+
1,
|
| 105 |
+
1,
|
| 106 |
+
1
|
| 107 |
+
],
|
| 108 |
+
"torch_dtype": "float32",
|
| 109 |
+
"transformers_version": "4.46.1"
|
| 110 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33608119b8e1cae5ca9a617ad3fc5fa7c0741855892c5b54cfbcbd29e05decff
|
| 3 |
+
size 125239600
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24247a4de87045fe59420349a5e553200b83a5924d4cb424a4364561325242a1
|
| 3 |
+
size 5176
|