Hugging Face's logo

mateoluksenberg
/
Seed_Classifier

Image Classification
Transformers
TensorBoard
Safetensors
beit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mateoluksenberg commited on
Commit
c147e8a
•
1 Parent(s): fc87776

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +8 -0
  2. train_results.json +8 -0
  3. trainer_state.json +387 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 18.0,
3
+ "total_flos": 1.6740517517918208e+16,
4
+ "train_loss": 0.32068005369769204,
5
+ "train_runtime": 242.8786,
6
+ "train_samples_per_second": 0.889,
7
+ "train_steps_per_second": 0.074
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 18.0,
3
+ "total_flos": 1.6740517517918208e+16,
4
+ "train_loss": 0.32068005369769204,
5
+ "train_runtime": 242.8786,
6
+ "train_samples_per_second": 0.889,
7
+ "train_steps_per_second": 0.074
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,387 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 18.0,
5
+ "eval_steps": 500,
6
+ "global_step": 18,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 2.5107996463775635,
14
+ "learning_rate": 2.5e-05,
15
+ "loss": 0.3646,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_Macro F1": 0.0,
21
+ "eval_Macro Precision": 0.0,
22
+ "eval_Macro Recall": 0.0,
23
+ "eval_Micro F1": 0.0,
24
+ "eval_Micro Precision": 0.0,
25
+ "eval_Micro Recall": 0.0,
26
+ "eval_Weighted F1": 0.0,
27
+ "eval_Weighted Precision": 0.0,
28
+ "eval_Weighted Recall": 0.0,
29
+ "eval_accuracy": 0.0,
30
+ "eval_loss": 2.4555206298828125,
31
+ "eval_runtime": 7.0509,
32
+ "eval_samples_per_second": 0.425,
33
+ "eval_steps_per_second": 0.142,
34
+ "step": 1
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_Macro F1": 0.0,
39
+ "eval_Macro Precision": 0.0,
40
+ "eval_Macro Recall": 0.0,
41
+ "eval_Micro F1": 0.0,
42
+ "eval_Micro Precision": 0.0,
43
+ "eval_Micro Recall": 0.0,
44
+ "eval_Weighted F1": 0.0,
45
+ "eval_Weighted Precision": 0.0,
46
+ "eval_Weighted Recall": 0.0,
47
+ "eval_accuracy": 0.0,
48
+ "eval_loss": 2.4605119228363037,
49
+ "eval_runtime": 5.0672,
50
+ "eval_samples_per_second": 0.592,
51
+ "eval_steps_per_second": 0.197,
52
+ "step": 2
53
+ },
54
+ {
55
+ "epoch": 3.0,
56
+ "eval_Macro F1": 0.0,
57
+ "eval_Macro Precision": 0.0,
58
+ "eval_Macro Recall": 0.0,
59
+ "eval_Micro F1": 0.0,
60
+ "eval_Micro Precision": 0.0,
61
+ "eval_Micro Recall": 0.0,
62
+ "eval_Weighted F1": 0.0,
63
+ "eval_Weighted Precision": 0.0,
64
+ "eval_Weighted Recall": 0.0,
65
+ "eval_accuracy": 0.0,
66
+ "eval_loss": 2.600870370864868,
67
+ "eval_runtime": 5.1285,
68
+ "eval_samples_per_second": 0.585,
69
+ "eval_steps_per_second": 0.195,
70
+ "step": 3
71
+ },
72
+ {
73
+ "epoch": 4.0,
74
+ "eval_Macro F1": 0.0,
75
+ "eval_Macro Precision": 0.0,
76
+ "eval_Macro Recall": 0.0,
77
+ "eval_Micro F1": 0.0,
78
+ "eval_Micro Precision": 0.0,
79
+ "eval_Micro Recall": 0.0,
80
