Upload folder using huggingface_hub
Browse files- config.json +68 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +23 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +258 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Parveshiiii/Image-Classifier",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Swinv2ForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"depths": [
|
| 9 |
+
2,
|
| 10 |
+
2,
|
| 11 |
+
18,
|
| 12 |
+
2
|
| 13 |
+
],
|
| 14 |
+
"drop_path_rate": 0.1,
|
| 15 |
+
"embed_dim": 192,
|
| 16 |
+
"encoder_stride": 32,
|
| 17 |
+
"hidden_act": "gelu",
|
| 18 |
+
"hidden_dropout_prob": 0.0,
|
| 19 |
+
"hidden_size": 1536,
|
| 20 |
+
"id2label": {
|
| 21 |
+
"0": "artificial",
|
| 22 |
+
"1": "real"
|
| 23 |
+
},
|
| 24 |
+
"image_size": 256,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"artificial": 0,
|
| 28 |
+
"real": 1
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-05,
|
| 31 |
+
"mlp_ratio": 4.0,
|
| 32 |
+
"model_type": "swinv2",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"num_heads": [
|
| 35 |
+
6,
|
| 36 |
+
12,
|
| 37 |
+
24,
|
| 38 |
+
48
|
| 39 |
+
],
|
| 40 |
+
"num_layers": 4,
|
| 41 |
+
"out_features": [
|
| 42 |
+
"stage4"
|
| 43 |
+
],
|
| 44 |
+
"out_indices": [
|
| 45 |
+
4
|
| 46 |
+
],
|
| 47 |
+
"patch_size": 4,
|
| 48 |
+
"path_norm": true,
|
| 49 |
+
"pretrained_window_sizes": [
|
| 50 |
+
12,
|
| 51 |
+
12,
|
| 52 |
+
12,
|
| 53 |
+
6
|
| 54 |
+
],
|
| 55 |
+
"problem_type": "single_label_classification",
|
| 56 |
+
"qkv_bias": true,
|
| 57 |
+
"stage_names": [
|
| 58 |
+
"stem",
|
| 59 |
+
"stage1",
|
| 60 |
+
"stage2",
|
| 61 |
+
"stage3",
|
| 62 |
+
"stage4"
|
| 63 |
+
],
|
| 64 |
+
"torch_dtype": "float32",
|
| 65 |
+
"transformers_version": "4.48.0",
|
| 66 |
+
"use_absolute_embeddings": false,
|
| 67 |
+
"window_size": 16
|
| 68 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec72a1b7df34678177321e183298b0afdfd8125c44b167ba3439853799fe3edb
|
| 3 |
+
size 780886280
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df3a2dbd264a3963673fd99f34f401298ca33cef3a107863aa43f466e0407fd8
|
| 3 |
+
size 1562043374
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 256,
|
| 21 |
+
"width": 256
|
| 22 |
+
}
|
| 23 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e775cb4fe9730878db35426f0181978a5391b1fd249e364cc44ef183c09e74c
|
| 3 |
+
size 14645
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:849f9652e8ec6e696a81423a4ec0e973ddbaed18b6ef63e48bebf62a22220233
|
| 3 |
+
size 1465
|
trainer_state.json
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9989996083884333,
|
| 3 |
+
"best_model_checkpoint": "./swinv2-ai-vs-human/checkpoint-500",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2,
|
| 13 |
+
"grad_norm": 0.027848800644278526,
|
| 14 |
+
"learning_rate": 4.804e-05,
|
| 15 |
+
"loss": 0.0547,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.4,
|
| 20 |
+
"grad_norm": 0.19660699367523193,
|
| 21 |
+
"learning_rate": 4.604e-05,
|
| 22 |
+
"loss": 0.0147,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6,
|
| 27 |
+
"grad_norm": 0.003552996786311269,
|
| 28 |
+
"learning_rate": 4.4040000000000005e-05,
|
| 29 |
+
"loss": 0.0043,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8,
|
| 34 |
+
"grad_norm": 0.13383957743644714,
|
| 35 |
+
