Upload folder using huggingface_hub
Browse files- checkpoint-792/config.json +32 -0
- checkpoint-792/model.safetensors +3 -0
- checkpoint-792/optimizer.pt +3 -0
- checkpoint-792/preprocessor_config.json +36 -0
- checkpoint-792/rng_state.pth +3 -0
- checkpoint-792/scheduler.pt +3 -0
- checkpoint-792/trainer_state.json +424 -0
- checkpoint-792/training_args.bin +3 -0
- config.json +32 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- training_args.bin +3 -0
checkpoint-792/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/beard_face_image_detection",
|
| 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": "beard",
|
| 13 |
+
"1": "non-beard"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"beard": 0,
|
| 20 |
+
"non-beard": 1
|
| 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": "4.40.2"
|
| 32 |
+
}
|
checkpoint-792/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d3addfbee080e4529a2e0131e63c615a64fa81a5439ea3382dd15cb5fc175a
|
| 3 |
+
size 343223968
|
checkpoint-792/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50e8b186de264c2147d86ef6e394ac6d936930b57467f806013adb0508918085
|
| 3 |
+
size 686568890
|
checkpoint-792/preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
checkpoint-792/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c75af1b382231b2dd19955869478480896f06da6c2e047e6dcb29ebb6cd07ecc
|
| 3 |
+
size 14244
|
checkpoint-792/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a27df957ca9b4f686eed7c5564c8c7cff9e3b2a442e7413225303d1b1f932b20
|
| 3 |
+
size 1064
|
checkpoint-792/trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.13810816407203674,
|
| 3 |
+
"best_model_checkpoint": "beard detection/checkpoint-792",
|
| 4 |
+
"epoch": 44.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 792,
|
| 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": 0.821522309711286,
|
| 14 |
+
"eval_loss": 0.4623703360557556,
|
| 15 |
+
"eval_runtime": 15.5872,
|
| 16 |
+
"eval_samples_per_second": 48.886,
|
| 17 |
+
"eval_steps_per_second": 3.079,
|
| 18 |
+
"step": 18
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.8595800524934383,
|
| 23 |
+
"eval_loss": 0.3484641909599304,
|
| 24 |
+
"eval_runtime": 16.0868,
|
| 25 |
+
"eval_samples_per_second": 47.368,
|
| 26 |
+
"eval_steps_per_second": 2.984,
|
| 27 |
+
"step": 36
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.8989501312335958,
|
| 32 |
+
"eval_loss": 0.23234562575817108,
|
| 33 |
+
"eval_runtime": 15.6679,
|
| 34 |
+
"eval_samples_per_second": 48.635,
|
| 35 |
+
"eval_steps_per_second": 3.064,
|
| 36 |
+
"step": 54
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.9291338582677166,
|
| 41 |
+
"eval_loss": 0.19474641978740692,
|
| 42 |
+
"eval_runtime": 15.5907,
|
| 43 |
+
"eval_samples_per_second": 48.875,
|
| 44 |
+
"eval_steps_per_second": 3.079,
|
| 45 |
+
"step": 72
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.9330708661417323,
|
| 50 |
+
"eval_loss": 0.17998209595680237,
|
| 51 |
+
"eval_runtime": 15.6016,
|
| 52 |
+
"eval_samples_per_second": 48.841,
|
| 53 |
+
"eval_steps_per_second": 3.077,
|
| 54 |
+
"step": 90
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.937007874015748,
|
| 59 |
+
"eval_loss": 0.17380793392658234,
|
| 60 |
+
"eval_runtime": 15.5655,
|
| 61 |
+
