Upload folder using huggingface_hub
Browse files- checkpoint-15190/config.json +46 -0
- checkpoint-15190/model.safetensors +3 -0
- checkpoint-15190/optimizer.pt +3 -0
- checkpoint-15190/preprocessor_config.json +23 -0
- checkpoint-15190/rng_state.pth +3 -0
- checkpoint-15190/scheduler.pt +3 -0
- checkpoint-15190/trainer_state.json +343 -0
- checkpoint-15190/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- training_args.bin +3 -0
checkpoint-15190/config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Down",
|
| 13 |
+
"1": "Left Swipe",
|
| 14 |
+
"2": "Right Swipe",
|
| 15 |
+
"3": "Stop",
|
| 16 |
+
"4": "Stop Gesture",
|
| 17 |
+
"5": "Swipe",
|
| 18 |
+
"6": "Thumbs Down",
|
| 19 |
+
"7": "Thumbs Up",
|
| 20 |
+
"8": "Up"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"Down": 0,
|
| 27 |
+
"Left Swipe": 1,
|
| 28 |
+
"Right Swipe": 2,
|
| 29 |
+
"Stop": 3,
|
| 30 |
+
"Stop Gesture": 4,
|
| 31 |
+
"Swipe": 5,
|
| 32 |
+
"Thumbs Down": 6,
|
| 33 |
+
"Thumbs Up": 7,
|
| 34 |
+
"Up": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.48.1"
|
| 46 |
+
}
|
checkpoint-15190/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79bb991cfdeabcaebb97dfb043d3bdc3aaf43549e81ce77f9b3516b1c47410ff
|
| 3 |
+
size 343245508
|
checkpoint-15190/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66585cc84314597e9f83c866cc3a45589d70485d4c14887c504cadf0152eb202
|
| 3 |
+
size 686611898
|
checkpoint-15190/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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-15190/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a303ba2ab58b508c69de3f998fdc7fd9d7e762ee82e6c757111acf74c5df157
|
| 3 |
+
size 14244
|
checkpoint-15190/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8f632990a80e8bdd73cf5af524bdc72f4527d9e44b0fc21b8981de9abbaed27
|
| 3 |
+
size 1064
|
checkpoint-15190/trainer_state.json
ADDED
|
@@ -0,0 +1,343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.15759548544883728,
|
| 3 |
+
"best_model_checkpoint": "smart_tv_hand_gestures_image_detection/checkpoint-15190",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 15190,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.32916392363396973,
|
| 13 |
+
"grad_norm": 1.4565895795822144,
|
| 14 |
+
"learning_rate": 9.702774108322324e-07,
|
| 15 |
+
"loss": 2.1185,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6583278472679395,
|
| 20 |
+
"grad_norm": 1.595917820930481,
|
| 21 |
+
"learning_rate": 9.372523117569352e-07,
|
| 22 |
+
"loss": 1.8436,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.9874917709019092,
|
| 27 |
+
"grad_norm": 2.2012250423431396,
|
| 28 |
+
"learning_rate": 9.04227212681638e-07,
|
| 29 |
+
"loss": 1.4844,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"eval_accuracy": 0.9256790123456791,
|
| 35 |
+
"eval_loss": 1.3686660528182983,
|
| 36 |
+
"eval_model_preparation_time": 0.0043,
|
| 37 |
+
"eval_runtime": 139.1921,
|
| 38 |
+
"eval_samples_per_second": 87.289,
|
| 39 |
+
"eval_steps_per_second": 10.913,
|
| 40 |
+
"step": 1519
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.316655694535879,
|
| 44 |
+
"grad_norm": 1.8626253604888916,
|
| 45 |
+
"learning_rate": 8.712021136063408e-07,
|
| 46 |
+
"loss": 1.1357,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.6458196181698486,
|
| 51 |
+
"grad_norm": 1.5412793159484863,
|
| 52 |
+
"learning_rate": 8.381770145310435e-07,
|
| 53 |
+
"loss": 0.8734,
|
| 54 |
+
"step": 2500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.9749835418038182,
|
| 58 |
+
"grad_norm": 1.9414352178573608,
