jaypratap commited on
Commit
b74a66b
1 Parent(s): 60eaeee

Model save

Browse files
README.md ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/vit-mae-base
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ model-index:
9
+ - name: vit-pretraining-2024_04_02
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # vit-pretraining-2024_04_02
17
+
18
+ This model is a fine-tuned version of [facebook/vit-mae-base](https://huggingface.co/facebook/vit-mae-base) on the imagefolder dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0131
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 4.6875e-06
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_ratio: 0.05
46
+ - num_epochs: 400.0
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-------:|:---------------:|
52
+ | 0.0282 | 1.0 | 3583 | 0.0275 |
53
+ | 0.0271 | 2.0 | 7166 | 0.0234 |
54
+ | 0.0203 | 3.0 | 10749 | 0.0218 |
55
+ | 0.0218 | 4.0 | 14332 | 0.0203 |
56
+ | 0.0195 | 5.0 | 17915 | 0.0191 |
57
+ | 0.0174 | 6.0 | 21498 | 0.0186 |
58
+ | 0.0173 | 7.0 | 25081 | 0.0181 |
59
+ | 0.0163 | 8.0 | 28664 | 0.0177 |
60
+ | 0.0172 | 9.0 | 32247 | 0.0173 |
61
+ | 0.0165 | 10.0 | 35830 | 0.0173 |
62
+ | 0.0173 | 11.0 | 39413 | 0.0169 |
63
+ | 0.0156 | 12.0 | 42996 | 0.0166 |
64
+ | 0.0168 | 13.0 | 46579 | 0.0165 |
65
+ | 0.0156 | 14.0 | 50162 | 0.0163 |
66
+ | 0.0152 | 15.0 | 53745 | 0.0161 |
67
+ | 0.0153 | 16.0 | 57328 | 0.0159 |
68
+ | 0.0163 | 17.0 | 60911 | 0.0158 |
69
+ | 0.0148 | 18.0 | 64494 | 0.0160 |
70
+ | 0.0144 | 19.0 | 68077 | 0.0159 |
71
+ | 0.0148 | 20.0 | 71660 | 0.0155 |
72
+ | 0.0169 | 21.0 | 75243 | 0.0156 |
73
+ | 0.0154 | 22.0 | 78826 | 0.0155 |
74
+ | 0.0151 | 23.0 | 82409 | 0.0154 |
75
+ | 0.0135 | 24.0 | 85992 | 0.0153 |
76
+ | 0.0157 | 25.0 | 89575 | 0.0153 |
77
+ | 0.0165 | 26.0 | 93158 | 0.0152 |
78
+ | 0.0146 | 27.0 | 96741 | 0.0151 |
79
+ | 0.0171 | 28.0 | 100324 | 0.0150 |
80
+ | 0.015 | 29.0 | 103907 | 0.0151 |
81
+ | 0.0165 | 30.0 | 107490 | 0.0152 |
82
+ | 0.0136 | 31.0 | 111073 | 0.0150 |
83
+ | 0.0147 | 32.0 | 114656 | 0.0147 |
84
+ | 0.0153 | 33.0 | 118239 | 0.0149 |
85
+ | 0.0135 | 34.0 | 121822 | 0.0147 |
86
+ | 0.0144 | 35.0 | 125405 | 0.0147 |
87
+ | 0.0155 | 36.0 | 128988 | 0.0148 |
88
+ | 0.0172 | 37.0 | 132571 | 0.0147 |
89
+ | 0.0141 | 38.0 | 136154 | 0.0149 |
90
+ | 0.0152 | 39.0 | 139737 | 0.0146 |
