Hugging Face's logo

panda992
/
fish_disease_datasets

Image Classification
Transformers
TensorBoard
Safetensors
vit
vision-transformer
aquaculture
fish-disease
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
panda992 commited on
Commit
1a74299
·
verified ·
1 Parent(s): f86485a

🍻 cheers

Browse files
Files changed (6) hide show
  1. README.md +2 -1
  2. all_results.json +13 -0
  3. eval_results.json +8 -0
  4. runs/May10_06-15-04_35deed949fff/events.out.tfevents.1746857891.35deed949fff.185.1 +3 -0
  5. train_results.json +8 -0
  6. trainer_state.json +452 -0
README.md CHANGED
@@ -3,6 +3,7 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
 
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # fish_disease_datasets
18
 
19
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.1053
22
  - Accuracy: 0.9728
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224-in21k
5
  tags:
6
+ - image-classification
7
  - generated_from_trainer
8
  metrics:
9
  - accuracy
 
17
 
18
  # fish_disease_datasets
19
 
20
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the fish_disease_datasets dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 0.1053
23
  - Accuracy: 0.9728
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9728260869565217,
4
+ "eval_loss": 0.10525541752576828,
5
+ "eval_runtime": 1.7228,
6
+ "eval_samples_per_second": 213.607,
7
+ "eval_steps_per_second": 26.701,
8
+ "total_flos": 6.45382209997357e+17,
9
+ "train_loss": 0.4479620875293062,
10
+ "train_runtime": 145.1835,
11
+ "train_samples_per_second": 57.362,
12
+ "train_steps_per_second": 3.609
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9728260869565217,
4
+ "eval_loss": 0.10525541752576828,
5
+ "eval_runtime": 1.7228,
6
+ "eval_samples_per_second": 213.607,
7
+ "eval_steps_per_second": 26.701
8
+ }
runs/May10_06-15-04_35deed949fff/events.out.tfevents.1746857891.35deed949fff.185.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a3dbd33854e4a208d3a50dff89afec3b162a870f4a88fa8479c1ce31e500ed6
3
+ size 411
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 6.45382209997357e+17,
4
+ "train_loss": 0.4479620875293062,
5
+ "train_runtime": 145.1835,
6
+ "train_samples_per_second": 57.362,
7
+ "train_steps_per_second": 3.609
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,452 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 500,
3
+ "best_metric": 0.10525541752576828,
4
+ "best_model_checkpoint": "fish_disease_datasets/checkpoint-500",
5
+ "epoch": 4.0,
6
+ "eval_steps": 100,
7
+ "global_step": 524,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.07633587786259542,
14
+ "grad_norm": 1.9409185647964478,
15
+ "learning_rate": 0.00019656488549618322,
16
+ "loss": 1.8218,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.15267175572519084,
21
+ "grad_norm": 2.1680898666381836,
22
+ "learning_rate": 0.00019274809160305345,
23
+ "loss": 1.5952,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.22900763358778625,
28
+ "grad_norm": 2.6097843647003174,
29
+ "learning_rate": 0.00018893129770992367,
30
+ "loss": 1.3356,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.3053435114503817,
35
+ "grad_norm": 3.603273391723633,
36
+ "learning_rate": 0.0001851145038167939,
37
+ "loss": 1.2841,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.3816793893129771,
42
+ "grad_norm": 2.5564615726470947,
43
+ "learning_rate": 0.00018129770992366412,
44
+ "loss": 1.1569,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.4580152671755725,
