Hugging Face's logo

IParraMartin
/
impossible-llms-spanish-random-trigram

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
IParraMartin commited on
Commit
8a888f9
·
verified ·
1 Parent(s): b12ef1a

End of training

Browse files
Files changed (2) hide show
  1. README.md +438 -0
  2. generation_config.json +6 -0
README.md ADDED
@@ -0,0 +1,438 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: impossible-llms-spanish-random-trigram
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # impossible-llms-spanish-random-trigram
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 7.7066
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: 0.0001
37
+ - train_batch_size: 12
38
+ - eval_batch_size: 8
39
+ - seed: 0
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 4
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 384
44
+ - total_eval_batch_size: 32
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_ratio: 0.1
48
+ - training_steps: 3000
49
+ - mixed_precision_training: Native AMP
50
+ - label_smoothing_factor: 0.1
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:---------------:|
56
+ | 82.9733 | 1.0 | 8 | 10.1380 |
57
+ | 75.8627 | 2.0 | 16 | 9.3943 |
58
+ | 72.9515 | 3.0 | 24 | 9.0643 |
59
+ | 71.6032 | 4.0 | 32 | 8.9186 |
60
+ | 70.43 | 5.0 | 40 | 8.7530 |
61
+ | 68.9775 | 6.0 | 48 | 8.5889 |
62
+ | 67.4266 | 7.0 | 56 | 8.4027 |
63
+ | 65.7647 | 8.0 | 64 | 8.1834 |
64
+ | 63.9125 | 9.0 | 72 | 7.9671 |
65
+ | 62.2846 | 10.0 | 80 | 7.7450 |
66
+ | 60.585 | 11.0 | 88 | 7.5208 |
67
+ | 58.6086 | 12.0 | 96 | 7.3007 |
68
+ | 57.0585 | 13.0 | 104 | 7.0879 |
69
+ | 55.3789 | 14.0 | 112 | 6.8909 |
70
+ | 53.8711 | 15.0 | 120 | 6.7159 |
71
+ | 52.8598 | 16.0 | 128 | 6.5712 |
72
+ | 51.8931 | 17.0 | 136 | 6.4712 |
73
+ | 51.0249 | 18.0 | 144 | 6.3874 |
74
+ | 50.7649 | 19.0 | 152 | 6.3245 |
75
+ | 49.9938 | 20.0 | 160 | 6.2685 |
76
+ | 49.6 | 21.0 | 168 | 6.2156 |
77
+ | 49.3546 | 22.0 | 176 | 6.1711 |
78
+ | 49.0595 | 23.0 | 184 | 6.1315 |
79
+ | 48.5708 | 24.0 | 192 | 6.1018 |
80
+ | 48.2928 | 25.0 | 200 | 6.0545 |
81
+ | 47.994 | 26.0 | 208 | 6.0289 |
82
+ | 47.4027 | 27.0 | 216 | 5.9954 |
83
+ | 47.4567 | 28.0 | 224 | 5.9669 |
84
+ | 47.1224 | 29.0 | 232 | 5.9427 |
85
+ | 46.9763 | 30.0 | 240 | 5.9195 |
86
+ | 46.8013 | 31.0 | 248 | 5.8970 |
87
+ | 46.4533 | 32.0 | 256 | 5.8863 |
88
+ | 46.258 | 33.0 | 264 | 5.8621 |
89
+ | 46.0531 | 34.0 | 272 | 5.8469 |