91
+ | 0.014 | 40.0 | 143320 | 0.0148 |
92
+ | 0.0158 | 41.0 | 146903 | 0.0147 |
93
+ | 0.0151 | 42.0 | 150486 | 0.0145 |
94
+ | 0.0155 | 43.0 | 154069 | 0.0147 |
95
+ | 0.0152 | 44.0 | 157652 | 0.0148 |
96
+ | 0.014 | 45.0 | 161235 | 0.0147 |
97
+ | 0.0142 | 46.0 | 164818 | 0.0145 |
98
+ | 0.014 | 47.0 | 168401 | 0.0147 |
99
+ | 0.0156 | 48.0 | 171984 | 0.0147 |
100
+ | 0.0138 | 49.0 | 175567 | 0.0145 |
101
+ | 0.0142 | 50.0 | 179150 | 0.0147 |
102
+ | 0.0142 | 51.0 | 182733 | 0.0143 |
103
+ | 0.014 | 52.0 | 186316 | 0.0143 |
104
+ | 0.0139 | 53.0 | 189899 | 0.0145 |
105
+ | 0.0133 | 54.0 | 193482 | 0.0146 |
106
+ | 0.0135 | 55.0 | 197065 | 0.0144 |
107
+ | 0.0137 | 56.0 | 200648 | 0.0145 |
108
+ | 0.0138 | 57.0 | 204231 | 0.0144 |
109
+ | 0.014 | 58.0 | 207814 | 0.0144 |
110
+ | 0.0139 | 59.0 | 211397 | 0.0144 |
111
+ | 0.0163 | 60.0 | 214980 | 0.0144 |
112
+ | 0.0163 | 61.0 | 218563 | 0.0142 |
113
+ | 0.016 | 62.0 | 222146 | 0.0144 |
114
+ | 0.0136 | 63.0 | 225729 | 0.0141 |
115
+ | 0.0152 | 64.0 | 229312 | 0.0142 |
116
+ | 0.0134 | 65.0 | 232895 | 0.0143 |
117
+ | 0.0146 | 66.0 | 236478 | 0.0143 |
118
+ | 0.0149 | 67.0 | 240061 | 0.0141 |
119
+ | 0.0148 | 68.0 | 243644 | 0.0144 |
120
+ | 0.0141 | 69.0 | 247227 | 0.0143 |
121
+ | 0.0145 | 70.0 | 250810 | 0.0142 |
122
+ | 0.0137 | 71.0 | 254393 | 0.0141 |
123
+ | 0.0137 | 72.0 | 257976 | 0.0141 |
124
+ | 0.0134 | 73.0 | 261559 | 0.0143 |
125
+ | 0.0186 | 74.0 | 265142 | 0.0141 |
126
+ | 0.0143 | 75.0 | 268725 | 0.0141 |
127
+ | 0.0155 | 76.0 | 272308 | 0.0142 |
128
+ | 0.0164 | 77.0 | 275891 | 0.0142 |
129
+ | 0.0137 | 78.0 | 279474 | 0.0141 |
130
+ | 0.0148 | 79.0 | 283057 | 0.0141 |
131
+ | 0.0136 | 80.0 | 286640 | 0.0142 |
132
+ | 0.0151 | 81.0 | 290223 | 0.0142 |
133
+ | 0.0137 | 82.0 | 293806 | 0.0141 |
134
+ | 0.0149 | 83.0 | 297389 | 0.0142 |
135
+ | 0.0145 | 84.0 | 300972 | 0.0141 |
136
+ | 0.0129 | 85.0 | 304555 | 0.0140 |
137
+ | 0.0144 | 86.0 | 308138 | 0.0142 |
138
+ | 0.0145 | 87.0 | 311721 | 0.0141 |
139
+ | 0.0125 | 88.0 | 315304 | 0.0140 |
140
+ | 0.0136 | 89.0 | 318887 | 0.0139 |
141
+ | 0.0138 | 90.0 | 322470 | 0.0141 |
142
+ | 0.0138 | 91.0 | 326053 | 0.0139 |
143
+ | 0.0144 | 92.0 | 329636 | 0.0139 |
144
+ | 0.0145 | 93.0 | 333219 | 0.0140 |
145
+ | 0.0136 | 94.0 | 336802 | 0.0140 |
146
+ | 0.0126 | 95.0 | 340385 | 0.0139 |
