Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-DMAE-15e

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
Augusto777 commited on
Commit
6b80442
·
verified ·
1 Parent(s): fd4d5a2

End of training

Browse files
Files changed (9) hide show
  1. README.md +27 -27
  2. all_results.json +7 -7
  3. eval_results.json +3 -3
  4. model.safetensors +1 -1
  5. runs/Dec02_11-01-24_DESKTOP-SKBE9FB/events.out.tfevents.1733158885.DESKTOP-SKBE9FB.18420.0 +3 -0
  6. runs/Dec02_11-01-24_DESKTOP-SKBE9FB/events.out.tfevents.1733159077.DESKTOP-SKBE9FB.18420.1 +3 -0
  7. train_results.json +4 -4
  8. trainer_state.json +151 -151
  9. training_args.bin +1 -1
README.md CHANGED
@@ -74,33 +74,33 @@ The following hyperparameters were used during training:
74
  | 7.6529 | 6.0 | 21 | 7.4189 | 0.1087 |
75
  | 7.6529 | 6.86 | 24 | 7.2678 | 0.1087 |
76
  | 7.6529 | 8.0 | 28 | 7.0489 | 0.1087 |
77
- | 7.1056 | 8.86 | 31 | 6.8860 | 0.1087 |
78
- | 7.1056 | 10.0 | 35 | 6.6867 | 0.1087 |
79
- | 7.1056 | 10.86 | 38 | 6.5549 | 0.1087 |
80
- | 6.8482 | 12.0 | 42 | 6.3655 | 0.1087 |
81
- | 6.8482 | 12.86 | 45 | 6.2153 | 0.1087 |
82
- | 6.8482 | 14.0 | 49 | 6.0311 | 0.1087 |
83
- | 6.223 | 14.86 | 52 | 5.9038 | 0.1087 |
84
- | 6.223 | 16.0 | 56 | 5.7400 | 0.1087 |
85
- | 6.223 | 16.86 | 59 | 5.6276 | 0.1087 |
86
- | 5.8233 | 18.0 | 63 | 5.4884 | 0.1087 |
87
- | 5.8233 | 18.86 | 66 | 5.3910 | 0.1087 |
88
- | 5.5432 | 20.0 | 70 | 5.2690 | 0.1087 |
89
- | 5.5432 | 20.86 | 73 | 5.1828 | 0.1087 |
90
- | 5.5432 | 22.0 | 77 | 5.0761 | 0.1087 |
91
- | 5.2554 | 22.86 | 80 | 5.0026 | 0.1087 |
92
- | 5.2554 | 24.0 | 84 | 4.9136 | 0.1087 |
93
- | 5.2554 | 24.86 | 87 | 4.8525 | 0.1087 |
94
- | 5.0175 | 26.0 | 91 | 4.7792 | 0.1087 |
95
- | 5.0175 | 26.86 | 94 | 4.7304 | 0.1087 |
96
- | 5.0175 | 28.0 | 98 | 4.6736 | 0.1087 |
97
- | 4.7765 | 28.86 | 101 | 4.6371 | 0.1087 |
98
- | 4.7765 | 30.0 | 105 | 4.5968 | 0.1087 |
99
- | 4.7765 | 30.86 | 108 | 4.5726 | 0.1087 |
100
- | 4.7339 | 32.0 | 112 | 4.5483 | 0.1087 |
101
- | 4.7339 | 32.86 | 115 | 4.5361 | 0.1087 |
102
- | 4.7339 | 34.0 | 119 | 4.5280 | 0.1087 |
103
- | 4.6747 | 34.29 | 120 | 4.5274 | 0.1087 |
104
 
105
 
106
  ### Framework versions
 
74
  | 7.6529 | 6.0 | 21 | 7.4189 | 0.1087 |
75
  | 7.6529 | 6.86 | 24 | 7.2678 | 0.1087 |
76
  | 7.6529 | 8.0 | 28 | 7.0489 | 0.1087 |
77
+ | 7.1057 | 8.86 | 31 | 6.8846 | 0.1087 |
78
+ | 7.1057 | 10.0 | 35 | 6.6868 | 0.1087 |
79
+ | 7.1057 | 10.86 | 38 | 6.5595 | 0.1087 |
80
+ | 6.8483 | 12.0 | 42 | 6.3826 | 0.1087 |
81
+ | 6.8483 | 12.86 | 45 | 6.2276 | 0.1087 |
82
+ | 6.8483 | 14.0 | 49 | 6.0366 | 0.1087 |
83
+ | 6.224 | 14.86 | 52 | 5.9044 | 0.1087 |
84
+ | 6.224 | 16.0 | 56 | 5.7383 | 0.1087 |
85
+ | 6.224 | 16.86 | 59 | 5.6266 | 0.1087 |
86
+ | 5.8234 | 18.0 | 63 | 5.4871 | 0.1087 |
87
+ | 5.8234 | 18.86 | 66 | 5.3891 | 0.1087 |
88
+ | 5.5423 | 20.0 | 70 | 5.2672 | 0.1087 |
89
+ | 5.5423 | 20.86 | 73 | 5.1809 | 0.1087 |
90
+ | 5.5423 | 22.0 | 77 | 5.0741 | 0.1087 |
91
+ | 5.2547 | 22.86 | 80 | 5.0007 | 0.1087 |
92
+ | 5.2547 | 24.0 | 84 | 4.9116 | 0.1087 |
