danelcsb commited on
Commit
7064399
1 Parent(s): 041288b

End of training

Browse files
README.md CHANGED
@@ -2,6 +2,8 @@
2
  license: apache-2.0
3
  base_model: IDEA-Research/grounding-dino-tiny
4
  tags:
 
 
5
  - generated_from_trainer
6
  model-index:
7
  - name: grounding-dino-tiny-finetuned-cppe-5-10k-steps
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # grounding-dino-tiny-finetuned-cppe-5-10k-steps
15
 
16
- This model is a fine-tuned version of [IDEA-Research/grounding-dino-tiny](https://huggingface.co/IDEA-Research/grounding-dino-tiny) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 5.5317
19
  - Map: 0.0151
 
2
  license: apache-2.0
3
  base_model: IDEA-Research/grounding-dino-tiny
4
  tags:
5
+ - object-detection
6
+ - vision
7
  - generated_from_trainer
8
  model-index:
9
  - name: grounding-dino-tiny-finetuned-cppe-5-10k-steps
 
15
 
16
  # grounding-dino-tiny-finetuned-cppe-5-10k-steps
17
 
18
+ This model is a fine-tuned version of [IDEA-Research/grounding-dino-tiny](https://huggingface.co/IDEA-Research/grounding-dino-tiny) on the cppe-5 dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 5.5317
21
  - Map: 0.0151
all_results.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "test_loss": 4.769590377807617,
4
+ "test_map": 0.0362,
5
+ "test_map_50": 0.0515,
6
+ "test_map_75": 0.0389,
7
+ "test_map_Coverall": 0.181,
8
+ "test_map_Face_Shield": 0.0,
9
+ "test_map_Gloves": 0.0,
10
+ "test_map_Goggles": 0.0,
11
+ "test_map_Mask": 0.0,
12
+ "test_map_large": 0.0462,
13
+ "test_map_medium": 0.0376,
14
+ "test_map_small": 0.1143,
15
+ "test_mar_1": 0.0221,
16
+ "test_mar_10": 0.1204,
17
+ "test_mar_100": 0.1421,
18
+ "test_mar_100_Coverall": 0.7106,
19
+ "test_mar_100_Face_Shield": 0.0,
20
+ "test_mar_100_Gloves": 0.0,
21
+ "test_mar_100_Goggles": 0.0,
22
+ "test_mar_100_Mask": 0.0,
23
+ "test_mar_large": 0.1588,
24
+ "test_mar_medium": 0.1544,
25
+ "test_mar_small": 0.1667,
26
+ "test_runtime": 9.2109,
27
+ "test_samples_per_second": 3.148,
28
+ "test_steps_per_second": 3.148,
29
+ "total_flos": 1.946309821216161e+19,
30
+ "train_loss": 841.0750103975183,
31
+ "train_runtime": 4302.0466,
32
+ "train_samples_per_second": 1.976,
33
+ "train_steps_per_second": 1.976
34
+ }
runs/Aug09_04-42-08_a44b5742ff80/events.out.tfevents.1723182963.a44b5742ff80.6692.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f7f7a2c73ccfafca67527ccc3d8535bd844684d4fae4a40fdffa87e7e35f1e
3
+ size 1548
test_results.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "test_loss": 4.769590377807617,
4
+ "test_map": 0.0362,
5
+ "test_map_50": 0.0515,
6
+ "test_map_75": 0.0389,
7
+ "test_map_Coverall": 0.181,
8
+ "test_map_Face_Shield": 0.0,
9
+ "test_map_Gloves": 0.0,
10
+ "test_map_Goggles": 0.0,
11
+ "test_map_Mask": 0.0,
12
+ "test_map_large": 0.0462,
13
+ "test_map_medium": 0.0376,
14
+ "test_map_small": 0.1143,
15
+ "test_mar_1": 0.0221,
16
+ "test_mar_10": 0.1204,
17
+ "test_mar_100": 0.1421,
18
+ "test_mar_100_Coverall": 0.7106,
19
+ "test_mar_100_Face_Shield": 0.0,