147
+ | 0.0154 | 96.0 | 343968 | 0.0140 |
148
+ | 0.0139 | 97.0 | 347551 | 0.0141 |
149
+ | 0.0135 | 98.0 | 351134 | 0.0138 |
150
+ | 0.0131 | 99.0 | 354717 | 0.0138 |
151
+ | 0.0123 | 100.0 | 358300 | 0.0139 |
152
+ | 0.014 | 101.0 | 361883 | 0.0140 |
153
+ | 0.0118 | 102.0 | 365466 | 0.0138 |
154
+ | 0.0151 | 103.0 | 369049 | 0.0140 |
155
+ | 0.0138 | 104.0 | 372632 | 0.0140 |
156
+ | 0.0156 | 105.0 | 376215 | 0.0139 |
157
+ | 0.0137 | 106.0 | 379798 | 0.0139 |
158
+ | 0.0136 | 107.0 | 383381 | 0.0140 |
159
+ | 0.0137 | 108.0 | 386964 | 0.0139 |
160
+ | 0.0151 | 109.0 | 390547 | 0.0138 |
161
+ | 0.0154 | 110.0 | 394130 | 0.0137 |
162
+ | 0.0142 | 111.0 | 397713 | 0.0140 |
163
+ | 0.0121 | 112.0 | 401296 | 0.0139 |
164
+ | 0.0131 | 113.0 | 404879 | 0.0139 |
165
+ | 0.0127 | 114.0 | 408462 | 0.0139 |
166
+ | 0.0131 | 115.0 | 412045 | 0.0140 |
167
+ | 0.014 | 116.0 | 415628 | 0.0137 |
168
+ | 0.0126 | 117.0 | 419211 | 0.0140 |
169
+ | 0.0135 | 118.0 | 422794 | 0.0140 |
170
+ | 0.0131 | 119.0 | 426377 | 0.0138 |
171
+ | 0.013 | 120.0 | 429960 | 0.0138 |
172
+ | 0.0145 | 121.0 | 433543 | 0.0139 |
173
+ | 0.0141 | 122.0 | 437126 | 0.0139 |
174
+ | 0.0134 | 123.0 | 440709 | 0.0140 |
175
+ | 0.0134 | 124.0 | 444292 | 0.0139 |
176
+ | 0.0138 | 125.0 | 447875 | 0.0139 |
177
+ | 0.0143 | 126.0 | 451458 | 0.0139 |
178
+ | 0.0127 | 127.0 | 455041 | 0.0139 |
179
+ | 0.0126 | 128.0 | 458624 | 0.0139 |
180
+ | 0.0141 | 129.0 | 462207 | 0.0139 |
181
+ | 0.0129 | 130.0 | 465790 | 0.0138 |
182
+ | 0.0138 | 131.0 | 469373 | 0.0139 |
183
+ | 0.0137 | 132.0 | 472956 | 0.0140 |
184
+ | 0.0143 | 133.0 | 476539 | 0.0138 |
185
+ | 0.0136 | 134.0 | 480122 | 0.0138 |
186
+ | 0.0142 | 135.0 | 483705 | 0.0138 |
187
+ | 0.0133 | 136.0 | 487288 | 0.0138 |
188
+ | 0.0162 | 137.0 | 490871 | 0.0136 |
189
+ | 0.0128 | 138.0 | 494454 | 0.0140 |
190
+ | 0.0137 | 139.0 | 498037 | 0.0139 |
191
+ | 0.0131 | 140.0 | 501620 | 0.0139 |
192
+ | 0.0137 | 141.0 | 505203 | 0.0138 |
193
+ | 0.0122 | 142.0 | 508786 | 0.0138 |
194
+ | 0.0132 | 143.0 | 512369 | 0.0137 |
195
+ | 0.0131 | 144.0 | 515952 | 0.0136 |
196
+ | 0.0139 | 145.0 | 519535 | 0.0138 |
197
+ | 0.0141 | 146.0 | 523118 | 0.0139 |
198
+ | 0.0148 | 147.0 | 526701 | 0.0137 |
199
+ | 0.0138 | 148.0 | 530284 | 0.0136 |
200
+ | 0.0139 | 149.0 | 533867 | 0.0139 |
201