49
+ "grad_norm": 1.7292225360870361,
50
+ "learning_rate": 0.00017748091603053437,
51
+ "loss": 0.9338,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.5343511450381679,
56
+ "grad_norm": 2.0024733543395996,
57
+ "learning_rate": 0.0001736641221374046,
58
+ "loss": 0.8578,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.6106870229007634,
63
+ "grad_norm": 3.2344448566436768,
64
+ "learning_rate": 0.00016984732824427482,
65
+ "loss": 0.9114,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.6870229007633588,
70
+ "grad_norm": 2.080090045928955,
71
+ "learning_rate": 0.00016603053435114505,
72
+ "loss": 0.7153,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.7633587786259542,
77
+ "grad_norm": 3.047137975692749,
78
+ "learning_rate": 0.00016221374045801527,
79
+ "loss": 0.7341,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.7633587786259542,
84
+ "eval_accuracy": 0.8994565217391305,
85
+ "eval_loss": 0.47246649861335754,
86
+ "eval_runtime": 1.6845,
87
+ "eval_samples_per_second": 218.467,
88
+ "eval_steps_per_second": 27.308,
89
+ "step": 100
90
+ },
91
+ {
92
+ "epoch": 0.8396946564885496,
93
+ "grad_norm": 2.9488649368286133,
94
+ "learning_rate": 0.0001583969465648855,
95
+ "loss": 0.6839,
96
+ "step": 110
97
+ },
98
+ {
99
+ "epoch": 0.916030534351145,
100
+ "grad_norm": 7.901376724243164,
101
+ "learning_rate": 0.00015458015267175574,
102
+ "loss": 0.6448,
103
+ "step": 120
104
+ },
105
+ {
106
+ "epoch": 0.9923664122137404,
107
+ "grad_norm": 2.6855387687683105,
108
+ "learning_rate": 0.00015076335877862594,
109
+ "loss": 0.5792,
110
+ "step": 130
111
+ },
112
+ {
113
+ "epoch": 1.0687022900763359,
114
+ "grad_norm": 3.498868703842163,
115
+ "learning_rate": 0.0001469465648854962,
116
+ "loss": 0.4598,
117
+ "step": 140
118
+ },
119
+ {
120
+ "epoch": 1.1450381679389312,
121
+ "grad_norm": 1.6161444187164307,
122
+ "learning_rate": 0.00014312977099236642,
123
+ "loss": 0.346,
124
+ "step": 150
125
+ },
126
+ {
127
+ "epoch": 1.2213740458015268,
128
+ "grad_norm": 3.7343335151672363,
129
+ "learning_rate": 0.00013931297709923664,
130
+ "loss": 0.3722,
131
+ "step": 160
132
+ },
133
+ {
134
+ "epoch": 1.297709923664122,
135
+ "grad_norm": 3.1330108642578125,
136
+ "learning_rate": 0.0001354961832061069,
137
+ "loss": 0.3455,
138
+ "step": 170
139
+ },
140
+ {
141
+ "epoch": 1.3740458015267176,
142
+ "grad_norm": 3.1974072456359863,
143
+ "learning_rate": 0.0001316793893129771,
144
+ "loss": 0.4522,
145
+ "step": 180
146
+ },
147
+ {
148
+ "epoch": 1.450381679389313,
149
+ "grad_norm": 4.500912189483643,
150
+ "learning_rate": 0.00012786259541984734,
151
+ "loss": 0.5162,
152
+ "step": 190
153
+ },
154
+ {
155
+ "epoch": 1.5267175572519083,
156
+ "grad_norm": 1.8331102132797241,
157
+ "learning_rate": 0.00012404580152671757,
158
+ "loss": 0.4232,
159
+ "step": 200
160
+ },
161
+ {
162
+ "epoch": 1.5267175572519083,
163
+ "eval_accuracy": 0.9538043478260869,
164
+ "eval_loss": 0.24539989233016968,
165
+ "eval_runtime": 1.9758,
166
+ "eval_samples_per_second": 186.25,
167
+ "eval_steps_per_second": 23.281,
168
+ "step": 200
169
+ },
170
+ {
171
+ "epoch": 1.6030534351145038,
172
+ "grad_norm": 5.288910388946533,
173
+ "learning_rate": 0.0001202290076335878,
174
+ "loss": 0.3414,
175
+ "step": 210
176
+ },
177
+ {
178
+ "epoch": 1.6793893129770994,
179
+ "grad_norm": 3.0168659687042236,
180
+ "learning_rate": 0.00011641221374045803,
181