"eval_samples_per_second": 48.954,
|
| 62 |
+
"eval_steps_per_second": 3.084,
|
| 63 |
+
"step": 108
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.9343832020997376,
|
| 68 |
+
"eval_loss": 0.1779448390007019,
|
| 69 |
+
"eval_runtime": 15.5371,
|
| 70 |
+
"eval_samples_per_second": 49.044,
|
| 71 |
+
"eval_steps_per_second": 3.089,
|
| 72 |
+
"step": 126
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 8.0,
|
| 76 |
+
"eval_accuracy": 0.9409448818897638,
|
| 77 |
+
"eval_loss": 0.17088069021701813,
|
| 78 |
+
"eval_runtime": 15.4793,
|
| 79 |
+
"eval_samples_per_second": 49.227,
|
| 80 |
+
"eval_steps_per_second": 3.101,
|
| 81 |
+
"step": 144
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 9.0,
|
| 85 |
+
"eval_accuracy": 0.9422572178477691,
|
| 86 |
+
"eval_loss": 0.16723193228244781,
|
| 87 |
+
"eval_runtime": 15.4321,
|
| 88 |
+
"eval_samples_per_second": 49.378,
|
| 89 |
+
"eval_steps_per_second": 3.11,
|
| 90 |
+
"step": 162
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 10.0,
|
| 94 |
+
"eval_accuracy": 0.9422572178477691,
|
| 95 |
+
"eval_loss": 0.16475225985050201,
|
| 96 |
+
"eval_runtime": 15.6535,
|
| 97 |
+
"eval_samples_per_second": 48.679,
|
| 98 |
+
"eval_steps_per_second": 3.066,
|
| 99 |
+
"step": 180
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 11.0,
|
| 103 |
+
"eval_accuracy": 0.9435695538057742,
|
| 104 |
+
"eval_loss": 0.1620875746011734,
|
| 105 |
+
"eval_runtime": 15.5668,
|
| 106 |
+
"eval_samples_per_second": 48.95,
|
| 107 |
+
"eval_steps_per_second": 3.083,
|
| 108 |
+
"step": 198
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 12.0,
|
| 112 |
+
"eval_accuracy": 0.9435695538057742,
|
| 113 |
+
"eval_loss": 0.16018643975257874,
|
| 114 |
+
"eval_runtime": 15.6106,
|
| 115 |
+
"eval_samples_per_second": 48.813,
|
| 116 |
+
"eval_steps_per_second": 3.075,
|
| 117 |
+
"step": 216
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 13.0,
|
| 121 |
+
"eval_accuracy": 0.9435695538057742,
|
| 122 |
+
"eval_loss": 0.160698801279068,
|
| 123 |
+
"eval_runtime": 15.3643,
|
| 124 |
+
"eval_samples_per_second": 49.596,
|
| 125 |
+
"eval_steps_per_second": 3.124,
|
| 126 |
+
"step": 234
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 14.0,
|
| 130 |
+
"eval_accuracy": 0.9435695538057742,
|
| 131 |
+
"eval_loss": 0.1587902307510376,
|
| 132 |
+
"eval_runtime": 15.4701,
|
| 133 |
+
"eval_samples_per_second": 49.256,
|
| 134 |
+
"eval_steps_per_second": 3.103,
|
| 135 |
+
"step": 252
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 15.0,
|
| 139 |
+
"eval_accuracy": 0.9435695538057742,
|
| 140 |
+
"eval_loss": 0.1586388796567917,
|
| 141 |
+
"eval_runtime": 15.979,
|
| 142 |
+
"eval_samples_per_second": 47.688,
|
| 143 |
+
"eval_steps_per_second": 3.004,
|
| 144 |
+
"step": 270
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 16.0,
|
| 148 |
+
"eval_accuracy": 0.9448818897637795,
|
| 149 |
+
"eval_loss": 0.15598240494728088,
|
| 150 |
+
"eval_runtime": 15.4614,
|
| 151 |
+
"eval_samples_per_second": 49.284,
|
| 152 |
+
"eval_steps_per_second": 3.105,
|
| 153 |
+
"step": 288
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 17.0,
|
| 157 |
+
"eval_accuracy": 0.9448818897637795,
|
| 158 |
+
"eval_loss": 0.15293540060520172,
|
| 159 |
