Commit
•
2de1c38
1
Parent(s):
80c310f
Upload folder using huggingface_hub
Browse files- README.md +32 -0
- checkpoint-162/config.json +33 -0
- checkpoint-162/model.safetensors +3 -0
- checkpoint-162/optimizer.pt +3 -0
- checkpoint-162/rng_state.pth +3 -0
- checkpoint-162/scheduler.pt +3 -0
- checkpoint-162/trainer_state.json +546 -0
- checkpoint-162/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 |
+
- autotrain-qfdfq-d86gh/autotrain-data
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.077054463326931
|
| 23 |
+
|
| 24 |
+
f1: 0.9904761904761905
|
| 25 |
+
|
| 26 |
+
precision: 0.9811320754716981
|
| 27 |
+
|
| 28 |
+
recall: 1.0
|
| 29 |
+
|
| 30 |
+
auc: 0.9927884615384616
|
| 31 |
+
|
| 32 |
+
accuracy: 0.9907407407407407
|
checkpoint-162/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": "post",
|
| 14 |
+
"1": "pre"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"post": 0,
|
| 21 |
+
"pre": 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-162/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cae6d619a50aa28c1427e645ac34dcce59532b85f5d556be07cacaf3251cc9a1
|
| 3 |
+
size 343223968
|
checkpoint-162/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ea0d4046ee0ce5750f6a49a33725e52b19d027af0068aeedb24e2096a82d4d8
|
| 3 |
+
size 686568890
|
checkpoint-162/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0f167b3dfd4005cd23b3828bf12d171cd7583ecefe1095d20d7a81b8b673455
|
| 3 |
+
size 14180
|
checkpoint-162/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af475ce7e69ec84bd89361200b60d3d28891c0e6bf4474fad8420a5c1c8c4a7a
|
| 3 |
+
size 1064
|
checkpoint-162/trainer_state.json
ADDED
|
@@ -0,0 +1,546 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.077054463326931,
|
| 3 |
+
"best_model_checkpoint": "autotrain-qfdfq-d86gh/checkpoint-162",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 162,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 5.882352941176471e-06,
|
| 14 |
+
"loss": 0.7948,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 20 |
+
"loss": 0.8714,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.11,
|
| 25 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 26 |
+
"loss": 0.9453,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.15,
|
| 31 |
+
"learning_rate": 2.058823529411765e-05,
|
| 32 |
+
"loss": 0.6547,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 2.647058823529412e-05,
|
| 38 |
+
"loss": 0.6176,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.22,
|
| 43 |
+
"learning_rate": 3.235294117647059e-05,
|
| 44 |
+
"loss": 0.7582,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.26,
|
| 49 |
+
"learning_rate": 3.8235294117647055e-05,
|
| 50 |
+
"loss": 0.4007,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3,
|
| 55 |
+
"learning_rate": 4.411764705882353e-05,
|
| 56 |
+
"loss": 0.5664,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.33,
|
| 61 |
+
"learning_rate": 5e-05,
|
| 62 |
+
"loss": 0.5553,
|
| 63 |
+
"step": 18
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.37,
|
| 67 |
+
"learning_rate": 4.931034482758621e-05,
|
| 68 |
+
"loss": 0.3891,
|
| 69 |
+
"step": 20
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.41,
|
| 73 |
+
"learning_rate": 4.862068965517241e-05,
|
| 74 |
+
"loss": 0.5564,
|
| 75 |
+
"step": 22
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.44,
|
| 79 |
+
"learning_rate": 4.793103448275863e-05,
|
| 80 |
+
"loss": 0.452,
|
| 81 |
+
"step": 24
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.48,