+ "loss": 0.3141,
182
+ "step": 220
183
+ },
184
+ {
185
+ "epoch": 1.7557251908396947,
186
+ "grad_norm": 3.6415915489196777,
187
+ "learning_rate": 0.00011259541984732824,
188
+ "loss": 0.3561,
189
+ "step": 230
190
+ },
191
+ {
192
+ "epoch": 1.83206106870229,
193
+ "grad_norm": 4.600650787353516,
194
+ "learning_rate": 0.00010877862595419848,
195
+ "loss": 0.3937,
196
+ "step": 240
197
+ },
198
+ {
199
+ "epoch": 1.9083969465648853,
200
+ "grad_norm": 1.985364317893982,
201
+ "learning_rate": 0.00010496183206106871,
202
+ "loss": 0.325,
203
+ "step": 250
204
+ },
205
+ {
206
+ "epoch": 1.984732824427481,
207
+ "grad_norm": 4.19254732131958,
208
+ "learning_rate": 0.00010114503816793894,
209
+ "loss": 0.3214,
210
+ "step": 260
211
+ },
212
+ {
213
+ "epoch": 2.0610687022900764,
214
+ "grad_norm": 0.3229253888130188,
215
+ "learning_rate": 9.732824427480916e-05,
216
+ "loss": 0.2053,
217
+ "step": 270
218
+ },
219
+ {
220
+ "epoch": 2.1374045801526718,
221
+ "grad_norm": 4.743760108947754,
222
+ "learning_rate": 9.351145038167939e-05,
223
+ "loss": 0.3318,
224
+ "step": 280
225
+ },
226
+ {
227
+ "epoch": 2.213740458015267,
228
+ "grad_norm": 2.43632435798645,
229
+ "learning_rate": 8.969465648854962e-05,
230
+ "loss": 0.2364,
231
+ "step": 290
232
+ },
233
+ {
234
+ "epoch": 2.2900763358778624,
235
+ "grad_norm": 0.9254801869392395,
236
+ "learning_rate": 8.587786259541986e-05,
237
+ "loss": 0.1134,
238
+ "step": 300
239
+ },
240
+ {
241
+ "epoch": 2.2900763358778624,
242
+ "eval_accuracy": 0.9755434782608695,
243
+ "eval_loss": 0.16888892650604248,
244
+ "eval_runtime": 1.9035,
245
+ "eval_samples_per_second": 193.324,
246
+ "eval_steps_per_second": 24.166,
247
+ "step": 300
248
+ },
249
+ {
250
+ "epoch": 2.366412213740458,
251
+ "grad_norm": 6.0736894607543945,
252
+ "learning_rate": 8.206106870229007e-05,
253
+ "loss": 0.2712,
254
+ "step": 310
255
+ },
256
+ {
257
+ "epoch": 2.4427480916030535,
258
+ "grad_norm": 7.306392192840576,
259
+ "learning_rate": 7.824427480916031e-05,
260
+ "loss": 0.3705,
261
+ "step": 320
262
+ },
263
+ {
264
+ "epoch": 2.519083969465649,
265
+ "grad_norm": 0.37736839056015015,
266
+ "learning_rate": 7.442748091603053e-05,
267
+ "loss": 0.2431,
268
+ "step": 330
269
+ },
270
+ {
271
+ "epoch": 2.595419847328244,
272
+ "grad_norm": 3.2378218173980713,
273
+ "learning_rate": 7.061068702290077e-05,
274
+ "loss": 0.2495,
275
+ "step": 340
276
+ },
277
+ {
278
+ "epoch": 2.67175572519084,
279
+ "grad_norm": 4.0994086265563965,
280
+ "learning_rate": 6.6793893129771e-05,
281
+ "loss": 0.2218,
282
+ "step": 350
283
+ },
284
+ {
285
+ "epoch": 2.7480916030534353,
286
+ "grad_norm": 0.19563277065753937,
287
+ "learning_rate": 6.297709923664122e-05,
288
+ "loss": 0.2717,
289
+ "step": 360
290
+ },
291
+ {
292
+ "epoch": 2.8244274809160306,
293
+ "grad_norm": 2.251434803009033,
294
+ "learning_rate": 5.916030534351146e-05,
295
+ "loss": 0.134,
296
+ "step": 370
297
+ },
298
+ {
299
+ "epoch": 2.900763358778626,
300
+ "grad_norm": 2.093945026397705,
301
+ "learning_rate": 5.534351145038168e-05,
302
+ "loss": 0.1724,
303
+ "step": 380
304
+ },
305
+ {
306
+ "epoch": 2.9770992366412212,
307
+ "grad_norm": 2.778428554534912,
308
+ "learning_rate": 5.152671755725191e-05,
309
+ "loss": 0.2283,
310
+ "step": 390
311
+ },
312
+ {
313
+ "epoch": 3.053435114503817,
314
+ "grad_norm": 6.020068168640137,
315
+ "learning_rate": 4.7709923664122144e-05,
316
+ "loss": 0.2237,
317
+ "step": 400
