Upload folder using huggingface_hub
Browse files- checkpoint-2340/config.json +32 -0
- checkpoint-2340/optimizer.pt +3 -0
- checkpoint-2340/preprocessor_config.json +22 -0
- checkpoint-2340/pytorch_model.bin +3 -0
- checkpoint-2340/rng_state.pth +3 -0
- checkpoint-2340/scheduler.pt +3 -0
- checkpoint-2340/trainer_state.json +394 -0
- checkpoint-2340/training_args.bin +3 -0
- config.json +32 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-2340/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "food",
|
| 13 |
+
"1": "beverage"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"beverage": 1,
|
| 20 |
+
"food": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.34.0"
|
| 32 |
+
}
|
checkpoint-2340/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a32eb39caf85afc1fa00fc69e5a2df8e27c5ff99b15948d1cd8701399d10992
|
| 3 |
+
size 686568453
|
checkpoint-2340/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-2340/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7690a6365b86e0a5a2c891df93896284e9a425fd219ccd1720c194bbd6a66e7d
|
| 3 |
+
size 343268717
|
checkpoint-2340/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd70d9239897b0884e8df145427e40ef0b84abc91467fbf35938bcf6b1568e7a
|
| 3 |
+
size 14575
|
checkpoint-2340/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48333eb7a27600e24022af26291022b410554f24c21a3dcc1f93c21030f8e64e
|
| 3 |
+
size 627
|
checkpoint-2340/trainer_state.json
ADDED
|
@@ -0,0 +1,394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4006434977054596,
|
| 3 |
+
"best_model_checkpoint": "food_beverages_japan_image_detection/checkpoint-2340",
|
| 4 |
+
"epoch": 39.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2340,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6215644820295984,
|
| 14 |
+
"eval_loss": 0.6740179657936096,
|
| 15 |
+
"eval_runtime": 8.3101,
|
| 16 |
+
"eval_samples_per_second": 56.919,
|
| 17 |
+
"eval_steps_per_second": 7.22,
|
| 18 |
+
"step": 60
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.7019027484143763,
|
| 23 |
+
"eval_loss": 0.6518784165382385,
|
| 24 |
+
"eval_runtime": 8.3128,
|
| 25 |
+
"eval_samples_per_second": 56.9,
|
| 26 |
+
"eval_steps_per_second": 7.218,
|
| 27 |
+
"step": 120
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.7315010570824524,
|
| 32 |
+
"eval_loss": 0.6313825249671936,
|
| 33 |
+
"eval_runtime": 8.4056,
|
| 34 |
+
"eval_samples_per_second": 56.272,
|
| 35 |
+
"eval_steps_per_second": 7.138,
|
| 36 |
+
"step": 180
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.7378435517970402,
|
| 41 |
+
"eval_loss": 0.6076480150222778,
|
| 42 |
+
"eval_runtime": 8.3695,
|
| 43 |
+
"eval_samples_per_second": 56.515,
|
| 44 |
+
"eval_steps_per_second": 7.169,
|
| 45 |
+
"step": 240
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.7505285412262156,
|
| 50 |
+
"eval_loss": 0.5873068571090698,
|
| 51 |
+
"eval_runtime": 8.3314,
|
| 52 |
+
"eval_samples_per_second": 56.773,
|
| 53 |
+
"eval_steps_per_second": 7.202,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.7758985200845666,
|
| 59 |
+
"eval_loss": 0.5679311752319336,
|
| 60 |
+
"eval_runtime": 8.239,
|
| 61 |
+
"eval_samples_per_second": 57.41,
|
| 62 |
+
"eval_steps_per_second": 7.282,
|
| 63 |
+
"step": 360
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7780126849894292,
|
| 68 |
+
"eval_loss": 0.5512701869010925,
|
| 69 |
+
"eval_runtime": 7.9131,
|
| 70 |
+
"eval_samples_per_second": 59.775,
|
| 71 |
+
"eval_steps_per_second": 7.582,
|
| 72 |
+
"step": 420
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.7801268498942917,
|
| 77 |
+
"eval_loss": 0.5363279581069946,
|
| 78 |
+
"eval_runtime": 7.9214,
|
| 79 |
+
"eval_samples_per_second": 59.712,
|
| 80 |
+
"eval_steps_per_second": 7.574,
