Upload folder using huggingface_hub
Browse files- README.md +32 -0
- checkpoint-44/config.json +33 -0
- checkpoint-44/model.safetensors +3 -0
- checkpoint-44/optimizer.pt +3 -0
- checkpoint-44/rng_state.pth +3 -0
- checkpoint-44/scheduler.pt +3 -0
- checkpoint-44/trainer_state.json +428 -0
- checkpoint-44/training_args.bin +3 -0
- config.json +33 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
- training_params.json +29 -0
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
widget:
|
| 7 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 8 |
+
example_title: Tiger
|
| 9 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
| 10 |
+
example_title: Teapot
|
| 11 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
| 12 |
+
example_title: Palace
|
| 13 |
+
datasets:
|
| 14 |
+
- mulder-scully-2024/autotrain-data
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.01787894032895565
|
| 23 |
+
|
| 24 |
+
f1: 1.0
|
| 25 |
+
|
| 26 |
+
precision: 1.0
|
| 27 |
+
|
| 28 |
+
recall: 1.0
|
| 29 |
+
|
| 30 |
+
auc: 1.0
|
| 31 |
+
|
| 32 |
+
accuracy: 1.0
|
checkpoint-44/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ViTForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"encoder_stride": 16,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "mulder",
|
| 14 |
+
"1": "scully"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"mulder": 0,
|
| 21 |
+
"scully": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"model_type": "vit",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qkv_bias": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.37.0"
|
| 33 |
+
}
|
checkpoint-44/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e84cd6f36a4c58aafc4fd643b2225ad9c2c130d14aaf439b86fa32fff5acd7f7
|
| 3 |
+
size 343223968
|
checkpoint-44/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a4474112a0320de45a9b5f99e4917409acc144d23e1a4a00e7c3c6106e94875
|
| 3 |
+
size 686568890
|
checkpoint-44/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58576c8ecb1f1e79d50113fc193489511010be3af71973d1497b9bf0b8d52cca
|
| 3 |
+
size 14244
|
checkpoint-44/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e31bfe17e7918e51029e48151765eb552f7ac7597e7ed4f96457cd2bcef40871
|
| 3 |
+
size 1064
|
checkpoint-44/trainer_state.json
ADDED
|
@@ -0,0 +1,428 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.01787894032895565,
|
| 3 |
+
"best_model_checkpoint": "mulder-scully-2024/checkpoint-44",
|
| 4 |
+
"epoch": 11.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 44,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"learning_rate": 6.25e-06,
|
| 14 |
+
"loss": 0.7706,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.5,
|
| 19 |
+
"learning_rate": 1.25e-05,
|
| 20 |
+
"loss": 0.6318,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.75,
|
| 25 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 26 |
+
"loss": 0.892,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"learning_rate": 2.5e-05,
|
| 32 |
+
"loss": 0.36,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.0,
|
| 37 |
+
"eval_accuracy": 0.42857142857142855,
|
| 38 |
+
"eval_auc": 0.8333333333333334,
|
| 39 |
+
"eval_f1": 0.3333333333333333,
|
| 40 |
+
"eval_loss": 0.7393712401390076,
|
| 41 |
+
"eval_precision": 0.5,
|
| 42 |
+
"eval_recall": 0.25,
|
| 43 |
+
"eval_runtime": 0.2422,
|
| 44 |
+
"eval_samples_per_second": 28.896,
|
| 45 |
+
"eval_steps_per_second": 4.128,
|
| 46 |
+
"step": 4
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.25,
|
| 50 |
+
"learning_rate": 3.125e-05,
|
| 51 |
+
"loss": 0.7442,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.5,
|
| 56 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 57 |
+
"loss": 0.6257,
|
| 58 |
+
"step": 6
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.75,
|
| 62 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 63 |
+
"loss": 0.6755,
|
| 64 |
+
"step": 7
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.0,
|
| 68 |
+
"learning_rate": 4.375e-05,
|
| 69 |
+
"loss": 0.5589,
|
| 70 |
+
"step": 8
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.0,