+ | 0.0136 | 150.0 | 537450 | 0.0137 |
202
+ | 0.0121 | 151.0 | 541033 | 0.0139 |
203
+ | 0.014 | 152.0 | 544616 | 0.0138 |
204
+ | 0.013 | 153.0 | 548199 | 0.0136 |
205
+ | 0.0146 | 154.0 | 551782 | 0.0136 |
206
+ | 0.0138 | 155.0 | 555365 | 0.0136 |
207
+ | 0.0144 | 156.0 | 558948 | 0.0137 |
208
+ | 0.0141 | 157.0 | 562531 | 0.0138 |
209
+ | 0.0141 | 158.0 | 566114 | 0.0136 |
210
+ | 0.0116 | 159.0 | 569697 | 0.0137 |
211
+ | 0.012 | 160.0 | 573280 | 0.0136 |
212
+ | 0.0131 | 161.0 | 576863 | 0.0138 |
213
+ | 0.0131 | 162.0 | 580446 | 0.0136 |
214
+ | 0.0125 | 163.0 | 584029 | 0.0137 |
215
+ | 0.0145 | 164.0 | 587612 | 0.0137 |
216
+ | 0.0135 | 165.0 | 591195 | 0.0139 |
217
+ | 0.012 | 166.0 | 594778 | 0.0138 |
218
+ | 0.0144 | 167.0 | 598361 | 0.0137 |
219
+ | 0.0136 | 168.0 | 601944 | 0.0137 |
220
+ | 0.0123 | 169.0 | 605527 | 0.0136 |
221
+ | 0.0134 | 170.0 | 609110 | 0.0136 |
222
+ | 0.0128 | 171.0 | 612693 | 0.0134 |
223
+ | 0.0134 | 172.0 | 616276 | 0.0137 |
224
+ | 0.0129 | 173.0 | 619859 | 0.0137 |
225
+ | 0.014 | 174.0 | 623442 | 0.0136 |
226
+ | 0.0152 | 175.0 | 627025 | 0.0138 |
227
+ | 0.0139 | 176.0 | 630608 | 0.0136 |
228
+ | 0.0125 | 177.0 | 634191 | 0.0138 |
229
+ | 0.0142 | 178.0 | 637774 | 0.0136 |
230
+ | 0.0137 | 179.0 | 641357 | 0.0136 |
231
+ | 0.0168 | 180.0 | 644940 | 0.0134 |
232
+ | 0.0143 | 181.0 | 648523 | 0.0135 |
233
+ | 0.0118 | 182.0 | 652106 | 0.0137 |
234
+ | 0.0144 | 183.0 | 655689 | 0.0136 |
235
+ | 0.0125 | 184.0 | 659272 | 0.0136 |
236
+ | 0.014 | 185.0 | 662855 | 0.0136 |
237
+ | 0.0132 | 186.0 | 666438 | 0.0136 |
238
+ | 0.013 | 187.0 | 670021 | 0.0137 |
239
+ | 0.0128 | 188.0 | 673604 | 0.0136 |
240
+ | 0.0134 | 189.0 | 677187 | 0.0136 |
241
+ | 0.0138 | 190.0 | 680770 | 0.0137 |
242
+ | 0.013 | 191.0 | 684353 | 0.0135 |
243
+ | 0.0137 | 192.0 | 687936 | 0.0136 |
244
+ | 0.0124 | 193.0 | 691519 | 0.0135 |
245
+ | 0.0133 | 194.0 | 695102 | 0.0135 |
246
+ | 0.0135 | 195.0 | 698685 | 0.0136 |
247
+ | 0.0142 | 196.0 | 702268 | 0.0136 |
248
+ | 0.0122 | 197.0 | 705851 | 0.0136 |
249
+ | 0.0124 | 198.0 | 709434 | 0.0137 |
250
+ | 0.0154 | 199.0 | 713017 | 0.0136 |
251
+ | 0.0137 | 200.0 | 716600 | 0.0135 |
252
+ | 0.0128 | 201.0 | 720183 | 0.0135 |
253
+ | 0.0133 | 202.0 | 723766 | 0.0136 |
254
+ | 0.0139 | 203.0 | 727349 | 0.0136 |
255
+ | 0.0136 | 204.0 | 730932 | 0.0136 |
