Upload folder using huggingface_hub
Browse files- README.md +32 -0
- checkpoint-393/config.json +50 -0
- checkpoint-393/model.safetensors +3 -0
- checkpoint-393/optimizer.pt +3 -0
- checkpoint-393/rng_state.pth +3 -0
- checkpoint-393/scheduler.pt +3 -0
- checkpoint-393/trainer_state.json +450 -0
- checkpoint-393/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-YT_REDD_V2.1_BASE
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# Model Trained Using AutoTrain
|
| 18 |
+
|
| 19 |
+
- Problem type: Image Classification
|
| 20 |
+
|
| 21 |
+
## Validation Metricsg
|
| 22 |
+
loss: 0.11768843978643417
|
| 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-393/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": "redd",
|
| 25 |
+
"1": "short"
|
| 26 |
+
},
|
| 27 |
+
"label2id": {
|
| 28 |
+
"redd": 0,
|
| 29 |
+
"short": 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-393/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7671d2117bb0bc04d47b807d555b20a2d240b2307b29ca83e61c6fabd3dea711
|
| 3 |
+
size 94302952
|
checkpoint-393/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0a850f480a09bc6bba183cda646e02e70b1d17ce707ee409fbe4caf4be1e8cc
|
| 3 |
+
size 188228026
|
checkpoint-393/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2f9f0c1341f36b39175524469ca61b2452e6ce0a491d281ade3e52a101f9d3
|
| 3 |
+
size 13990
|
checkpoint-393/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28fdc88c2219c56bc9e45cd8c066c091157240780c93e8239c4f6fcbf19d3e3a
|
| 3 |
+
size 1064
|
checkpoint-393/trainer_state.json
ADDED
|
@@ -0,0 +1,450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.11768843978643417,
|
| 3 |
+
"best_model_checkpoint": "/tmp/model/checkpoint-393",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 393,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 7.8e-06,
|
| 14 |
+
"loss": 0.6931,
|
| 15 |
+
"step": 6
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"learning_rate": 1.56e-05,
|
| 20 |
+
"loss": 0.6929,
|
| 21 |
+
"step": 12
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.14,
|
| 25 |
+
"learning_rate": 2.34e-05,
|
| 26 |
+
"loss": 0.6921,
|
| 27 |
+
"step": 18
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.18,
|
| 31 |
+
"learning_rate": 3.12e-05,
|
| 32 |
+
"loss": 0.6908,
|
| 33 |
+
"step": 24
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.23,
|
| 37 |
+
"learning_rate": 3.9e-05,
|
| 38 |
+
"loss": 0.6896,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.27,
|
| 43 |
+
"learning_rate": 4.68e-05,
|
| 44 |
+
"loss": 0.6873,
|
| 45 |
+
"step": 36
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.32,
|
| 49 |
+
"learning_rate": 5.170538243626062e-05,
|
| 50 |
+
"loss": 0.6809,
|
| 51 |
+
"step": 42
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.37,
|
| 55 |
+
"learning_rate": 5.082152974504249e-05,
|
| 56 |
+
"loss": 0.6779,
|
| 57 |
+
"step": 48
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.41,
|
| 61 |
+
"learning_rate": 4.9937677053824355e-05,
|
| 62 |
+
"loss": 0.6679,
|
| 63 |
+
"step": 54
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.46,
|
| 67 |
+
"learning_rate": 4.9053824362606226e-05,
|
| 68 |
+
"loss": 0.6602,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.5,
|
| 73 |
+
"learning_rate": 4.81699716713881e-05,
|
| 74 |
+
"loss": 0.6476,
|
| 75 |
+
"step": 66
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.55,
|
| 79 |
+
"learning_rate": 4.728611898016997e-05,
|
| 80 |
+
"loss": 0.64,
|
| 81 |
+
"step": 72
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.6,
|
| 85 |
+
"learning_rate": 4.640226628895184e-05,
|
| 86 |
+
"loss": 0.6289,
|
| 87 |
+
"step": 78
