Hugging Face's logo

perrytheplatypus
/
falconsai-finetuned-nsfw-detect

Image Classification
TensorBoard
Safetensors
vit
Trained with AutoTrain
Model card Files Metrics Community
perrytheplatypus commited on
Commit
7b3bc7c
·
verified ·
1 Parent(s): 658e795

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. README.md +31 -0
  2. checkpoint-52/config.json +33 -0
  3. checkpoint-52/model.safetensors +3 -0
  4. checkpoint-52/optimizer.pt +3 -0
  5. checkpoint-52/rng_state.pth +3 -0
  6. checkpoint-52/scheduler.pt +3 -0
  7. checkpoint-52/trainer_state.json +575 -0
  8. checkpoint-52/training_args.bin +3 -0
  9. config.json +33 -0
  10. model.safetensors +3 -0
  11. preprocessor_config.json +22 -0
  12. runs/Sep07_07-37-24_r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14/events.out.tfevents.1725694646.r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14.142.0 +2 -2
  13. runs/Sep07_07-37-24_r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14/events.out.tfevents.1725695145.r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14.142.1 +3 -0
  14. training_args.bin +3 -0
  15. training_params.json +29 -0
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - autotrain
5
+ - image-classification
6
+ base_model: Falconsai/nsfw_image_detection
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: 0.0005376620101742446
22
+
23
+ f1: 1.0
24
+
25
+ precision: 1.0
26
+
27
+ recall: 1.0
28
+
29
+ auc: 1.0
30
+
31
+ accuracy: 1.0
checkpoint-52/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Falconsai/nsfw_image_detection",
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": "normal",
14
+ "1": "nsfw"
15
+ },
16
+ "image_size": 224,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "normal": 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": "4.44.2"
33
+ }
checkpoint-52/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057f1b3035c9323421300577ac5c2339b7f68be8ee7ccaee6045ec40999777d9
3
+ size 343223968
checkpoint-52/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc9105115e80bf28729ebf94e9d73e83f5a1fcebe44f396dc0605b191b6216f
3
+ size 686563258
checkpoint-52/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2454649601262c2bb5ee4a3eb086fca8a9778ea14245b331bcbc61c5aac9f7
3
+ size 13990
checkpoint-52/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913879b74bb1cd75923f9fb8043410e8eeeefec738fcd339516157f60ede4c92
3
+ size 1064
checkpoint-52/trainer_state.json ADDED
@@ -0,0 +1,575 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0005376620101742446,
3
+ "best_model_checkpoint": "autotrain-okqe6-pd7eh/checkpoint-52",
4
+ "epoch": 13.0,
5
+ "eval_steps": 500,
6
+ "global_step": 52,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 14.21432876586914,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 1.7194,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 26.781686782836914,
21
+ "learning_rate": 5e-06,
22
+ "loss": 1.6298,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 11.112658500671387,