90
+ | 45.8693 | 35.0 | 280 | 5.8301 |
91
+ | 45.7775 | 36.0 | 288 | 5.8110 |
92
+ | 45.4574 | 37.0 | 296 | 5.7973 |
93
+ | 45.384 | 38.0 | 304 | 5.7860 |
94
+ | 45.14 | 39.0 | 312 | 5.7715 |
95
+ | 44.9259 | 40.0 | 320 | 5.7627 |
96
+ | 44.8364 | 41.0 | 328 | 5.7461 |
97
+ | 44.5589 | 42.0 | 336 | 5.7299 |
98
+ | 44.2769 | 43.0 | 344 | 5.7123 |
99
+ | 44.2618 | 44.0 | 352 | 5.7029 |
100
+ | 44.1485 | 45.0 | 360 | 5.6984 |
101
+ | 43.8223 | 46.0 | 368 | 5.6889 |
102
+ | 43.6464 | 47.0 | 376 | 5.6691 |
103
+ | 43.5192 | 48.0 | 384 | 5.6708 |
104
+ | 43.3381 | 49.0 | 392 | 5.6586 |
105
+ | 43.1446 | 50.0 | 400 | 5.6500 |
106
+ | 42.92 | 51.0 | 408 | 5.6444 |
107
+ | 42.7591 | 52.0 | 416 | 5.6324 |
108
+ | 42.5581 | 53.0 | 424 | 5.6303 |
109
+ | 42.2034 | 54.0 | 432 | 5.6273 |
110
+ | 42.298 | 55.0 | 440 | 5.6196 |
111
+ | 42.0519 | 56.0 | 448 | 5.6137 |
112
+ | 41.7271 | 57.0 | 456 | 5.6116 |
113
+ | 41.475 | 58.0 | 464 | 5.6048 |
114
+ | 41.4602 | 59.0 | 472 | 5.6002 |
115
+ | 41.3604 | 60.0 | 480 | 5.6077 |
116
+ | 41.221 | 61.0 | 488 | 5.5998 |
117
+ | 41.0521 | 62.0 | 496 | 5.6056 |
118
+ | 40.794 | 63.0 | 504 | 5.6033 |
119
+ | 40.5781 | 64.0 | 512 | 5.6023 |
120
+ | 40.5309 | 65.0 | 520 | 5.6056 |
121
+ | 40.304 | 66.0 | 528 | 5.6056 |
122
+ | 39.9717 | 67.0 | 536 | 5.6076 |
123
+ | 39.7713 | 68.0 | 544 | 5.6163 |
124
+ | 39.7593 | 69.0 | 552 | 5.6194 |
125
+ | 39.5544 | 70.0 | 560 | 5.6221 |
126
+ | 39.4424 | 71.0 | 568 | 5.6286 |
127
+ | 39.1879 | 72.0 | 576 | 5.6344 |
128
+ | 38.9627 | 73.0 | 584 | 5.6377 |
129
+ | 38.7648 | 74.0 | 592 | 5.6504 |
130
+ | 38.6023 | 75.0 | 600 | 5.6627 |
131
+ | 38.4814 | 76.0 | 608 | 5.6589 |
132
+ | 38.3261 | 77.0 | 616 | 5.6667 |
133
+ | 38.0804 | 78.0 | 624 | 5.6782 |
134
+ | 37.8844 | 79.0 | 632 | 5.6908 |
135
+ | 37.6588 | 80.0 | 640 | 5.7084 |
136
+ | 37.4768 | 81.0 | 648 | 5.7185 |
137
+ | 37.3375 | 82.0 | 656 | 5.7297 |
138
+ | 37.031 | 83.0 | 664 | 5.7300 |
139
+ | 36.7817 | 84.0 | 672 | 5.7480 |
140
+ | 36.8966 | 85.0 | 680 | 5.7470 |
141
+ | 36.5525 | 86.0 | 688 | 5.7592 |
142
+ | 36.478 | 87.0 | 696 | 5.7775 |
143
+ | 36.176 | 88.0 | 704 | 5.7889 |
144
+ | 35.9584 | 89.0 | 712 | 5.8079 |
145
+ | 35.8365 | 90.0 | 720 | 5.8175 |
146
+ | 35.6729 | 91.0 | 728 | 5.8303 |
147
+ | 35.4745 | 92.0 | 736 | 5.8376 |
148
+ | 35.3489 | 93.0 | 744 | 5.8577 |
149
+ | 35.1739 | 94.0 | 752 | 5.8575 |
150
+ | 34.9136 | 95.0 | 760 | 5.8791 |