+
"eval_runtime": 15.5549,
|
| 160 |
+
"eval_samples_per_second": 48.988,
|
| 161 |
+
"eval_steps_per_second": 3.086,
|
| 162 |
+
"step": 306
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 18.0,
|
| 166 |
+
"eval_accuracy": 0.9461942257217848,
|
| 167 |
+
"eval_loss": 0.1483953446149826,
|
| 168 |
+
"eval_runtime": 15.5258,
|
| 169 |
+
"eval_samples_per_second": 49.08,
|
| 170 |
+
"eval_steps_per_second": 3.092,
|
| 171 |
+
"step": 324
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 19.0,
|
| 175 |
+
"eval_accuracy": 0.9448818897637795,
|
| 176 |
+
"eval_loss": 0.14892004430294037,
|
| 177 |
+
"eval_runtime": 15.383,
|
| 178 |
+
"eval_samples_per_second": 49.535,
|
| 179 |
+
"eval_steps_per_second": 3.12,
|
| 180 |
+
"step": 342
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 20.0,
|
| 184 |
+
"eval_accuracy": 0.9448818897637795,
|
| 185 |
+
"eval_loss": 0.14962303638458252,
|
| 186 |
+
"eval_runtime": 15.5979,
|
| 187 |
+
"eval_samples_per_second": 48.853,
|
| 188 |
+
"eval_steps_per_second": 3.077,
|
| 189 |
+
"step": 360
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 21.0,
|
| 193 |
+
"eval_accuracy": 0.9448818897637795,
|
| 194 |
+
"eval_loss": 0.14834122359752655,
|
| 195 |
+
"eval_runtime": 15.2733,
|
| 196 |
+
"eval_samples_per_second": 49.891,
|
| 197 |
+
"eval_steps_per_second": 3.143,
|
| 198 |
+
"step": 378
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 22.0,
|
| 202 |
+
"eval_accuracy": 0.9488188976377953,
|
| 203 |
+
"eval_loss": 0.1453154981136322,
|
| 204 |
+
"eval_runtime": 15.5367,
|
| 205 |
+
"eval_samples_per_second": 49.045,
|
| 206 |
+
"eval_steps_per_second": 3.089,
|
| 207 |
+
"step": 396
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 23.0,
|
| 211 |
+
"eval_accuracy": 0.94750656167979,
|
| 212 |
+
"eval_loss": 0.14801156520843506,
|
| 213 |
+
"eval_runtime": 15.2319,
|
| 214 |
+
"eval_samples_per_second": 50.027,
|
| 215 |
+
"eval_steps_per_second": 3.151,
|
| 216 |
+
"step": 414
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 24.0,
|
| 220 |
+
"eval_accuracy": 0.9448818897637795,
|
| 221 |
+
"eval_loss": 0.14965900778770447,
|
| 222 |
+
"eval_runtime": 15.5253,
|
| 223 |
+
"eval_samples_per_second": 49.081,
|
| 224 |
+
"eval_steps_per_second": 3.092,
|
| 225 |
+
"step": 432
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 25.0,
|
| 229 |
+
"eval_accuracy": 0.9461942257217848,
|
| 230 |
+
"eval_loss": 0.14808818697929382,
|
| 231 |
+
"eval_runtime": 15.4954,
|
| 232 |
+
"eval_samples_per_second": 49.176,
|
| 233 |
+
"eval_steps_per_second": 3.098,
|
| 234 |
+
"step": 450
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 26.0,
|
| 238 |
+
"eval_accuracy": 0.9461942257217848,
|
| 239 |
+
"eval_loss": 0.14772780239582062,
|
| 240 |
+
"eval_runtime": 15.6303,
|
| 241 |
+
"eval_samples_per_second": 48.751,
|
| 242 |
+
"eval_steps_per_second": 3.071,
|
| 243 |
+
"step": 468
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 27.0,
|
| 247 |
+
"eval_accuracy": 0.9488188976377953,
|
| 248 |
+
"eval_loss": 0.14494165778160095,
|
| 249 |
+
"eval_runtime": 15.3557,
|
| 250 |
+
"eval_samples_per_second": 49.623,
|
| 251 |
+
"eval_steps_per_second": 3.126,
|
| 252 |
+
"step": 486
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 27.77777777777778,