|
| 81 |
+
"step": 480
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 8.33,
|
| 85 |
+
"learning_rate": 4.042553191489362e-06,
|
| 86 |
+
"loss": 0.5935,
|
| 87 |
+
"step": 500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 9.0,
|
| 91 |
+
"eval_accuracy": 0.7843551797040169,
|
| 92 |
+
"eval_loss": 0.5246909260749817,
|
| 93 |
+
"eval_runtime": 7.9484,
|
| 94 |
+
"eval_samples_per_second": 59.509,
|
| 95 |
+
"eval_steps_per_second": 7.549,
|
| 96 |
+
"step": 540
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 10.0,
|
| 100 |
+
"eval_accuracy": 0.7906976744186046,
|
| 101 |
+
"eval_loss": 0.5121592283248901,
|
| 102 |
+
"eval_runtime": 7.9961,
|
| 103 |
+
"eval_samples_per_second": 59.154,
|
| 104 |
+
"eval_steps_per_second": 7.504,
|
| 105 |
+
"step": 600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 11.0,
|
| 109 |
+
"eval_accuracy": 0.7991543340380549,
|
| 110 |
+
"eval_loss": 0.4976297616958618,
|
| 111 |
+
"eval_runtime": 7.9409,
|
| 112 |
+
"eval_samples_per_second": 59.565,
|
| 113 |
+
"eval_steps_per_second": 7.556,
|
| 114 |
+
"step": 660
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 12.0,
|
| 118 |
+
"eval_accuracy": 0.8054968287526427,
|
| 119 |
+
"eval_loss": 0.48714011907577515,
|
| 120 |
+
"eval_runtime": 7.9777,
|
| 121 |
+
"eval_samples_per_second": 59.29,
|
| 122 |
+
"eval_steps_per_second": 7.521,
|
| 123 |
+
"step": 720
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 13.0,
|
| 127 |
+
"eval_accuracy": 0.8033826638477801,
|
| 128 |
+
"eval_loss": 0.47856396436691284,
|
| 129 |
+
"eval_runtime": 8.0373,
|
| 130 |
+
"eval_samples_per_second": 58.85,
|
| 131 |
+
"eval_steps_per_second": 7.465,
|
| 132 |
+
"step": 780
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 14.0,
|
| 136 |
+
"eval_accuracy": 0.8054968287526427,
|
| 137 |
+
"eval_loss": 0.4685792028903961,
|
| 138 |
+
"eval_runtime": 8.0022,
|
| 139 |
+
"eval_samples_per_second": 59.109,
|
| 140 |
+
"eval_steps_per_second": 7.498,
|
| 141 |
+
"step": 840
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 15.0,
|
| 145 |
+
"eval_accuracy": 0.8076109936575053,
|
| 146 |
+
"eval_loss": 0.4633488357067108,
|
| 147 |
+
"eval_runtime": 7.897,
|
| 148 |
+
"eval_samples_per_second": 59.896,
|
| 149 |
+
"eval_steps_per_second": 7.598,
|
| 150 |
+
"step": 900
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 16.0,
|
| 154 |
+
"eval_accuracy": 0.8097251585623678,
|
| 155 |
+
"eval_loss": 0.4541207253932953,
|
| 156 |
+
"eval_runtime": 7.9062,
|
| 157 |
+
"eval_samples_per_second": 59.826,
|
| 158 |
+
"eval_steps_per_second": 7.589,
|
| 159 |
+
"step": 960
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 16.67,
|
| 163 |
+
"learning_rate": 2.978723404255319e-06,
|
| 164 |
+
"loss": 0.3919,
|
| 165 |
+
"step": 1000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 17.0,
|
| 169 |
+
"eval_accuracy": 0.8181818181818182,
|
| 170 |
+
"eval_loss": 0.44693174958229065,
|
| 171 |
+
"eval_runtime": 7.9465,
|
| 172 |
+
"eval_samples_per_second": 59.523,
|
| 173 |
+
"eval_steps_per_second": 7.551,
|
| 174 |
+
"step": 1020
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 18.0,
|
| 178 |
+
"eval_accuracy": 0.8202959830866807,
|
| 179 |
+
"eval_loss": 0.4403076171875,
|
| 180 |
+
"eval_runtime": 7.9729,
|
| 181 |
+
"eval_samples_per_second": 59.326,
|
| 182 |
+
"eval_steps_per_second": 7.526,
|
| 183 |
+
"step": 1080
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 19.0,
|
| 187 |
+
"eval_accuracy": 0.8181818181818182,
|
| 188 |
+
"eval_loss": 0.43559935688972473,
|
| 189 |
+
"eval_runtime": 7.8143,
|
| 190 |
+
"eval_samples_per_second": 60.53,
|
| 191 |
+
"eval_steps_per_second": 7.678,
|
| 192 |
+
"step": 1140