|
| 59 |
+
"learning_rate": 8.051519154557464e-07,
|
| 60 |
+
"loss": 0.6898,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.0,
|
| 65 |
+
"eval_accuracy": 0.98559670781893,
|
| 66 |
+
"eval_loss": 0.6899833679199219,
|
| 67 |
+
"eval_model_preparation_time": 0.0043,
|
| 68 |
+
"eval_runtime": 140.1792,
|
| 69 |
+
"eval_samples_per_second": 86.675,
|
| 70 |
+
"eval_steps_per_second": 10.836,
|
| 71 |
+
"step": 3038
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.3041474654377883,
|
| 75 |
+
"grad_norm": 1.410414218902588,
|
| 76 |
+
"learning_rate": 7.72126816380449e-07,
|
| 77 |
+
"loss": 0.5598,
|
| 78 |
+
"step": 3500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.633311389071758,
|
| 82 |
+
"grad_norm": 1.2400822639465332,
|
| 83 |
+
"learning_rate": 7.391017173051519e-07,
|
| 84 |
+
"loss": 0.4651,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.9624753127057275,
|
| 89 |
+
"grad_norm": 0.9760797023773193,
|
| 90 |
+
"learning_rate": 7.060766182298547e-07,
|
| 91 |
+
"loss": 0.3972,
|
| 92 |
+
"step": 4500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.0,
|
| 96 |
+
"eval_accuracy": 0.9925925925925926,
|
| 97 |
+
"eval_loss": 0.42788437008857727,
|
| 98 |
+
"eval_model_preparation_time": 0.0043,
|
| 99 |
+
"eval_runtime": 138.4606,
|
| 100 |
+
"eval_samples_per_second": 87.751,
|
| 101 |
+
"eval_steps_per_second": 10.971,
|
| 102 |
+
"step": 4557
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 3.291639236339697,
|
| 106 |
+
"grad_norm": 0.7729864120483398,
|
| 107 |
+
"learning_rate": 6.730515191545574e-07,
|
| 108 |
+
"loss": 0.3433,
|
| 109 |
+
"step": 5000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.6208031599736668,
|
| 113 |
+
"grad_norm": 0.7019414305686951,
|
| 114 |
+
"learning_rate": 6.400264200792602e-07,
|
| 115 |
+
"loss": 0.3052,
|
| 116 |
+
"step": 5500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.9499670836076364,
|
| 120 |
+
"grad_norm": 0.6397891044616699,
|
| 121 |
+
"learning_rate": 6.070013210039629e-07,
|
| 122 |
+
"loss": 0.2739,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.0,
|
| 127 |
+
"eval_accuracy": 0.9956378600823045,
|
| 128 |
+
"eval_loss": 0.3098331689834595,
|
| 129 |
+
"eval_model_preparation_time": 0.0043,
|
| 130 |
+
"eval_runtime": 140.6468,
|
| 131 |
+
"eval_samples_per_second": 86.387,
|
| 132 |
+
"eval_steps_per_second": 10.8,
|
| 133 |
+
"step": 6076
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 4.279131007241606,
|
| 137 |
+
"grad_norm": 0.9204681515693665,
|
| 138 |
+
"learning_rate": 5.739762219286658e-07,
|
| 139 |
+
"loss": 0.2502,
|
| 140 |
+
"step": 6500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 4.6082949308755765,
|
| 144 |
+
"grad_norm": 0.8557950854301453,
|
| 145 |
+
"learning_rate": 5.409511228533686e-07,
|
| 146 |
+
"loss": 0.2293,
|
| 147 |
+
"step": 7000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.937458854509546,
|
| 151 |
+
"grad_norm": 0.5376387238502502,
|
| 152 |
+
"learning_rate": 5.079260237780713e-07,
|
| 153 |
+
"loss": 0.2135,
|
| 154 |
+
"step": 7500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.0,
|
| 158 |
+
"eval_accuracy": 0.9967901234567901,
|
| 159 |
+
"eval_loss": 0.2464514970779419,
|
| 160 |
+
"eval_model_preparation_time": 0.0043,
|
| 161 |
+
"eval_runtime": 143.0601,
|
| 162 |
+
"eval_samples_per_second": 84.929,
|
| 163 |
+
"eval_steps_per_second": 10.618,
|
| 164 |
+
"step": 7595
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.266622778143516,
|
| 168 |
+
"grad_norm": 2.1749770641326904,
|
| 169 |