|
| 74 |
+
"eval_accuracy": 0.7142857142857143,
|
| 75 |
+
"eval_auc": 1.0,
|
| 76 |
+
"eval_f1": 0.75,
|
| 77 |
+
"eval_loss": 0.5653250813484192,
|
| 78 |
+
"eval_precision": 0.75,
|
| 79 |
+
"eval_recall": 0.75,
|
| 80 |
+
"eval_runtime": 0.2778,
|
| 81 |
+
"eval_samples_per_second": 25.2,
|
| 82 |
+
"eval_steps_per_second": 3.6,
|
| 83 |
+
"step": 8
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.25,
|
| 87 |
+
"learning_rate": 5e-05,
|
| 88 |
+
"loss": 0.5628,
|
| 89 |
+
"step": 9
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.5,
|
| 93 |
+
"learning_rate": 4.930555555555556e-05,
|
| 94 |
+
"loss": 0.3517,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.75,
|
| 99 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 100 |
+
"loss": 0.5619,
|
| 101 |
+
"step": 11
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.0,
|
| 105 |
+
"learning_rate": 4.791666666666667e-05,
|
| 106 |
+
"loss": 0.1437,
|
| 107 |
+
"step": 12
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.0,
|
| 111 |
+
"eval_accuracy": 0.8571428571428571,
|
| 112 |
+
"eval_auc": 1.0,
|
| 113 |
+
"eval_f1": 0.888888888888889,
|
| 114 |
+
"eval_loss": 0.385323703289032,
|
| 115 |
+
"eval_precision": 0.8,
|
| 116 |
+
"eval_recall": 1.0,
|
| 117 |
+
"eval_runtime": 0.234,
|
| 118 |
+
"eval_samples_per_second": 29.911,
|
| 119 |
+
"eval_steps_per_second": 4.273,
|
| 120 |
+
"step": 12
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.25,
|
| 124 |
+
"learning_rate": 4.722222222222222e-05,
|
| 125 |
+
"loss": 0.5414,
|
| 126 |
+
"step": 13
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.5,
|
| 130 |
+
"learning_rate": 4.652777777777778e-05,
|
| 131 |
+
"loss": 0.2829,
|
| 132 |
+
"step": 14
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.75,
|
| 136 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 137 |
+
"loss": 0.3696,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.0,
|
| 142 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 143 |
+
"loss": 0.3601,
|
| 144 |
+
"step": 16
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.0,
|
| 148 |
+
"eval_accuracy": 1.0,
|
| 149 |
+
"eval_auc": 1.0,
|
| 150 |
+
"eval_f1": 1.0,
|
| 151 |
+
"eval_loss": 0.2203500121831894,
|
| 152 |
+
"eval_precision": 1.0,
|
| 153 |
+
"eval_recall": 1.0,
|
| 154 |
+
"eval_runtime": 0.2467,
|
| 155 |
+
"eval_samples_per_second": 28.369,
|
| 156 |
+
"eval_steps_per_second": 4.053,
|
| 157 |
+
"step": 16
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 4.25,
|
| 161 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 162 |
+
"loss": 0.1114,
|
| 163 |
+
"step": 17
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.5,
|
| 167 |
+
"learning_rate": 4.375e-05,
|
| 168 |
+
"loss": 0.4256,
|
| 169 |
+
"step": 18
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.75,
|
| 173 |
+
"learning_rate": 4.305555555555556e-05,
|
| 174 |
+
"loss": 0.2173,
|
| 175 |
+
"step": 19
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.0,
|
| 179 |
+
"learning_rate": 4.236111111111111e-05,
|
| 180 |
+
"loss": 0.2773,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.0,
|
| 185 |
+
"eval_accuracy": 1.0,
|
| 186 |
+
"eval_auc": 1.0,
|
| 187 |
+
"eval_f1": 1.0,
|
| 188 |
+
"eval_loss": 0.117597296833992,
|
| 189 |
+
"eval_precision": 1.0,
|
| 190 |
+
"eval_recall": 1.0,
|
| 191 |
+
"eval_runtime": 0.3084,
|
| 192 |
+
"eval_samples_per_second": 22.696,
|
| 193 |
+
"eval_steps_per_second": 3.242,
|
| 194 |
+
"step": 20
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.25,
|
| 198 |
+
"learning_rate": 4.166666666666667e-05,
|
| 199 |
+
"loss": 0.2782,
|
| 200 |
+
"step": 21
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 5.5,
|
| 204 |
+
"learning_rate": 4.0972222222222225e-05,
|
| 205 |
+
"loss": 0.162,
|
| 206 |
+
"step": 22
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.75,
|
| 210 |
+
"learning_rate": 4.027777777777778e-05,
|
| 211 |
+
"loss": 0.1054,
|
| 212 |
+
"step": 23
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.0,
|
| 216 |
+