|
| 256 |
+
"grad_norm": 1.454528570175171,
|
| 257 |
+
"learning_rate": 4.705882352941176e-07,
|
| 258 |
+
"loss": 0.2091,
|
| 259 |
+
"step": 500
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 28.0,
|
| 263 |
+
"eval_accuracy": 0.9461942257217848,
|
| 264 |
+
"eval_loss": 0.14676755666732788,
|
| 265 |
+
"eval_runtime": 15.271,
|
| 266 |
+
"eval_samples_per_second": 49.899,
|
| 267 |
+
"eval_steps_per_second": 3.143,
|
| 268 |
+
"step": 504
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 29.0,
|
| 272 |
+
"eval_accuracy": 0.9488188976377953,
|
| 273 |
+
"eval_loss": 0.14510495960712433,
|
| 274 |
+
"eval_runtime": 15.5258,
|
| 275 |
+
"eval_samples_per_second": 49.079,
|
| 276 |
+
"eval_steps_per_second": 3.092,
|
| 277 |
+
"step": 522
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 30.0,
|
| 281 |
+
"eval_accuracy": 0.9514435695538058,
|
| 282 |
+
"eval_loss": 0.14374305307865143,
|
| 283 |
+
"eval_runtime": 15.5529,
|
| 284 |
+
"eval_samples_per_second": 48.994,
|
| 285 |
+
"eval_steps_per_second": 3.086,
|
| 286 |
+
"step": 540
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 31.0,
|
| 290 |
+
"eval_accuracy": 0.9501312335958005,
|
| 291 |
+
"eval_loss": 0.14374108612537384,
|
| 292 |
+
"eval_runtime": 15.2492,
|
| 293 |
+
"eval_samples_per_second": 49.97,
|
| 294 |
+
"eval_steps_per_second": 3.148,
|
| 295 |
+
"step": 558
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 32.0,
|
| 299 |
+
"eval_accuracy": 0.9501312335958005,
|
| 300 |
+
"eval_loss": 0.14367464184761047,
|
| 301 |
+
"eval_runtime": 15.2728,
|
| 302 |
+
"eval_samples_per_second": 49.893,
|
| 303 |
+
"eval_steps_per_second": 3.143,
|
| 304 |
+
"step": 576
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 33.0,
|
| 308 |
+
"eval_accuracy": 0.9501312335958005,
|
| 309 |
+
"eval_loss": 0.14097823202610016,
|
| 310 |
+
"eval_runtime": 15.4432,
|
| 311 |
+
"eval_samples_per_second": 49.342,
|
| 312 |
+
"eval_steps_per_second": 3.108,
|
| 313 |
+
"step": 594
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 34.0,
|
| 317 |
+
"eval_accuracy": 0.9501312335958005,
|
| 318 |
+
"eval_loss": 0.14191950857639313,
|
| 319 |
+
"eval_runtime": 15.3388,
|
| 320 |
+
"eval_samples_per_second": 49.678,
|
| 321 |
+
"eval_steps_per_second": 3.129,
|
| 322 |
+
"step": 612
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 35.0,
|
| 326 |
+
"eval_accuracy": 0.9501312335958005,
|
| 327 |
+
"eval_loss": 0.1414215862751007,
|
| 328 |
+
"eval_runtime": 15.9739,
|
| 329 |
+
"eval_samples_per_second": 47.703,
|
| 330 |
+
"eval_steps_per_second": 3.005,
|
| 331 |
+
"step": 630
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 36.0,
|
| 335 |
+
"eval_accuracy": 0.9501312335958005,
|
| 336 |
+
"eval_loss": 0.14236187934875488,
|
| 337 |
+
"eval_runtime": 15.5397,
|
| 338 |
+
"eval_samples_per_second": 49.036,
|
| 339 |
+
"eval_steps_per_second": 3.089,
|
| 340 |
+
"step": 648
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 37.0,
|
| 344 |
+
"eval_accuracy": 0.9501312335958005,
|
| 345 |
+
"eval_loss": 0.14204008877277374,
|
| 346 |
+
"eval_runtime": 15.3972,
|
| 347 |
+
"eval_samples_per_second": 49.49,
|
| 348 |
+
"eval_steps_per_second": 3.117,
|
| 349 |
+
"step": 666
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 38.0,
