lakelee commited on
Commit
2bfe43a
·
verified ·
1 Parent(s): 19093fc

Model save

Browse files
Files changed (2) hide show
  1. README.md +59 -0
  2. trainer_state.json +421 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen3-VL-2B-Instruct
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: STRIDE-T002-PBCE-Qwen3-VL-2B
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # STRIDE-T002-PBCE-Qwen3-VL-2B
16
+
17
+ This model is a fine-tuned version of [Qwen/Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 8
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 128
44
+ - total_eval_batch_size: 64
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_steps: 512.0
48
+ - num_epochs: 1.0
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 5.2.0.dev0
57
+ - Pytorch 2.8.0+cu128
58
+ - Datasets 4.4.1
59
+ - Tokenizers 0.22.1
trainer_state.json ADDED
@@ -0,0 +1,421 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 54,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.018604651162790697,
14
+ "grad_norm": 51.7990608215332,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.71331787109375,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.037209302325581395,
21
+ "grad_norm": 56.753963470458984,
22
+ "learning_rate": 7.8125e-08,
23
+ "loss": 0.71588134765625,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.05581395348837209,
28
+ "grad_norm": 45.70652389526367,
29
+ "learning_rate": 1.5625e-07,
30
+ "loss": 0.7108154296875,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.07441860465116279,
35
+ "grad_norm": 53.1850700378418,
36
+ "learning_rate": 2.3437500000000003e-07,
37
+ "loss": 0.7137451171875,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.09302325581395349,
42
+ "grad_norm": 49.760826110839844,
43
+ "learning_rate": 3.125e-07,
44
+ "loss": 0.71337890625,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.11162790697674418,
49
+ "grad_norm": 57.31139373779297,
50
+ "learning_rate": 3.90625e-07,
51
+ "loss": 0.71978759765625,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.13023255813953488,
56
+ "grad_norm": 56.42349624633789,
57
+ "learning_rate": 4.6875000000000006e-07,
58
+ "loss": 0.7164306640625,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.14883720930232558,
63
+ "grad_norm": 54.40520477294922,
64
+ "learning_rate": 5.468750000000001e-07,
65
+ "loss": 0.71539306640625,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.16744186046511628,
70
+ "grad_norm": 50.69281768798828,
71
+ "learning_rate": 6.25e-07,
72
+ "loss": 0.71405029296875,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.18604651162790697,
77
+ "grad_norm": 58.078224182128906,
78
+ "learning_rate": 7.03125e-07,
79
+ "loss": 0.71514892578125,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.20465116279069767,
84
+ "grad_norm": 60.195770263671875,
85
+ "learning_rate": 7.8125e-07,
86
+ "loss": 0.71466064453125,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.22325581395348837,
91
+ "grad_norm": 53.095191955566406,
92
+ "learning_rate": 8.59375e-07,
93
+ "loss": 0.71002197265625,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.24186046511627907,
98
+ "grad_norm": 49.17010498046875,
99
+ "learning_rate": 9.375000000000001e-07,
100
+ "loss": 0.70770263671875,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.26046511627906976,
105
+ "grad_norm": 50.612850189208984,
106
+ "learning_rate": 1.0156250000000001e-06,
107
+ "loss": 0.7069091796875,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.27906976744186046,
112
+ "grad_norm": 52.69828414916992,
113
+ "learning_rate": 1.0937500000000001e-06,
114
+ "loss": 0.71014404296875,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.29767441860465116,
119
+ "grad_norm": 59.4550895690918,
120
+ "learning_rate": 1.1718750000000001e-06,
121
+ "loss": 0.701416015625,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.31627906976744186,
126
+ "grad_norm": 55.300506591796875,
127
+ "learning_rate": 1.25e-06,
128
+ "loss": 0.6976318359375,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.33488372093023255,
133
+ "grad_norm": 47.445289611816406,
134
+ "learning_rate": 1.328125e-06,
135
+ "loss": 0.69403076171875,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.35348837209302325,
140
+ "grad_norm": 52.989654541015625,
141
+ "learning_rate": 1.40625e-06,
142
+ "loss": 0.69329833984375,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.37209302325581395,
147
+ "grad_norm": 45.23550033569336,
148
+ "learning_rate": 1.484375e-06,
149
+ "loss": 0.692138671875,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.39069767441860465,
154
+ "grad_norm": 51.775882720947266,
155
+ "learning_rate": 1.5625e-06,
156
+ "loss": 0.69146728515625,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.40930232558139534,
161
+ "grad_norm": 44.17149353027344,
162
+ "learning_rate": 1.640625e-06,
163
+ "loss": 0.66351318359375,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.42790697674418604,
168
+ "grad_norm": 44.85835266113281,
169
+ "learning_rate": 1.71875e-06,
170
+ "loss": 0.65997314453125,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.44651162790697674,
175
+ "grad_norm": 43.70960998535156,
176
+ "learning_rate": 1.796875e-06,
177
+ "loss": 0.65948486328125,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.46511627906976744,
182
+ "grad_norm": 43.53929138183594,
183
+ "learning_rate": 1.8750000000000003e-06,
184
+ "loss": 0.6571044921875,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.48372093023255813,
189
+ "grad_norm": 41.27622985839844,
190
+ "learning_rate": 1.953125e-06,
191
+ "loss": 0.65191650390625,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.5023255813953489,
196
+ "grad_norm": 45.456512451171875,
197
+ "learning_rate": 2.0312500000000002e-06,
198
