Upload folder using huggingface_hub
Browse files- README.md +32 -0
- checkpoint-144/config.json +50 -0
- checkpoint-144/model.safetensors +3 -0
- checkpoint-144/optimizer.pt +3 -0
- checkpoint-144/rng_state.pth +3 -0
- checkpoint-144/scheduler.pt +3 -0
- checkpoint-144/trainer_state.json +492 -0
- checkpoint-144/training_args.bin +3 -0
- config.json +50 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
- training_params.json +28 -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 |
+
- Naterea/autotrain-data-vxbcsdf123
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.5112138390541077
|
| 23 |
+
|
| 24 |
+
f1: 0.7499999999999999
|
| 25 |
+
|
| 26 |
+
precision: 0.6
|
| 27 |
+
|
| 28 |
+
recall: 1.0
|
| 29 |
+
|
| 30 |
+
auc: 1.0
|
| 31 |
+
|
| 32 |
+
accuracy: 0.6
|
checkpoint-144/config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ResNetForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
3
|
| 12 |
+
],
|
| 13 |
+
"downsample_in_bottleneck": false,
|
| 14 |
+
"downsample_in_first_stage": false,
|
| 15 |
+
"embedding_size": 64,
|
| 16 |
+
"hidden_act": "relu",
|
| 17 |
+
"hidden_sizes": [
|
| 18 |
+
256,
|
| 19 |
+
512,
|
| 20 |
+
1024,
|
| 21 |
+
2048
|
| 22 |
+
],
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "noyt",
|
| 25 |
+
"1": "yt"
|
| 26 |
+
},
|
| 27 |
+
"label2id": {
|
| 28 |
+
"noyt": 0,
|
| 29 |
+
"yt": 1
|
| 30 |
+
},
|
| 31 |
+
"layer_type": "bottleneck",
|
| 32 |
+
"model_type": "resnet",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"out_features": [
|
| 35 |
+
"stage4"
|
| 36 |
+
],
|
| 37 |
+
"out_indices": [
|
| 38 |
+
4
|
| 39 |
+
],
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"stage_names": [
|
| 42 |
+
"stem",
|
| 43 |
+
"stage1",
|
| 44 |
+
"stage2",
|
| 45 |
+
"stage3",
|
| 46 |
+
"stage4"
|
| 47 |
+
],
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.36.1"
|
| 50 |
+
}
|
checkpoint-144/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcfaa05a310d5fc834686b1932269939a0d3e6fbfb4069fc3c22c85c71809bde
|
| 3 |
+
size 94302952
|
checkpoint-144/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a530c95a2ac209ba7c17e8f02745ccbff3e823636673852716bf6397878af2a2
|
| 3 |
+
size 188228026
|
checkpoint-144/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50786970f24eea4f798ee55ca7b96921c8a3a3121ed357c6ac6185cf6a6597ba
|
| 3 |
+
size 13990
|
checkpoint-144/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a949ed3376a9a4a304f122136113b4c5f21dfd67a7b9a8fc7bdacc0383de61c
|
| 3 |
+
size 1064
|
checkpoint-144/trainer_state.json
ADDED
|
@@ -0,0 +1,492 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5112138390541077,
|
| 3 |
+
"best_model_checkpoint": "/tmp/model/checkpoint-144",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 144,
|
| 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": 6.666666666666667e-06,
|
| 14 |
+
"loss": 0.6931,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 20 |
+
"loss": 0.6931,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 2e-05,
|
| 26 |
+
"loss": 0.6931,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.17,
|
| 31 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 32 |
+
"loss": 0.6916,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.21,
|
| 37 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 38 |
+
"loss": 0.6917,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.25,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 0.6899,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.29,
|
| 49 |
+
"learning_rate": 4.666666666666667e-05,
|
| 50 |
+
"loss": 0.6889,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.33,