151
+ | 34.7444 | 96.0 | 768 | 5.9020 |
152
+ | 34.5735 | 97.0 | 776 | 5.9112 |
153
+ | 34.3098 | 98.0 | 784 | 5.9218 |
154
+ | 34.3126 | 99.0 | 792 | 5.9277 |
155
+ | 34.1658 | 100.0 | 800 | 5.9521 |
156
+ | 33.9487 | 101.0 | 808 | 5.9522 |
157
+ | 33.6928 | 102.0 | 816 | 5.9800 |
158
+ | 33.5653 | 103.0 | 824 | 5.9805 |
159
+ | 33.4678 | 104.0 | 832 | 5.9987 |
160
+ | 33.1124 | 105.0 | 840 | 6.0220 |
161
+ | 33.0137 | 106.0 | 848 | 6.0320 |
162
+ | 32.8984 | 107.0 | 856 | 6.0514 |
163
+ | 32.8075 | 108.0 | 864 | 6.0507 |
164
+ | 32.5741 | 109.0 | 872 | 6.0704 |
165
+ | 32.4494 | 110.0 | 880 | 6.0746 |
166
+ | 32.1832 | 111.0 | 888 | 6.1016 |
167
+ | 32.0472 | 112.0 | 896 | 6.1236 |
168
+ | 32.0669 | 113.0 | 904 | 6.1315 |
169
+ | 31.7332 | 114.0 | 912 | 6.1548 |
170
+ | 31.6171 | 115.0 | 920 | 6.1677 |
171
+ | 31.2678 | 116.0 | 928 | 6.1799 |
172
+ | 31.4348 | 117.0 | 936 | 6.1924 |
173
+ | 31.0856 | 118.0 | 944 | 6.2054 |
174
+ | 30.8131 | 119.0 | 952 | 6.2164 |
175
+ | 30.8044 | 120.0 | 960 | 6.2283 |
176
+ | 30.653 | 121.0 | 968 | 6.2490 |
177
+ | 30.2781 | 122.0 | 976 | 6.2766 |
178
+ | 30.3348 | 123.0 | 984 | 6.2750 |
179
+ | 30.1585 | 124.0 | 992 | 6.2834 |
180
+ | 30.0486 | 125.0 | 1000 | 6.2987 |
181
+ | 29.8699 | 126.0 | 1008 | 6.3086 |
182
+ | 29.7011 | 127.0 | 1016 | 6.3194 |
183
+ | 29.6424 | 128.0 | 1024 | 6.3398 |
184
+ | 29.436 | 129.0 | 1032 | 6.3594 |
185
+ | 29.2558 | 130.0 | 1040 | 6.3784 |
186
+ | 29.2634 | 131.0 | 1048 | 6.3784 |
187
+ | 28.9683 | 132.0 | 1056 | 6.3980 |
188
+ | 28.9409 | 133.0 | 1064 | 6.4186 |
189
+ | 28.7912 | 134.0 | 1072 | 6.4259 |
190
+ | 28.7214 | 135.0 | 1080 | 6.4451 |
191
+ | 28.3626 | 136.0 | 1088 | 6.4447 |
192
+ | 28.303 | 137.0 | 1096 | 6.4764 |
193
+ | 28.0938 | 138.0 | 1104 | 6.4765 |
194
+ | 27.9736 | 139.0 | 1112 | 6.4947 |
195
+ | 27.9646 | 140.0 | 1120 | 6.5150 |
196
+ | 27.7595 | 141.0 | 1128 | 6.5219 |
197
+ | 27.6672 | 142.0 | 1136 | 6.5349 |
198
+ | 27.5115 | 143.0 | 1144 | 6.5418 |
199
+ | 27.3989 | 144.0 | 1152 | 6.5525 |
200
+ | 27.2322 | 145.0 | 1160 | 6.5750 |
201
+ | 27.1536 | 146.0 | 1168 | 6.5788 |
202
+ | 26.918 | 147.0 | 1176 | 6.6096 |
203
+ | 26.93 | 148.0 | 1184 | 6.6063 |
204
+ | 26.8101 | 149.0 | 1192 | 6.6146 |
205
+ | 26.6292 | 150.0 | 1200 | 6.6443 |
206
+ | 26.5597 | 151.0 | 1208 | 6.6378 |
207
+ | 26.3258 | 152.0 | 1216 | 6.6476 |
208
+ | 26.3014 | 153.0 | 1224 | 6.6655 |
209
+ | 26.2341 | 154.0 | 1232 | 6.6871 |