"learning_rate": 4.2040000000000004e-05,
|
| 36 |
+
"loss": 0.0061,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"grad_norm": 0.001965691801160574,
|
| 42 |
+
"learning_rate": 4.004e-05,
|
| 43 |
+
"loss": 0.0015,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.998,
|
| 49 |
+
"eval_f1": 0.998,
|
| 50 |
+
"eval_loss": 0.006758809555321932,
|
| 51 |
+
"eval_runtime": 42.7981,
|
| 52 |
+
"eval_samples_per_second": 23.366,
|
| 53 |
+
"eval_steps_per_second": 2.921,
|
| 54 |
+
"step": 250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.2,
|
| 58 |
+
"grad_norm": 0.0014331854181364179,
|
| 59 |
+
"learning_rate": 3.804e-05,
|
| 60 |
+
"loss": 0.0,
|
| 61 |
+
"step": 300
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.4,
|
| 65 |
+
"grad_norm": 0.0010366585338488221,
|
| 66 |
+
"learning_rate": 3.604e-05,
|
| 67 |
+
"loss": 0.0,
|
| 68 |
+
"step": 350
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.6,
|
| 72 |
+
"grad_norm": 0.0017909109592437744,
|
| 73 |
+
"learning_rate": 3.404e-05,
|
| 74 |
+
"loss": 0.0,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.8,
|
| 79 |
+
"grad_norm": 0.0012696795165538788,
|
| 80 |
+
"learning_rate": 3.2040000000000005e-05,
|
| 81 |
+
"loss": 0.0,
|
| 82 |
+
"step": 450
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.0,
|
| 86 |
+
"grad_norm": 0.12196046859025955,
|
| 87 |
+
"learning_rate": 3.004e-05,
|
| 88 |
+
"loss": 0.0,
|
| 89 |
+
"step": 500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.0,
|
| 93 |
+
"eval_accuracy": 0.999,
|
| 94 |
+
"eval_f1": 0.9989996083884333,
|
| 95 |
+
"eval_loss": 0.006264013703912497,
|
| 96 |
+
"eval_runtime": 42.8166,
|
| 97 |
+
"eval_samples_per_second": 23.355,
|
| 98 |
+
"eval_steps_per_second": 2.919,
|
| 99 |
+
"step": 500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.2,
|
| 103 |
+
"grad_norm": 0.0006243517273105681,
|
| 104 |
+
"learning_rate": 2.804e-05,
|
| 105 |
+
"loss": 0.0,
|
| 106 |
+
"step": 550
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.4,
|
| 110 |
+
"grad_norm": 0.0006688985740765929,
|
| 111 |
+
"learning_rate": 2.6040000000000005e-05,
|
| 112 |
+
"loss": 0.0,
|
| 113 |
+
"step": 600
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.6,
|
| 117 |
+
"grad_norm": 0.00047493071178905666,
|
| 118 |
+
"learning_rate": 2.404e-05,
|
| 119 |
+
"loss": 0.0,
|
| 120 |
+
"step": 650
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.8,
|
| 124 |
+
"grad_norm": 0.0006771540502086282,
|
| 125 |
+
"learning_rate": 2.2040000000000002e-05,
|
| 126 |
+
"loss": 0.0024,
|
| 127 |
+
"step": 700
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.0,
|
| 131 |
+
"grad_norm": 0.000500071793794632,
|
| 132 |
+
"learning_rate": 2.004e-05,
|
| 133 |
+
"loss": 0.0,
|
| 134 |
+
"step": 750
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.0,
|
| 138 |
+
"eval_accuracy": 0.998,
|
| 139 |
+
"eval_f1": 0.998,
|
| 140 |
+
"eval_loss": 0.005241448991000652,
|
| 141 |
+
"eval_runtime": 43.2836,
|
| 142 |
+
"eval_samples_per_second": 23.103,
|
| 143 |
+
"eval_steps_per_second": 2.888,
|
| 144 |
+
"step": 750
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.2,
|
| 148 |
+
"grad_norm": 0.000668955675791949,
|
| 149 |
+
"learning_rate": 1.804e-05,
|
| 150 |
+
"loss": 0.0,
|
| 151 |
+
"step": 800
