Upload folder using huggingface_hub
Browse files- README.md +31 -0
- checkpoint-1868/config.json +33 -0
- checkpoint-1868/model.safetensors +3 -0
- checkpoint-1868/optimizer.pt +3 -0
- checkpoint-1868/rng_state.pth +3 -0
- checkpoint-1868/scheduler.pt +3 -0
- checkpoint-1868/trainer_state.json +573 -0
- checkpoint-1868/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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
tags:
|
| 4 |
+
- autotrain
|
| 5 |
+
- image-classification
|
| 6 |
+
base_model: google/vit-base-patch16-224
|
| 7 |
+
widget:
|
| 8 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 9 |
+
example_title: Tiger
|
| 10 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
|
| 11 |
+
example_title: Teapot
|
| 12 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
|
| 13 |
+
example_title: Palace
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# Model Trained Using AutoTrain
|
| 17 |
+
|
| 18 |
+
- Problem type: Image Classification
|
| 19 |
+
|
| 20 |
+
## Validation Metrics
|
| 21 |
+
loss: 0.2235843539237976
|
| 22 |
+
|
| 23 |
+
f1: 0.0
|
| 24 |
+
|
| 25 |
+
precision: 0.0
|
| 26 |
+
|
| 27 |
+
recall: 0.0
|
| 28 |
+
|
| 29 |
+
auc: 0.8326772729757805
|
| 30 |
+
|
| 31 |
+
accuracy: 0.9325481798715204
|
checkpoint-1868/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": "not_nsfw",
|
| 14 |
+
"1": "nsfw"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"not_nsfw": 0,
|
| 21 |
+
"nsfw": 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": "4.42.2"
|
| 33 |
+
}
|
checkpoint-1868/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82ae3ca91b166969980d149b72c71a04a3f1f0c7572e7e8152e3c918afa4c8dc
|
| 3 |
+
size 343223968
|
checkpoint-1868/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f21f9da4295e212647a6fb4ca186146b2193f85acf4b48e143d8149d785499b0
|
| 3 |
+
size 686568890
|
checkpoint-1868/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f794d1819e82e0c5a35cb84196ca59760b58c2517fc2c450e8f037c1655f63b4
|
| 3 |
+
size 14244
|
checkpoint-1868/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7963e7da6570363a25c1d4d4972ef5fd9c50e166148e7e5839b507ae06bab2a8
|
| 3 |
+
size 1064
|
checkpoint-1868/trainer_state.json
ADDED
|
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2235843539237976,
|
| 3 |
+
"best_model_checkpoint": "nsfw-images-2/checkpoint-1868",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1868,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013383297644539615,
|
| 13 |
+
"grad_norm": 18.170637130737305,
|
| 14 |
+
"learning_rate": 1.2312633832976446e-05,
|
| 15 |
+
"loss": 0.7179,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02676659528907923,
|
| 20 |
+
"grad_norm": 3.0997555255889893,
|
| 21 |
+
"learning_rate": 2.569593147751606e-05,
|
| 22 |
+
"loss": 0.3338,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04014989293361884,
|
| 27 |
+
"grad_norm": 31.291412353515625,
|
| 28 |
+
"learning_rate": 3.9079229122055675e-05,
|
| 29 |
+
"loss": 0.3848,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05353319057815846,
|
| 34 |
+
"grad_norm": 0.03622590750455856,
|
| 35 |
+
"learning_rate": 5.246252676659529e-05,
|
| 36 |
+
"loss": 0.0596,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06691648822269808,
|
| 41 |
+
"grad_norm": 26.821062088012695,
|
| 42 |
+
"learning_rate": 6.58458244111349e-05,
|
| 43 |
+
"loss": 0.3471,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08029978586723768,