93
+ | 5.2547 | 24.86 | 87 | 4.8505 | 0.1087 |
94
+ | 5.0166 | 26.0 | 91 | 4.7770 | 0.1087 |
95
+ | 5.0166 | 26.86 | 94 | 4.7281 | 0.1087 |
96
+ | 5.0166 | 28.0 | 98 | 4.6712 | 0.1087 |
97
+ | 4.7751 | 28.86 | 101 | 4.6348 | 0.1087 |
98
+ | 4.7751 | 30.0 | 105 | 4.5943 | 0.1087 |
99
+ | 4.7751 | 30.86 | 108 | 4.5701 | 0.1087 |
100
+ | 4.7321 | 32.0 | 112 | 4.5458 | 0.1087 |
101
+ | 4.7321 | 32.86 | 115 | 4.5336 | 0.1087 |
102
+ | 4.7321 | 34.0 | 119 | 4.5255 | 0.1087 |
103
+ | 4.6731 | 34.29 | 120 | 4.5249 | 0.1087 |
104
 
105
 
106
  ### Framework versions
all_results.json CHANGED
@@ -2,11 +2,11 @@
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
  "eval_loss": 7.923763275146484,
5
- "eval_runtime": 0.9442,
6
- "eval_samples_per_second": 48.718,
7
- "eval_steps_per_second": 3.177,
8
- "train_loss": 5.965131664276123,
9
- "train_runtime": 192.4021,
10
- "train_samples_per_second": 44.282,
11
- "train_steps_per_second": 0.624
12
  }
 
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
  "eval_loss": 7.923763275146484,
5
+ "eval_runtime": 0.7612,
6
+ "eval_samples_per_second": 60.433,
7
+ "eval_steps_per_second": 3.941,
8
+ "train_loss": 5.964630603790283,
9
+ "train_runtime": 190.6471,
10
+ "train_samples_per_second": 44.69,
11
+ "train_steps_per_second": 0.629
12
  }
eval_results.json CHANGED
@@ -2,7 +2,7 @@
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
  "eval_loss": 7.923763275146484,
5
- "eval_runtime": 0.9442,
6
- "eval_samples_per_second": 48.718,
7
- "eval_steps_per_second": 3.177
8
  }
 
2
  "epoch": 34.29,
3
  "eval_accuracy": 0.10869565217391304,
4
  "eval_loss": 7.923763275146484,
5
+ "eval_runtime": 0.7612,
6
+ "eval_samples_per_second": 60.433,
7
+ "eval_steps_per_second": 3.941
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:210c09ff57d6f6d1e95232c07f47902171a10512323b61a5d5359942f62d8d52
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe81af29b698b42444742e7393ba8242b4c95958e1a2f510ad96d8851537cc90
3
  size 110356296
runs/Dec02_11-01-24_DESKTOP-SKBE9FB/events.out.tfevents.1733158885.DESKTOP-SKBE9FB.18420.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c8a8e9614016810c0af1175fe044d9cd513723ab01f5a8c2ec06fc51a18d901
3
+ size 18095
runs/Dec02_11-01-24_DESKTOP-SKBE9FB/events.out.tfevents.1733159077.DESKTOP-SKBE9FB.18420.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b05c4ac0e2a77bd349b782a3d95901d7277c8cd4fc22f2318d58f7d6db4262
3
+ size 405
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 34.29,
3
- "train_loss": 5.965131664276123,
4
- "train_runtime": 192.4021,
5
- "train_samples_per_second": 44.282,
6
- "train_steps_per_second": 0.624
7
  }
 
1
  {
2
  "epoch": 34.29,
3
+ "train_loss": 5.964630603790283,
4
+ "train_runtime": 190.6471,
5
+ "train_samples_per_second": 44.69,
6
+ "train_steps_per_second": 0.629
7
  }
trainer_state.json CHANGED
@@ -12,18 +12,18 @@
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
  "eval_loss": 7.923763275146484,
15
- "eval_runtime": 0.7392,
16
- "eval_samples_per_second": 62.232,
17