|
| 85 |
+
"learning_rate": 4.724137931034483e-05,
|
| 86 |
+
"loss": 0.3223,
|
| 87 |
+
"step": 26
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.52,
|
| 91 |
+
"learning_rate": 4.655172413793104e-05,
|
| 92 |
+
"loss": 0.3602,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.56,
|
| 97 |
+
"learning_rate": 4.586206896551724e-05,
|
| 98 |
+
"loss": 0.3069,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.59,
|
| 103 |
+
"learning_rate": 4.5172413793103454e-05,
|
| 104 |
+
"loss": 0.2233,
|
| 105 |
+
"step": 32
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.63,
|
| 109 |
+
"learning_rate": 4.4482758620689656e-05,
|
| 110 |
+
"loss": 0.2493,
|
| 111 |
+
"step": 34
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.67,
|
| 115 |
+
"learning_rate": 4.3793103448275864e-05,
|
| 116 |
+
"loss": 0.1294,
|
| 117 |
+
"step": 36
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.7,
|
| 121 |
+
"learning_rate": 4.3103448275862066e-05,
|
| 122 |
+
"loss": 0.1497,
|
| 123 |
+
"step": 38
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.74,
|
| 127 |
+
"learning_rate": 4.241379310344828e-05,
|
| 128 |
+
"loss": 0.1235,
|
| 129 |
+
"step": 40
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.78,
|
| 133 |
+
"learning_rate": 4.172413793103448e-05,
|
| 134 |
+
"loss": 0.4971,
|
| 135 |
+
"step": 42
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.81,
|
| 139 |
+
"learning_rate": 4.103448275862069e-05,
|
| 140 |
+
"loss": 0.7793,
|
| 141 |
+
"step": 44
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.85,
|
| 145 |
+
"learning_rate": 4.03448275862069e-05,
|
| 146 |
+
"loss": 0.3153,
|
| 147 |
+
"step": 46
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.89,
|
| 151 |
+
"learning_rate": 3.965517241379311e-05,
|
| 152 |
+
"loss": 0.3956,
|
| 153 |
+
"step": 48
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.93,
|
| 157 |
+
"learning_rate": 3.896551724137931e-05,
|
| 158 |
+
"loss": 0.2401,
|
| 159 |
+
"step": 50
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.96,
|
| 163 |
+
"learning_rate": 3.827586206896552e-05,
|
| 164 |
+
"loss": 0.1951,
|
| 165 |
+
"step": 52
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0,
|
| 169 |
+
"learning_rate": 3.7586206896551726e-05,
|
| 170 |
+
"loss": 0.3379,
|
| 171 |
+
"step": 54
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.0,
|
| 175 |
+
"eval_accuracy": 0.9351851851851852,
|
| 176 |
+
"eval_auc": 0.9950206043956044,
|
| 177 |
+
"eval_f1": 0.936936936936937,
|
| 178 |
+
"eval_loss": 0.14235283434391022,
|
| 179 |
+
"eval_precision": 0.8813559322033898,
|
| 180 |
+
"eval_recall": 1.0,
|
| 181 |
+
"eval_runtime": 1.791,
|
| 182 |
+
"eval_samples_per_second": 60.301,
|
| 183 |
+
"eval_steps_per_second": 3.908,
|
| 184 |
+
"step": 54
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.04,
|
| 188 |
+
"learning_rate": 3.6896551724137934e-05,
|
| 189 |
+
"loss": 0.2265,
|
| 190 |
+
"step": 56
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.07,
|
| 194 |
+
"learning_rate": 3.620689655172414e-05,
|
| 195 |
+
"loss": 0.2889,
|
| 196 |
+
"step": 58
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.11,
|
| 200 |
+
"learning_rate": 3.5517241379310344e-05,
|
| 201 |
+
"loss": 0.1082,
|
| 202 |
+
"step": 60
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.15,
|
| 206 |
+
"learning_rate": 3.482758620689655e-05,
|
| 207 |
+
"loss": 0.0784,
|
| 208 |
+
"step": 62
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.19,