20
+ "test_mar_100_Gloves": 0.0,
21
+ "test_mar_100_Goggles": 0.0,
22
+ "test_mar_100_Mask": 0.0,
23
+ "test_mar_large": 0.1588,
24
+ "test_mar_medium": 0.1544,
25
+ "test_mar_small": 0.1667,
26
+ "test_runtime": 9.2109,
27
+ "test_samples_per_second": 3.148,
28
+ "test_steps_per_second": 3.148
29
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 1.946309821216161e+19,
4
+ "train_loss": 841.0750103975183,
5
+ "train_runtime": 4302.0466,
6
+ "train_samples_per_second": 1.976,
7
+ "train_steps_per_second": 1.976
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,412 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0182,
3
+ "best_model_checkpoint": "grounding-dino-tiny-finetuned-cppe-5-10k-steps/checkpoint-7650",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8500,
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": 64.9486312866211,
14
+ "learning_rate": 4.5e-05,
15
+ "loss": 8355.9482,
16
+ "step": 850
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 6.613674163818359,
21
+ "eval_map": 0.014,
22
+ "eval_map_50": 0.0272,
23
+ "eval_map_75": 0.0134,
24
+ "eval_map_Coverall": 0.0702,
25
+ "eval_map_Face_Shield": 0.0,
26
+ "eval_map_Gloves": 0.0,
27
+ "eval_map_Goggles": 0.0,
28
+ "eval_map_Mask": 0.0,
29
+ "eval_map_large": 0.0243,
30
+ "eval_map_medium": 0.0111,
31
+ "eval_map_small": 0.0048,
32
+ "eval_mar_1": 0.0149,
33
+ "eval_mar_10": 0.0893,
34
+ "eval_mar_100": 0.1073,
35
+ "eval_mar_100_Coverall": 0.5366,
36
+ "eval_mar_100_Face_Shield": 0.0,
37
+ "eval_mar_100_Gloves": 0.0,
38
+ "eval_mar_100_Goggles": 0.0,
39
+ "eval_mar_100_Mask": 0.0,
40
+ "eval_mar_large": 0.1328,
41
+ "eval_mar_medium": 0.0889,
42
+ "eval_mar_small": 0.0523,
43
+ "eval_runtime": 39.8427,
44
+ "eval_samples_per_second": 3.765,
45
+ "eval_steps_per_second": 3.765,
46
+ "step": 850
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "grad_norm": 49.31262969970703,
51
+ "learning_rate": 4e-05,
52
+ "loss": 6.7523,
53
+ "step": 1700
54
+ },
55
+ {
56
+ "epoch": 2.0,
57
+ "eval_loss": 6.2356672286987305,
58
+ "eval_map": 0.0162,
59
+ "eval_map_50": 0.0302,
60
+ "eval_map_75": 0.0148,
61
+ "eval_map_Coverall": 0.0809,
62
+ "eval_map_Face_Shield": 0.0,
63
+ "eval_map_Gloves": 0.0,
64
+ "eval_map_Goggles": 0.0,
65
+ "eval_map_Mask": 0.0,
66
+ "eval_map_large": 0.0192,
67
+ "eval_map_medium": 0.0189,
68
+ "eval_map_small": 0.0106,
69
+ "eval_mar_1": 0.0247,
70
+ "eval_mar_10": 0.0894,
71
+ "eval_mar_100": 0.107,
72
+ "eval_mar_100_Coverall": 0.535,
73
+ "eval_mar_100_Face_Shield": 0.0,
74
+ "eval_mar_100_Gloves": 0.0,
75
+ "eval_mar_100_Goggles": 0.0,
76
+ "eval_mar_100_Mask": 0.0,
77
+ "eval_mar_large": 0.1258,
78
+ "eval_mar_medium": 0.0968,
79
+ "eval_mar_small": 0.0643,
80
+ "eval_runtime": 38.5396,
81
+ "eval_samples_per_second": 3.892,
82
+ "eval_steps_per_second": 3.892,
83
+ "step": 1700
84
+ },
85
+ {
86
+ "epoch": 3.0,
87
+ "grad_norm": 112.90940856933594,
88
+ "learning_rate": 3.5e-05,
89
+ "loss": 6.5566,
90
+ "step": 2550
91
+ },
92
+ {
93