|
| 48 |
+
"grad_norm": 0.011622205376625061,
|
| 49 |
+
"learning_rate": 7.922912205567452e-05,
|
| 50 |
+
"loss": 0.1036,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.0936830835117773,
|
| 55 |
+
"grad_norm": 0.07030396908521652,
|
| 56 |
+
"learning_rate": 9.261241970021414e-05,
|
| 57 |
+
"loss": 0.0683,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10706638115631692,
|
| 62 |
+
"grad_norm": 0.1393502801656723,
|
| 63 |
+
"learning_rate": 0.00010599571734475374,
|
| 64 |
+
"loss": 0.3868,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.12044967880085652,
|
| 69 |
+
"grad_norm": 0.019323009997606277,
|
| 70 |
+
"learning_rate": 0.00011937901498929336,
|
| 71 |
+
"loss": 0.5266,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.13383297644539616,
|
| 76 |
+
"grad_norm": 0.02416042983531952,
|
| 77 |
+
"learning_rate": 0.000132762312633833,
|
| 78 |
+
"loss": 0.2695,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14721627408993576,
|
| 83 |
+
"grad_norm": 2.2118706703186035,
|
| 84 |
+
"learning_rate": 0.0001461456102783726,
|
| 85 |
+
"loss": 0.4989,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.16059957173447537,
|
| 90 |
+
"grad_norm": 11.72065258026123,
|
| 91 |
+
"learning_rate": 0.0001595289079229122,
|
| 92 |
+
"loss": 0.3731,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.173982869379015,
|
| 97 |
+
"grad_norm": 0.0027222177013754845,
|
| 98 |
+
"learning_rate": 0.00017291220556745181,
|
| 99 |
+
"loss": 0.1109,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1873661670235546,
|
| 104 |
+
"grad_norm": 0.0008230574312619865,
|
| 105 |
+
"learning_rate": 0.00018629550321199142,
|
| 106 |
+
"loss": 0.2094,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.2007494646680942,
|
| 111 |
+
"grad_norm": 0.036911237984895706,
|
| 112 |
+
"learning_rate": 0.00019967880085653106,
|
| 113 |
+
"loss": 0.6709,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.21413276231263384,
|
| 118 |
+
"grad_norm": 20.274892807006836,
|
| 119 |
+
"learning_rate": 0.00021306209850107066,
|
| 120 |
+
"loss": 0.5297,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.22751605995717344,
|
| 125 |
+
"grad_norm": 0.04864942654967308,
|
| 126 |
+
"learning_rate": 0.00022644539614561027,
|
| 127 |
+
"loss": 0.1467,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.24089935760171305,
|
| 132 |
+
"grad_norm": 0.12074282765388489,
|
| 133 |
+
"learning_rate": 0.0002398286937901499,
|
| 134 |
+
"loss": 0.6298,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.25428265524625265,
|
| 139 |
+
"grad_norm": 0.11845938861370087,
|
| 140 |
+
"learning_rate": 0.00025321199143468954,
|
| 141 |
+
"loss": 0.257,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2676659528907923,
|
| 146 |
+
"grad_norm": 0.09819821268320084,
|
| 147 |
+
"learning_rate": 0.00026659528907922915,
|
| 148 |
+
"loss": 0.8714,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2810492505353319,
|
| 153 |
+
"grad_norm": 0.09790199995040894,
|
| 154 |
+
"learning_rate": 0.00027997858672376875,
|
| 155 |
+
"loss": 0.2357,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.2944325481798715,
|
| 160 |
+
"grad_norm": 0.5837295055389404,
|
| 161 |
+
"learning_rate": 0.00029336188436830836,
|
| 162 |
+
"loss": 0.7943,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3078158458244111,
|
| 167 |
+
"grad_norm": 0.14801590144634247,
|
| 168 |
+