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 20.0,
|
| 196 |
+
"eval_accuracy": 0.8245243128964059,
|
| 197 |
+
"eval_loss": 0.43019139766693115,
|
| 198 |
+
"eval_runtime": 7.7993,
|
| 199 |
+
"eval_samples_per_second": 60.646,
|
| 200 |
+
"eval_steps_per_second": 7.693,
|
| 201 |
+
"step": 1200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 21.0,
|
| 205 |
+
"eval_accuracy": 0.8202959830866807,
|
| 206 |
+
"eval_loss": 0.42576563358306885,
|
| 207 |
+
"eval_runtime": 7.7862,
|
| 208 |
+
"eval_samples_per_second": 60.749,
|
| 209 |
+
"eval_steps_per_second": 7.706,
|
| 210 |
+
"step": 1260
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 22.0,
|
| 214 |
+
"eval_accuracy": 0.8245243128964059,
|
| 215 |
+
"eval_loss": 0.4226011633872986,
|
| 216 |
+
"eval_runtime": 7.8089,
|
| 217 |
+
"eval_samples_per_second": 60.572,
|
| 218 |
+
"eval_steps_per_second": 7.684,
|
| 219 |
+
"step": 1320
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 23.0,
|
| 223 |
+
"eval_accuracy": 0.8266384778012685,
|
| 224 |
+
"eval_loss": 0.4196974039077759,
|
| 225 |
+
"eval_runtime": 7.7453,
|
| 226 |
+
"eval_samples_per_second": 61.069,
|
| 227 |
+
"eval_steps_per_second": 7.747,
|
| 228 |
+
"step": 1380
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 24.0,
|
| 232 |
+
"eval_accuracy": 0.8308668076109936,
|
| 233 |
+
"eval_loss": 0.4153010845184326,
|
| 234 |
+
"eval_runtime": 7.7967,
|
| 235 |
+
"eval_samples_per_second": 60.667,
|
| 236 |
+
"eval_steps_per_second": 7.696,
|
| 237 |
+
"step": 1440
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 25.0,
|
| 241 |
+
"learning_rate": 1.9148936170212767e-06,
|
| 242 |
+
"loss": 0.2598,
|
| 243 |
+
"step": 1500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 25.0,
|
| 247 |
+
"eval_accuracy": 0.8245243128964059,
|
| 248 |
+
"eval_loss": 0.41346848011016846,
|
| 249 |
+
"eval_runtime": 8.0165,
|
| 250 |
+
"eval_samples_per_second": 59.003,
|
| 251 |
+
"eval_steps_per_second": 7.485,
|
| 252 |
+
"step": 1500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 26.0,
|
| 256 |
+
"eval_accuracy": 0.828752642706131,
|
| 257 |
+
"eval_loss": 0.41087058186531067,
|
| 258 |
+
"eval_runtime": 8.2057,
|
| 259 |
+
"eval_samples_per_second": 57.643,
|
| 260 |
+
"eval_steps_per_second": 7.312,
|
| 261 |
+
"step": 1560
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 27.0,
|
| 265 |
+
"eval_accuracy": 0.8350951374207188,
|
| 266 |
+
"eval_loss": 0.410675048828125,
|
| 267 |
+
"eval_runtime": 8.1905,
|
| 268 |
+
"eval_samples_per_second": 57.75,
|
| 269 |
+
"eval_steps_per_second": 7.326,
|
| 270 |
+
"step": 1620
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 28.0,
|
| 274 |
+
"eval_accuracy": 0.8372093023255814,
|
| 275 |
+
"eval_loss": 0.4087086319923401,
|
| 276 |
+
"eval_runtime": 8.1633,
|
| 277 |
+
"eval_samples_per_second": 57.942,
|
| 278 |
+
"eval_steps_per_second": 7.35,
|
| 279 |
+
"step": 1680
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 29.0,
|
| 283 |
+
"eval_accuracy": 0.8266384778012685,
|
| 284 |
+
"eval_loss": 0.41004815697669983,
|
| 285 |
+
"eval_runtime": 8.2033,
|
| 286 |
+
"eval_samples_per_second": 57.66,
|
| 287 |
+
"eval_steps_per_second": 7.314,
|
| 288 |
+
"step": 1740
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 30.0,
|
| 292 |
+
"eval_accuracy": 0.8372093023255814,
|
| 293 |
+
"eval_loss": 0.40502193570137024,
|
| 294 |
+
"eval_runtime": 8.171,
|
| 295 |
+
"eval_samples_per_second": 57.888,
|
| 296 |
+
"eval_steps_per_second": 7.343,
|
| 297 |
+
"step": 1800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 31.0,
|
| 301 |
+
"eval_accuracy": 0.828752642706131,
|
| 302 |
+
"eval_loss": 0.40703651309013367,
|
| 303 |
+
"eval_runtime": 8.1556,
|
| 304 |
+