|
| 55 |
+
"learning_rate": 4.96124031007752e-05,
|
| 56 |
+
"loss": 0.6856,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.38,
|
| 61 |
+
"learning_rate": 4.883720930232558e-05,
|
| 62 |
+
"loss": 0.6874,
|
| 63 |
+
"step": 18
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.42,
|
| 67 |
+
"learning_rate": 4.8062015503875976e-05,
|
| 68 |
+
"loss": 0.6862,
|
| 69 |
+
"step": 20
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.46,
|
| 73 |
+
"learning_rate": 4.728682170542636e-05,
|
| 74 |
+
"loss": 0.6849,
|
| 75 |
+
"step": 22
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.5,
|
| 79 |
+
"learning_rate": 4.651162790697675e-05,
|
| 80 |
+
"loss": 0.677,
|
| 81 |
+
"step": 24
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.54,
|
| 85 |
+
"learning_rate": 4.573643410852713e-05,
|
| 86 |
+
"loss": 0.6701,
|
| 87 |
+
"step": 26
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.58,
|
| 91 |
+
"learning_rate": 4.496124031007753e-05,
|
| 92 |
+
"loss": 0.6784,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.62,
|
| 97 |
+
"learning_rate": 4.418604651162791e-05,
|
| 98 |
+
"loss": 0.6784,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.67,
|
| 103 |
+
"learning_rate": 4.34108527131783e-05,
|
| 104 |
+
"loss": 0.6687,
|
| 105 |
+
"step": 32
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.71,
|
| 109 |
+
"learning_rate": 4.263565891472868e-05,
|
| 110 |
+
"loss": 0.6648,
|
| 111 |
+
"step": 34
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.75,
|
| 115 |
+
"learning_rate": 4.186046511627907e-05,
|
| 116 |
+
"loss": 0.6661,
|
| 117 |
+
"step": 36
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.79,
|
| 121 |
+
"learning_rate": 4.108527131782946e-05,
|
| 122 |
+
"loss": 0.6421,
|
| 123 |
+
"step": 38
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.83,
|
| 127 |
+
"learning_rate": 4.0310077519379843e-05,
|
| 128 |
+
"loss": 0.6458,
|
| 129 |
+
"step": 40
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.88,
|
| 133 |
+
"learning_rate": 3.953488372093023e-05,
|
| 134 |
+
"loss": 0.6615,
|
| 135 |
+
"step": 42
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.92,
|
| 139 |
+
"learning_rate": 3.875968992248062e-05,
|
| 140 |
+
"loss": 0.6294,
|
| 141 |
+
"step": 44
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.96,
|
| 145 |
+
"learning_rate": 3.798449612403101e-05,
|
| 146 |
+
"loss": 0.6471,
|
| 147 |
+
"step": 46
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.0,
|
| 151 |
+
"learning_rate": 3.7209302325581394e-05,
|
| 152 |
+
"loss": 0.6923,
|
| 153 |
+
"step": 48
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.0,
|
| 157 |
+
"eval_accuracy": 0.6,
|
| 158 |
+
"eval_auc": 1.0,
|
| 159 |
+
"eval_f1": 0.7499999999999999,
|
| 160 |
+
"eval_loss": 0.6188636422157288,
|
| 161 |
+
"eval_precision": 0.6,
|
| 162 |
+
"eval_recall": 1.0,
|
| 163 |
+
"eval_runtime": 13.3176,
|
| 164 |
+
"eval_samples_per_second": 7.133,
|
| 165 |
+
"eval_steps_per_second": 0.451,
|
| 166 |
+
"step": 48
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.04,
|
| 170 |
+
"learning_rate": 3.6434108527131784e-05,
|
| 171 |
+
"loss": 0.6528,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.08,
|
| 176 |
+
"learning_rate": 3.565891472868217e-05,
|
| 177 |
+
"loss": 0.6468,
|
| 178 |
+
"step": 52
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.12,
|
| 182 |
+
"learning_rate": 3.488372093023256e-05,
|
| 183 |
+
"loss": 0.6816,
|
| 184 |
+
"step": 54
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.17,
|
| 188 |
+
"learning_rate": 3.4108527131782945e-05,
|
| 189 |
+
"loss": 0.6155,
