Upload folder using huggingface_hub
Browse files- checkpoint-11556/config.json +40 -0
- checkpoint-11556/optimizer.pt +3 -0
- checkpoint-11556/preprocessor_config.json +22 -0
- checkpoint-11556/pytorch_model.bin +3 -0
- checkpoint-11556/rng_state.pth +3 -0
- checkpoint-11556/scheduler.pt +3 -0
- checkpoint-11556/trainer_state.json +238 -0
- checkpoint-11556/training_args.bin +3 -0
- config.json +12 -12
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
checkpoint-11556/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "sunglasses",
|
| 13 |
+
"1": "glasses",
|
| 14 |
+
"2": "other",
|
| 15 |
+
"3": "mask",
|
| 16 |
+
"4": "hand",
|
| 17 |
+
"5": "none"
|
| 18 |
+
},
|
| 19 |
+
"image_size": 224,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"glasses": 1,
|
| 24 |
+
"hand": 4,
|
| 25 |
+
"mask": 3,
|
| 26 |
+
"none": 5,
|
| 27 |
+
"other": 2,
|
| 28 |
+
"sunglasses": 0
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"model_type": "vit",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"patch_size": 16,
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"qkv_bias": true,
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.34.0"
|
| 40 |
+
}
|
checkpoint-11556/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13ba6a359ce6dc8e4460841d9cec765ba2b1a92475ee104b869ad6a5a0673c50
|
| 3 |
+
size 686593029
|
checkpoint-11556/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-11556/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:343af7f156ae8317a6e6e97a9c97afc077aa433e5f680e3aba1bb7eef43b5640
|
| 3 |
+
size 343281005
|
checkpoint-11556/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22d6710d23f5580093e38d4586d591818bf92e48b1bb9ce6cc5212b5c9520e7a
|
| 3 |
+
size 14575
|
checkpoint-11556/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd2c88d7cb7df270d0f4b681942c391dd75db74e7fa5df68351d34ba77fd6660
|
| 3 |
+
size 627
|
checkpoint-11556/trainer_state.json
ADDED
|
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.18186990916728973,
|
| 3 |
+
"best_model_checkpoint": "face_obstruction_image_detection/checkpoint-11556",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 11556,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.39,
|
| 13 |
+
"learning_rate": 9.648162627052385e-06,
|
| 14 |
+
"loss": 0.8123,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.78,
|
| 19 |
+
"learning_rate": 9.257232212666147e-06,
|
| 20 |
+
"loss": 0.3519,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"eval_accuracy": 0.8846678355737385,
|
| 26 |
+
"eval_loss": 0.2906096577644348,
|
| 27 |
+
"eval_runtime": 140.8808,
|
| 28 |
+
"eval_samples_per_second": 72.87,
|
| 29 |
+
"eval_steps_per_second": 9.114,
|
| 30 |
+
"step": 1284
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.17,
|
| 34 |
+
"learning_rate": 8.866301798279907e-06,
|
| 35 |
+
"loss": 0.2891,
|
| 36 |
+
"step": 1500
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.56,
|
| 40 |
+
"learning_rate": 8.475371383893667e-06,
|
| 41 |
+
"loss": 0.2514,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.95,
|
| 46 |
+
"learning_rate": 8.08444096950743e-06,
|
| 47 |
+
"loss": 0.2335,
|
| 48 |
+
"step": 2500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.0,
|
| 52 |
+
"eval_accuracy": 0.8915838690824079,
|
| 53 |
+
"eval_loss": 0.2299681454896927,
|
| 54 |
+
"eval_runtime": 140.059,
|
| 55 |
+
"eval_samples_per_second": 73.298,
|
| 56 |
+
"eval_steps_per_second": 9.168,