318
+ },
319
+ {
320
+ "epoch": 3.053435114503817,
321
+ "eval_accuracy": 0.9592391304347826,
322
+ "eval_loss": 0.16388548910617828,
323
+ "eval_runtime": 1.6041,
324
+ "eval_samples_per_second": 229.414,
325
+ "eval_steps_per_second": 28.677,
326
+ "step": 400
327
+ },
328
+ {
329
+ "epoch": 3.1297709923664123,
330
+ "grad_norm": 0.23176027834415436,
331
+ "learning_rate": 4.389312977099237e-05,
332
+ "loss": 0.2231,
333
+ "step": 410
334
+ },
335
+ {
336
+ "epoch": 3.2061068702290076,
337
+ "grad_norm": 2.9403698444366455,
338
+ "learning_rate": 4.00763358778626e-05,
339
+ "loss": 0.1379,
340
+ "step": 420
341
+ },
342
+ {
343
+ "epoch": 3.282442748091603,
344
+ "grad_norm": 3.401761531829834,
345
+ "learning_rate": 3.625954198473282e-05,
346
+ "loss": 0.2339,
347
+ "step": 430
348
+ },
349
+ {
350
+ "epoch": 3.3587786259541983,
351
+ "grad_norm": 2.4639177322387695,
352
+ "learning_rate": 3.2442748091603054e-05,
353
+ "loss": 0.1795,
354
+ "step": 440
355
+ },
356
+ {
357
+ "epoch": 3.435114503816794,
358
+ "grad_norm": 3.926365613937378,
359
+ "learning_rate": 2.862595419847328e-05,
360
+ "loss": 0.1326,
361
+ "step": 450
362
+ },
363
+ {
364
+ "epoch": 3.5114503816793894,
365
+ "grad_norm": 3.4511287212371826,
366
+ "learning_rate": 2.4809160305343512e-05,
367
+ "loss": 0.2162,
368
+ "step": 460
369
+ },
370
+ {
371
+ "epoch": 3.5877862595419847,
372
+ "grad_norm": 0.1071397215127945,
373
+ "learning_rate": 2.099236641221374e-05,
374
+ "loss": 0.0821,
375
+ "step": 470
376
+ },
377
+ {
378
+ "epoch": 3.66412213740458,
379
+ "grad_norm": 0.11275670677423477,
380
+ "learning_rate": 1.717557251908397e-05,
381
+ "loss": 0.0965,
382
+ "step": 480
383
+ },
384
+ {
385
+ "epoch": 3.7404580152671754,
386
+ "grad_norm": 1.8266428709030151,
387
+ "learning_rate": 1.3358778625954198e-05,
388
+ "loss": 0.2015,
389
+ "step": 490
390
+ },
391
+ {
392
+ "epoch": 3.816793893129771,
393
+ "grad_norm": 1.146474003791809,
394
+ "learning_rate": 9.541984732824428e-06,
395
+ "loss": 0.1431,
396
+ "step": 500
397
+ },
398
+ {
399
+ "epoch": 3.816793893129771,
400
+ "eval_accuracy": 0.9728260869565217,
401
+ "eval_loss": 0.10525541752576828,
402
+ "eval_runtime": 1.5956,
403
+ "eval_samples_per_second": 230.634,
404
+ "eval_steps_per_second": 28.829,
405
+ "step": 500
406
+ },
407
+ {
408
+ "epoch": 3.8931297709923665,
409
+ "grad_norm": 4.4021992683410645,
410
+ "learning_rate": 5.725190839694657e-06,
411
+ "loss": 0.1294,
412
+ "step": 510
413
+ },
414
+ {
415
+ "epoch": 3.969465648854962,
416
+ "grad_norm": 0.27708983421325684,
417
+ "learning_rate": 1.908396946564886e-06,
418
+ "loss": 0.1359,
419
+ "step": 520
420
+ },
421
+ {
422
+ "epoch": 4.0,
423
+ "step": 524,
424
+ "total_flos": 6.45382209997357e+17,
425
+ "train_loss": 0.4479620875293062,
426
+ "train_runtime": 145.1835,
427
+ "train_samples_per_second": 57.362,
428
+ "train_steps_per_second": 3.609
429
+ }
430
+ ],
431
+ "logging_steps": 10,
432
+ "max_steps": 524,
433
+ "num_input_tokens_seen": 0,
434
+ "num_train_epochs": 4,
435
+ "save_steps": 100,
436
+ "stateful_callbacks": {
437
+ "TrainerControl": {
438
+ "args": {
439
+ "should_epoch_stop": false,
440
+ "should_evaluate": false,
441
+ "should_log": false,
442
+ "should_save": true,
443
+ "should_training_stop": true
444
+ },
445
+ "attributes": {}
446
+ }
447
+ },
448
+ "total_flos": 6.45382209997357e+17,
449
+ "train_batch_size": 16,
450
+ "trial_name": null,
451
+ "trial_params": null
452
+ }