|
| 212 |
+
"learning_rate": 3.413793103448276e-05,
|
| 213 |
+
"loss": 0.2341,
|
| 214 |
+
"step": 64
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.22,
|
| 218 |
+
"learning_rate": 3.344827586206897e-05,
|
| 219 |
+
"loss": 0.051,
|
| 220 |
+
"step": 66
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.26,
|
| 224 |
+
"learning_rate": 3.275862068965517e-05,
|
| 225 |
+
"loss": 0.4885,
|
| 226 |
+
"step": 68
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.3,
|
| 230 |
+
"learning_rate": 3.206896551724138e-05,
|
| 231 |
+
"loss": 0.3152,
|
| 232 |
+
"step": 70
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.33,
|
| 236 |
+
"learning_rate": 3.137931034482759e-05,
|
| 237 |
+
"loss": 0.0971,
|
| 238 |
+
"step": 72
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.37,
|
| 242 |
+
"learning_rate": 3.0689655172413796e-05,
|
| 243 |
+
"loss": 0.0529,
|
| 244 |
+
"step": 74
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.41,
|
| 248 |
+
"learning_rate": 3e-05,
|
| 249 |
+
"loss": 0.3742,
|
| 250 |
+
"step": 76
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.44,
|
| 254 |
+
"learning_rate": 2.9310344827586206e-05,
|
| 255 |
+
"loss": 0.193,
|
| 256 |
+
"step": 78
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.48,
|
| 260 |
+
"learning_rate": 2.8620689655172417e-05,
|
| 261 |
+
"loss": 0.1045,
|
| 262 |
+
"step": 80
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.52,
|
| 266 |
+
"learning_rate": 2.7931034482758622e-05,
|
| 267 |
+
"loss": 0.1086,
|
| 268 |
+
"step": 82
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.56,
|
| 272 |
+
"learning_rate": 2.7241379310344827e-05,
|
| 273 |
+
"loss": 0.1334,
|
| 274 |
+
"step": 84
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.59,
|
| 278 |
+
"learning_rate": 2.6551724137931032e-05,
|
| 279 |
+
"loss": 0.0626,
|
| 280 |
+
"step": 86
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.63,
|
| 284 |
+
"learning_rate": 2.5862068965517244e-05,
|
| 285 |
+
"loss": 0.0763,
|
| 286 |
+
"step": 88
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.67,
|
| 290 |
+
"learning_rate": 2.517241379310345e-05,
|
| 291 |
+
"loss": 0.0682,
|
| 292 |
+
"step": 90
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.7,
|
| 296 |
+
"learning_rate": 2.4482758620689654e-05,
|
| 297 |
+
"loss": 0.1008,
|
| 298 |
+
"step": 92
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.74,
|
| 302 |
+
"learning_rate": 2.3793103448275862e-05,
|
| 303 |
+
"loss": 0.1169,
|
| 304 |
+
"step": 94
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.78,
|
| 308 |
+
"learning_rate": 2.3103448275862067e-05,
|
| 309 |
+
"loss": 0.3976,
|
| 310 |
+
"step": 96
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.81,
|
| 314 |
+
"learning_rate": 2.2413793103448276e-05,
|
| 315 |
+
"loss": 0.499,
|
| 316 |
+
"step": 98
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.85,
|
| 320 |
+
"learning_rate": 2.1724137931034484e-05,
|
| 321 |
+
"loss": 0.0471,
|
| 322 |
+
"step": 100
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.89,
|
| 326 |
+
"learning_rate": 2.1034482758620692e-05,
|
| 327 |
+
"loss": 0.1424,
|
| 328 |
+
"step": 102
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.93,
|
| 332 |
+
"learning_rate": 2.0344827586206897e-05,
|
| 333 |
+
"loss": 0.312,
|
| 334 |
+
"step": 104
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.96,
|
| 338 |
+
"learning_rate": 1.9655172413793106e-05,
|
| 339 |
+
"loss": 0.1831,