256
+ | 0.0143 | 205.0 | 734515 | 0.0134 |
257
+ | 0.0129 | 206.0 | 738098 | 0.0134 |
258
+ | 0.0142 | 207.0 | 741681 | 0.0136 |
259
+ | 0.0135 | 208.0 | 745264 | 0.0136 |
260
+ | 0.014 | 209.0 | 748847 | 0.0136 |
261
+ | 0.0132 | 210.0 | 752430 | 0.0135 |
262
+ | 0.0142 | 211.0 | 756013 | 0.0135 |
263
+ | 0.0136 | 212.0 | 759596 | 0.0134 |
264
+ | 0.0131 | 213.0 | 763179 | 0.0135 |
265
+ | 0.014 | 214.0 | 766762 | 0.0135 |
266
+ | 0.0131 | 215.0 | 770345 | 0.0135 |
267
+ | 0.0122 | 216.0 | 773928 | 0.0135 |
268
+ | 0.0128 | 217.0 | 777511 | 0.0135 |
269
+ | 0.0135 | 218.0 | 781094 | 0.0136 |
270
+ | 0.0136 | 219.0 | 784677 | 0.0135 |
271
+ | 0.0151 | 220.0 | 788260 | 0.0135 |
272
+ | 0.013 | 221.0 | 791843 | 0.0135 |
273
+ | 0.0123 | 222.0 | 795426 | 0.0135 |
274
+ | 0.013 | 223.0 | 799009 | 0.0134 |
275
+ | 0.0146 | 224.0 | 802592 | 0.0134 |
276
+ | 0.0144 | 225.0 | 806175 | 0.0135 |
277
+ | 0.0137 | 226.0 | 809758 | 0.0135 |
278
+ | 0.0115 | 227.0 | 813341 | 0.0134 |
279
+ | 0.0132 | 228.0 | 816924 | 0.0135 |
280
+ | 0.0141 | 229.0 | 820507 | 0.0135 |
281
+ | 0.013 | 230.0 | 824090 | 0.0136 |
282
+ | 0.0128 | 231.0 | 827673 | 0.0134 |
283
+ | 0.0138 | 232.0 | 831256 | 0.0135 |
284
+ | 0.0136 | 233.0 | 834839 | 0.0135 |
285
+ | 0.013 | 234.0 | 838422 | 0.0135 |
286
+ | 0.0137 | 235.0 | 842005 | 0.0134 |
287
+ | 0.0147 | 236.0 | 845588 | 0.0135 |
288
+ | 0.0134 | 237.0 | 849171 | 0.0135 |
289
+ | 0.013 | 238.0 | 852754 | 0.0133 |
290
+ | 0.0146 | 239.0 | 856337 | 0.0135 |
291
+ | 0.0145 | 240.0 | 859920 | 0.0136 |
292
+ | 0.0149 | 241.0 | 863503 | 0.0136 |
293
+ | 0.0131 | 242.0 | 867086 | 0.0134 |
294
+ | 0.0128 | 243.0 | 870669 | 0.0134 |
295
+ | 0.0139 | 244.0 | 874252 | 0.0133 |
296
+ | 0.0128 | 245.0 | 877835 | 0.0132 |
297
+ | 0.0138 | 246.0 | 881418 | 0.0135 |
298
+ | 0.0126 | 247.0 | 885001 | 0.0133 |
299
+ | 0.0144 | 248.0 | 888584 | 0.0134 |
300
+ | 0.0138 | 249.0 | 892167 | 0.0134 |
301
+ | 0.0137 | 250.0 | 895750 | 0.0134 |
302
+ | 0.0146 | 251.0 | 899333 | 0.0136 |
303
+ | 0.0135 | 252.0 | 902916 | 0.0134 |
304
+ | 0.0124 | 253.0 | 906499 | 0.0134 |
305
+ | 0.013 | 254.0 | 910082 | 0.0135 |
306
+ | 0.0136 | 255.0 | 913665 | 0.0134 |
307
+ | 0.0146 | 256.0 | 917248 | 0.0133 |
308
+ | 0.0129 | 257.0 | 920831 | 0.0136 |
309
+ | 0.013 | 258.0 | 924414 | 0.0134 |
310