|
| 190 |
+
"step": 56
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.21,
|
| 194 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 195 |
+
"loss": 0.6151,
|
| 196 |
+
"step": 58
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.25,
|
| 200 |
+
"learning_rate": 3.2558139534883724e-05,
|
| 201 |
+
"loss": 0.6055,
|
| 202 |
+
"step": 60
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.29,
|
| 206 |
+
"learning_rate": 3.1782945736434114e-05,
|
| 207 |
+
"loss": 0.63,
|
| 208 |
+
"step": 62
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.33,
|
| 212 |
+
"learning_rate": 3.1007751937984497e-05,
|
| 213 |
+
"loss": 0.6136,
|
| 214 |
+
"step": 64
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.38,
|
| 218 |
+
"learning_rate": 3.0232558139534883e-05,
|
| 219 |
+
"loss": 0.6024,
|
| 220 |
+
"step": 66
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.42,
|
| 224 |
+
"learning_rate": 2.9457364341085275e-05,
|
| 225 |
+
"loss": 0.6039,
|
| 226 |
+
"step": 68
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.46,
|
| 230 |
+
"learning_rate": 2.868217054263566e-05,
|
| 231 |
+
"loss": 0.6381,
|
| 232 |
+
"step": 70
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.5,
|
| 236 |
+
"learning_rate": 2.7906976744186048e-05,
|
| 237 |
+
"loss": 0.6171,
|
| 238 |
+
"step": 72
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.54,
|
| 242 |
+
"learning_rate": 2.7131782945736434e-05,
|
| 243 |
+
"loss": 0.5989,
|
| 244 |
+
"step": 74
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.58,
|
| 248 |
+
"learning_rate": 2.6356589147286826e-05,
|
| 249 |
+
"loss": 0.6496,
|
| 250 |
+
"step": 76
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.62,
|
| 254 |
+
"learning_rate": 2.5581395348837212e-05,
|
| 255 |
+
"loss": 0.5904,
|
| 256 |
+
"step": 78
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.67,
|
| 260 |
+
"learning_rate": 2.48062015503876e-05,
|
| 261 |
+
"loss": 0.5641,
|
| 262 |
+
"step": 80
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.71,
|
| 266 |
+
"learning_rate": 2.4031007751937988e-05,
|
| 267 |
+
"loss": 0.6415,
|
| 268 |
+
"step": 82
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.75,
|
| 272 |
+
"learning_rate": 2.3255813953488374e-05,
|
| 273 |
+
"loss": 0.5581,
|
| 274 |
+
"step": 84
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.79,
|
| 278 |
+
"learning_rate": 2.2480620155038764e-05,
|
| 279 |
+
"loss": 0.5596,
|
| 280 |
+
"step": 86
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.83,
|
| 284 |
+
"learning_rate": 2.170542635658915e-05,
|
| 285 |
+
"loss": 0.6017,
|
| 286 |
+
"step": 88
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.88,
|
| 290 |
+
"learning_rate": 2.0930232558139536e-05,
|
| 291 |
+
"loss": 0.5437,
|
| 292 |
+
"step": 90
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.92,
|
| 296 |
+
"learning_rate": 2.0155038759689922e-05,
|
| 297 |
+
"loss": 0.5613,
|
| 298 |
+
"step": 92
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.96,
|
| 302 |
+
"learning_rate": 1.937984496124031e-05,
|
| 303 |
+
"loss": 0.617,
|
| 304 |
+
"step": 94
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 2.0,
|
| 308 |
+
"learning_rate": 1.8604651162790697e-05,
|
| 309 |
+
"loss": 0.7115,
|
| 310 |
+
"step": 96
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.0,
|
| 314 |
+
"eval_accuracy": 0.6,
|
| 315 |
+
"eval_auc": 1.0,
|
| 316 |
+
"eval_f1": 0.7499999999999999,
|
| 317 |
+
"eval_loss": 0.5825784206390381,
|
| 318 |
+
"eval_precision": 0.6,
|
| 319 |
+
"eval_recall": 1.0,
|
| 320 |
+
"eval_runtime": 12.6935,
|
| 321 |
+
"eval_samples_per_second": 7.484,