"learning_rate": 0.00030674518201284797,
|
| 169 |
+
"loss": 0.4615,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.32119914346895073,
|
| 174 |
+
"grad_norm": 0.05935389921069145,
|
| 175 |
+
"learning_rate": 0.0003201284796573876,
|
| 176 |
+
"loss": 0.2401,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.33458244111349034,
|
| 181 |
+
"grad_norm": 12.694086074829102,
|
| 182 |
+
"learning_rate": 0.00033297644539614566,
|
| 183 |
+
"loss": 0.6572,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.34796573875803,
|
| 188 |
+
"grad_norm": 0.05311077833175659,
|
| 189 |
+
"learning_rate": 0.00034635974304068526,
|
| 190 |
+
"loss": 0.3569,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3613490364025696,
|
| 195 |
+
"grad_norm": 0.03182295709848404,
|
| 196 |
+
"learning_rate": 0.0003597430406852248,
|
| 197 |
+
"loss": 0.1498,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3747323340471092,
|
| 202 |
+
"grad_norm": 0.33807849884033203,
|
| 203 |
+
"learning_rate": 0.0003731263383297644,
|
| 204 |
+
"loss": 0.3766,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3881156316916488,
|
| 209 |
+
"grad_norm": 0.08421733975410461,
|
| 210 |
+
"learning_rate": 0.00038650963597430403,
|
| 211 |
+
"loss": 0.2979,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4014989293361884,
|
| 216 |
+
"grad_norm": 0.01755744405090809,
|
| 217 |
+
"learning_rate": 0.0003998929336188437,
|
| 218 |
+
"loss": 0.0031,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4148822269807281,
|
| 223 |
+
"grad_norm": 0.21543407440185547,
|
| 224 |
+
"learning_rate": 0.0004132762312633833,
|
| 225 |
+
"loss": 0.4799,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4282655246252677,
|
| 230 |
+
"grad_norm": 0.18580827116966248,
|
| 231 |
+
"learning_rate": 0.0004266595289079229,
|
| 232 |
+
"loss": 0.3885,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4416488222698073,
|
| 237 |
+
"grad_norm": 11.58962631225586,
|
| 238 |
+
"learning_rate": 0.0004400428265524625,
|
| 239 |
+
"loss": 0.3268,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4550321199143469,
|
| 244 |
+
"grad_norm": 0.0360148549079895,
|
| 245 |
+
"learning_rate": 0.0004534261241970021,
|
| 246 |
+
"loss": 0.3201,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4684154175588865,
|
| 251 |
+
"grad_norm": 0.09959446638822556,
|
| 252 |
+
"learning_rate": 0.0004668094218415418,
|
| 253 |
+
"loss": 0.2712,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4817987152034261,
|
| 258 |
+
"grad_norm": 0.25127506256103516,
|
| 259 |
+
"learning_rate": 0.0004801927194860814,
|
| 260 |
+
"loss": 0.3106,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.49518201284796576,
|
| 265 |
+
"grad_norm": 11.287735939025879,
|
| 266 |
+
"learning_rate": 0.000493576017130621,
|
| 267 |
+
"loss": 0.2296,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5085653104925053,
|
| 272 |
+
"grad_norm": 10.859394073486328,
|
| 273 |
+
"learning_rate": 0.0004992267428027599,
|
| 274 |
+
"loss": 0.3712,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.521948608137045,
|
| 279 |
+
"grad_norm": 0.18585732579231262,
|
| 280 |
+
"learning_rate": 0.0004977397097311444,
|
| 281 |
+
"loss": 0.3561,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5353319057815846,
|
| 286 |
+
"grad_norm": 14.576325416564941,
|
| 287 |
+
"learning_rate": 0.000496252676659529,
|
| 288 |
+
"loss": 0.3283,
|
| 289 |
+