|
| 57 |
+
"step": 2568
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.34,
|
| 61 |
+
"learning_rate": 7.693510555121188e-06,
|
| 62 |
+
"loss": 0.2103,
|
| 63 |
+
"step": 3000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.73,
|
| 67 |
+
"learning_rate": 7.30258014073495e-06,
|
| 68 |
+
"loss": 0.2044,
|
| 69 |
+
"step": 3500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.0,
|
| 73 |
+
"eval_accuracy": 0.891291642314436,
|
| 74 |
+
"eval_loss": 0.2096417248249054,
|
| 75 |
+
"eval_runtime": 141.1058,
|
| 76 |
+
"eval_samples_per_second": 72.754,
|
| 77 |
+
"eval_steps_per_second": 9.1,
|
| 78 |
+
"step": 3852
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.12,
|
| 82 |
+
"learning_rate": 6.91164972634871e-06,
|
| 83 |
+
"loss": 0.1924,
|
| 84 |
+
"step": 4000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.5,
|
| 88 |
+
"learning_rate": 6.520719311962471e-06,
|
| 89 |
+
"loss": 0.1837,
|
| 90 |
+
"step": 4500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.89,
|
| 94 |
+
"learning_rate": 6.129788897576232e-06,
|
| 95 |
+
"loss": 0.1807,
|
| 96 |
+
"step": 5000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 4.0,
|
| 100 |
+
"eval_accuracy": 0.8915838690824079,
|
| 101 |
+
"eval_loss": 0.19587308168411255,
|
| 102 |
+
"eval_runtime": 137.5403,
|
| 103 |
+
"eval_samples_per_second": 74.64,
|
| 104 |
+
"eval_steps_per_second": 9.335,
|
| 105 |
+
"step": 5136
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.28,
|
| 109 |
+
"learning_rate": 5.7388584831899925e-06,
|
| 110 |
+
"loss": 0.1679,
|
| 111 |
+
"step": 5500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.67,
|
| 115 |
+
"learning_rate": 5.347928068803754e-06,
|
| 116 |
+
"loss": 0.1686,
|
| 117 |
+
"step": 6000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.0,
|
| 121 |
+
"eval_accuracy": 0.8925579583089811,
|
| 122 |
+
"eval_loss": 0.18770596385002136,
|
| 123 |
+
"eval_runtime": 139.4839,
|
| 124 |
+
"eval_samples_per_second": 73.6,
|
| 125 |
+
"eval_steps_per_second": 9.205,
|
| 126 |
+
"step": 6420
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.06,
|
| 130 |
+
"learning_rate": 4.956997654417514e-06,
|
| 131 |
+
"loss": 0.1696,
|
| 132 |
+
"step": 6500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 5.45,
|
| 136 |
+
"learning_rate": 4.566067240031275e-06,
|
| 137 |
+
"loss": 0.165,
|
| 138 |
+
"step": 7000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.84,
|
| 142 |
+
"learning_rate": 4.175136825645035e-06,
|
| 143 |
+
"loss": 0.1566,
|
| 144 |
+
"step": 7500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 6.0,
|
| 148 |
+
"eval_accuracy": 0.8901227352425483,
|
| 149 |
+
"eval_loss": 0.1865508109331131,
|
| 150 |
+
"eval_runtime": 140.3224,
|
| 151 |
+
"eval_samples_per_second": 73.16,
|
| 152 |
+
"eval_steps_per_second": 9.15,
|
| 153 |
+
"step": 7704
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 6.23,
|
| 157 |
+
"learning_rate": 3.7842064112587963e-06,
|
| 158 |
+
"loss": 0.1586,
|
| 159 |
+
"step": 8000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.62,
|
| 163 |
+
"learning_rate": 3.393275996872557e-06,
|
| 164 |
+
"loss": 0.1556,
|
| 165 |
+
"step": 8500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 7.0,
|
| 169 |
+
"eval_accuracy": 0.8917786869277226,
|
| 170 |
+
"eval_loss": 0.18248248100280762,
|
| 171 |
+
"eval_runtime": 141.8634,
|
| 172 |
+
"eval_samples_per_second": 72.365,
|
| 173 |
+