- "eval_steps_per_second": 4.059,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
  "eval_loss": 7.874618053436279,
24
- "eval_runtime": 0.7127,
25
- "eval_samples_per_second": 64.546,
26
- "eval_steps_per_second": 4.21,
27
  "step": 7
28
  },
29
  {
@@ -35,28 +35,28 @@
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
- "eval_loss": 7.818479537963867,
39
- "eval_runtime": 0.7227,
40
- "eval_samples_per_second": 63.653,
41
- "eval_steps_per_second": 4.151,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
  "eval_loss": 7.699648857116699,
48
- "eval_runtime": 0.7342,
49
- "eval_samples_per_second": 62.655,
50
- "eval_steps_per_second": 4.086,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
- "eval_loss": 7.587607383728027,
57
- "eval_runtime": 0.7147,
58
- "eval_samples_per_second": 64.365,
59
- "eval_steps_per_second": 4.198,
60
  "step": 17
61
  },
62
  {
@@ -68,341 +68,341 @@
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
- "eval_loss": 7.418882846832275,
72
- "eval_runtime": 0.7092,
73
- "eval_samples_per_second": 64.866,
74
- "eval_steps_per_second": 4.23,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
- "eval_loss": 7.2678446769714355,
81
- "eval_runtime": 0.7064,
82
- "eval_samples_per_second": 65.116,
83
- "eval_steps_per_second": 4.247,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
- "eval_loss": 7.0488600730896,
90
- "eval_runtime": 0.8282,
91
- "eval_samples_per_second": 55.543,
92
- "eval_steps_per_second": 3.622,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
  "learning_rate": 1.125e-05,
98
- "loss": 7.1056,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
- "eval_loss": 6.886016368865967,
105
- "eval_runtime": 0.7082,
106
- "eval_samples_per_second": 64.957,
107
- "eval_steps_per_second": 4.236,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
- "eval_loss": 6.686739921569824,
114
- "eval_runtime": 0.7412,
115
- "eval_samples_per_second": 62.064,
116
- "eval_steps_per_second": 4.048,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
- "eval_loss": 6.55491304397583,
123
- "eval_runtime": 0.7112,
124
- "eval_samples_per_second": 64.683,
125
- "eval_steps_per_second": 4.218,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
  "learning_rate": 9.999999999999999e-06,
131
- "loss": 6.8482,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
- "eval_loss": 6.365451335906982,
138
- "eval_runtime": 0.7332,
139
- "eval_samples_per_second": 62.742,
140
- "eval_steps_per_second": 4.092,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
- "eval_loss": 6.215301990509033,
147
- "eval_runtime": 0.7252,
148
- "eval_samples_per_second": 63.433,
149
- "eval_steps_per_second": 4.137,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
- "eval_loss": 6.0311198234558105,
156
- "eval_runtime": 0.7212,
157
- "eval_samples_per_second": 63.785,
158
- "eval_steps_per_second": 4.16,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
  "learning_rate": 8.750000000000001e-06,
164
- "loss": 6.223,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
- "eval_loss": 5.903781414031982,