"step": 1000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5487152034261242,
|
| 293 |
+
"grad_norm": 0.00898987427353859,
|
| 294 |
+
"learning_rate": 0.0004947656435879134,
|
| 295 |
+
"loss": 0.0033,
|
| 296 |
+
"step": 1025
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5620985010706638,
|
| 300 |
+
"grad_norm": 0.27176257967948914,
|
| 301 |
+
"learning_rate": 0.0004932786105162979,
|
| 302 |
+
"loss": 0.5933,
|
| 303 |
+
"step": 1050
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5754817987152034,
|
| 307 |
+
"grad_norm": 0.012289056554436684,
|
| 308 |
+
"learning_rate": 0.0004917915774446823,
|
| 309 |
+
"loss": 0.1723,
|
| 310 |
+
"step": 1075
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.588865096359743,
|
| 314 |
+
"grad_norm": 0.050152458250522614,
|
| 315 |
+
"learning_rate": 0.0004903045443730669,
|
| 316 |
+
"loss": 0.5719,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6022483940042827,
|
| 321 |
+
"grad_norm": 0.6666317582130432,
|
| 322 |
+
"learning_rate": 0.0004888175113014514,
|
| 323 |
+
"loss": 0.7938,
|
| 324 |
+
"step": 1125
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6156316916488223,
|
| 328 |
+
"grad_norm": 0.35938775539398193,
|
| 329 |
+
"learning_rate": 0.00048733047822983584,
|
| 330 |
+
"loss": 0.4964,
|
| 331 |
+
"step": 1150
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6290149892933619,
|
| 335 |
+
"grad_norm": 0.08501864224672318,
|
| 336 |
+
"learning_rate": 0.0004858434451582203,
|
| 337 |
+
"loss": 0.2737,
|
| 338 |
+
"step": 1175
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6423982869379015,
|
| 342 |
+
"grad_norm": 0.02361874282360077,
|
| 343 |
+
"learning_rate": 0.0004843564120866048,
|
| 344 |
+
"loss": 0.15,
|
| 345 |
+
"step": 1200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6557815845824411,
|
| 349 |
+
"grad_norm": 0.05745585262775421,
|
| 350 |
+
"learning_rate": 0.0004828693790149893,
|
| 351 |
+
"loss": 0.2676,
|
| 352 |
+
"step": 1225
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6691648822269807,
|
| 356 |
+
"grad_norm": 0.15592187643051147,
|
| 357 |
+
"learning_rate": 0.00048138234594337375,
|
| 358 |
+
"loss": 0.3195,
|
| 359 |
+
"step": 1250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6825481798715204,
|
| 363 |
+
"grad_norm": 0.01977529190480709,
|
| 364 |
+
"learning_rate": 0.0004798953128717583,
|
| 365 |
+
"loss": 0.1439,
|
| 366 |
+
"step": 1275
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.69593147751606,
|
| 370 |
+
"grad_norm": 11.418144226074219,
|
| 371 |
+
"learning_rate": 0.0004784082798001428,
|
| 372 |
+
"loss": 0.2578,
|
| 373 |
+
"step": 1300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7093147751605996,
|
| 377 |
+
"grad_norm": 0.12220004945993423,
|
| 378 |
+
"learning_rate": 0.00047692124672852725,
|
| 379 |
+
"loss": 0.2181,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7226980728051392,
|
| 384 |
+
"grad_norm": 0.2515058219432831,
|
| 385 |
+
"learning_rate": 0.00047543421365691177,
|
| 386 |
+
"loss": 0.4207,
|
| 387 |
+
"step": 1350
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7360813704496788,
|
| 391 |
+
"grad_norm": 10.930126190185547,
|
| 392 |
+
"learning_rate": 0.00047394718058529624,
|
| 393 |
+
"loss": 0.3217,
|
| 394 |
+
"step": 1375
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7494646680942184,
|
| 398 |
+
"grad_norm": 0.1796221137046814,
|
| 399 |
+
"learning_rate": 0.0004724601475136807,
|
| 400 |