"eval_steps_per_second": 9.051,
|
| 174 |
+
"step": 8988
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 7.01,
|
| 178 |
+
"learning_rate": 3.002345582486318e-06,
|
| 179 |
+
"loss": 0.1591,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 7.4,
|
| 184 |
+
"learning_rate": 2.6114151681000783e-06,
|
| 185 |
+
"loss": 0.1544,
|
| 186 |
+
"step": 9500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 7.79,
|
| 190 |
+
"learning_rate": 2.220484753713839e-06,
|
| 191 |
+
"loss": 0.1491,
|
| 192 |
+
"step": 10000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 8.0,
|
| 196 |
+
"eval_accuracy": 0.893142411844925,
|
| 197 |
+
"eval_loss": 0.18403713405132294,
|
| 198 |
+
"eval_runtime": 143.6244,
|
| 199 |
+
"eval_samples_per_second": 71.478,
|
| 200 |
+
"eval_steps_per_second": 8.94,
|
| 201 |
+
"step": 10272
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 8.18,
|
| 205 |
+
"learning_rate": 1.8295543393276e-06,
|
| 206 |
+
"loss": 0.1522,
|
| 207 |
+
"step": 10500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 8.57,
|
| 211 |
+
"learning_rate": 1.4386239249413605e-06,
|
| 212 |
+
"loss": 0.1468,
|
| 213 |
+
"step": 11000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 8.96,
|
| 217 |
+
"learning_rate": 1.0476935105551214e-06,
|
| 218 |
+
"loss": 0.1477,
|
| 219 |
+
"step": 11500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 9.0,
|
| 223 |
+
"eval_accuracy": 0.8919735047730372,
|
| 224 |
+
"eval_loss": 0.18186990916728973,
|
| 225 |
+
"eval_runtime": 143.3138,
|
| 226 |
+
"eval_samples_per_second": 71.633,
|
| 227 |
+
"eval_steps_per_second": 8.959,
|
| 228 |
+
"step": 11556
|
| 229 |
+
}
|
| 230 |
+
],
|
| 231 |
+
"logging_steps": 500,
|
| 232 |
+
"max_steps": 12840,
|
| 233 |
+
"num_train_epochs": 10,
|
| 234 |
+
"save_steps": 500,
|
| 235 |
+
"total_flos": 2.864020628943323e+19,
|
| 236 |
+
"trial_name": null,
|
| 237 |
+
"trial_params": null
|
| 238 |
+
}
|
checkpoint-11556/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:441186ba0ec47e142146060acbd4fe34c142670d259df2594c861e230e6ac5c7
|
| 3 |
+
size 4027
|
config.json
CHANGED
|
@@ -9,23 +9,23 @@
|
|
| 9 |
"hidden_dropout_prob": 0.0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
},
|
| 19 |
"image_size": 224,
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"label2id": {
|
| 23 |
-
"glasses":
|
| 24 |
-
"hand":
|
| 25 |
-
"mask":
|
| 26 |
-
"none":
|
| 27 |
-
"other":
|
| 28 |
-
"sunglasses":
|
| 29 |
},
|
| 30 |
"layer_norm_eps": 1e-12,
|
| 31 |
"model_type": "vit",
|
|
|
|
| 9 |
"hidden_dropout_prob": 0.0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
+
"0": "sunglasses",
|
| 13 |
+
"1": "glasses",
|
| 14 |
+
"2": "other",
|
| 15 |
+
"3": "mask",
|
| 16 |
+
"4": "hand",
|
| 17 |
+
"5": "none"
|
| 18 |
},
|
| 19 |
"image_size": 224,
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 3072,
|
| 22 |
"label2id": {
|
| 23 |
+
"glasses": 1,
|
| 24 |
+
"hand": 4,
|
| 25 |
+
"mask": 3,
|
| 26 |
+
"none": 5,
|
| 27 |
+
"other": 2,
|
| 28 |
+
"sunglasses": 0
|
| 29 |
},
|
| 30 |
"layer_norm_eps": 1e-12,
|
| 31 |
"model_type": "vit",
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343281005
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:343af7f156ae8317a6e6e97a9c97afc077aa433e5f680e3aba1bb7eef43b5640
|
| 3 |
size 343281005
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:441186ba0ec47e142146060acbd4fe34c142670d259df2594c861e230e6ac5c7
|
| 3 |
size 4027
|