|
| 322 |
+
"eval_steps_per_second": 0.473,
|
| 323 |
+
"step": 96
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.04,
|
| 327 |
+
"learning_rate": 1.7829457364341087e-05,
|
| 328 |
+
"loss": 0.6016,
|
| 329 |
+
"step": 98
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.08,
|
| 333 |
+
"learning_rate": 1.7054263565891473e-05,
|
| 334 |
+
"loss": 0.5401,
|
| 335 |
+
"step": 100
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.12,
|
| 339 |
+
"learning_rate": 1.6279069767441862e-05,
|
| 340 |
+
"loss": 0.5289,
|
| 341 |
+
"step": 102
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.17,
|
| 345 |
+
"learning_rate": 1.5503875968992248e-05,
|
| 346 |
+
"loss": 0.521,
|
| 347 |
+
"step": 104
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.21,
|
| 351 |
+
"learning_rate": 1.4728682170542638e-05,
|
| 352 |
+
"loss": 0.5441,
|
| 353 |
+
"step": 106
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.25,
|
| 357 |
+
"learning_rate": 1.3953488372093024e-05,
|
| 358 |
+
"loss": 0.5942,
|
| 359 |
+
"step": 108
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.29,
|
| 363 |
+
"learning_rate": 1.3178294573643413e-05,
|
| 364 |
+
"loss": 0.5576,
|
| 365 |
+
"step": 110
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.33,
|
| 369 |
+
"learning_rate": 1.24031007751938e-05,
|
| 370 |
+
"loss": 0.5702,
|
| 371 |
+
"step": 112
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.38,
|
| 375 |
+
"learning_rate": 1.1627906976744187e-05,
|
| 376 |
+
"loss": 0.5567,
|
| 377 |
+
"step": 114
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.42,
|
| 381 |
+
"learning_rate": 1.0852713178294575e-05,
|
| 382 |
+
"loss": 0.5222,
|
| 383 |
+
"step": 116
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.46,
|
| 387 |
+
"learning_rate": 1.0077519379844961e-05,
|
| 388 |
+
"loss": 0.565,
|
| 389 |
+
"step": 118
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.5,
|
| 393 |
+
"learning_rate": 9.302325581395349e-06,
|
| 394 |
+
"loss": 0.5274,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.54,
|
| 399 |
+
"learning_rate": 8.527131782945736e-06,
|
| 400 |
+
"loss": 0.5156,
|
| 401 |
+
"step": 122
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.58,
|
| 405 |
+
"learning_rate": 7.751937984496124e-06,
|
| 406 |
+
"loss": 0.562,
|
| 407 |
+
"step": 124
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.62,
|
| 411 |
+
"learning_rate": 6.976744186046512e-06,
|
| 412 |
+
"loss": 0.5159,
|
| 413 |
+
"step": 126
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.67,
|
| 417 |
+
"learning_rate": 6.2015503875969e-06,
|
| 418 |
+
"loss": 0.5327,
|
| 419 |
+
"step": 128
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.71,
|
| 423 |
+
"learning_rate": 5.426356589147287e-06,
|
| 424 |
+
"loss": 0.5364,
|
| 425 |
+
"step": 130
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.75,
|
| 429 |
+
"learning_rate": 4.651162790697674e-06,
|
| 430 |
+
"loss": 0.5982,
|
| 431 |
+
"step": 132
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.79,
|
| 435 |
+
"learning_rate": 3.875968992248062e-06,
|
| 436 |
+
"loss": 0.6285,
|
| 437 |
+
"step": 134
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.83,
|
| 441 |
+
"learning_rate": 3.10077519379845e-06,
|
| 442 |
+
"loss": 0.5116,
|
| 443 |
+
"step": 136
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.88,
|
| 447 |
+
"learning_rate": 2.325581395348837e-06,
|
| 448 |
+
"loss": 0.5596,
|
| 449 |
+
"step": 138
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.92,
|
| 453 |
+
"learning_rate": 1.550387596899225e-06,
|
| 454 |
+
"loss": 0.5538,
|
| 455 |
+
"step": 140