28
+ "learning_rate": 7.5e-06,
29
+ "loss": 1.5897,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 27.626598358154297,
35
+ "learning_rate": 1e-05,
36
+ "loss": 5.1747,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "eval_accuracy": 0.5714285714285714,
42
+ "eval_auc": 0.7619047619047619,
43
+ "eval_f1": 0.625,
44
+ "eval_loss": 2.144031047821045,
45
+ "eval_precision": 0.9090909090909091,
46
+ "eval_recall": 0.47619047619047616,
47
+ "eval_runtime": 9.1146,
48
+ "eval_samples_per_second": 3.072,
49
+ "eval_steps_per_second": 0.219,
50
+ "step": 4
51
+ },
52
+ {
53
+ "epoch": 1.25,
54
+ "grad_norm": 15.852094650268555,
55
+ "learning_rate": 1.25e-05,
56
+ "loss": 0.758,
57
+ "step": 5
58
+ },
59
+ {
60
+ "epoch": 1.5,
61
+ "grad_norm": 12.443609237670898,
62
+ "learning_rate": 1.5e-05,
63
+ "loss": 2.5724,
64
+ "step": 6
65
+ },
66
+ {
67
+ "epoch": 1.75,
68
+ "grad_norm": 10.946976661682129,
69
+ "learning_rate": 1.75e-05,
70
+ "loss": 0.4912,
71
+ "step": 7
72
+ },
73
+ {
74
+ "epoch": 2.0,
75
+ "grad_norm": 14.185081481933594,
76
+ "learning_rate": 2e-05,
77
+ "loss": 1.245,
78
+ "step": 8
79
+ },
80
+ {
81
+ "epoch": 2.0,
82
+ "eval_accuracy": 0.6428571428571429,
83
+ "eval_auc": 0.8095238095238095,
84
+ "eval_f1": 0.7058823529411765,
85
+ "eval_loss": 1.4039461612701416,
86
+ "eval_precision": 0.9230769230769231,
87
+ "eval_recall": 0.5714285714285714,
88
+ "eval_runtime": 8.4655,
89
+ "eval_samples_per_second": 3.308,
90
+ "eval_steps_per_second": 0.236,
91
+ "step": 8
92
+ },
93
+ {
94
+ "epoch": 2.25,
95
+ "grad_norm": 14.650551795959473,
96
+ "learning_rate": 2.25e-05,
97
+ "loss": 0.7346,
98
+ "step": 9
99
+ },
100
+ {
101
+ "epoch": 2.5,
102
+ "grad_norm": 10.59030818939209,
103
+ "learning_rate": 2.5e-05,
104
+ "loss": 1.124,
105
+ "step": 10
106
+ },
107
+ {
108
+ "epoch": 2.75,
109
+ "grad_norm": 15.367939949035645,
110
+ "learning_rate": 2.7500000000000004e-05,
111
+ "loss": 2.1564,
112
+ "step": 11
113
+ },
114
+ {
115
+ "epoch": 3.0,
116
+ "grad_norm": 2.77498459815979,
117
+ "learning_rate": 3e-05,
118
+ "loss": 0.0703,
119
+ "step": 12
120
+ },
121
+ {
122
+ "epoch": 3.0,
123
+ "eval_accuracy": 0.75,
124
+ "eval_auc": 0.9047619047619048,
125
+ "eval_f1": 0.8108108108108109,
126
+ "eval_loss": 0.6543990969657898,
127
+ "eval_precision": 0.9375,
128
+ "eval_recall": 0.7142857142857143,
129
+ "eval_runtime": 8.6388,
130
+ "eval_samples_per_second": 3.241,
131
+ "eval_steps_per_second": 0.232,
132
+ "step": 12
133
+ },
134
+ {
135
+ "epoch": 3.25,
136
+ "grad_norm": 19.424549102783203,
137
+ "learning_rate": 3.2500000000000004e-05,
138
+ "loss": 1.2086,
139
+ "step": 13
140
+ },
141
+ {
142
+ "epoch": 3.5,
143
+ "grad_norm": 15.029265403747559,
144
+ "learning_rate": 3.5e-05,
145
+ "loss": 1.5127,
146
+ "step": 14
147
+ },
148
+ {
149
+ "epoch": 3.75,
150
+ "grad_norm": 6.021083354949951,
151
+ "learning_rate": 3.7500000000000003e-05,
152
+ "loss": 0.1327,
153
+ "step": 15
154
+ },
155
+ {
156
+ "epoch": 4.0,