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.64,
|
| 91 |
+
"learning_rate": 4.551841359773371e-05,
|
| 92 |
+
"loss": 0.613,
|
| 93 |
+
"step": 84
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.69,
|
| 97 |
+
"learning_rate": 4.4634560906515584e-05,
|
| 98 |
+
"loss": 0.6233,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.73,
|
| 103 |
+
"learning_rate": 4.375070821529745e-05,
|
| 104 |
+
"loss": 0.6072,
|
| 105 |
+
"step": 96
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.78,
|
| 109 |
+
"learning_rate": 4.286685552407932e-05,
|
| 110 |
+
"loss": 0.5765,
|
| 111 |
+
"step": 102
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.82,
|
| 115 |
+
"learning_rate": 4.198300283286119e-05,
|
| 116 |
+
"loss": 0.5677,
|
| 117 |
+
"step": 108
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.87,
|
| 121 |
+
"learning_rate": 4.1099150141643056e-05,
|
| 122 |
+
"loss": 0.5538,
|
| 123 |
+
"step": 114
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.92,
|
| 127 |
+
"learning_rate": 4.021529745042493e-05,
|
| 128 |
+
"loss": 0.5368,
|
| 129 |
+
"step": 120
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.96,
|
| 133 |
+
"learning_rate": 3.93314447592068e-05,
|
| 134 |
+
"loss": 0.5341,
|
| 135 |
+
"step": 126
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_accuracy": 1.0,
|
| 140 |
+
"eval_auc": 1.0,
|
| 141 |
+
"eval_f1": 1.0,
|
| 142 |
+
"eval_loss": 0.4369600713253021,
|
| 143 |
+
"eval_precision": 1.0,
|
| 144 |
+
"eval_recall": 1.0,
|
| 145 |
+
"eval_runtime": 33.4023,
|
| 146 |
+
"eval_samples_per_second": 7.844,
|
| 147 |
+
"eval_steps_per_second": 0.509,
|
| 148 |
+
"step": 131
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.01,
|
| 152 |
+
"learning_rate": 3.8447592067988664e-05,
|
| 153 |
+
"loss": 0.4985,
|
| 154 |
+
"step": 132
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.05,
|
| 158 |
+
"learning_rate": 3.7563739376770535e-05,
|
| 159 |
+
"loss": 0.4917,
|
| 160 |
+
"step": 138
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.1,
|
| 164 |
+
"learning_rate": 3.667988668555241e-05,
|
| 165 |
+
"loss": 0.4849,
|
| 166 |
+
"step": 144
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.15,
|
| 170 |
+
"learning_rate": 3.579603399433428e-05,
|
| 171 |
+
"loss": 0.49,
|
| 172 |
+
"step": 150
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.19,
|
| 176 |
+
"learning_rate": 3.491218130311614e-05,
|
| 177 |
+
"loss": 0.4381,
|
| 178 |
+
"step": 156
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.24,
|
| 182 |
+
"learning_rate": 3.4028328611898015e-05,
|
| 183 |
+
"loss": 0.479,
|
| 184 |
+
"step": 162
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.28,
|
| 188 |
+
"learning_rate": 3.3144475920679886e-05,
|
| 189 |
+
"loss": 0.4316,
|
| 190 |
+
"step": 168
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.33,
|
| 194 |
+
"learning_rate": 3.226062322946175e-05,
|
| 195 |
+
"loss": 0.4146,
|
| 196 |
+
"step": 174
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.37,
|
| 200 |
+
"learning_rate": 3.137677053824362e-05,
|
| 201 |
+
"loss": 0.4161,
|
| 202 |
+
"step": 180
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.42,
|
| 206 |
+
"learning_rate": 3.0492917847025494e-05,
|
| 207 |
+
"loss": 0.3932,
|
| 208 |
+
"step": 186
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.47,
|
| 212 |
+
"learning_rate": 2.9609065155807362e-05,
|
| 213 |
+
"loss": 0.3577,
|
| 214 |
+
"step": 192
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.51,
|
| 218 |
+
"learning_rate": 2.8725212464589234e-05,
|
| 219 |
+
"loss": 0.3574,
|
| 220 |
+
"step": 198
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.56,