+
"loss": 0.4147,
|
| 401 |
+
"step": 1400
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.762847965738758,
|
| 405 |
+
"grad_norm": 0.12057535350322723,
|
| 406 |
+
"learning_rate": 0.0004709731144420652,
|
| 407 |
+
"loss": 0.2845,
|
| 408 |
+
"step": 1425
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7762312633832976,
|
| 412 |
+
"grad_norm": 0.6278265714645386,
|
| 413 |
+
"learning_rate": 0.0004694860813704497,
|
| 414 |
+
"loss": 0.6357,
|
| 415 |
+
"step": 1450
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7896145610278372,
|
| 419 |
+
"grad_norm": 0.08220059424638748,
|
| 420 |
+
"learning_rate": 0.00046799904829883415,
|
| 421 |
+
"loss": 0.4283,
|
| 422 |
+
"step": 1475
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8029978586723768,
|
| 426 |
+
"grad_norm": 10.042654991149902,
|
| 427 |
+
"learning_rate": 0.00046651201522721866,
|
| 428 |
+
"loss": 0.3957,
|
| 429 |
+
"step": 1500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8163811563169164,
|
| 433 |
+
"grad_norm": 0.20416533946990967,
|
| 434 |
+
"learning_rate": 0.00046502498215560313,
|
| 435 |
+
"loss": 0.4242,
|
| 436 |
+
"step": 1525
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8297644539614561,
|
| 440 |
+
"grad_norm": 0.12127134948968887,
|
| 441 |
+
"learning_rate": 0.00046353794908398765,
|
| 442 |
+
"loss": 0.1901,
|
| 443 |
+
"step": 1550
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8431477516059958,
|
| 447 |
+
"grad_norm": 0.07789531350135803,
|
| 448 |
+
"learning_rate": 0.00046205091601237216,
|
| 449 |
+
"loss": 0.2266,
|
| 450 |
+
"step": 1575
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.8565310492505354,
|
| 454 |
+
"grad_norm": 0.03442813456058502,
|
| 455 |
+
"learning_rate": 0.00046056388294075663,
|
| 456 |
+
"loss": 0.2767,
|
| 457 |
+
"step": 1600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.869914346895075,
|
| 461 |
+
"grad_norm": 0.2261192798614502,
|
| 462 |
+
"learning_rate": 0.0004590768498691411,
|
| 463 |
+
"loss": 0.3227,
|
| 464 |
+
"step": 1625
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8832976445396146,
|
| 468 |
+
"grad_norm": 0.05203871801495552,
|
| 469 |
+
"learning_rate": 0.0004575898167975256,
|
| 470 |
+
"loss": 0.1059,
|
| 471 |
+
"step": 1650
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8966809421841542,
|
| 475 |
+
"grad_norm": 0.17587050795555115,
|
| 476 |
+
"learning_rate": 0.0004561027837259101,
|
| 477 |
+
"loss": 0.4627,
|
| 478 |
+
"step": 1675
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9100642398286938,
|
| 482 |
+
"grad_norm": 0.04208080843091011,
|
| 483 |
+
"learning_rate": 0.00045461575065429454,
|
| 484 |
+
"loss": 0.1095,
|
| 485 |
+
"step": 1700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9234475374732334,
|
| 489 |
+
"grad_norm": 0.07704867422580719,
|
| 490 |
+
"learning_rate": 0.00045312871758267906,
|
| 491 |
+
"loss": 0.2484,
|
| 492 |
+
"step": 1725
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.936830835117773,
|
| 496 |
+
"grad_norm": 9.084434509277344,
|
| 497 |
+
"learning_rate": 0.0004516416845110635,
|
| 498 |
+
"loss": 0.4368,
|
| 499 |
+
"step": 1750
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.9502141327623126,
|
| 503 |
+
"grad_norm": 0.09450817853212357,
|
| 504 |
+
"learning_rate": 0.000450154651439448,
|
| 505 |
+
"loss": 0.2326,
|
| 506 |
+
"step": 1775
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9635974304068522,