171
- "eval_runtime": 0.7222,
172
- "eval_samples_per_second": 63.696,
173
- "eval_steps_per_second": 4.154,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
- "eval_loss": 5.7399983406066895,
180
- "eval_runtime": 0.7477,
181
- "eval_samples_per_second": 61.524,
182
- "eval_steps_per_second": 4.012,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
- "eval_loss": 5.627634525299072,
189
- "eval_runtime": 0.7197,
190
- "eval_samples_per_second": 63.918,
191
- "eval_steps_per_second": 4.169,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
  "learning_rate": 7.5e-06,
197
- "loss": 5.8233,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
- "eval_loss": 5.488417148590088,
204
- "eval_runtime": 0.7112,
205
- "eval_samples_per_second": 64.683,
206
- "eval_steps_per_second": 4.218,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
- "eval_loss": 5.391030311584473,
213
- "eval_runtime": 0.7452,
214
- "eval_samples_per_second": 61.731,
215
- "eval_steps_per_second": 4.026,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
  "learning_rate": 6.25e-06,
221
- "loss": 5.5432,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
- "eval_loss": 5.2689528465271,
228
- "eval_runtime": 0.7257,
229
- "eval_samples_per_second": 63.39,
230
- "eval_steps_per_second": 4.134,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
- "eval_loss": 5.182785511016846,
237
- "eval_runtime": 0.7282,
238
- "eval_samples_per_second": 63.173,
239
- "eval_steps_per_second": 4.12,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
- "eval_loss": 5.076084136962891,
246
- "eval_runtime": 0.7192,
247
- "eval_samples_per_second": 63.963,
248
- "eval_steps_per_second": 4.172,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
  "learning_rate": 4.9999999999999996e-06,
254
- "loss": 5.2554,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
- "eval_loss": 5.0026044845581055,
261
- "eval_runtime": 0.8007,
262
- "eval_samples_per_second": 57.45,
263
- "eval_steps_per_second": 3.747,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
- "eval_loss": 4.913613796234131,
270
- "eval_runtime": 0.7312,
271
- "eval_samples_per_second": 62.913,
272
- "eval_steps_per_second": 4.103,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
- "eval_loss": 4.852543830871582,
279
- "eval_runtime": 0.7112,
280
- "eval_samples_per_second": 64.683,
281
- "eval_steps_per_second": 4.218,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
  "learning_rate": 3.75e-06,
287
- "loss": 5.0175,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
- "eval_loss": 4.7791571617126465,
294
- "eval_runtime": 0.7142,
295
- "eval_samples_per_second": 64.411,
296
- "eval_steps_per_second": 4.201,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
- "eval_loss": 4.730408191680908,
303
- "eval_runtime": 0.7222,
304
- "eval_samples_per_second": 63.698,
305
- "eval_steps_per_second": 4.154,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
- "eval_loss": 4.673551559448242,
312
- "eval_runtime": 0.7282,
313
- "eval_samples_per_second": 63.173,
314