"learning_rate": 3.958333333333333e-05,
|
| 217 |
+
"loss": 0.2455,
|
| 218 |
+
"step": 24
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.0,
|
| 222 |
+
"eval_accuracy": 1.0,
|
| 223 |
+
"eval_auc": 1.0,
|
| 224 |
+
"eval_f1": 1.0,
|
| 225 |
+
"eval_loss": 0.0715898796916008,
|
| 226 |
+
"eval_precision": 1.0,
|
| 227 |
+
"eval_recall": 1.0,
|
| 228 |
+
"eval_runtime": 0.2402,
|
| 229 |
+
"eval_samples_per_second": 29.148,
|
| 230 |
+
"eval_steps_per_second": 4.164,
|
| 231 |
+
"step": 24
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 6.25,
|
| 235 |
+
"learning_rate": 3.888888888888889e-05,
|
| 236 |
+
"loss": 0.1663,
|
| 237 |
+
"step": 25
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 6.5,
|
| 241 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 242 |
+
"loss": 0.0537,
|
| 243 |
+
"step": 26
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 6.75,
|
| 247 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 248 |
+
"loss": 0.1639,
|
| 249 |
+
"step": 27
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 7.0,
|
| 253 |
+
"learning_rate": 3.6805555555555556e-05,
|
| 254 |
+
"loss": 0.0457,
|
| 255 |
+
"step": 28
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.0,
|
| 259 |
+
"eval_accuracy": 1.0,
|
| 260 |
+
"eval_auc": 1.0,
|
| 261 |
+
"eval_f1": 1.0,
|
| 262 |
+
"eval_loss": 0.045065738260746,
|
| 263 |
+
"eval_precision": 1.0,
|
| 264 |
+
"eval_recall": 1.0,
|
| 265 |
+
"eval_runtime": 0.2361,
|
| 266 |
+
"eval_samples_per_second": 29.646,
|
| 267 |
+
"eval_steps_per_second": 4.235,
|
| 268 |
+
"step": 28
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 7.25,
|
| 272 |
+
"learning_rate": 3.611111111111111e-05,
|
| 273 |
+
"loss": 0.0697,
|
| 274 |
+
"step": 29
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 7.5,
|
| 278 |
+
"learning_rate": 3.541666666666667e-05,
|
| 279 |
+
"loss": 0.0911,
|
| 280 |
+
"step": 30
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 7.75,
|
| 284 |
+
"learning_rate": 3.472222222222222e-05,
|
| 285 |
+
"loss": 0.0988,
|
| 286 |
+
"step": 31
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 8.0,
|
| 290 |
+
"learning_rate": 3.402777777777778e-05,
|
| 291 |
+
"loss": 0.1209,
|
| 292 |
+
"step": 32
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 8.0,
|
| 296 |
+
"eval_accuracy": 1.0,
|
| 297 |
+
"eval_auc": 1.0,
|
| 298 |
+
"eval_f1": 1.0,
|
| 299 |
+
"eval_loss": 0.0308271162211895,
|
| 300 |
+
"eval_precision": 1.0,
|
| 301 |
+
"eval_recall": 1.0,
|
| 302 |
+
"eval_runtime": 0.239,
|
| 303 |
+
"eval_samples_per_second": 29.289,
|
| 304 |
+
"eval_steps_per_second": 4.184,
|
| 305 |
+
"step": 32
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 8.25,
|
| 309 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 310 |
+
"loss": 0.027,
|
| 311 |
+
"step": 33
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 8.5,
|
| 315 |
+
"learning_rate": 3.263888888888889e-05,
|
| 316 |
+
"loss": 0.0827,
|
| 317 |
+
"step": 34
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 8.75,
|
| 321 |
+
"learning_rate": 3.194444444444444e-05,
|
| 322 |
+
"loss": 0.0694,
|
| 323 |
+
"step": 35
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 9.0,
|
| 327 |
+
"learning_rate": 3.125e-05,
|
| 328 |
+
"loss": 0.2395,
|
| 329 |
+
"step": 36
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 9.0,
|
| 333 |
+
"eval_accuracy": 1.0,
|
| 334 |
+
"eval_auc": 1.0,
|
| 335 |
+
"eval_f1": 1.0,
|
| 336 |
+
"eval_loss": 0.02402932569384575,
|
| 337 |
+
"eval_precision": 1.0,
|
| 338 |
+
"eval_recall": 1.0,
|
| 339 |
+
"eval_runtime": 0.2369,
|
| 340 |
+
"eval_samples_per_second": 29.554,
|
| 341 |
+
"eval_steps_per_second": 4.222,
|
| 342 |
+
"step": 36
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 9.25,
|
| 346 |
+
"learning_rate": 3.055555555555556e-05,
|
| 347 |
+
"loss": 0.0317,
|
| 348 |
+
"step": 37
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 9.5,
|
| 352 |
+
"learning_rate": 2.9861111111111113e-05,
|
| 353 |
+
"loss": 0.2163,
|
| 354 |
+
"step": 38
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 9.75,