|
| 340 |
+
"step": 106
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.0,
|
| 344 |
+
"learning_rate": 1.896551724137931e-05,
|
| 345 |
+
"loss": 0.1266,
|
| 346 |
+
"step": 108
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.0,
|
| 350 |
+
"eval_accuracy": 0.9444444444444444,
|
| 351 |
+
"eval_auc": 0.9905563186813187,
|
| 352 |
+
"eval_f1": 0.9400000000000001,
|
| 353 |
+
"eval_loss": 0.12038230895996094,
|
| 354 |
+
"eval_precision": 0.9791666666666666,
|
| 355 |
+
"eval_recall": 0.9038461538461539,
|
| 356 |
+
"eval_runtime": 1.792,
|
| 357 |
+
"eval_samples_per_second": 60.267,
|
| 358 |
+
"eval_steps_per_second": 3.906,
|
| 359 |
+
"step": 108
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.04,
|
| 363 |
+
"learning_rate": 1.827586206896552e-05,
|
| 364 |
+
"loss": 0.0687,
|
| 365 |
+
"step": 110
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.07,
|
| 369 |
+
"learning_rate": 1.7586206896551724e-05,
|
| 370 |
+
"loss": 0.2379,
|
| 371 |
+
"step": 112
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.11,
|
| 375 |
+
"learning_rate": 1.6896551724137932e-05,
|
| 376 |
+
"loss": 0.1226,
|
| 377 |
+
"step": 114
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.15,
|
| 381 |
+
"learning_rate": 1.6206896551724137e-05,
|
| 382 |
+
"loss": 0.3007,
|
| 383 |
+
"step": 116
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.19,
|
| 387 |
+
"learning_rate": 1.5517241379310346e-05,
|
| 388 |
+
"loss": 0.248,
|
| 389 |
+
"step": 118
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.22,
|
| 393 |
+
"learning_rate": 1.482758620689655e-05,
|
| 394 |
+
"loss": 0.1432,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.26,
|
| 399 |
+
"learning_rate": 1.4137931034482759e-05,
|
| 400 |
+
"loss": 0.1437,
|
| 401 |
+
"step": 122
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.3,
|
| 405 |
+
"learning_rate": 1.3448275862068966e-05,
|
| 406 |
+
"loss": 0.0223,
|
| 407 |
+
"step": 124
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.33,
|
| 411 |
+
"learning_rate": 1.2758620689655174e-05,
|
| 412 |
+
"loss": 0.0694,
|
| 413 |
+
"step": 126
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.37,
|
| 417 |
+
"learning_rate": 1.206896551724138e-05,
|
| 418 |
+
"loss": 0.0218,
|
| 419 |
+
"step": 128
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.41,
|
| 423 |
+
"learning_rate": 1.1379310344827587e-05,
|
| 424 |
+
"loss": 0.0894,
|
| 425 |
+
"step": 130
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.44,
|
| 429 |
+
"learning_rate": 1.0689655172413794e-05,
|
| 430 |
+
"loss": 0.0909,
|
| 431 |
+
"step": 132
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.48,
|
| 435 |
+
"learning_rate": 1e-05,
|
| 436 |
+
"loss": 0.1203,
|
| 437 |
+
"step": 134
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.52,
|
| 441 |
+
"learning_rate": 9.310344827586207e-06,
|
| 442 |
+
"loss": 0.101,
|
| 443 |
+
"step": 136
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.56,
|
| 447 |
+
"learning_rate": 8.620689655172414e-06,
|
| 448 |
+
"loss": 0.0672,
|
| 449 |
+
"step": 138
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.59,
|
| 453 |
+
"learning_rate": 7.93103448275862e-06,
|
| 454 |
+
"loss": 0.2234,
|
| 455 |
+
"step": 140
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.63,
|
| 459 |
+
"learning_rate": 7.241379310344828e-06,
|
| 460 |
+
"loss": 0.1012,
|
| 461 |
+
"step": 142
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.67,
|
| 465 |
+