|
| 510 |
+
"grad_norm": 0.27564939856529236,
|
| 511 |
+
"learning_rate": 0.0004486676183678325,
|
| 512 |
+
"loss": 0.5406,
|
| 513 |
+
"step": 1800
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9769807280513919,
|
| 517 |
+
"grad_norm": 0.1096988320350647,
|
| 518 |
+
"learning_rate": 0.000447180585296217,
|
| 519 |
+
"loss": 0.2194,
|
| 520 |
+
"step": 1825
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9903640256959315,
|
| 524 |
+
"grad_norm": 0.06793688237667084,
|
| 525 |
+
"learning_rate": 0.0004456935522246015,
|
| 526 |
+
"loss": 0.3206,
|
| 527 |
+
"step": 1850
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.0,
|
| 531 |
+
"eval_accuracy": 0.9325481798715204,
|
| 532 |
+
"eval_auc": 0.8326772729757805,
|
| 533 |
+
"eval_f1": 0.0,
|
| 534 |
+
"eval_loss": 0.2235843539237976,
|
| 535 |
+
"eval_precision": 0.0,
|
| 536 |
+
"eval_recall": 0.0,
|
| 537 |
+
"eval_runtime": 12.9282,
|
| 538 |
+
"eval_samples_per_second": 72.245,
|
| 539 |
+
"eval_steps_per_second": 18.1,
|
| 540 |
+
"step": 1868
|
| 541 |
+
}
|
| 542 |
+
],
|
| 543 |
+
"logging_steps": 25,
|
| 544 |
+
"max_steps": 9340,
|
| 545 |
+
"num_input_tokens_seen": 0,
|
| 546 |
+
"num_train_epochs": 5,
|
| 547 |
+
"save_steps": 500,
|
| 548 |
+
"stateful_callbacks": {
|
| 549 |
+
"EarlyStoppingCallback": {
|
| 550 |
+
"args": {
|
| 551 |
+
"early_stopping_patience": 5,
|
| 552 |
+
"early_stopping_threshold": 0.01
|
| 553 |
+
},
|
| 554 |
+
"attributes": {
|
| 555 |
+
"early_stopping_patience_counter": 0
|
| 556 |
+
}
|
| 557 |
+
},
|
| 558 |
+
"TrainerControl": {
|
| 559 |
+
"args": {
|
| 560 |
+
"should_epoch_stop": false,
|
| 561 |
+
"should_evaluate": false,
|
| 562 |
+
"should_log": false,
|
| 563 |
+
"should_save": true,
|
| 564 |
+
"should_training_stop": false
|
| 565 |
+
},
|
| 566 |
+
"attributes": {}
|
| 567 |
+
}
|
| 568 |
+
},
|
| 569 |
+
"total_flos": 2.894325812105011e+17,
|
| 570 |
+
"train_batch_size": 2,
|
| 571 |
+
"trial_name": null,
|
| 572 |
+
"trial_params": null
|
| 573 |
+
}
|
checkpoint-1868/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0801e673065b9e4a3d65e6e88bc40447e1f7ab750aad36d4123875acc49b867a
|
| 3 |
+
size 5112
|
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": "not_nsfw",
|
| 14 |
+
"1": "nsfw"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"not_nsfw": 0,
|
| 21 |
+
"nsfw": 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": "4.42.2"
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82ae3ca91b166969980d149b72c71a04a3f1f0c7572e7e8152e3c918afa4c8dc
|
| 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 sha256:0801e673065b9e4a3d65e6e88bc40447e1f7ab750aad36d4123875acc49b867a
|
| 3 |
+
size 5112
|
training_params.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"data_path": "nsfw-images-2/autotrain-data",
|
| 3 |
+
"model": "google/vit-base-patch16-224",
|
| 4 |
+
"username": "haiefff",
|
| 5 |
+
"lr": 0.0005,
|
| 6 |
+
"epochs": 5,
|
| 7 |
+
"batch_size": 2,
|
| 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": "nsfw-images-2",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "fp16",
|
| 21 |
+
"save_total_limit": 1,
|
| 22 |
+
"push_to_hub": true,
|
| 23 |
+
"eval_strategy": "epoch",
|
| 24 |
+
"image_column": "autotrain_image",
|
| 25 |
+
"target_column": "autotrain_label",
|
| 26 |
+
"log": "none",
|
| 27 |
+
"early_stopping_patience": 5,
|
| 28 |
+
"early_stopping_threshold": 0.01
|
| 29 |
+
}
|