+ "eval_Weighted F1": 0.0,
81
+ "eval_Weighted Precision": 0.0,
82
+ "eval_Weighted Recall": 0.0,
83
+ "eval_accuracy": 0.0,
84
+ "eval_loss": 2.7373969554901123,
85
+ "eval_runtime": 5.1975,
86
+ "eval_samples_per_second": 0.577,
87
+ "eval_steps_per_second": 0.192,
88
+ "step": 4
89
+ },
90
+ {
91
+ "epoch": 5.0,
92
+ "eval_Macro F1": 0.0,
93
+ "eval_Macro Precision": 0.0,
94
+ "eval_Macro Recall": 0.0,
95
+ "eval_Micro F1": 0.0,
96
+ "eval_Micro Precision": 0.0,
97
+ "eval_Micro Recall": 0.0,
98
+ "eval_Weighted F1": 0.0,
99
+ "eval_Weighted Precision": 0.0,
100
+ "eval_Weighted Recall": 0.0,
101
+ "eval_accuracy": 0.0,
102
+ "eval_loss": 2.764043092727661,
103
+ "eval_runtime": 5.6381,
104
+ "eval_samples_per_second": 0.532,
105
+ "eval_steps_per_second": 0.177,
106
+ "step": 5
107
+ },
108
+ {
109
+ "epoch": 6.0,
110
+ "eval_Macro F1": 0.0,
111
+ "eval_Macro Precision": 0.0,
112
+ "eval_Macro Recall": 0.0,
113
+ "eval_Micro F1": 0.0,
114
+ "eval_Micro Precision": 0.0,
115
+ "eval_Micro Recall": 0.0,
116
+ "eval_Weighted F1": 0.0,
117
+ "eval_Weighted Precision": 0.0,
118
+ "eval_Weighted Recall": 0.0,
119
+ "eval_accuracy": 0.0,
120
+ "eval_loss": 2.7440683841705322,
121
+ "eval_runtime": 5.2121,
122
+ "eval_samples_per_second": 0.576,
123
+ "eval_steps_per_second": 0.192,
124
+ "step": 6
125
+ },
126
+ {
127
+ "epoch": 7.0,
128
+ "eval_Macro F1": 0.0,
129
+ "eval_Macro Precision": 0.0,
130
+ "eval_Macro Recall": 0.0,
131
+ "eval_Micro F1": 0.0,
132
+ "eval_Micro Precision": 0.0,
133
+ "eval_Micro Recall": 0.0,
134
+ "eval_Weighted F1": 0.0,
135
+ "eval_Weighted Precision": 0.0,
136
+ "eval_Weighted Recall": 0.0,
137
+ "eval_accuracy": 0.0,
138
+ "eval_loss": 2.7819652557373047,
139
+ "eval_runtime": 5.5977,
140
+ "eval_samples_per_second": 0.536,
141
+ "eval_steps_per_second": 0.179,
142
+ "step": 7
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 0.9609292149543762,
147
+ "learning_rate": 3.125e-05,
148
+ "loss": 0.3442,
149
+ "step": 8
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_Macro F1": 0.0,
154
+ "eval_Macro Precision": 0.0,
155
+ "eval_Macro Recall": 0.0,
156
+ "eval_Micro F1": 0.0,
157
+ "eval_Micro Precision": 0.0,
158
+ "eval_Micro Recall": 0.0,
159
+ "eval_Weighted F1": 0.0,
160
+ "eval_Weighted Precision": 0.0,
161
+ "eval_Weighted Recall": 0.0,
162
+ "eval_accuracy": 0.0,
163
+ "eval_loss": 2.8066508769989014,
164
+ "eval_runtime": 5.2493,
165
+ "eval_samples_per_second": 0.572,
166
+ "eval_steps_per_second": 0.191,
167
+ "step": 8
168
+ },
169
+ {
170
+ "epoch": 9.0,
171
+ "eval_Macro F1": 0.0,
172
+ "eval_Macro Precision": 0.0,
173
+ "eval_Macro Recall": 0.0,
174
+ "eval_Micro F1": 0.0,
175
+ "eval_Micro Precision": 0.0,
176
+ "eval_Micro Recall": 0.0,
177
+ "eval_Weighted F1": 0.0,
178
+ "eval_Weighted Precision": 0.0,
179
+ "eval_Weighted Recall": 0.0,
180
+ "eval_accuracy": 0.0,
181
+ "eval_loss": 2.8143389225006104,