|
| 224 |
+
"learning_rate": 2.7841359773371105e-05,
|
| 225 |
+
"loss": 0.3468,
|
| 226 |
+
"step": 204
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.6,
|
| 230 |
+
"learning_rate": 2.6957507082152977e-05,
|
| 231 |
+
"loss": 0.3356,
|
| 232 |
+
"step": 210
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.65,
|
| 236 |
+
"learning_rate": 2.607365439093484e-05,
|
| 237 |
+
"loss": 0.2927,
|
| 238 |
+
"step": 216
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.69,
|
| 242 |
+
"learning_rate": 2.5189801699716713e-05,
|
| 243 |
+
"loss": 0.2838,
|
| 244 |
+
"step": 222
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.74,
|
| 248 |
+
"learning_rate": 2.430594900849858e-05,
|
| 249 |
+
"loss": 0.3153,
|
| 250 |
+
"step": 228
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.79,
|
| 254 |
+
"learning_rate": 2.3422096317280452e-05,
|
| 255 |
+
"loss": 0.2586,
|
| 256 |
+
"step": 234
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.83,
|
| 260 |
+
"learning_rate": 2.253824362606232e-05,
|
| 261 |
+
"loss": 0.2912,
|
| 262 |
+
"step": 240
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.88,
|
| 266 |
+
"learning_rate": 2.1654390934844192e-05,
|
| 267 |
+
"loss": 0.3014,
|
| 268 |
+
"step": 246
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.92,
|
| 272 |
+
"learning_rate": 2.077053824362606e-05,
|
| 273 |
+
"loss": 0.2679,
|
| 274 |
+
"step": 252
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.97,
|
| 278 |
+
"learning_rate": 1.988668555240793e-05,
|
| 279 |
+
"loss": 0.331,
|
| 280 |
+
"step": 258
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.0,
|
| 284 |
+
"eval_accuracy": 1.0,
|
| 285 |
+
"eval_auc": 1.0,
|
| 286 |
+
"eval_f1": 1.0,
|
| 287 |
+
"eval_loss": 0.17224115133285522,
|
| 288 |
+
"eval_precision": 1.0,
|
| 289 |
+
"eval_recall": 1.0,
|
| 290 |
+
"eval_runtime": 32.4437,
|
| 291 |
+
"eval_samples_per_second": 8.076,
|
| 292 |
+
"eval_steps_per_second": 0.524,
|
| 293 |
+
"step": 262
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.02,
|
| 297 |
+
"learning_rate": 1.90028328611898e-05,
|
| 298 |
+
"loss": 0.2564,
|
| 299 |
+
"step": 264
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.06,
|
| 303 |
+
"learning_rate": 1.811898016997167e-05,
|
| 304 |
+
"loss": 0.2979,
|
| 305 |
+
"step": 270
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.11,
|
| 309 |
+
"learning_rate": 1.7235127478753543e-05,
|
| 310 |
+
"loss": 0.2363,
|
| 311 |
+
"step": 276
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.15,
|
| 315 |
+
"learning_rate": 1.635127478753541e-05,
|
| 316 |
+
"loss": 0.1956,
|
| 317 |
+
"step": 282
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.2,
|
| 321 |
+
"learning_rate": 1.546742209631728e-05,
|
| 322 |
+
"loss": 0.217,
|
| 323 |
+
"step": 288
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.24,
|
| 327 |
+
"learning_rate": 1.458356940509915e-05,
|
| 328 |
+
"loss": 0.2207,
|
| 329 |
+
"step": 294
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.29,
|
| 333 |
+
"learning_rate": 1.3699716713881019e-05,
|
| 334 |
+
"loss": 0.2602,
|
| 335 |
+
"step": 300
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.34,
|
| 339 |
+
"learning_rate": 1.2815864022662889e-05,
|
| 340 |
+
"loss": 0.2192,
|
| 341 |
+
"step": 306
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.38,
|
| 345 |
+
"learning_rate": 1.1932011331444758e-05,
|
| 346 |
+
"loss": 0.2306,
|
| 347 |
+
"step": 312
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.43,
|
| 351 |
+
"learning_rate": 1.1048158640226628e-05,
|
| 352 |
+
"loss": 0.1996,
|
| 353 |
+
"step": 318
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.47,