157
+ "grad_norm": 23.40821647644043,
158
+ "learning_rate": 4e-05,
159
+ "loss": 1.3535,
160
+ "step": 16
161
+ },
162
+ {
163
+ "epoch": 4.0,
164
+ "eval_accuracy": 0.8928571428571429,
165
+ "eval_auc": 0.9795918367346939,
166
+ "eval_f1": 0.9230769230769231,
167
+ "eval_loss": 0.28167834877967834,
168
+ "eval_precision": 1.0,
169
+ "eval_recall": 0.8571428571428571,
170
+ "eval_runtime": 9.1138,
171
+ "eval_samples_per_second": 3.072,
172
+ "eval_steps_per_second": 0.219,
173
+ "step": 16
174
+ },
175
+ {
176
+ "epoch": 4.25,
177
+ "grad_norm": 5.730878829956055,
178
+ "learning_rate": 4.25e-05,
179
+ "loss": 0.3334,
180
+ "step": 17
181
+ },
182
+ {
183
+ "epoch": 4.5,
184
+ "grad_norm": 13.562226295471191,
185
+ "learning_rate": 4.5e-05,
186
+ "loss": 0.4879,
187
+ "step": 18
188
+ },
189
+ {
190
+ "epoch": 4.75,
191
+ "grad_norm": 15.55147647857666,
192
+ "learning_rate": 4.75e-05,
193
+ "loss": 0.6376,
194
+ "step": 19
195
+ },
196
+ {
197
+ "epoch": 5.0,
198
+ "grad_norm": 4.316409111022949,
199
+ "learning_rate": 5e-05,
200
+ "loss": 0.143,
201
+ "step": 20
202
+ },
203
+ {
204
+ "epoch": 5.0,
205
+ "eval_accuracy": 1.0,
206
+ "eval_auc": 1.0,
207
+ "eval_f1": 1.0,
208
+ "eval_loss": 0.10469154268503189,
209
+ "eval_precision": 1.0,
210
+ "eval_recall": 1.0,
211
+ "eval_runtime": 8.9428,
212
+ "eval_samples_per_second": 3.131,
213
+ "eval_steps_per_second": 0.224,
214
+ "step": 20
215
+ },
216
+ {
217
+ "epoch": 5.25,
218
+ "grad_norm": 4.850322246551514,
219
+ "learning_rate": 4.972222222222223e-05,
220
+ "loss": 0.1503,
221
+ "step": 21
222
+ },
223
+ {
224
+ "epoch": 5.5,
225
+ "grad_norm": 7.610826015472412,
226
+ "learning_rate": 4.9444444444444446e-05,
227
+ "loss": 0.3183,
228
+ "step": 22
229
+ },
230
+ {
231
+ "epoch": 5.75,
232
+ "grad_norm": 9.175180435180664,
233
+ "learning_rate": 4.9166666666666665e-05,
234
+ "loss": 0.6048,
235
+ "step": 23
236
+ },
237
+ {
238
+ "epoch": 6.0,
239
+ "grad_norm": 5.765699863433838,
240
+ "learning_rate": 4.888888888888889e-05,
241
+ "loss": 0.0806,
242
+ "step": 24
243
+ },
244
+ {
245
+ "epoch": 6.0,
246
+ "eval_accuracy": 1.0,
247
+ "eval_auc": 1.0,
248
+ "eval_f1": 1.0,
249
+ "eval_loss": 0.0491504967212677,
250
+ "eval_precision": 1.0,
251
+ "eval_recall": 1.0,
252
+ "eval_runtime": 9.0668,
253
+ "eval_samples_per_second": 3.088,
254
+ "eval_steps_per_second": 0.221,
255
+ "step": 24
256
+ },
257
+ {
258
+ "epoch": 6.25,
259
+ "grad_norm": 10.618638038635254,
260
+ "learning_rate": 4.8611111111111115e-05,
261
+ "loss": 0.2229,
262
+ "step": 25
263
+ },
264
+ {
265
+ "epoch": 6.5,
266
+ "grad_norm": 2.024526596069336,
267
+ "learning_rate": 4.8333333333333334e-05,
268
+ "loss": 0.0809,
269
+ "step": 26
270
+ },
271
+ {
272
+ "epoch": 6.75,
273
+ "grad_norm": 3.5910582542419434,
274
+ "learning_rate": 4.805555555555556e-05,
275
+ "loss": 0.2059,
276
+ "step": 27
277
+ },
278
+ {
279
+ "epoch": 7.0,
280
+ "grad_norm": 0.8639962077140808,
281
+ "learning_rate": 4.7777777777777784e-05,