|
| 358 |
+
"learning_rate": 2.916666666666667e-05,
|
| 359 |
+
"loss": 0.0338,
|
| 360 |
+
"step": 39
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 10.0,
|
| 364 |
+
"learning_rate": 2.8472222222222223e-05,
|
| 365 |
+
"loss": 0.0082,
|
| 366 |
+
"step": 40
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 10.0,
|
| 370 |
+
"eval_accuracy": 1.0,
|
| 371 |
+
"eval_auc": 1.0,
|
| 372 |
+
"eval_f1": 1.0,
|
| 373 |
+
"eval_loss": 0.01993233896791935,
|
| 374 |
+
"eval_precision": 1.0,
|
| 375 |
+
"eval_recall": 1.0,
|
| 376 |
+
"eval_runtime": 0.2369,
|
| 377 |
+
"eval_samples_per_second": 29.546,
|
| 378 |
+
"eval_steps_per_second": 4.221,
|
| 379 |
+
"step": 40
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 10.25,
|
| 383 |
+
"learning_rate": 2.777777777777778e-05,
|
| 384 |
+
"loss": 0.1323,
|
| 385 |
+
"step": 41
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 10.5,
|
| 389 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 390 |
+
"loss": 0.0175,
|
| 391 |
+
"step": 42
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 10.75,
|
| 395 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 396 |
+
"loss": 0.0088,
|
| 397 |
+
"step": 43
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 11.0,
|
| 401 |
+
"learning_rate": 2.5694444444444445e-05,
|
| 402 |
+
"loss": 0.0176,
|
| 403 |
+
"step": 44
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 11.0,
|
| 407 |
+
"eval_accuracy": 1.0,
|
| 408 |
+
"eval_auc": 1.0,
|
| 409 |
+
"eval_f1": 1.0,
|
| 410 |
+
"eval_loss": 0.01787894032895565,
|
| 411 |
+
"eval_precision": 1.0,
|
| 412 |
+
"eval_recall": 1.0,
|
| 413 |
+
"eval_runtime": 0.2348,
|
| 414 |
+
"eval_samples_per_second": 29.813,
|
| 415 |
+
"eval_steps_per_second": 4.259,
|
| 416 |
+
"step": 44
|
| 417 |
+
}
|
| 418 |
+
],
|
| 419 |
+
"logging_steps": 1,
|
| 420 |
+
"max_steps": 80,
|
| 421 |
+
"num_input_tokens_seen": 0,
|
| 422 |
+
"num_train_epochs": 20,
|
| 423 |
+
"save_steps": 500,
|
| 424 |
+
"total_flos": 2.3015120915533824e+16,
|
| 425 |
+
"train_batch_size": 8,
|
| 426 |
+
"trial_name": null,
|
| 427 |
+
"trial_params": null
|
| 428 |
+
}
|
checkpoint-44/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dea32ca958067475e15581215a3b5777282bc101d9acaa54586169cfd734266
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ViTForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"encoder_stride": 16,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "mulder",
|
| 14 |
+
"1": "scully"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"mulder": 0,
|
| 21 |
+
"scully": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"model_type": "vit",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_channels": 3,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"patch_size": 16,
|
| 29 |
+
"problem_type": "single_label_classification",
|
| 30 |
+
"qkv_bias": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.37.0"
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e84cd6f36a4c58aafc4fd643b2225ad9c2c130d14aaf439b86fa32fff5acd7f7
|
| 3 |
+
size 343223968
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dea32ca958067475e15581215a3b5777282bc101d9acaa54586169cfd734266
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "mulder-scully-2024/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "dvs",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 20,
|
| 7 |
+
"batch_size": 8,
|
| 8 |
+
"warmup_ratio": 0.1,
|
| 9 |
+
"gradient_accumulation": 1,
|
| 10 |
+
"optimizer": "adamw_torch",
|
| 11 |
+
"scheduler": "linear",
|
| 12 |
+
"weight_decay": 0.0,
|
| 13 |
+
"max_grad_norm": 1.0,
|
| 14 |
+
"seed": 42,
|
| 15 |
+
"train_split": "train",
|
| 16 |
+
"valid_split": "validation",
|
| 17 |
+
"logging_steps": -1,
|
| 18 |
+
"project_name": "mulder-scully-2024",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "fp16",
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"save_strategy": "epoch",
|
| 23 |
+
"push_to_hub": true,
|
| 24 |
+
"repo_id": "dvs/mulder-scully-2024",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|