Training in progress, epoch 1
Browse files- .DS_Store +0 -0
- all_results.json +7 -0
- config.json +36 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +7 -0
- trainer_state.json +292 -0
- training_args.bin +3 -0
.DS_Store
ADDED
|
Binary file (10.2 kB). View file
|
|
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.7178522997889025,
|
| 4 |
+
"train_runtime": 2833.88,
|
| 5 |
+
"train_samples_per_second": 6.514,
|
| 6 |
+
"train_steps_per_second": 0.102
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "0.0",
|
| 13 |
+
"1": "1/3",
|
| 14 |
+
"2": "2/3",
|
| 15 |
+
"3": "1.0"
|
| 16 |
+
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"0.0": "0",
|
| 22 |
+
"1.0": "3",
|
| 23 |
+
"1/3": "1",
|
| 24 |
+
"2/3": "2"
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"model_type": "vit",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_channels": 3,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"patch_size": 16,
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"qkv_bias": true,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.35.0"
|
| 36 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94d22a7251fa08080292b70c8a84fe557851a94bf339e1855d36b0a9286bab4d
|
| 3 |
+
size 343230128
|
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 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.7178522997889025,
|
| 4 |
+
"train_runtime": 2833.88,
|
| 5 |
+
"train_samples_per_second": 6.514,
|
| 6 |
+
"train_steps_per_second": 0.102
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7518796992481203,
|
| 3 |
+
"best_model_checkpoint": "../results/elpv-vit/checkpoint-232",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 290,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.34,
|
| 13 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 14 |
+
"loss": 1.3357,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.69,
|
| 19 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 20 |
+
"loss": 1.1598,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"eval_accuracy": 0.6954887218045113,
|
| 26 |
+
"eval_loss": 0.9091870188713074,
|
| 27 |
+
"eval_runtime": 10.3022,
|
| 28 |
+
"eval_samples_per_second": 25.82,
|
| 29 |
+
"eval_steps_per_second": 1.65,
|
| 30 |
+
"step": 29
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.03,
|
| 34 |
+
"learning_rate": 4.980842911877395e-05,
|
| 35 |
+
"loss": 0.9746,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.38,
|
| 40 |
+
"learning_rate": 4.789272030651341e-05,
|
| 41 |
+
"loss": 0.8597,
|
| 42 |
+
"step": 40
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.72,
|
| 46 |
+
"learning_rate": 4.597701149425287e-05,
|
| 47 |
+
"loss": 0.8226,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.0,
|
| 52 |
+
"eval_accuracy": 0.7368421052631579,
|
| 53 |
+
"eval_loss": 0.7852613925933838,
|
| 54 |
+
"eval_runtime": 10.1106,
|
| 55 |
+
"eval_samples_per_second": 26.309,
|
| 56 |
+
"eval_steps_per_second": 1.681,
|
| 57 |
+
"step": 58
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.07,
|
| 61 |
+
"learning_rate": 4.406130268199234e-05,
|
| 62 |
+
"loss": 0.7585,
|
| 63 |
+
"step": 60
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.41,
|
| 67 |
+
"learning_rate": 4.21455938697318e-05,
|
| 68 |
+
"loss": 0.7611,
|
| 69 |
+
"step": 70
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.76,
|
| 73 |
+
"learning_rate": 4.0229885057471265e-05,
|
| 74 |
+
"loss": 0.6841,
|
| 75 |
+
"step": 80
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.0,
|
| 79 |
+
"eval_accuracy": 0.7180451127819549,
|
| 80 |
+
"eval_loss": 0.811350405216217,
|
| 81 |
+
"eval_runtime": 13.3447,
|
| 82 |
+
"eval_samples_per_second": 19.933,
|
| 83 |
+
"eval_steps_per_second": 1.274,
|
| 84 |
+
"step": 87
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.1,
|
| 88 |
+
"learning_rate": 3.831417624521073e-05,
|
| 89 |
+
"loss": 0.7207,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.45,
|
| 94 |
+
"learning_rate": 3.6398467432950195e-05,
|
| 95 |
+
"loss": 0.7422,
|
| 96 |
+
"step": 100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.79,
|
| 100 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 101 |
+
"loss": 0.73,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.0,
|
| 106 |
+
"eval_accuracy": 0.7293233082706767,
|
| 107 |
+
"eval_loss": 0.7547905445098877,
|
| 108 |
+
"eval_runtime": 11.7612,
|
| 109 |
+
"eval_samples_per_second": 22.617,
|
| 110 |
+
"eval_steps_per_second": 1.445,
|
| 111 |
+
"step": 116
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.14,
|
| 115 |
+
"learning_rate": 3.256704980842912e-05,
|
| 116 |
+
"loss": 0.6787,
|
| 117 |
+
"step": 120
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.48,
|
| 121 |
+
"learning_rate": 3.065134099616858e-05,
|
| 122 |
+
"loss": 0.6738,
|
| 123 |
+
"step": 130
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.83,
|
| 127 |
+
"learning_rate": 2.8735632183908045e-05,
|
| 128 |
+
"loss": 0.6725,