282
+ "loss": 0.0232,
283
+ "step": 28
284
+ },
285
+ {
286
+ "epoch": 7.0,
287
+ "eval_accuracy": 1.0,
288
+ "eval_auc": 1.0,
289
+ "eval_f1": 1.0,
290
+ "eval_loss": 0.033924441784620285,
291
+ "eval_precision": 1.0,
292
+ "eval_recall": 1.0,
293
+ "eval_runtime": 8.9013,
294
+ "eval_samples_per_second": 3.146,
295
+ "eval_steps_per_second": 0.225,
296
+ "step": 28
297
+ },
298
+ {
299
+ "epoch": 7.25,
300
+ "grad_norm": 6.809825897216797,
301
+ "learning_rate": 4.75e-05,
302
+ "loss": 0.2383,
303
+ "step": 29
304
+ },
305
+ {
306
+ "epoch": 7.5,
307
+ "grad_norm": 1.3117998838424683,
308
+ "learning_rate": 4.722222222222222e-05,
309
+ "loss": 0.0335,
310
+ "step": 30
311
+ },
312
+ {
313
+ "epoch": 7.75,
314
+ "grad_norm": 4.045058250427246,
315
+ "learning_rate": 4.6944444444444446e-05,
316
+ "loss": 0.1796,
317
+ "step": 31
318
+ },
319
+ {
320
+ "epoch": 8.0,
321
+ "grad_norm": 10.013517379760742,
322
+ "learning_rate": 4.666666666666667e-05,
323
+ "loss": 0.3612,
324
+ "step": 32
325
+ },
326
+ {
327
+ "epoch": 8.0,
328
+ "eval_accuracy": 1.0,
329
+ "eval_auc": 1.0,
330
+ "eval_f1": 1.0,
331
+ "eval_loss": 0.010722639039158821,
332
+ "eval_precision": 1.0,
333
+ "eval_recall": 1.0,
334
+ "eval_runtime": 8.7618,
335
+ "eval_samples_per_second": 3.196,
336
+ "eval_steps_per_second": 0.228,
337
+ "step": 32
338
+ },
339
+ {
340
+ "epoch": 8.25,
341
+ "grad_norm": 3.8245110511779785,
342
+ "learning_rate": 4.638888888888889e-05,
343
+ "loss": 0.0614,
344
+ "step": 33
345
+ },
346
+ {
347
+ "epoch": 8.5,
348
+ "grad_norm": 0.46702659130096436,
349
+ "learning_rate": 4.6111111111111115e-05,
350
+ "loss": 0.0137,
351
+ "step": 34
352
+ },
353
+ {
354
+ "epoch": 8.75,
355
+ "grad_norm": 0.9684951901435852,
356
+ "learning_rate": 4.5833333333333334e-05,
357
+ "loss": 0.024,
358
+ "step": 35
359
+ },
360
+ {
361
+ "epoch": 9.0,
362
+ "grad_norm": 0.3815953731536865,
363
+ "learning_rate": 4.555555555555556e-05,
364
+ "loss": 0.0101,
365
+ "step": 36
366
+ },
367
+ {
368
+ "epoch": 9.0,
369
+ "eval_accuracy": 1.0,
370
+ "eval_auc": 1.0,
371
+ "eval_f1": 1.0,
372
+ "eval_loss": 0.002381645841524005,
373
+ "eval_precision": 1.0,
374
+ "eval_recall": 1.0,
375
+ "eval_runtime": 8.8895,
376
+ "eval_samples_per_second": 3.15,
377
+ "eval_steps_per_second": 0.225,
378
+ "step": 36
379
+ },
380
+ {
381
+ "epoch": 9.25,
382
+ "grad_norm": 0.10922980308532715,
383
+ "learning_rate": 4.527777777777778e-05,
384
+ "loss": 0.0026,
385
+ "step": 37
386
+ },
387
+ {
388
+ "epoch": 9.5,
389
+ "grad_norm": 10.054232597351074,
390
+ "learning_rate": 4.5e-05,
391
+ "loss": 0.2193,
392
+ "step": 38
393
+ },
394
+ {
395
+ "epoch": 9.75,
396
+ "grad_norm": 0.452944278717041,
397
+ "learning_rate": 4.472222222222223e-05,
398
+ "loss": 0.0045,
399
+ "step": 39
400
+ },
401
+ {
402
+ "epoch": 10.0,
403
+ "grad_norm": 31.92047119140625,
404
+ "learning_rate": 4.4444444444444447e-05,
405
+ "loss": 0.4483,
406
+ "step": 40
407
+ },
408
+ {
409
+ "epoch": 10.0,
410