- "eval_steps_per_second": 4.12,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
  "learning_rate": 2.4999999999999998e-06,
320
- "loss": 4.7765,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
- "eval_loss": 4.637141227722168,
327
- "eval_runtime": 0.7492,
328
- "eval_samples_per_second": 61.401,
329
- "eval_steps_per_second": 4.004,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
- "eval_loss": 4.596778392791748,
336
- "eval_runtime": 0.7372,
337
- "eval_samples_per_second": 62.401,
338
- "eval_steps_per_second": 4.07,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
- "eval_loss": 4.572619915008545,
345
- "eval_runtime": 0.7372,
346
- "eval_samples_per_second": 62.401,
347
- "eval_steps_per_second": 4.07,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
  "learning_rate": 1.2499999999999999e-06,
353
- "loss": 4.7339,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
- "eval_loss": 4.548309326171875,
360
- "eval_runtime": 0.7537,
361
- "eval_samples_per_second": 61.034,
362
- "eval_steps_per_second": 3.98,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
- "eval_loss": 4.536120414733887,
369
- "eval_runtime": 0.7227,
370
- "eval_samples_per_second": 63.652,
371
- "eval_steps_per_second": 4.151,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
- "eval_loss": 4.528027057647705,
378
- "eval_runtime": 0.7282,
379
- "eval_samples_per_second": 63.172,
380
- "eval_steps_per_second": 4.12,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
- "loss": 4.6747,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
- "eval_loss": 4.527446746826172,
393
- "eval_runtime": 0.7392,
394
- "eval_samples_per_second": 62.232,
395
- "eval_steps_per_second": 4.059,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.3770905934823424e+17,
402
- "train_loss": 5.965131664276123,
403
- "train_runtime": 192.4021,
404
- "train_samples_per_second": 44.282,
405
- "train_steps_per_second": 0.624
406
  }
407
  ],
408
  "logging_steps": 10,
 
12
  "epoch": 0.86,
13
  "eval_accuracy": 0.10869565217391304,
14
  "eval_loss": 7.923763275146484,
15
+ "eval_runtime": 0.7307,
16
+ "eval_samples_per_second": 62.956,
17
+ "eval_steps_per_second": 4.106,
18
  "step": 3
19
  },
20
  {
21
  "epoch": 2.0,
22
  "eval_accuracy": 0.10869565217391304,
23
  "eval_loss": 7.874618053436279,
24
+ "eval_runtime": 0.7097,
25
+ "eval_samples_per_second": 64.819,
26
+ "eval_steps_per_second": 4.227,
27
  "step": 7
28
  },
29
  {
 
35
  {
36
  "epoch": 2.86,
37
  "eval_accuracy": 0.10869565217391304,
38
+ "eval_loss": 7.818480014801025,
39
+ "eval_runtime": 0.7207,
40
+ "eval_samples_per_second": 63.83,
41
+ "eval_steps_per_second": 4.163,
42
  "step": 10
43
  },
44
  {
45
  "epoch": 4.0,
46
  "eval_accuracy": 0.10869565217391304,
47
  "eval_loss": 7.699648857116699,
48
+ "eval_runtime": 0.7117,
49
+ "eval_samples_per_second": 64.637,
50
+ "eval_steps_per_second": 4.215,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 4.86,
55
  "eval_accuracy": 0.10869565217391304,
56
+ "eval_loss": 7.5876078605651855,
57
+ "eval_runtime": 0.7162,