+ | 0.0135 | 259.0 | 927997 | 0.0134 |
311
+ | 0.0134 | 260.0 | 931580 | 0.0131 |
312
+ | 0.0151 | 261.0 | 935163 | 0.0133 |
313
+ | 0.0126 | 262.0 | 938746 | 0.0133 |
314
+ | 0.0124 | 263.0 | 942329 | 0.0134 |
315
+ | 0.013 | 264.0 | 945912 | 0.0134 |
316
+ | 0.0139 | 265.0 | 949495 | 0.0133 |
317
+ | 0.0142 | 266.0 | 953078 | 0.0133 |
318
+ | 0.0129 | 267.0 | 956661 | 0.0134 |
319
+ | 0.0128 | 268.0 | 960244 | 0.0134 |
320
+ | 0.0177 | 269.0 | 963827 | 0.0133 |
321
+ | 0.0124 | 270.0 | 967410 | 0.0134 |
322
+ | 0.0165 | 271.0 | 970993 | 0.0133 |
323
+ | 0.0131 | 272.0 | 974576 | 0.0135 |
324
+ | 0.0119 | 273.0 | 978159 | 0.0133 |
325
+ | 0.0125 | 274.0 | 981742 | 0.0133 |
326
+ | 0.0127 | 275.0 | 985325 | 0.0133 |
327
+ | 0.013 | 276.0 | 988908 | 0.0134 |
328
+ | 0.0131 | 277.0 | 992491 | 0.0136 |
329
+ | 0.0131 | 278.0 | 996074 | 0.0134 |
330
+ | 0.0128 | 279.0 | 999657 | 0.0133 |
331
+ | 0.0146 | 280.0 | 1003240 | 0.0133 |
332
+ | 0.0138 | 281.0 | 1006823 | 0.0134 |
333
+ | 0.0125 | 282.0 | 1010406 | 0.0135 |
334
+ | 0.0121 | 283.0 | 1013989 | 0.0133 |
335
+ | 0.0137 | 284.0 | 1017572 | 0.0135 |
336
+ | 0.0144 | 285.0 | 1021155 | 0.0135 |
337
+ | 0.0131 | 286.0 | 1024738 | 0.0134 |
338
+ | 0.0133 | 287.0 | 1028321 | 0.0134 |
339
+ | 0.013 | 288.0 | 1031904 | 0.0133 |
340
+ | 0.013 | 289.0 | 1035487 | 0.0132 |
341
+ | 0.0133 | 290.0 | 1039070 | 0.0134 |
342
+ | 0.0127 | 291.0 | 1042653 | 0.0133 |
343
+ | 0.0121 | 292.0 | 1046236 | 0.0133 |
344
+ | 0.013 | 293.0 | 1049819 | 0.0132 |
345
+ | 0.0116 | 294.0 | 1053402 | 0.0131 |
346
+ | 0.0151 | 295.0 | 1056985 | 0.0133 |
347
+ | 0.013 | 296.0 | 1060568 | 0.0133 |
348
+ | 0.0121 | 297.0 | 1064151 | 0.0133 |
349
+ | 0.0127 | 298.0 | 1067734 | 0.0132 |
350
+ | 0.0125 | 299.0 | 1071317 | 0.0134 |
351
+ | 0.0132 | 300.0 | 1074900 | 0.0131 |
352
+ | 0.0121 | 301.0 | 1078483 | 0.0134 |
353
+ | 0.0147 | 302.0 | 1082066 | 0.0134 |
354
+ | 0.0127 | 303.0 | 1085649 | 0.0133 |
355
+ | 0.0131 | 304.0 | 1089232 | 0.0132 |
356
+ | 0.0144 | 305.0 | 1092815 | 0.0133 |
357
+ | 0.0145 | 306.0 | 1096398 | 0.0135 |
358
+ | 0.014 | 307.0 | 1099981 | 0.0132 |
359
+ | 0.0162 | 308.0 | 1103564 | 0.0132 |
360
+ | 0.0125 | 309.0 | 1107147 | 0.0133 |
361
+ | 0.0146 | 310.0 | 1110730 | 0.0134 |
362
+ | 0.0145 | 311.0 | 1114313 | 0.0132 |
363
+ | 0.0133 | 312.0 | 1117896 | 0.0133 |
364