+ "epoch": 3.0,
94
+ "eval_loss": 6.08903169631958,
95
+ "eval_map": 0.0158,
96
+ "eval_map_50": 0.0294,
97
+ "eval_map_75": 0.0134,
98
+ "eval_map_Coverall": 0.0791,
99
+ "eval_map_Face_Shield": 0.0,
100
+ "eval_map_Gloves": 0.0,
101
+ "eval_map_Goggles": 0.0,
102
+ "eval_map_Mask": 0.0,
103
+ "eval_map_large": 0.0215,
104
+ "eval_map_medium": 0.0199,
105
+ "eval_map_small": 0.01,
106
+ "eval_mar_1": 0.0222,
107
+ "eval_mar_10": 0.0876,
108
+ "eval_mar_100": 0.1065,
109
+ "eval_mar_100_Coverall": 0.5323,
110
+ "eval_mar_100_Face_Shield": 0.0,
111
+ "eval_mar_100_Gloves": 0.0,
112
+ "eval_mar_100_Goggles": 0.0,
113
+ "eval_mar_100_Mask": 0.0,
114
+ "eval_mar_large": 0.1324,
115
+ "eval_mar_medium": 0.0846,
116
+ "eval_mar_small": 0.0671,
117
+ "eval_runtime": 37.4163,
118
+ "eval_samples_per_second": 4.009,
119
+ "eval_steps_per_second": 4.009,
120
+ "step": 2550
121
+ },
122
+ {
123
+ "epoch": 4.0,
124
+ "grad_norm": 24.23554039001465,
125
+ "learning_rate": 3e-05,
126
+ "loss": 6.2217,
127
+ "step": 3400
128
+ },
129
+ {
130
+ "epoch": 4.0,
131
+ "eval_loss": 5.902782440185547,
132
+ "eval_map": 0.0144,
133
+ "eval_map_50": 0.0271,
134
+ "eval_map_75": 0.0134,
135
+ "eval_map_Coverall": 0.0721,
136
+ "eval_map_Face_Shield": 0.0,
137
+ "eval_map_Gloves": 0.0,
138
+ "eval_map_Goggles": 0.0,
139
+ "eval_map_Mask": 0.0,
140
+ "eval_map_large": 0.0225,
141
+ "eval_map_medium": 0.0096,
142
+ "eval_map_small": 0.0066,
143
+ "eval_mar_1": 0.0232,
144
+ "eval_mar_10": 0.0857,
145
+ "eval_mar_100": 0.107,
146
+ "eval_mar_100_Coverall": 0.5348,
147
+ "eval_mar_100_Face_Shield": 0.0,
148
+ "eval_mar_100_Gloves": 0.0,
149
+ "eval_mar_100_Goggles": 0.0,
150
+ "eval_mar_100_Mask": 0.0,
151
+ "eval_mar_large": 0.1397,
152
+ "eval_mar_medium": 0.0823,
153
+ "eval_mar_small": 0.06,
154
+ "eval_runtime": 38.3987,
155
+ "eval_samples_per_second": 3.906,
156
+ "eval_steps_per_second": 3.906,
157
+ "step": 3400
158
+ },
159
+ {
160
+ "epoch": 5.0,
161
+ "grad_norm": 103.00000762939453,
162
+ "learning_rate": 2.5e-05,
163
+ "loss": 6.0963,
164
+ "step": 4250
165
+ },
166
+ {
167
+ "epoch": 5.0,
168
+ "eval_loss": 5.841100692749023,
169
+ "eval_map": 0.0126,
170
+ "eval_map_50": 0.0215,
171
+ "eval_map_75": 0.014,
172
+ "eval_map_Coverall": 0.0631,
173
+ "eval_map_Face_Shield": 0.0,
174
+ "eval_map_Gloves": 0.0,
175
+ "eval_map_Goggles": 0.0,
176
+ "eval_map_Mask": 0.0,
177
+ "eval_map_large": 0.0178,
178
+ "eval_map_medium": 0.0138,
179
+ "eval_map_small": 0.0055,
180
+ "eval_mar_1": 0.0201,
181
+ "eval_mar_10": 0.0811,
182
+ "eval_mar_100": 0.1052,
183
+ "eval_mar_100_Coverall": 0.5258,
184
+ "eval_mar_100_Face_Shield": 0.0,
185
+ "eval_mar_100_Gloves": 0.0,
186
+ "eval_mar_100_Goggles": 0.0,
187
+ "eval_mar_100_Mask": 0.0,
188
+ "eval_mar_large": 0.1377,
189
+ "eval_mar_medium": 0.0942,
190
+ "eval_mar_small": 0.044,
191
+ "eval_runtime": 37.9192,
192
+ "eval_samples_per_second": 3.956,
193
+ "eval_steps_per_second": 3.956,
194
+ "step": 4250
195
+ },
196
+ {
197
+ "epoch": 6.0,