58
+ "eval_samples_per_second": 64.231,
59
+ "eval_steps_per_second": 4.189,
60
  "step": 17
61
  },
62
  {
 
68
  {
69
  "epoch": 6.0,
70
  "eval_accuracy": 0.10869565217391304,
71
+ "eval_loss": 7.418884754180908,
72
+ "eval_runtime": 0.7127,
73
+ "eval_samples_per_second": 64.546,
74
+ "eval_steps_per_second": 4.21,
75
  "step": 21
76
  },
77
  {
78
  "epoch": 6.86,
79
  "eval_accuracy": 0.10869565217391304,
80
+ "eval_loss": 7.267844200134277,
81
+ "eval_runtime": 0.7112,
82
+ "eval_samples_per_second": 64.683,
83
+ "eval_steps_per_second": 4.218,
84
  "step": 24
85
  },
86
  {
87
  "epoch": 8.0,
88
  "eval_accuracy": 0.10869565217391304,
89
+ "eval_loss": 7.048880577087402,
90
+ "eval_runtime": 0.7262,
91
+ "eval_samples_per_second": 63.347,
92
+ "eval_steps_per_second": 4.131,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 8.57,
97
  "learning_rate": 1.125e-05,
98
+ "loss": 7.1057,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 8.86,
103
  "eval_accuracy": 0.10869565217391304,
104
+ "eval_loss": 6.884642124176025,
105
+ "eval_runtime": 0.7182,
106
+ "eval_samples_per_second": 64.052,
107
+ "eval_steps_per_second": 4.177,
108
  "step": 31
109
  },
110
  {
111
  "epoch": 10.0,
112
  "eval_accuracy": 0.10869565217391304,
113
+ "eval_loss": 6.686830043792725,
114
+ "eval_runtime": 0.7417,
115
+ "eval_samples_per_second": 62.022,
116
+ "eval_steps_per_second": 4.045,
117
  "step": 35
118
  },
119
  {
120
  "epoch": 10.86,
121
  "eval_accuracy": 0.10869565217391304,
122
+ "eval_loss": 6.559473991394043,
123
+ "eval_runtime": 0.7132,
124
+ "eval_samples_per_second": 64.5,
125
+ "eval_steps_per_second": 4.207,
126
  "step": 38
127
  },
128
  {
129
  "epoch": 11.43,
130
  "learning_rate": 9.999999999999999e-06,
131
+ "loss": 6.8483,
132
  "step": 40
133
  },
134
  {
135
  "epoch": 12.0,
136
  "eval_accuracy": 0.10869565217391304,
137
+ "eval_loss": 6.38260555267334,
138
+ "eval_runtime": 0.7272,
139
+ "eval_samples_per_second": 63.258,
140
+ "eval_steps_per_second": 4.126,
141
  "step": 42
142
  },
143
  {
144
  "epoch": 12.86,
145
  "eval_accuracy": 0.10869565217391304,
146
+ "eval_loss": 6.227572917938232,
147
+ "eval_runtime": 0.7182,
148
+ "eval_samples_per_second": 64.051,
149
+ "eval_steps_per_second": 4.177,
150
  "step": 45
151
  },
152
  {
153
  "epoch": 14.0,
154
  "eval_accuracy": 0.10869565217391304,
155
+ "eval_loss": 6.03657341003418,
156
+ "eval_runtime": 0.7132,
157
+ "eval_samples_per_second": 64.5,
158
+ "eval_steps_per_second": 4.207,
159
  "step": 49
160
  },
161
  {
162
  "epoch": 14.29,
163
  "learning_rate": 8.750000000000001e-06,
164
+ "loss": 6.224,
165
  "step": 50
166
  },
167
  {
168
  "epoch": 14.86,
169
  "eval_accuracy": 0.10869565217391304,
170
+ "eval_loss": 5.904354095458984,
171
+ "eval_runtime": 0.7787,
172
+ "eval_samples_per_second": 59.074,
173
+ "eval_steps_per_second": 3.853,
174
  "step": 52
175
  },
176
  {
177
  "epoch": 16.0,
178
  "eval_accuracy": 0.10869565217391304,
179
+ "eval_loss": 5.738274574279785,
180
+ "eval_runtime": 0.7132,
181