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.4,
|
| 155 |
+
"grad_norm": 0.0005380553775466979,
|
| 156 |
+
"learning_rate": 1.604e-05,
|
| 157 |
+
"loss": 0.0,
|
| 158 |
+
"step": 850
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.6,
|
| 162 |
+
"grad_norm": 0.00043314267531968653,
|
| 163 |
+
"learning_rate": 1.4040000000000001e-05,
|
| 164 |
+
"loss": 0.0,
|
| 165 |
+
"step": 900
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.8,
|
| 169 |
+
"grad_norm": 0.000652027374599129,
|
| 170 |
+
"learning_rate": 1.204e-05,
|
| 171 |
+
"loss": 0.0,
|
| 172 |
+
"step": 950
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 4.0,
|
| 176 |
+
"grad_norm": 0.0004371394752524793,
|
| 177 |
+
"learning_rate": 1.004e-05,
|
| 178 |
+
"loss": 0.0,
|
| 179 |
+
"step": 1000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 4.0,
|
| 183 |
+
"eval_accuracy": 0.999,
|
| 184 |
+
"eval_f1": 0.9989996083884333,
|
| 185 |
+
"eval_loss": 0.004136711824685335,
|
| 186 |
+
"eval_runtime": 43.0268,
|
| 187 |
+
"eval_samples_per_second": 23.241,
|
| 188 |
+
"eval_steps_per_second": 2.905,
|
| 189 |
+
"step": 1000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.2,
|
| 193 |
+
"grad_norm": 0.000431750260759145,
|
| 194 |
+
"learning_rate": 8.040000000000001e-06,
|
| 195 |
+
"loss": 0.0,
|
| 196 |
+
"step": 1050
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 4.4,
|
| 200 |
+
"grad_norm": 0.0012624277733266354,
|
| 201 |
+
"learning_rate": 6.040000000000001e-06,
|
| 202 |
+
"loss": 0.0,
|
| 203 |
+
"step": 1100
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 4.6,
|
| 207 |
+
"grad_norm": 0.00036189553793519735,
|
| 208 |
+
"learning_rate": 4.04e-06,
|
| 209 |
+
"loss": 0.0,
|
| 210 |
+
"step": 1150
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 4.8,
|
| 214 |
+
"grad_norm": 0.00043084935168735683,
|
| 215 |
+
"learning_rate": 2.0400000000000004e-06,
|
| 216 |
+
"loss": 0.0,
|
| 217 |
+
"step": 1200
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 5.0,
|
| 221 |
+
"grad_norm": 0.0005352545995265245,
|
| 222 |
+
"learning_rate": 4e-08,
|
| 223 |
+
"loss": 0.0,
|
| 224 |
+
"step": 1250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 5.0,
|
| 228 |
+
"eval_accuracy": 0.999,
|
| 229 |
+
"eval_f1": 0.9989996083884333,
|
| 230 |
+
"eval_loss": 0.00451634032651782,
|
| 231 |
+
"eval_runtime": 43.0272,
|
| 232 |
+
"eval_samples_per_second": 23.241,
|
| 233 |
+
"eval_steps_per_second": 2.905,
|
| 234 |
+
"step": 1250
|
| 235 |
+
}
|
| 236 |
+
],
|
| 237 |
+
"logging_steps": 50,
|
| 238 |
+
"max_steps": 1250,
|
| 239 |
+
"num_input_tokens_seen": 0,
|
| 240 |
+
"num_train_epochs": 5,
|
| 241 |
+
"save_steps": 500,
|
| 242 |
+
"stateful_callbacks": {
|
| 243 |
+
"TrainerControl": {
|
| 244 |
+
"args": {
|
| 245 |
+
"should_epoch_stop": false,
|
| 246 |
+
"should_evaluate": false,
|
| 247 |
+
"should_log": false,
|
| 248 |
+
"should_save": true,
|
| 249 |
+
"should_training_stop": true
|
| 250 |
+
},
|
| 251 |
+
"attributes": {}
|
| 252 |
+
}
|
| 253 |
+
},
|
| 254 |
+
"total_flos": 9.209823610762691e+18,
|
| 255 |
+
"train_batch_size": 8,
|
| 256 |
+
"trial_name": null,
|
| 257 |
+
"trial_params": null
|
| 258 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47628360372bebad07c80b96d1d87660feee1d0587c3deab36ff7065baeb2870
|
| 3 |
+
size 5713
|