198
+ "grad_norm": 100.59229278564453,
199
+ "learning_rate": 2e-05,
200
+ "loss": 5.996,
201
+ "step": 5100
202
+ },
203
+ {
204
+ "epoch": 6.0,
205
+ "eval_loss": 5.724414825439453,
206
+ "eval_map": 0.0162,
207
+ "eval_map_50": 0.0311,
208
+ "eval_map_75": 0.0166,
209
+ "eval_map_Coverall": 0.0812,
210
+ "eval_map_Face_Shield": 0.0,
211
+ "eval_map_Gloves": 0.0,
212
+ "eval_map_Goggles": 0.0,
213
+ "eval_map_Mask": 0.0,
214
+ "eval_map_large": 0.0221,
215
+ "eval_map_medium": 0.0145,
216
+ "eval_map_small": 0.0059,
217
+ "eval_mar_1": 0.0223,
218
+ "eval_mar_10": 0.0869,
219
+ "eval_mar_100": 0.1088,
220
+ "eval_mar_100_Coverall": 0.5437,
221
+ "eval_mar_100_Face_Shield": 0.0,
222
+ "eval_mar_100_Gloves": 0.0,
223
+ "eval_mar_100_Goggles": 0.0,
224
+ "eval_mar_100_Mask": 0.0,
225
+ "eval_mar_large": 0.1328,
226
+ "eval_mar_medium": 0.0919,
227
+ "eval_mar_small": 0.0667,
228
+ "eval_runtime": 37.3147,
229
+ "eval_samples_per_second": 4.02,
230
+ "eval_steps_per_second": 4.02,
231
+ "step": 5100
232
+ },
233
+ {
234
+ "epoch": 7.0,
235
+ "grad_norm": 121.10063934326172,
236
+ "learning_rate": 1.5e-05,
237
+ "loss": 5.8971,
238
+ "step": 5950
239
+ },
240
+ {
241
+ "epoch": 7.0,
242
+ "eval_loss": 5.547349452972412,
243
+ "eval_map": 0.0154,
244
+ "eval_map_50": 0.027,
245
+ "eval_map_75": 0.016,
246
+ "eval_map_Coverall": 0.0769,
247
+ "eval_map_Face_Shield": 0.0,
248
+ "eval_map_Gloves": 0.0,
249
+ "eval_map_Goggles": 0.0,
250
+ "eval_map_Mask": 0.0,
251
+ "eval_map_large": 0.0208,
252
+ "eval_map_medium": 0.014,
253
+ "eval_map_small": 0.01,
254
+ "eval_mar_1": 0.0244,
255
+ "eval_mar_10": 0.0946,
256
+ "eval_mar_100": 0.1154,
257
+ "eval_mar_100_Coverall": 0.5772,
258
+ "eval_mar_100_Face_Shield": 0.0,
259
+ "eval_mar_100_Gloves": 0.0,
260
+ "eval_mar_100_Goggles": 0.0,
261
+ "eval_mar_100_Mask": 0.0,
262
+ "eval_mar_large": 0.1311,
263
+ "eval_mar_medium": 0.106,
264
+ "eval_mar_small": 0.084,
265
+ "eval_runtime": 37.3478,
266
+ "eval_samples_per_second": 4.016,
267
+ "eval_steps_per_second": 4.016,
268
+ "step": 5950
269
+ },
270
+ {
271
+ "epoch": 8.0,
272
+ "grad_norm": 67.22107696533203,
273
+ "learning_rate": 1e-05,
274
+ "loss": 5.7451,
275
+ "step": 6800
276
+ },
277
+ {
278
+ "epoch": 8.0,
279
+ "eval_loss": 5.523053169250488,
280
+ "eval_map": 0.0146,
281
+ "eval_map_50": 0.0267,
282
+ "eval_map_75": 0.0148,
283
+ "eval_map_Coverall": 0.0731,
284
+ "eval_map_Face_Shield": 0.0,
285
+ "eval_map_Gloves": 0.0,
286
+ "eval_map_Goggles": 0.0,
287
+ "eval_map_Mask": 0.0,
288
+ "eval_map_large": 0.0183,
289
+ "eval_map_medium": 0.0161,
290
+ "eval_map_small": 0.0021,
291
+ "eval_mar_1": 0.0256,
292
+ "eval_mar_10": 0.0905,
293
+ "eval_mar_100": 0.1125,
294
+ "eval_mar_100_Coverall": 0.5624,
295
+ "eval_mar_100_Face_Shield": 0.0,
296
+ "eval_mar_100_Gloves": 0.0,
297
+ "eval_mar_100_Goggles": 0.0,
298
+ "eval_mar_100_Mask": 0.0,
299
+ "eval_mar_large": 0.128,
300
+ "eval_mar_medium": 0.1062,
301
+ "eval_mar_small": 0.0325,
302
+ "eval_runtime": 37.1808,