+
"learning_rate": 4.749009247027741e-07,
|
| 170 |
+
"loss": 0.1991,
|
| 171 |
+
"step": 8000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.595786701777485,
|
| 175 |
+
"grad_norm": 0.4924432039260864,
|
| 176 |
+
"learning_rate": 4.418758256274769e-07,
|
| 177 |
+
"loss": 0.1887,
|
| 178 |
+
"step": 8500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 5.924950625411455,
|
| 182 |
+
"grad_norm": 0.44754961133003235,
|
| 183 |
+
"learning_rate": 4.088507265521796e-07,
|
| 184 |
+
"loss": 0.1787,
|
| 185 |
+
"step": 9000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 6.0,
|
| 189 |
+
"eval_accuracy": 0.9973662551440329,
|
| 190 |
+
"eval_loss": 0.20901748538017273,
|
| 191 |
+
"eval_model_preparation_time": 0.0043,
|
| 192 |
+
"eval_runtime": 143.6019,
|
| 193 |
+
"eval_samples_per_second": 84.609,
|
| 194 |
+
"eval_steps_per_second": 10.578,
|
| 195 |
+
"step": 9114
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.254114549045425,
|
| 199 |
+
"grad_norm": 1.0733314752578735,
|
| 200 |
+
"learning_rate": 3.758256274768824e-07,
|
| 201 |
+
"loss": 0.1706,
|
| 202 |
+
"step": 9500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 6.583278472679394,
|
| 206 |
+
"grad_norm": 0.45371586084365845,
|
| 207 |
+
"learning_rate": 3.428005284015852e-07,
|
| 208 |
+
"loss": 0.1637,
|
| 209 |
+
"step": 10000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 6.912442396313364,
|
| 213 |
+
"grad_norm": 0.3785471022129059,
|
| 214 |
+
"learning_rate": 3.09775429326288e-07,
|
| 215 |
+
"loss": 0.1571,
|
| 216 |
+
"step": 10500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 7.0,
|
| 220 |
+
"eval_accuracy": 0.9988477366255144,
|
| 221 |
+
"eval_loss": 0.1836911290884018,
|
| 222 |
+
"eval_model_preparation_time": 0.0043,
|
| 223 |
+
"eval_runtime": 141.3146,
|
| 224 |
+
"eval_samples_per_second": 85.978,
|
| 225 |
+
"eval_steps_per_second": 10.749,
|
| 226 |
+
"step": 10633
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.2416063199473335,
|
| 230 |
+
"grad_norm": 0.774605393409729,
|
| 231 |
+
"learning_rate": 2.7675033025099076e-07,
|
| 232 |
+
"loss": 0.1517,
|
| 233 |
+
"step": 11000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.570770243581303,
|
| 237 |
+
"grad_norm": 0.49195748567581177,
|
| 238 |
+
"learning_rate": 2.437252311756935e-07,
|
| 239 |
+
"loss": 0.1477,
|
| 240 |
+
"step": 11500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.899934167215273,
|
| 244 |
+
"grad_norm": 0.32700517773628235,
|
| 245 |
+
"learning_rate": 2.107001321003963e-07,
|
| 246 |
+
"loss": 0.1439,
|
| 247 |
+
"step": 12000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.0,
|
| 251 |
+
"eval_accuracy": 0.9981069958847737,
|
| 252 |
+
"eval_loss": 0.17038238048553467,
|
| 253 |
+
"eval_model_preparation_time": 0.0043,
|
| 254 |
+
"eval_runtime": 142.0518,
|
| 255 |
+
"eval_samples_per_second": 85.532,
|
| 256 |
+
"eval_steps_per_second": 10.693,
|
| 257 |
+
"step": 12152
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 8.229098090849243,
|
| 261 |
+
"grad_norm": 0.36188894510269165,
|
| 262 |
+
"learning_rate": 1.7767503302509906e-07,
|
| 263 |
+
"loss": 0.1402,
|
| 264 |
+
"step": 12500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 8.558262014483212,
|
| 268 |
+
"grad_norm": 0.38871052861213684,
|
| 269 |
+
"learning_rate": 1.4464993394980185e-07,
|
| 270 |
+
"loss": 0.1385,
|
| 271 |
+
"step": 13000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 8.887425938117183,
|
| 275 |
+
"grad_norm": 0.33406054973602295,
|
| 276 |
+
"learning_rate": 1.1162483487450462e-07,