182
+ "eval_runtime": 5.448,
183
+ "eval_samples_per_second": 0.551,
184
+ "eval_steps_per_second": 0.184,
185
+ "step": 9
186
+ },
187
+ {
188
+ "epoch": 10.0,
189
+ "eval_Macro F1": 0.0,
190
+ "eval_Macro Precision": 0.0,
191
+ "eval_Macro Recall": 0.0,
192
+ "eval_Micro F1": 0.0,
193
+ "eval_Micro Precision": 0.0,
194
+ "eval_Micro Recall": 0.0,
195
+ "eval_Weighted F1": 0.0,
196
+ "eval_Weighted Precision": 0.0,
197
+ "eval_Weighted Recall": 0.0,
198
+ "eval_accuracy": 0.0,
199
+ "eval_loss": 2.796605348587036,
200
+ "eval_runtime": 5.2784,
201
+ "eval_samples_per_second": 0.568,
202
+ "eval_steps_per_second": 0.189,
203
+ "step": 10
204
+ },
205
+ {
206
+ "epoch": 11.0,
207
+ "eval_Macro F1": 0.0,
208
+ "eval_Macro Precision": 0.0,
209
+ "eval_Macro Recall": 0.0,
210
+ "eval_Micro F1": 0.0,
211
+ "eval_Micro Precision": 0.0,
212
+ "eval_Micro Recall": 0.0,
213
+ "eval_Weighted F1": 0.0,
214
+ "eval_Weighted Precision": 0.0,
215
+ "eval_Weighted Recall": 0.0,
216
+ "eval_accuracy": 0.0,
217
+ "eval_loss": 2.783594846725464,
218
+ "eval_runtime": 5.0956,
219
+ "eval_samples_per_second": 0.589,
220
+ "eval_steps_per_second": 0.196,
221
+ "step": 11
222
+ },
223
+ {
224
+ "epoch": 12.0,
225
+ "eval_Macro F1": 0.0,
226
+ "eval_Macro Precision": 0.0,
227
+ "eval_Macro Recall": 0.0,
228
+ "eval_Micro F1": 0.0,
229
+ "eval_Micro Precision": 0.0,
230
+ "eval_Micro Recall": 0.0,
231
+ "eval_Weighted F1": 0.0,
232
+ "eval_Weighted Precision": 0.0,
233
+ "eval_Weighted Recall": 0.0,
234
+ "eval_accuracy": 0.0,
235
+ "eval_loss": 2.7537152767181396,
236
+ "eval_runtime": 5.2933,
237
+ "eval_samples_per_second": 0.567,
238
+ "eval_steps_per_second": 0.189,
239
+ "step": 12
240
+ },
241
+ {
242
+ "epoch": 13.0,
243
+ "eval_Macro F1": 0.0,
244
+ "eval_Macro Precision": 0.0,
245
+ "eval_Macro Recall": 0.0,
246
+ "eval_Micro F1": 0.0,
247
+ "eval_Micro Precision": 0.0,
248
+ "eval_Micro Recall": 0.0,
249
+ "eval_Weighted F1": 0.0,
250
+ "eval_Weighted Precision": 0.0,
251
+ "eval_Weighted Recall": 0.0,
252
+ "eval_accuracy": 0.0,
253
+ "eval_loss": 2.72334885597229,
254
+ "eval_runtime": 5.2117,
255
+ "eval_samples_per_second": 0.576,
256
+ "eval_steps_per_second": 0.192,
257
+ "step": 13
258
+ },
259
+ {
260
+ "epoch": 14.0,
261
+ "eval_Macro F1": 0.0,
262
+ "eval_Macro Precision": 0.0,
263
+ "eval_Macro Recall": 0.0,
264
+ "eval_Micro F1": 0.0,
265
+ "eval_Micro Precision": 0.0,
266
+ "eval_Micro Recall": 0.0,
267
+ "eval_Weighted F1": 0.0,
268
+ "eval_Weighted Precision": 0.0,
269
+ "eval_Weighted Recall": 0.0,
270
+ "eval_accuracy": 0.0,
271
+ "eval_loss": 2.6946322917938232,
272
+ "eval_runtime": 5.2603,
273
+ "eval_samples_per_second": 0.57,
274
+ "eval_steps_per_second": 0.19,
275
+ "step": 14
276
+ },
277
+ {
278
+ "epoch": 15.0,
279
+ "eval_Macro F1": 0.0,
280
+ "eval_Macro Precision": 0.0,
281
+ "eval_Macro Recall": 0.0,
282
+ "eval_Micro F1": 0.0,