|
| 357 |
+
"learning_rate": 1.0164305949008498e-05,
|
| 358 |
+
"loss": 0.2363,
|
| 359 |
+
"step": 324
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.52,
|
| 363 |
+
"learning_rate": 9.280453257790368e-06,
|
| 364 |
+
"loss": 0.2426,
|
| 365 |
+
"step": 330
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.56,
|
| 369 |
+
"learning_rate": 8.396600566572238e-06,
|
| 370 |
+
"loss": 0.2642,
|
| 371 |
+
"step": 336
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.61,
|
| 375 |
+
"learning_rate": 7.512747875354107e-06,
|
| 376 |
+
"loss": 0.2303,
|
| 377 |
+
"step": 342
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.66,
|
| 381 |
+
"learning_rate": 6.628895184135977e-06,
|
| 382 |
+
"loss": 0.26,
|
| 383 |
+
"step": 348
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.7,
|
| 387 |
+
"learning_rate": 5.745042492917846e-06,
|
| 388 |
+
"loss": 0.2661,
|
| 389 |
+
"step": 354
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.75,
|
| 393 |
+
"learning_rate": 4.861189801699716e-06,
|
| 394 |
+
"loss": 0.2323,
|
| 395 |
+
"step": 360
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.79,
|
| 399 |
+
"learning_rate": 3.977337110481587e-06,
|
| 400 |
+
"loss": 0.2782,
|
| 401 |
+
"step": 366
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.84,
|
| 405 |
+
"learning_rate": 3.093484419263456e-06,
|
| 406 |
+
"loss": 0.2154,
|
| 407 |
+
"step": 372
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.89,
|
| 411 |
+
"learning_rate": 2.209631728045326e-06,
|
| 412 |
+
"loss": 0.1829,
|
| 413 |
+
"step": 378
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.93,
|
| 417 |
+
"learning_rate": 1.3257790368271953e-06,
|
| 418 |
+
"loss": 0.2378,
|
| 419 |
+
"step": 384
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.98,
|
| 423 |
+
"learning_rate": 4.419263456090652e-07,
|
| 424 |
+
"loss": 0.2288,
|
| 425 |
+
"step": 390
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.0,
|
| 429 |
+
"eval_accuracy": 1.0,
|
| 430 |
+
"eval_auc": 1.0,
|
| 431 |
+
"eval_f1": 1.0,
|
| 432 |
+
"eval_loss": 0.11768843978643417,
|
| 433 |
+
"eval_precision": 1.0,
|
| 434 |
+
"eval_recall": 1.0,
|
| 435 |
+
"eval_runtime": 32.1685,
|
| 436 |
+
"eval_samples_per_second": 8.145,
|
| 437 |
+
"eval_steps_per_second": 0.528,
|
| 438 |
+
"step": 393
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 6,
|
| 442 |
+
"max_steps": 393,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 3,
|
| 445 |
+
"save_steps": 500,
|
| 446 |
+
"total_flos": 6.650928353599488e+16,
|
| 447 |
+
"train_batch_size": 8,
|
| 448 |
+
"trial_name": null,
|
| 449 |
+
"trial_params": null
|
| 450 |
+
}
|
checkpoint-393/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce7418b5729ab89bdc6a672aa750faebc93f9292d20b3a245f7e02090088a10b
|
| 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": "redd",
|
| 25 |
+
"1": "short"
|
| 26 |
+
},
|
| 27 |
+
"label2id": {
|
| 28 |
+
"redd": 0,
|
| 29 |
+
"short": 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 sha256:7671d2117bb0bc04d47b807d555b20a2d240b2307b29ca83e61c6fabd3dea711
|
| 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:ce7418b5729ab89bdc6a672aa750faebc93f9292d20b3a245f7e02090088a10b
|
| 3 |
+
size 4728
|
training_params.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "Naterea/autotrain-data-YT_REDD_V2.1_BASE",
|
| 3 |
+
"model": "microsoft/resnet-50",
|
| 4 |
+
"lr": 5.2e-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/YT_REDD_V2.1_BASE-0",
|
| 24 |
+
"evaluation_strategy": "epoch",
|
| 25 |
+
"image_column": "autotrain_image",
|
| 26 |
+
"target_column": "autotrain_label",
|
| 27 |
+
"log": "none"
|
| 28 |
+
}
|