+ "loss": 0.6461181640625,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.5209302325581395,
203
+ "grad_norm": 47.72049331665039,
204
+ "learning_rate": 2.109375e-06,
205
+ "loss": 0.639892578125,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.5395348837209303,
210
+ "grad_norm": 39.66932678222656,
211
+ "learning_rate": 2.1875000000000002e-06,
212
+ "loss": 0.64697265625,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.5581395348837209,
217
+ "grad_norm": 32.290470123291016,
218
+ "learning_rate": 2.265625e-06,
219
+ "loss": 0.61138916015625,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.5767441860465117,
224
+ "grad_norm": 33.039894104003906,
225
+ "learning_rate": 2.3437500000000002e-06,
226
+ "loss": 0.6019287109375,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.5953488372093023,
231
+ "grad_norm": 38.35325622558594,
232
+ "learning_rate": 2.421875e-06,
233
+ "loss": 0.5806884765625,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.6139534883720931,
238
+ "grad_norm": 33.649505615234375,
239
+ "learning_rate": 2.5e-06,
240
+ "loss": 0.58551025390625,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.6325581395348837,
245
+ "grad_norm": 30.9255428314209,
246
+ "learning_rate": 2.5781250000000004e-06,
247
+ "loss": 0.58953857421875,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.6511627906976745,
252
+ "grad_norm": 35.72899627685547,
253
+ "learning_rate": 2.65625e-06,
254
+ "loss": 0.572021484375,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.6697674418604651,
259
+ "grad_norm": 35.09605026245117,
260
+ "learning_rate": 2.7343750000000004e-06,
261
+ "loss": 0.555633544921875,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.6883720930232559,
266
+ "grad_norm": 29.248594284057617,
267
+ "learning_rate": 2.8125e-06,
268
+ "loss": 0.567535400390625,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.7069767441860465,
273
+ "grad_norm": 31.37779426574707,
274
+ "learning_rate": 2.8906250000000004e-06,
275
+ "loss": 0.5550537109375,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.7255813953488373,
280
+ "grad_norm": 30.69561767578125,
281
+ "learning_rate": 2.96875e-06,
282
+ "loss": 0.540008544921875,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.7441860465116279,
287
+ "grad_norm": 30.249013900756836,
288
+ "learning_rate": 3.0468750000000004e-06,
289
+ "loss": 0.526031494140625,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.7627906976744186,
294
+ "grad_norm": 30.84266471862793,
295
+ "learning_rate": 3.125e-06,
296
+ "loss": 0.4935302734375,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.7813953488372093,
301
+ "grad_norm": 23.530658721923828,
302
+ "learning_rate": 3.2031250000000004e-06,
303
+ "loss": 0.506683349609375,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.8,
308
+ "grad_norm": 26.80575180053711,
309
+ "learning_rate": 3.28125e-06,
310
+ "loss": 0.476959228515625,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.8186046511627907,
315
+ "grad_norm": 27.92676544189453,
316
+ "learning_rate": 3.3593750000000003e-06,
317
+ "loss": 0.452056884765625,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.8372093023255814,
322
+ "grad_norm": 14.391761779785156,
323
+ "learning_rate": 3.4375e-06,
324
+ "loss": 0.516387939453125,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.8558139534883721,
329
+ "grad_norm": 21.352672576904297,
330
+ "learning_rate": 3.5156250000000003e-06,
331
+ "loss": 0.4576416015625,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.8744186046511628,
336
+ "grad_norm": 17.331666946411133,
337
+ "learning_rate": 3.59375e-06,
338
+ "loss": 0.467803955078125,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.8930232558139535,
343
+ "grad_norm": 18.73495864868164,
344
+ "learning_rate": 3.6718750000000003e-06,
345
+ "loss": 0.446685791015625,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.9116279069767442,
350
+ "grad_norm": 16.758777618408203,
351
+ "learning_rate": 3.7500000000000005e-06,
352
+ "loss": 0.442779541015625,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.9302325581395349,
357
+ "grad_norm": 17.156814575195312,
358
+ "learning_rate": 3.828125000000001e-06,
359
+ "loss": 0.4298095703125,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.9488372093023256,
364
+ "grad_norm": 11.690564155578613,
365
+ "learning_rate": 3.90625e-06,
366
+ "loss": 0.448089599609375,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.9674418604651163,
371
+ "grad_norm": 12.62314510345459,
372
+ "learning_rate": 3.984375e-06,
373
+ "loss": 0.424957275390625,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.986046511627907,
378
+ "grad_norm": 8.785666465759277,
379
+ "learning_rate": 4.0625000000000005e-06,
380
+ "loss": 0.44073486328125,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.0,
385
+ "grad_norm": 9.357829093933105,
386
+ "learning_rate": 4.140625000000001e-06,
387
+ "loss": 0.413665771484375,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.0,
392
+ "step": 54,
393
+ "total_flos": 1.4367917178722714e+17,
394
+ "train_loss": 0.6073235405815972,
395
+ "train_runtime": 2167.6199,
396
+ "train_samples_per_second": 3.168,
397
+ "train_steps_per_second": 0.025
398
+ }
399
+ ],
400
+ "logging_steps": 1.0,
401
+ "max_steps": 54,
402
+ "num_input_tokens_seen": 0,
403
+ "num_train_epochs": 1,
404
+ "save_steps": 1000,
405
+ "stateful_callbacks": {
406
+ "TrainerControl": {
407
+ "args": {
408
+ "should_epoch_stop": false,
409
+ "should_evaluate": false,
410
+ "should_log": false,
411
+ "should_save": true,
412
+ "should_training_stop": true
413
+ },
414
+ "attributes": {}
415
+ }
416
+ },
417
+ "total_flos": 1.4367917178722714e+17,
418
+ "train_batch_size": 2,
419
+ "trial_name": null,
420
+ "trial_params": null
421
+ }