+ "eval_accuracy": 1.0,
411
+ "eval_auc": 1.0,
412
+ "eval_f1": 1.0,
413
+ "eval_loss": 0.0012448489433154464,
414
+ "eval_precision": 1.0,
415
+ "eval_recall": 1.0,
416
+ "eval_runtime": 9.1493,
417
+ "eval_samples_per_second": 3.06,
418
+ "eval_steps_per_second": 0.219,
419
+ "step": 40
420
+ },
421
+ {
422
+ "epoch": 10.25,
423
+ "grad_norm": 0.061426494270563126,
424
+ "learning_rate": 4.4166666666666665e-05,
425
+ "loss": 0.0023,
426
+ "step": 41
427
+ },
428
+ {
429
+ "epoch": 10.5,
430
+ "grad_norm": 4.463461399078369,
431
+ "learning_rate": 4.388888888888889e-05,
432
+ "loss": 0.0456,
433
+ "step": 42
434
+ },
435
+ {
436
+ "epoch": 10.75,
437
+ "grad_norm": 1.7845221757888794,
438
+ "learning_rate": 4.3611111111111116e-05,
439
+ "loss": 0.0437,
440
+ "step": 43
441
+ },
442
+ {
443
+ "epoch": 11.0,
444
+ "grad_norm": 0.04194610193371773,
445
+ "learning_rate": 4.3333333333333334e-05,
446
+ "loss": 0.001,
447
+ "step": 44
448
+ },
449
+ {
450
+ "epoch": 11.0,
451
+ "eval_accuracy": 1.0,
452
+ "eval_auc": 1.0,
453
+ "eval_f1": 1.0,
454
+ "eval_loss": 0.0008708243840374053,
455
+ "eval_precision": 1.0,
456
+ "eval_recall": 1.0,
457
+ "eval_runtime": 8.9245,
458
+ "eval_samples_per_second": 3.137,
459
+ "eval_steps_per_second": 0.224,
460
+ "step": 44
461
+ },
462
+ {
463
+ "epoch": 11.25,
464
+ "grad_norm": 1.2456785440444946,
465
+ "learning_rate": 4.305555555555556e-05,
466
+ "loss": 0.018,
467
+ "step": 45
468
+ },
469
+ {
470
+ "epoch": 11.5,
471
+ "grad_norm": 10.299635887145996,
472
+ "learning_rate": 4.277777777777778e-05,
473
+ "loss": 0.1391,
474
+ "step": 46
475
+ },
476
+ {
477
+ "epoch": 11.75,
478
+ "grad_norm": 0.06855878978967667,
479
+ "learning_rate": 4.25e-05,
480
+ "loss": 0.0014,
481
+ "step": 47
482
+ },
483
+ {
484
+ "epoch": 12.0,
485
+ "grad_norm": 5.5674285888671875,
486
+ "learning_rate": 4.222222222222222e-05,
487
+ "loss": 0.0784,
488
+ "step": 48
489
+ },
490
+ {
491
+ "epoch": 12.0,
492
+ "eval_accuracy": 1.0,
493
+ "eval_auc": 1.0,
494
+ "eval_f1": 1.0,
495
+ "eval_loss": 0.0006320010288618505,
496
+ "eval_precision": 1.0,
497
+ "eval_recall": 1.0,
498
+ "eval_runtime": 9.1551,
499
+ "eval_samples_per_second": 3.058,
500
+ "eval_steps_per_second": 0.218,
501
+ "step": 48
502
+ },
503
+ {
504
+ "epoch": 12.25,
505
+ "grad_norm": 0.02712714672088623,
506
+ "learning_rate": 4.194444444444445e-05,
507
+ "loss": 0.0012,
508
+ "step": 49
509
+ },
510
+ {
511
+ "epoch": 12.5,
512
+ "grad_norm": 0.01984160952270031,
513
+ "learning_rate": 4.166666666666667e-05,
514
+ "loss": 0.001,
515
+ "step": 50
516
+ },
517
+ {
518
+ "epoch": 12.75,
519
+ "grad_norm": 0.0771925300359726,
520
+ "learning_rate": 4.138888888888889e-05,
521
+ "loss": 0.0012,
522
+ "step": 51
523
+ },
524
+ {
525
+ "epoch": 13.0,
526
+ "grad_norm": 12.30930233001709,
527
+ "learning_rate": 4.111111111111111e-05,
528
+ "loss": 0.2424,
529
+ "step": 52
530
+ },
531
+ {
532
+ "epoch": 13.0,
533
+ "eval_accuracy": 1.0,
534
+ "eval_auc": 1.0,
535