+ "eval_samples_per_second": 64.502,
182
+ "eval_steps_per_second": 4.207,
183
  "step": 56
184
  },
185
  {
186
  "epoch": 16.86,
187
  "eval_accuracy": 0.10869565217391304,
188
+ "eval_loss": 5.626614570617676,
189
+ "eval_runtime": 0.7317,
190
+ "eval_samples_per_second": 62.87,
191
+ "eval_steps_per_second": 4.1,
192
  "step": 59
193
  },
194
  {
195
  "epoch": 17.14,
196
  "learning_rate": 7.5e-06,
197
+ "loss": 5.8234,
198
  "step": 60
199
  },
200
  {
201
  "epoch": 18.0,
202
  "eval_accuracy": 0.10869565217391304,
203
+ "eval_loss": 5.487057209014893,
204
+ "eval_runtime": 0.7047,
205
+ "eval_samples_per_second": 65.279,
206
+ "eval_steps_per_second": 4.257,
207
  "step": 63
208
  },
209
  {
210
  "epoch": 18.86,
211
  "eval_accuracy": 0.10869565217391304,
212
+ "eval_loss": 5.389139652252197,
213
+ "eval_runtime": 0.7212,
214
+ "eval_samples_per_second": 63.786,
215
+ "eval_steps_per_second": 4.16,
216
  "step": 66
217
  },
218
  {
219
  "epoch": 20.0,
220
  "learning_rate": 6.25e-06,
221
+ "loss": 5.5423,
222
  "step": 70
223
  },
224
  {
225
  "epoch": 20.0,
226
  "eval_accuracy": 0.10869565217391304,
227
+ "eval_loss": 5.267205238342285,
228
+ "eval_runtime": 0.7192,
229
+ "eval_samples_per_second": 63.963,
230
+ "eval_steps_per_second": 4.172,
231
  "step": 70
232
  },
233
  {
234
  "epoch": 20.86,
235
  "eval_accuracy": 0.10869565217391304,
236
+ "eval_loss": 5.180857181549072,
237
+ "eval_runtime": 0.7337,
238
+ "eval_samples_per_second": 62.698,
239
+ "eval_steps_per_second": 4.089,
240
  "step": 73
241
  },
242
  {
243
  "epoch": 22.0,
244
  "eval_accuracy": 0.10869565217391304,
245
+ "eval_loss": 5.0741496086120605,
246
+ "eval_runtime": 0.7262,
247
+ "eval_samples_per_second": 63.347,
248
+ "eval_steps_per_second": 4.131,
249
  "step": 77
250
  },
251
  {
252
  "epoch": 22.86,
253
  "learning_rate": 4.9999999999999996e-06,
254
+ "loss": 5.2547,
255
  "step": 80
256
  },
257
  {
258
  "epoch": 22.86,
259
  "eval_accuracy": 0.10869565217391304,
260
+ "eval_loss": 5.000693321228027,
261
+ "eval_runtime": 0.6972,
262
+ "eval_samples_per_second": 65.982,
263
+ "eval_steps_per_second": 4.303,
264
  "step": 80
265
  },
266
  {
267
  "epoch": 24.0,
268
  "eval_accuracy": 0.10869565217391304,
269
+ "eval_loss": 4.911642551422119,
270
+ "eval_runtime": 0.7242,
271
+ "eval_samples_per_second": 63.522,
272
+ "eval_steps_per_second": 4.143,
273
  "step": 84
274
  },
275
  {
276
  "epoch": 24.86,
277
  "eval_accuracy": 0.10869565217391304,
278
+ "eval_loss": 4.850471019744873,
279
+ "eval_runtime": 0.7197,
280
+ "eval_samples_per_second": 63.918,
281
+ "eval_steps_per_second": 4.169,
282
  "step": 87
283
  },
284
  {
285
  "epoch": 25.71,
286
  "learning_rate": 3.75e-06,
287
+ "loss": 5.0166,
288
  "step": 90
289
  },
290
  {
291
  "epoch": 26.0,
292
  "eval_accuracy": 0.10869565217391304,
293
+ "eval_loss": 4.776952266693115,
294
+ "eval_runtime": 0.7807,
295
+ "eval_samples_per_second": 58.923,
296
+ "eval_steps_per_second": 3.843,
297
  "step": 91
298
  },
299
  {
300
  "epoch": 26.86,
301