|
| 129 |
+
"step": 140
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.0,
|
| 133 |
+
"eval_accuracy": 0.7406015037593985,
|
| 134 |
+
"eval_loss": 0.75775146484375,
|
| 135 |
+
"eval_runtime": 12.9654,
|
| 136 |
+
"eval_samples_per_second": 20.516,
|
| 137 |
+
"eval_steps_per_second": 1.311,
|
| 138 |
+
"step": 145
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.17,
|
| 142 |
+
"learning_rate": 2.681992337164751e-05,
|
| 143 |
+
"loss": 0.6785,
|
| 144 |
+
"step": 150
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 5.52,
|
| 148 |
+
"learning_rate": 2.4904214559386975e-05,
|
| 149 |
+
"loss": 0.6259,
|
| 150 |
+
"step": 160
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 5.86,
|
| 154 |
+
"learning_rate": 2.2988505747126437e-05,
|
| 155 |
+
"loss": 0.6625,
|
| 156 |
+
"step": 170
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 6.0,
|
| 160 |
+
"eval_accuracy": 0.7368421052631579,
|
| 161 |
+
"eval_loss": 0.732495129108429,
|
| 162 |
+
"eval_runtime": 14.6428,
|
| 163 |
+
"eval_samples_per_second": 18.166,
|
| 164 |
+
"eval_steps_per_second": 1.161,
|
| 165 |
+
"step": 174
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.21,
|
| 169 |
+
"learning_rate": 2.10727969348659e-05,
|
| 170 |
+
"loss": 0.6335,
|
| 171 |
+
"step": 180
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.55,
|
| 175 |
+
"learning_rate": 1.9157088122605367e-05,
|
| 176 |
+
"loss": 0.6216,
|
| 177 |
+
"step": 190
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.9,
|
| 181 |
+
"learning_rate": 1.7241379310344828e-05,
|
| 182 |
+
"loss": 0.6214,
|
| 183 |
+
"step": 200
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 7.0,
|
| 187 |
+
"eval_accuracy": 0.7481203007518797,
|
| 188 |
+
"eval_loss": 0.6711514592170715,
|
| 189 |
+
"eval_runtime": 13.3792,
|
| 190 |
+
"eval_samples_per_second": 19.882,
|
| 191 |
+
"eval_steps_per_second": 1.271,
|
| 192 |
+
"step": 203
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 7.24,
|
| 196 |
+
"learning_rate": 1.532567049808429e-05,
|
| 197 |
+
"loss": 0.6385,
|
| 198 |
+
"step": 210
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 7.59,
|
| 202 |
+
"learning_rate": 1.3409961685823755e-05,
|
| 203 |
+
"loss": 0.6202,
|
| 204 |
+
"step": 220
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.93,
|
| 208 |
+
"learning_rate": 1.1494252873563218e-05,
|
| 209 |
+
"loss": 0.5911,
|
| 210 |
+
"step": 230
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 8.0,
|
| 214 |
+
"eval_accuracy": 0.7518796992481203,
|
| 215 |
+
"eval_loss": 0.6812042593955994,
|
| 216 |
+
"eval_runtime": 14.3277,
|
| 217 |
+
"eval_samples_per_second": 18.565,
|
| 218 |
+
"eval_steps_per_second": 1.187,
|
| 219 |
+
"step": 232
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.28,
|
| 223 |
+
"learning_rate": 9.578544061302683e-06,
|
| 224 |
+
"loss": 0.5925,
|
| 225 |
+
"step": 240
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.62,
|
| 229 |
+
"learning_rate": 7.662835249042145e-06,
|
| 230 |
+
"loss": 0.5711,
|
| 231 |
+
"step": 250
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 8.97,
|
| 235 |
+
"learning_rate": 5.747126436781609e-06,
|
| 236 |
+
"loss": 0.6169,
|
| 237 |
+
"step": 260
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.0,
|
| 241 |
+
"eval_accuracy": 0.7481203007518797,
|
| 242 |
+
"eval_loss": 0.7047642469406128,
|
| 243 |
+
"eval_runtime": 17.1552,
|
| 244 |
+
"eval_samples_per_second": 15.505,
|
| 245 |
+
"eval_steps_per_second": 0.991,
|
| 246 |
+
"step": 261
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 9.31,
|
| 250 |
+
"learning_rate": 3.8314176245210725e-06,
|
| 251 |
+
"loss": 0.6163,
|
| 252 |
+
"step": 270
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 9.66,
|
| 256 |
+
"learning_rate": 1.9157088122605362e-06,
|
| 257 |
+
"loss": 0.5672,
|
| 258 |
+
"step": 280
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 10.0,
|
| 262 |
+
"learning_rate": 0.0,
|
| 263 |
+
"loss": 0.5863,
|
| 264 |
+
"step": 290
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 10.0,
|
| 268 |
+
"eval_accuracy": 0.7406015037593985,
|
| 269 |
+
"eval_loss": 0.7278200387954712,
|
| 270 |
+
"eval_runtime": 12.3926,
|
| 271 |
+
"eval_samples_per_second": 21.464,
|
| 272 |
+
"eval_steps_per_second": 1.372,
|
| 273 |
+
"step": 290
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 10.0,
|
| 277 |
+
"step": 290,
|
| 278 |
+
"total_flos": 1.430527770561577e+18,
|
| 279 |
+
"train_loss": 0.7178522997889025,
|
| 280 |
+
"train_runtime": 2833.88,
|
| 281 |
+
"train_samples_per_second": 6.514,
|
| 282 |
+
"train_steps_per_second": 0.102
|
| 283 |
+
}
|
| 284 |
+
],
|
| 285 |
+
"logging_steps": 10,
|
| 286 |
+
"max_steps": 290,
|
| 287 |
+
"num_train_epochs": 10,
|
| 288 |
+
"save_steps": 500,
|
| 289 |
+
"total_flos": 1.430527770561577e+18,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:321bf62f0bb828ae9b9a88c70aa7a7f83bb62da583e16d3a70442dd7fa6e30ef
|
| 3 |
+
size 4536
|