|
| 353 |
+
"eval_accuracy": 0.9501312335958005,
|
| 354 |
+
"eval_loss": 0.1410112977027893,
|
| 355 |
+
"eval_runtime": 15.479,
|
| 356 |
+
"eval_samples_per_second": 49.228,
|
| 357 |
+
"eval_steps_per_second": 3.101,
|
| 358 |
+
"step": 684
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 39.0,
|
| 362 |
+
"eval_accuracy": 0.9501312335958005,
|
| 363 |
+
"eval_loss": 0.1409473717212677,
|
| 364 |
+
"eval_runtime": 15.3208,
|
| 365 |
+
"eval_samples_per_second": 49.736,
|
| 366 |
+
"eval_steps_per_second": 3.133,
|
| 367 |
+
"step": 702
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 40.0,
|
| 371 |
+
"eval_accuracy": 0.9514435695538058,
|
| 372 |
+
"eval_loss": 0.13949158787727356,
|
| 373 |
+
"eval_runtime": 15.5092,
|
| 374 |
+
"eval_samples_per_second": 49.132,
|
| 375 |
+
"eval_steps_per_second": 3.095,
|
| 376 |
+
"step": 720
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 41.0,
|
| 380 |
+
"eval_accuracy": 0.952755905511811,
|
| 381 |
+
"eval_loss": 0.13874106109142303,
|
| 382 |
+
"eval_runtime": 15.6493,
|
| 383 |
+
"eval_samples_per_second": 48.692,
|
| 384 |
+
"eval_steps_per_second": 3.067,
|
| 385 |
+
"step": 738
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 42.0,
|
| 389 |
+
"eval_accuracy": 0.952755905511811,
|
| 390 |
+
"eval_loss": 0.13839222490787506,
|
| 391 |
+
"eval_runtime": 15.5039,
|
| 392 |
+
"eval_samples_per_second": 49.149,
|
| 393 |
+
"eval_steps_per_second": 3.096,
|
| 394 |
+
"step": 756
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 43.0,
|
| 398 |
+
"eval_accuracy": 0.9514435695538058,
|
| 399 |
+
"eval_loss": 0.1389077603816986,
|
| 400 |
+
"eval_runtime": 15.5822,
|
| 401 |
+
"eval_samples_per_second": 48.902,
|
| 402 |
+
"eval_steps_per_second": 3.08,
|
| 403 |
+
"step": 774
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 44.0,
|
| 407 |
+
"eval_accuracy": 0.952755905511811,
|
| 408 |
+
"eval_loss": 0.13810816407203674,
|
| 409 |
+
"eval_runtime": 15.4669,
|
| 410 |
+
"eval_samples_per_second": 49.267,
|
| 411 |
+
"eval_steps_per_second": 3.103,
|
| 412 |
+
"step": 792
|
| 413 |
+
}
|
| 414 |
+
],
|
| 415 |
+
"logging_steps": 500,
|
| 416 |
+
"max_steps": 900,
|
| 417 |
+
"num_input_tokens_seen": 0,
|
| 418 |
+
"num_train_epochs": 50,
|
| 419 |
+
"save_steps": 500,
|
| 420 |
+
"total_flos": 3.893817494154019e+18,
|
| 421 |
+
"train_batch_size": 64,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|
checkpoint-792/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6282707cc3b540920843b4f019d25dff5a05140d241da1eb12f0643811f1003d
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/beard_face_image_detection",
|
| 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": "beard",
|
| 13 |
+
"1": "non-beard"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"beard": 0,
|
| 20 |
+
"non-beard": 1
|
| 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": "4.40.2"
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34d3addfbee080e4529a2e0131e63c615a64fa81a5439ea3382dd15cb5fc175a
|
| 3 |
+
size 343223968
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTImageProcessor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6282707cc3b540920843b4f019d25dff5a05140d241da1eb12f0643811f1003d
|
| 3 |
+
size 4920
|