  "eval_accuracy": 0.10869565217391304,
302
+ "eval_loss": 4.728125095367432,
303
+ "eval_runtime": 0.7177,
304
+ "eval_samples_per_second": 64.096,
305
+ "eval_steps_per_second": 4.18,
306
  "step": 94
307
  },
308
  {
309
  "epoch": 28.0,
310
  "eval_accuracy": 0.10869565217391304,
311
+ "eval_loss": 4.6712117195129395,
312
+ "eval_runtime": 0.7762,
313
+ "eval_samples_per_second": 59.264,
314
+ "eval_steps_per_second": 3.865,
315
  "step": 98
316
  },
317
  {
318
  "epoch": 28.57,
319
  "learning_rate": 2.4999999999999998e-06,
320
+ "loss": 4.7751,
321
  "step": 100
322
  },
323
  {
324
  "epoch": 28.86,
325
  "eval_accuracy": 0.10869565217391304,
326
+ "eval_loss": 4.634757041931152,
327
+ "eval_runtime": 0.7157,
328
+ "eval_samples_per_second": 64.275,
329
+ "eval_steps_per_second": 4.192,
330
  "step": 101
331
  },
332
  {
333
  "epoch": 30.0,
334
  "eval_accuracy": 0.10869565217391304,
335
+ "eval_loss": 4.594343185424805,
336
+ "eval_runtime": 0.7407,
337
+ "eval_samples_per_second": 62.106,
338
+ "eval_steps_per_second": 4.05,
339
  "step": 105
340
  },
341
  {
342
  "epoch": 30.86,
343
  "eval_accuracy": 0.10869565217391304,
344
+ "eval_loss": 4.570145130157471,
345
+ "eval_runtime": 0.7192,
346
+ "eval_samples_per_second": 63.963,
347
+ "eval_steps_per_second": 4.172,
348
  "step": 108
349
  },
350
  {
351
  "epoch": 31.43,
352
  "learning_rate": 1.2499999999999999e-06,
353
+ "loss": 4.7321,
354
  "step": 110
355
  },
356
  {
357
  "epoch": 32.0,
358
  "eval_accuracy": 0.10869565217391304,
359
+ "eval_loss": 4.545791149139404,
360
+ "eval_runtime": 0.7197,
361
+ "eval_samples_per_second": 63.918,
362
+ "eval_steps_per_second": 4.169,
363
  "step": 112
364
  },
365
  {
366
  "epoch": 32.86,
367
  "eval_accuracy": 0.10869565217391304,
368
+ "eval_loss": 4.533587455749512,
369
+ "eval_runtime": 0.7117,
370
+ "eval_samples_per_second": 64.637,
371
+ "eval_steps_per_second": 4.215,
372
  "step": 115
373
  },
374
  {
375
  "epoch": 34.0,
376
  "eval_accuracy": 0.10869565217391304,
377
+ "eval_loss": 4.525488376617432,
378
+ "eval_runtime": 0.7257,
379
+ "eval_samples_per_second": 63.39,
380
+ "eval_steps_per_second": 4.134,
381
  "step": 119
382
  },
383
  {
384
  "epoch": 34.29,
385
  "learning_rate": 0.0,
386
+ "loss": 4.6731,
387
  "step": 120
388
  },
389
  {
390
  "epoch": 34.29,
391
  "eval_accuracy": 0.10869565217391304,
392
+ "eval_loss": 4.524907112121582,
393
+ "eval_runtime": 0.7682,
394
+ "eval_samples_per_second": 59.882,
395
+ "eval_steps_per_second": 3.905,
396
  "step": 120
397
  },
398
  {
399
  "epoch": 34.29,
400
  "step": 120,
401
  "total_flos": 2.3770905934823424e+17,
402
+ "train_loss": 5.964630603790283,
403
+ "train_runtime": 190.6471,
404
+ "train_samples_per_second": 44.69,
405
+ "train_steps_per_second": 0.629
406
  }
407
  ],
408
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42e6dd5fe2185c3541871e6a294f52ee5dc548ee7730132acdfe07944e894b8f
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ed5746f1700e6d98774fcdfef20d22debc84c10727de3db3ef22a1113ee59f
3
  size 4792