+ | 0.0146 | 313.0 | 1121479 | 0.0133 |
365
+ | 0.0137 | 314.0 | 1125062 | 0.0133 |
366
+ | 0.0131 | 315.0 | 1128645 | 0.0132 |
367
+ | 0.014 | 316.0 | 1132228 | 0.0131 |
368
+ | 0.0134 | 317.0 | 1135811 | 0.0132 |
369
+ | 0.0138 | 318.0 | 1139394 | 0.0133 |
370
+ | 0.0133 | 319.0 | 1142977 | 0.0131 |
371
+ | 0.0131 | 320.0 | 1146560 | 0.0132 |
372
+ | 0.0127 | 321.0 | 1150143 | 0.0132 |
373
+ | 0.0137 | 322.0 | 1153726 | 0.0133 |
374
+ | 0.0129 | 323.0 | 1157309 | 0.0133 |
375
+ | 0.0123 | 324.0 | 1160892 | 0.0132 |
376
+ | 0.0135 | 325.0 | 1164475 | 0.0133 |
377
+ | 0.0132 | 326.0 | 1168058 | 0.0132 |
378
+ | 0.0125 | 327.0 | 1171641 | 0.0132 |
379
+ | 0.0135 | 328.0 | 1175224 | 0.0132 |
380
+ | 0.0135 | 329.0 | 1178807 | 0.0135 |
381
+ | 0.0139 | 330.0 | 1182390 | 0.0133 |
382
+ | 0.0133 | 331.0 | 1185973 | 0.0130 |
383
+ | 0.0123 | 332.0 | 1189556 | 0.0134 |
384
+ | 0.0141 | 333.0 | 1193139 | 0.0131 |
385
+ | 0.013 | 334.0 | 1196722 | 0.0130 |
386
+ | 0.015 | 335.0 | 1200305 | 0.0132 |
387
+ | 0.0139 | 336.0 | 1203888 | 0.0132 |
388
+ | 0.0125 | 337.0 | 1207471 | 0.0133 |
389
+ | 0.0133 | 338.0 | 1211054 | 0.0132 |
390
+ | 0.0131 | 339.0 | 1214637 | 0.0133 |
391
+ | 0.0136 | 340.0 | 1218220 | 0.0131 |
392
+ | 0.0114 | 341.0 | 1221803 | 0.0132 |
393
+ | 0.0146 | 342.0 | 1225386 | 0.0132 |
394
+ | 0.014 | 343.0 | 1228969 | 0.0132 |
395
+ | 0.0138 | 344.0 | 1232552 | 0.0131 |
396
+ | 0.0123 | 345.0 | 1236135 | 0.0133 |
397
+ | 0.0129 | 346.0 | 1239718 | 0.0132 |
398
+ | 0.0135 | 347.0 | 1243301 | 0.0133 |
399
+ | 0.0142 | 348.0 | 1246884 | 0.0132 |
400
+ | 0.0134 | 349.0 | 1250467 | 0.0132 |
401
+ | 0.0121 | 350.0 | 1254050 | 0.0132 |
402
+ | 0.0124 | 351.0 | 1257633 | 0.0132 |
403
+ | 0.0152 | 352.0 | 1261216 | 0.0133 |
404
+ | 0.0126 | 353.0 | 1264799 | 0.0134 |
405
+ | 0.012 | 354.0 | 1268382 | 0.0132 |
406
+ | 0.0138 | 355.0 | 1271965 | 0.0133 |
407
+ | 0.0136 | 356.0 | 1275548 | 0.0132 |
408
+ | 0.012 | 357.0 | 1279131 | 0.0132 |
409
+ | 0.0123 | 358.0 | 1282714 | 0.0134 |
410
+ | 0.0131 | 359.0 | 1286297 | 0.0131 |
411
+ | 0.0127 | 360.0 | 1289880 | 0.0133 |
412
+ | 0.0132 | 361.0 | 1293463 | 0.0131 |
413
+ | 0.0135 | 362.0 | 1297046 | 0.0131 |
414
+ | 0.0119 | 363.0 | 1300629 | 0.0132 |
415
+ | 0.0132 | 364.0 | 1304212 | 0.0132 |
416
+ | 0.013 | 365.0 | 1307795 | 0.0131 |
417