|
| 277 |
+
"loss": 0.1359,
|
| 278 |
+
"step": 13500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.0,
|
| 282 |
+
"eval_accuracy": 0.9986008230452675,
|
| 283 |
+
"eval_loss": 0.16055729985237122,
|
| 284 |
+
"eval_model_preparation_time": 0.0043,
|
| 285 |
+
"eval_runtime": 143.3485,
|
| 286 |
+
"eval_samples_per_second": 84.758,
|
| 287 |
+
"eval_steps_per_second": 10.597,
|
| 288 |
+
"step": 13671
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 9.216589861751151,
|
| 292 |
+
"grad_norm": 0.32042938470840454,
|
| 293 |
+
"learning_rate": 7.85997357992074e-08,
|
| 294 |
+
"loss": 0.1341,
|
| 295 |
+
"step": 14000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 9.545753785385122,
|
| 299 |
+
"grad_norm": 0.29274484515190125,
|
| 300 |
+
"learning_rate": 4.557463672391017e-08,
|
| 301 |
+
"loss": 0.1333,
|
| 302 |
+
"step": 14500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 9.874917709019092,
|
| 306 |
+
"grad_norm": 0.3197895288467407,
|
| 307 |
+
"learning_rate": 1.2549537648612946e-08,
|
| 308 |
+
"loss": 0.1331,
|
| 309 |
+
"step": 15000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 10.0,
|
| 313 |
+
"eval_accuracy": 0.9990123456790123,
|
| 314 |
+
"eval_loss": 0.15759548544883728,
|
| 315 |
+
"eval_model_preparation_time": 0.0043,
|
| 316 |
+
"eval_runtime": 142.0855,
|
| 317 |
+
"eval_samples_per_second": 85.512,
|
| 318 |
+
"eval_steps_per_second": 10.691,
|
| 319 |
+
"step": 15190
|
| 320 |
+
}
|
| 321 |
+
],
|
| 322 |
+
"logging_steps": 500,
|
| 323 |
+
"max_steps": 15190,
|
| 324 |
+
"num_input_tokens_seen": 0,
|
| 325 |
+
"num_train_epochs": 10,
|
| 326 |
+
"save_steps": 500,
|
| 327 |
+
"stateful_callbacks": {
|
| 328 |
+
"TrainerControl": {
|
| 329 |
+
"args": {
|
| 330 |
+
"should_epoch_stop": false,
|
| 331 |
+
"should_evaluate": false,
|
| 332 |
+
"should_log": false,
|
| 333 |
+
"should_save": true,
|
| 334 |
+
"should_training_stop": true
|
| 335 |
+
},
|
| 336 |
+
"attributes": {}
|
| 337 |
+
}
|
| 338 |
+
},
|
| 339 |
+
"total_flos": 3.76634697648169e+19,
|
| 340 |
+
"train_batch_size": 32,
|
| 341 |
+
"trial_name": null,
|
| 342 |
+
"trial_params": null
|
| 343 |
+
}
|
checkpoint-15190/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e7dd678aabd9d0ea23f0200be2e7cc55ac5dee2fd8ecb3c063ce03e74171147
|
| 3 |
+
size 5304
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Down",
|
| 13 |
+
"1": "Left Swipe",
|
| 14 |
+
"2": "Right Swipe",
|
| 15 |
+
"3": "Stop",
|
| 16 |
+
"4": "Stop Gesture",
|
| 17 |
+
"5": "Swipe",
|
| 18 |
+
"6": "Thumbs Down",
|
| 19 |
+
"7": "Thumbs Up",
|
| 20 |
+
"8": "Up"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"Down": 0,
|
| 27 |
+
"Left Swipe": 1,
|
| 28 |
+
"Right Swipe": 2,
|
| 29 |
+
"Stop": 3,
|
| 30 |
+
"Stop Gesture": 4,
|
| 31 |
+
"Swipe": 5,
|
| 32 |
+
"Thumbs Down": 6,
|
| 33 |
+
"Thumbs Up": 7,
|
| 34 |
+
"Up": 8
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-12,
|
| 37 |
+
"model_type": "vit",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_channels": 3,
|
| 40 |
+
"num_hidden_layers": 12,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"qkv_bias": true,
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.48.1"
|
| 46 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79bb991cfdeabcaebb97dfb043d3bdc3aaf43549e81ce77f9b3516b1c47410ff
|
| 3 |
+
size 343245508
|
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 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e7dd678aabd9d0ea23f0200be2e7cc55ac5dee2fd8ecb3c063ce03e74171147
|
| 3 |
+
size 5304
|