303
+ "eval_samples_per_second": 4.034,
304
+ "eval_steps_per_second": 4.034,
305
+ "step": 6800
306
+ },
307
+ {
308
+ "epoch": 9.0,
309
+ "grad_norm": 40.62353515625,
310
+ "learning_rate": 5e-06,
311
+ "loss": 5.7931,
312
+ "step": 7650
313
+ },
314
+ {
315
+ "epoch": 9.0,
316
+ "eval_loss": 5.518974781036377,
317
+ "eval_map": 0.0182,
318
+ "eval_map_50": 0.032,
319
+ "eval_map_75": 0.0195,
320
+ "eval_map_Coverall": 0.091,
321
+ "eval_map_Face_Shield": 0.0,
322
+ "eval_map_Gloves": 0.0,
323
+ "eval_map_Goggles": 0.0,
324
+ "eval_map_Mask": 0.0,
325
+ "eval_map_large": 0.0249,
326
+ "eval_map_medium": 0.0147,
327
+ "eval_map_small": 0.0175,
328
+ "eval_mar_1": 0.0299,
329
+ "eval_mar_10": 0.1048,
330
+ "eval_mar_100": 0.1138,
331
+ "eval_mar_100_Coverall": 0.5688,
332
+ "eval_mar_100_Face_Shield": 0.0,
333
+ "eval_mar_100_Gloves": 0.0,
334
+ "eval_mar_100_Goggles": 0.0,
335
+ "eval_mar_100_Mask": 0.0,
336
+ "eval_mar_large": 0.1309,
337
+ "eval_mar_medium": 0.0945,
338
+ "eval_mar_small": 0.08,
339
+ "eval_runtime": 36.2829,
340
+ "eval_samples_per_second": 4.134,
341
+ "eval_steps_per_second": 4.134,
342
+ "step": 7650
343
+ },
344
+ {
345
+ "epoch": 10.0,
346
+ "grad_norm": 38.14755630493164,
347
+ "learning_rate": 0.0,
348
+ "loss": 5.7435,
349
+ "step": 8500
350
+ },
351
+ {
352
+ "epoch": 10.0,
353
+ "eval_loss": 5.531744956970215,
354
+ "eval_map": 0.0151,
355
+ "eval_map_50": 0.0275,
356
+ "eval_map_75": 0.0157,
357
+ "eval_map_Coverall": 0.0755,
358
+ "eval_map_Face_Shield": 0.0,
359
+ "eval_map_Gloves": 0.0,
360
+ "eval_map_Goggles": 0.0,
361
+ "eval_map_Mask": 0.0,
362
+ "eval_map_large": 0.0236,
363
+ "eval_map_medium": 0.0149,
364
+ "eval_map_small": 0.0125,
365
+ "eval_mar_1": 0.0202,
366
+ "eval_mar_10": 0.0902,
367
+ "eval_mar_100": 0.1127,
368
+ "eval_mar_100_Coverall": 0.5636,
369
+ "eval_mar_100_Face_Shield": 0.0,
370
+ "eval_mar_100_Gloves": 0.0,
371
+ "eval_mar_100_Goggles": 0.0,
372
+ "eval_mar_100_Mask": 0.0,
373
+ "eval_mar_large": 0.1461,
374
+ "eval_mar_medium": 0.0975,
375
+ "eval_mar_small": 0.0815,
376
+ "eval_runtime": 36.9405,
377
+ "eval_samples_per_second": 4.061,
378
+ "eval_steps_per_second": 4.061,
379
+ "step": 8500
380
+ },
381
+ {
382
+ "epoch": 10.0,
383
+ "step": 8500,
384
+ "total_flos": 1.946309821216161e+19,
385
+ "train_loss": 841.0750103975183,
386
+ "train_runtime": 4302.0466,
387
+ "train_samples_per_second": 1.976,
388
+ "train_steps_per_second": 1.976
389
+ }
390
+ ],
391
+ "logging_steps": 500,
392
+ "max_steps": 8500,
393
+ "num_input_tokens_seen": 0,
394
+ "num_train_epochs": 10,
395
+ "save_steps": 500,
396
+ "stateful_callbacks": {
397
+ "TrainerControl": {
398
+ "args": {
399
+ "should_epoch_stop": false,
400
+ "should_evaluate": false,
401
+ "should_log": false,
402
+ "should_save": true,
403
+ "should_training_stop": true
404
+ },
405
+ "attributes": {}
406
+ }
407
+ },
408
+ "total_flos": 1.946309821216161e+19,
409
+ "train_batch_size": 1,
410
+ "trial_name": null,
411
+ "trial_params": null
412
+ }