283
+ "eval_Micro Precision": 0.0,
284
+ "eval_Micro Recall": 0.0,
285
+ "eval_Weighted F1": 0.0,
286
+ "eval_Weighted Precision": 0.0,
287
+ "eval_Weighted Recall": 0.0,
288
+ "eval_accuracy": 0.0,
289
+ "eval_loss": 2.6637771129608154,
290
+ "eval_runtime": 5.1635,
291
+ "eval_samples_per_second": 0.581,
292
+ "eval_steps_per_second": 0.194,
293
+ "step": 15
294
+ },
295
+ {
296
+ "epoch": 16.0,
297
+ "grad_norm": 1.235273838043213,
298
+ "learning_rate": 6.25e-06,
299
+ "loss": 0.3003,
300
+ "step": 16
301
+ },
302
+ {
303
+ "epoch": 16.0,
304
+ "eval_Macro F1": 0.0,
305
+ "eval_Macro Precision": 0.0,
306
+ "eval_Macro Recall": 0.0,
307
+ "eval_Micro F1": 0.0,
308
+ "eval_Micro Precision": 0.0,
309
+ "eval_Micro Recall": 0.0,
310
+ "eval_Weighted F1": 0.0,
311
+ "eval_Weighted Precision": 0.0,
312
+ "eval_Weighted Recall": 0.0,
313
+ "eval_accuracy": 0.0,
314
+ "eval_loss": 2.6449084281921387,
315
+ "eval_runtime": 5.3638,
316
+ "eval_samples_per_second": 0.559,
317
+ "eval_steps_per_second": 0.186,
318
+ "step": 16
319
+ },
320
+ {
321
+ "epoch": 17.0,
322
+ "eval_Macro F1": 0.0,
323
+ "eval_Macro Precision": 0.0,
324
+ "eval_Macro Recall": 0.0,
325
+ "eval_Micro F1": 0.0,
326
+ "eval_Micro Precision": 0.0,
327
+ "eval_Micro Recall": 0.0,
328
+ "eval_Weighted F1": 0.0,
329
+ "eval_Weighted Precision": 0.0,
330
+ "eval_Weighted Recall": 0.0,
331
+ "eval_accuracy": 0.0,
332
+ "eval_loss": 2.631160020828247,
333
+ "eval_runtime": 5.4042,
334
+ "eval_samples_per_second": 0.555,
335
+ "eval_steps_per_second": 0.185,
336
+ "step": 17
337
+ },
338
+ {
339
+ "epoch": 18.0,
340
+ "eval_Macro F1": 0.0,
341
+ "eval_Macro Precision": 0.0,
342
+ "eval_Macro Recall": 0.0,
343
+ "eval_Micro F1": 0.0,
344
+ "eval_Micro Precision": 0.0,
345
+ "eval_Micro Recall": 0.0,
346
+ "eval_Weighted F1": 0.0,
347
+ "eval_Weighted Precision": 0.0,
348
+ "eval_Weighted Recall": 0.0,
349
+ "eval_accuracy": 0.0,
350
+ "eval_loss": 2.6238577365875244,
351
+ "eval_runtime": 5.1807,
352
+ "eval_samples_per_second": 0.579,
353
+ "eval_steps_per_second": 0.193,
354
+ "step": 18
355
+ },
356
+ {
357
+ "epoch": 18.0,
358
+ "step": 18,
359
+ "total_flos": 1.6740517517918208e+16,
360
+ "train_loss": 0.32068005369769204,
361
+ "train_runtime": 242.8786,
362
+ "train_samples_per_second": 0.889,
363
+ "train_steps_per_second": 0.074
364
+ }
365
+ ],
366
+ "logging_steps": 8,
367
+ "max_steps": 18,
368
+ "num_input_tokens_seen": 0,
369
+ "num_train_epochs": 18,
370
+ "save_steps": 500,
371
+ "stateful_callbacks": {
372
+ "TrainerControl": {
373
+ "args": {
374
+ "should_epoch_stop": false,
375
+ "should_evaluate": false,
376
+ "should_log": false,
377
+ "should_save": true,
378
+ "should_training_stop": true
379
+ },
380
+ "attributes": {}
381
+ }
382
+ },
383
+ "total_flos": 1.6740517517918208e+16,
384
+ "train_batch_size": 32,
385
+ "trial_name": null,
386
+ "trial_params": null
387
+ }