"eval_samples_per_second": 57.997,
|
| 305 |
+
"eval_steps_per_second": 7.357,
|
| 306 |
+
"step": 1860
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 32.0,
|
| 310 |
+
"eval_accuracy": 0.8350951374207188,
|
| 311 |
+
"eval_loss": 0.40481287240982056,
|
| 312 |
+
"eval_runtime": 8.1436,
|
| 313 |
+
"eval_samples_per_second": 58.083,
|
| 314 |
+
"eval_steps_per_second": 7.368,
|
| 315 |
+
"step": 1920
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 33.0,
|
| 319 |
+
"eval_accuracy": 0.8329809725158562,
|
| 320 |
+
"eval_loss": 0.4047437608242035,
|
| 321 |
+
"eval_runtime": 8.1259,
|
| 322 |
+
"eval_samples_per_second": 58.209,
|
| 323 |
+
"eval_steps_per_second": 7.384,
|
| 324 |
+
"step": 1980
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 33.33,
|
| 328 |
+
"learning_rate": 8.510638297872341e-07,
|
| 329 |
+
"loss": 0.1847,
|
| 330 |
+
"step": 2000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 34.0,
|
| 334 |
+
"eval_accuracy": 0.8329809725158562,
|
| 335 |
+
"eval_loss": 0.4028582274913788,
|
| 336 |
+
"eval_runtime": 8.1842,
|
| 337 |
+
"eval_samples_per_second": 57.795,
|
| 338 |
+
"eval_steps_per_second": 7.331,
|
| 339 |
+
"step": 2040
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 35.0,
|
| 343 |
+
"eval_accuracy": 0.8329809725158562,
|
| 344 |
+
"eval_loss": 0.4015713930130005,
|
| 345 |
+
"eval_runtime": 8.1082,
|
| 346 |
+
"eval_samples_per_second": 58.336,
|
| 347 |
+
"eval_steps_per_second": 7.4,
|
| 348 |
+
"step": 2100
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 36.0,
|
| 352 |
+
"eval_accuracy": 0.8329809725158562,
|
| 353 |
+
"eval_loss": 0.4017912745475769,
|
| 354 |
+
"eval_runtime": 8.0144,
|
| 355 |
+
"eval_samples_per_second": 59.019,
|
| 356 |
+
"eval_steps_per_second": 7.487,
|
| 357 |
+
"step": 2160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 37.0,
|
| 361 |
+
"eval_accuracy": 0.8372093023255814,
|
| 362 |
+
"eval_loss": 0.401458203792572,
|
| 363 |
+
"eval_runtime": 7.7426,
|
| 364 |
+
"eval_samples_per_second": 61.091,
|
| 365 |
+
"eval_steps_per_second": 7.749,
|
| 366 |
+
"step": 2220
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 38.0,
|
| 370 |
+
"eval_accuracy": 0.8372093023255814,
|
| 371 |
+
"eval_loss": 0.40120792388916016,
|
| 372 |
+
"eval_runtime": 7.812,
|
| 373 |
+
"eval_samples_per_second": 60.548,
|
| 374 |
+
"eval_steps_per_second": 7.68,
|
| 375 |
+
"step": 2280
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 39.0,
|
| 379 |
+
"eval_accuracy": 0.8372093023255814,
|
| 380 |
+
"eval_loss": 0.4006434977054596,
|
| 381 |
+
"eval_runtime": 7.8268,
|
| 382 |
+
"eval_samples_per_second": 60.433,
|
| 383 |
+
"eval_steps_per_second": 7.666,
|
| 384 |
+
"step": 2340
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 500,
|
| 388 |
+
"max_steps": 2400,
|
| 389 |
+
"num_train_epochs": 40,
|
| 390 |
+
"save_steps": 500,
|
| 391 |
+
"total_flos": 5.714956742086545e+18,
|
| 392 |
+
"trial_name": null,
|
| 393 |
+
"trial_params": null
|
| 394 |
+
}
|
checkpoint-2340/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1769f67a92685cc0062cf921bb60504a412ec13b229e5dc6b9f14b8af157d8c0
|
| 3 |
+
size 4027
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "food",
|
| 13 |
+
"1": "beverage"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"beverage": 1,
|
| 20 |
+
"food": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.34.0"
|
| 32 |
+
}
|
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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7690a6365b86e0a5a2c891df93896284e9a425fd219ccd1720c194bbd6a66e7d
|
| 3 |
+
size 343268717
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1769f67a92685cc0062cf921bb60504a412ec13b229e5dc6b9f14b8af157d8c0
|
| 3 |
+
size 4027
|