+ "eval_f1": 1.0,
536
+ "eval_loss": 0.0005376620101742446,
537
+ "eval_precision": 1.0,
538
+ "eval_recall": 1.0,
539
+ "eval_runtime": 9.5896,
540
+ "eval_samples_per_second": 2.92,
541
+ "eval_steps_per_second": 0.209,
542
+ "step": 52
543
+ }
544
+ ],
545
+ "logging_steps": 1,
546
+ "max_steps": 200,
547
+ "num_input_tokens_seen": 0,
548
+ "num_train_epochs": 50,
549
+ "save_steps": 500,
550
+ "stateful_callbacks": {
551
+ "EarlyStoppingCallback": {
552
+ "args": {
553
+ "early_stopping_patience": 5,
554
+ "early_stopping_threshold": 0.01
555
+ },
556
+ "attributes": {
557
+ "early_stopping_patience_counter": 0
558
+ }
559
+ },
560
+ "TrainerControl": {
561
+ "args": {
562
+ "should_epoch_stop": false,
563
+ "should_evaluate": false,
564
+ "should_log": false,
565
+ "should_save": true,
566
+ "should_training_stop": true
567
+ },
568
+ "attributes": {}
569
+ }
570
+ },
571
+ "total_flos": 2.820708421971149e+16,
572
+ "train_batch_size": 8,
573
+ "trial_name": null,
574
+ "trial_params": null
575
+ }
checkpoint-52/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b2f258a9a7897b474396ed689af1960813a5e962a54c170f60f6f1a58910ed
3
+ size 5240
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Falconsai/nsfw_image_detection",
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": "normal",
14
+ "1": "nsfw"
15
+ },
16
+ "image_size": 224,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "normal": 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": "4.44.2"
33
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057f1b3035c9323421300577ac5c2339b7f68be8ee7ccaee6045ec40999777d9
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
+ }
runs/Sep07_07-37-24_r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14/events.out.tfevents.1725694646.r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14.142.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:637bf998c2f09e87ca3b703f01541a87004754df28c9b0a3f42cd8d8de2567a3
3
- size 5053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30bc8605d0edb72cd46a3958a0d2c61aebf3f3659900cc18f43d83727aa49253
3
+ size 22782
runs/Sep07_07-37-24_r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14/events.out.tfevents.1725695145.r-perrytheplatypus-falconsai-clone-6g1aqf3q-2dd83-ipw14.142.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a98a19d03f284491a4d8ab215b61bfbf897bbb2de932efcb208d5ad74c31d1f
3
+ size 597
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b2f258a9a7897b474396ed689af1960813a5e962a54c170f60f6f1a58910ed
3
+ size 5240
training_params.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data_path": "autotrain-okqe6-pd7eh/autotrain-data",
3
+ "model": "Falconsai/nsfw_image_detection",
4
+ "username": "perrytheplatypus",
5
+ "lr": 5e-05,
6
+ "epochs": 50,
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-okqe6-pd7eh",
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": "tensorboard",
27
+ "early_stopping_patience": 5,
28
+ "early_stopping_threshold": 0.01
29
+ }