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.96,
|
| 459 |
+
"learning_rate": 7.751937984496125e-07,
|
| 460 |
+
"loss": 0.568,
|
| 461 |
+
"step": 142
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.0,
|
| 465 |
+
"learning_rate": 0.0,
|
| 466 |
+
"loss": 0.5701,
|
| 467 |
+
"step": 144
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.0,
|
| 471 |
+
"eval_accuracy": 0.6,
|
| 472 |
+
"eval_auc": 1.0,
|
| 473 |
+
"eval_f1": 0.7499999999999999,
|
| 474 |
+
"eval_loss": 0.5112138390541077,
|
| 475 |
+
"eval_precision": 0.6,
|
| 476 |
+
"eval_recall": 1.0,
|
| 477 |
+
"eval_runtime": 11.597,
|
| 478 |
+
"eval_samples_per_second": 8.192,
|
| 479 |
+
"eval_steps_per_second": 0.517,
|
| 480 |
+
"step": 144
|
| 481 |
+
}
|
| 482 |
+
],
|
| 483 |
+
"logging_steps": 2,
|
| 484 |
+
"max_steps": 144,
|
| 485 |
+
"num_input_tokens_seen": 0,
|
| 486 |
+
"num_train_epochs": 3,
|
| 487 |
+
"save_steps": 500,
|
| 488 |
+
"total_flos": 2.401724127688704e+16,
|
| 489 |
+
"train_batch_size": 8,
|
| 490 |
+
"trial_name": null,
|
| 491 |
+
"trial_params": null
|
| 492 |
+
}
|
checkpoint-144/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e94913aab5093a6042199bccd8583e02d60ddd697dbe118787a86d7125b13ae3
|
| 3 |
+
size 4728
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"ResNetForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
3
|
| 12 |
+
],
|
| 13 |
+
"downsample_in_bottleneck": false,
|
| 14 |
+
"downsample_in_first_stage": false,
|
| 15 |
+
"embedding_size": 64,
|
| 16 |
+
"hidden_act": "relu",
|
| 17 |
+
"hidden_sizes": [
|
| 18 |
+
256,
|
| 19 |
+
512,
|
| 20 |
+
1024,
|
| 21 |
+
2048
|
| 22 |
+
],
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "noyt",
|
| 25 |
+
"1": "yt"
|
| 26 |
+
},
|
| 27 |
+
"label2id": {
|
| 28 |
+
"noyt": 0,
|
| 29 |
+
"yt": 1
|
| 30 |
+
},
|
| 31 |
+
"layer_type": "bottleneck",
|
| 32 |
+
"model_type": "resnet",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"out_features": [
|
| 35 |
+
"stage4"
|
| 36 |
+
],
|
| 37 |
+
"out_indices": [
|
| 38 |
+
4
|
| 39 |
+
],
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"stage_names": [
|
| 42 |
+
"stem",
|
| 43 |
+
"stage1",
|
| 44 |
+
"stage2",
|
| 45 |
+
"stage3",
|
| 46 |
+
"stage4"
|
| 47 |
+
],
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.36.1"
|
| 50 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcfaa05a310d5fc834686b1932269939a0d3e6fbfb4069fc3c22c85c71809bde
|
| 3 |
+
size 94302952
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"shortest_edge": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e94913aab5093a6042199bccd8583e02d60ddd697dbe118787a86d7125b13ae3
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "Naterea/autotrain-data-vxbcsdf123",
|
| 3 |
+
"model": "microsoft/resnet-50",
|
| 4 |
+
"lr": 5e-05,
|
| 5 |
+
"epochs": 3,
|
| 6 |
+
"batch_size": 8,
|
| 7 |
+
"warmup_ratio": 0.1,
|
| 8 |
+
"gradient_accumulation": 1,
|
| 9 |
+
"optimizer": "adamw_torch",
|
| 10 |
+
"scheduler": "linear",
|
| 11 |
+
"weight_decay": 0.0,
|
| 12 |
+
"max_grad_norm": 1.0,
|
| 13 |
+
"seed": 42,
|
| 14 |
+
"train_split": "train",
|
| 15 |
+
"valid_split": "validation",
|
| 16 |
+
"logging_steps": -1,
|
| 17 |
+
"project_name": "/tmp/model",
|
| 18 |
+
"auto_find_batch_size": false,
|
| 19 |
+
"mixed_precision": "fp32",
|
| 20 |
+
"save_total_limit": 1,
|
| 21 |
+
"save_strategy": "epoch",
|
| 22 |
+
"push_to_hub": true,
|
| 23 |
+
"repo_id": "Naterea/vxbcsdf123-0",
|
| 24 |
+
"evaluation_strategy": "epoch",
|
| 25 |
+
"image_column": "autotrain_image",
|
| 26 |
+
"target_column": "autotrain_label",
|
| 27 |
+
"log": "none"
|
| 28 |
+
}
|