"learning_rate": 6.551724137931035e-06,
|
| 466 |
+
"loss": 0.171,
|
| 467 |
+
"step": 144
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.7,
|
| 471 |
+
"learning_rate": 5.862068965517242e-06,
|
| 472 |
+
"loss": 0.1821,
|
| 473 |
+
"step": 146
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.74,
|
| 477 |
+
"learning_rate": 5.172413793103448e-06,
|
| 478 |
+
"loss": 0.0899,
|
| 479 |
+
"step": 148
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.78,
|
| 483 |
+
"learning_rate": 4.482758620689655e-06,
|
| 484 |
+
"loss": 0.1178,
|
| 485 |
+
"step": 150
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.81,
|
| 489 |
+
"learning_rate": 3.793103448275862e-06,
|
| 490 |
+
"loss": 0.0077,
|
| 491 |
+
"step": 152
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 2.85,
|
| 495 |
+
"learning_rate": 3.103448275862069e-06,
|
| 496 |
+
"loss": 0.1433,
|
| 497 |
+
"step": 154
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.89,
|
| 501 |
+
"learning_rate": 2.413793103448276e-06,
|
| 502 |
+
"loss": 0.0939,
|
| 503 |
+
"step": 156
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.93,
|
| 507 |
+
"learning_rate": 1.724137931034483e-06,
|
| 508 |
+
"loss": 0.09,
|
| 509 |
+
"step": 158
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.96,
|
| 513 |
+
"learning_rate": 1.0344827586206898e-06,
|
| 514 |
+
"loss": 0.347,
|
| 515 |
+
"step": 160
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 3.0,
|
| 519 |
+
"learning_rate": 3.4482758620689656e-07,
|
| 520 |
+
"loss": 0.0531,
|
| 521 |
+
"step": 162
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 3.0,
|
| 525 |
+
"eval_accuracy": 0.9907407407407407,
|
| 526 |
+
"eval_auc": 0.9927884615384616,
|
| 527 |
+
"eval_f1": 0.9904761904761905,
|
| 528 |
+
"eval_loss": 0.077054463326931,
|
| 529 |
+
"eval_precision": 0.9811320754716981,
|
| 530 |
+
"eval_recall": 1.0,
|
| 531 |
+
"eval_runtime": 1.7262,
|
| 532 |
+
"eval_samples_per_second": 62.566,
|
| 533 |
+
"eval_steps_per_second": 4.055,
|
| 534 |
+
"step": 162
|
| 535 |
+
}
|
| 536 |
+
],
|
| 537 |
+
"logging_steps": 2,
|
| 538 |
+
"max_steps": 162,
|
| 539 |
+
"num_input_tokens_seen": 0,
|
| 540 |
+
"num_train_epochs": 3,
|
| 541 |
+
"save_steps": 500,
|
| 542 |
+
"total_flos": 9.949971466513613e+16,
|
| 543 |
+
"train_batch_size": 8,
|
| 544 |
+
"trial_name": null,
|
| 545 |
+
"trial_params": null
|
| 546 |
+
}
|
checkpoint-162/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42e7e40238038578f390dd8cf2bcc1093b4141fa7c51c3669041cdacd94b64f3
|
| 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": "post",
|
| 14 |
+
"1": "pre"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"post": 0,
|
| 21 |
+
"pre": 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:cae6d619a50aa28c1427e645ac34dcce59532b85f5d556be07cacaf3251cc9a1
|
| 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 sha256:42e7e40238038578f390dd8cf2bcc1093b4141fa7c51c3669041cdacd94b64f3
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "autotrain-qfdfq-d86gh/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "carljohnson40",
|
| 5 |
+
"lr": 5e-05,
|
| 6 |
+
"epochs": 3,
|
| 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": "autotrain-qfdfq-d86gh",
|
| 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": "carljohnson40/autotrain-qfdfq-d86gh",
|
| 25 |
+
"evaluation_strategy": "epoch",
|
| 26 |
+
"image_column": "autotrain_image",
|
| 27 |
+
"target_column": "autotrain_label",
|
| 28 |
+
"log": "none"
|
| 29 |
+
}
|