+ | 0.0124 | 366.0 | 1311378 | 0.0132 |
418
+ | 0.0122 | 367.0 | 1314961 | 0.0132 |
419
+ | 0.0146 | 368.0 | 1318544 | 0.0132 |
420
+ | 0.0121 | 369.0 | 1322127 | 0.0134 |
421
+ | 0.0119 | 370.0 | 1325710 | 0.0131 |
422
+ | 0.0138 | 371.0 | 1329293 | 0.0134 |
423
+ | 0.0132 | 372.0 | 1332876 | 0.0134 |
424
+ | 0.0146 | 373.0 | 1336459 | 0.0133 |
425
+ | 0.0126 | 374.0 | 1340042 | 0.0132 |
426
+ | 0.0125 | 375.0 | 1343625 | 0.0133 |
427
+ | 0.0129 | 376.0 | 1347208 | 0.0132 |
428
+ | 0.0117 | 377.0 | 1350791 | 0.0133 |
429
+ | 0.0114 | 378.0 | 1354374 | 0.0132 |
430
+ | 0.0123 | 379.0 | 1357957 | 0.0132 |
431
+ | 0.0119 | 380.0 | 1361540 | 0.0132 |
432
+ | 0.0131 | 381.0 | 1365123 | 0.0133 |
433
+ | 0.0135 | 382.0 | 1368706 | 0.0132 |
434
+ | 0.0154 | 383.0 | 1372289 | 0.0131 |
435
+ | 0.0151 | 384.0 | 1375872 | 0.0133 |
436
+ | 0.0125 | 385.0 | 1379455 | 0.0132 |
437
+ | 0.0137 | 386.0 | 1383038 | 0.0132 |
438
+ | 0.0125 | 387.0 | 1386621 | 0.0132 |
439
+ | 0.012 | 388.0 | 1390204 | 0.0132 |
440
+ | 0.0155 | 389.0 | 1393787 | 0.0132 |
441
+ | 0.013 | 390.0 | 1397370 | 0.0133 |
442
+ | 0.0131 | 391.0 | 1400953 | 0.0131 |
443
+ | 0.013 | 392.0 | 1404536 | 0.0132 |
444
+ | 0.0141 | 393.0 | 1408119 | 0.0132 |
445
+ | 0.0123 | 394.0 | 1411702 | 0.0132 |
446
+ | 0.0126 | 395.0 | 1415285 | 0.0132 |
447
+ | 0.0122 | 396.0 | 1418868 | 0.0132 |
448
+ | 0.0126 | 397.0 | 1422451 | 0.0131 |
449
+ | 0.0135 | 398.0 | 1426034 | 0.0131 |
450
+ | 0.0126 | 399.0 | 1429617 | 0.0133 |
451
+ | 0.0136 | 400.0 | 1433200 | 0.0131 |
452
+
453
+
454
+ ### Framework versions
455
+
456
+ - Transformers 4.39.0.dev0
457
+ - Pytorch 2.2.1+cu121
458
+ - Datasets 2.18.0
459
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6edd4eb8766dea0efe983eec5de0a7dc7313913507e64ca786ee9d42c870964c
3
  size 447670680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f38191ae0c1755b524461bba107ded701870df91f066f5de1a226ce9eae0c3c
3
  size 447670680
runs/Apr02_20-19-44_ip-172-16-71-114.us-west-2.compute.internal/events.out.tfevents.1712089197.ip-172-16-71-114.us-west-2.compute.internal.1015.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f17c0b711c72b016e50a1cf0ee981f5b27a245ddcff10a58fefcd11f6395c01
3
- size 30922409
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:485f37fed7a4f912e659d519678036b3a24230a0d93bc7fc120487b87701f0f9
3
+ size 30922769