210
+ | 26.0496 | 155.0 | 1240 | 6.7034 |
211
+ | 25.8795 | 156.0 | 1248 | 6.7092 |
212
+ | 25.8079 | 157.0 | 1256 | 6.7204 |
213
+ | 25.6752 | 158.0 | 1264 | 6.7203 |
214
+ | 25.521 | 159.0 | 1272 | 6.7521 |
215
+ | 25.4696 | 160.0 | 1280 | 6.7610 |
216
+ | 25.3268 | 161.0 | 1288 | 6.7741 |
217
+ | 25.1959 | 162.0 | 1296 | 6.7791 |
218
+ | 25.2836 | 163.0 | 1304 | 6.7898 |
219
+ | 25.1064 | 164.0 | 1312 | 6.8028 |
220
+ | 25.0024 | 165.0 | 1320 | 6.8166 |
221
+ | 24.9199 | 166.0 | 1328 | 6.8173 |
222
+ | 24.6732 | 167.0 | 1336 | 6.8342 |
223
+ | 24.6356 | 168.0 | 1344 | 6.8470 |
224
+ | 24.5186 | 169.0 | 1352 | 6.8576 |
225
+ | 24.4474 | 170.0 | 1360 | 6.8696 |
226
+ | 24.2977 | 171.0 | 1368 | 6.8838 |
227
+ | 24.2159 | 172.0 | 1376 | 6.8885 |
228
+ | 24.0174 | 173.0 | 1384 | 6.8984 |
229
+ | 24.0456 | 174.0 | 1392 | 6.9146 |
230
+ | 23.9057 | 175.0 | 1400 | 6.9252 |
231
+ | 23.836 | 176.0 | 1408 | 6.9345 |
232
+ | 23.7763 | 177.0 | 1416 | 6.9459 |
233
+ | 23.6371 | 178.0 | 1424 | 6.9581 |
234
+ | 23.4964 | 179.0 | 1432 | 6.9567 |
235
+ | 23.4087 | 180.0 | 1440 | 6.9668 |
236
+ | 23.4787 | 181.0 | 1448 | 6.9878 |
237
+ | 23.2909 | 182.0 | 1456 | 7.0021 |
238
+ | 23.2037 | 183.0 | 1464 | 7.0044 |
239
+ | 23.1077 | 184.0 | 1472 | 7.0095 |
240
+ | 23.1223 | 185.0 | 1480 | 7.0237 |
241
+ | 23.0181 | 186.0 | 1488 | 7.0253 |
242
+ | 22.8319 | 187.0 | 1496 | 7.0433 |
243
+ | 22.6766 | 188.0 | 1504 | 7.0584 |
244
+ | 22.5745 | 189.0 | 1512 | 7.0734 |
245
+ | 22.6136 | 190.0 | 1520 | 7.0746 |
246
+ | 22.6386 | 191.0 | 1528 | 7.0769 |
247
+ | 22.3468 | 192.0 | 1536 | 7.0861 |
248
+ | 22.3324 | 193.0 | 1544 | 7.1038 |
249
+ | 22.3003 | 194.0 | 1552 | 7.1050 |
250
+ | 22.2035 | 195.0 | 1560 | 7.1135 |
251
+ | 22.2508 | 196.0 | 1568 | 7.1215 |
252
+ | 22.0929 | 197.0 | 1576 | 7.1224 |
253
+ | 21.8521 | 198.0 | 1584 | 7.1385 |
254
+ | 21.8427 | 199.0 | 1592 | 7.1534 |
255
+ | 21.8101 | 200.0 | 1600 | 7.1633 |
256
+ | 21.8117 | 201.0 | 1608 | 7.1737 |
257
+ | 21.7302 | 202.0 | 1616 | 7.1755 |
258
+ | 21.6858 | 203.0 | 1624 | 7.1771 |
259
+ | 21.5795 | 204.0 | 1632 | 7.1999 |
260
+ | 21.4033 | 205.0 | 1640 | 7.1998 |
261
+ | 21.3557 | 206.0 | 1648 | 7.2087 |
262
+ | 21.362 | 207.0 | 1656 | 7.2162 |
263
+ | 21.2887 | 208.0 | 1664 | 7.2278 |
264
+ | 21.2647 | 209.0 | 1672 | 7.2368 |
265
+ | 21.1294 | 210.0 | 1680 | 7.2437 |
266
+ | 21.0053 | 211.0 | 1688 | 7.2425 |
267
+ | 20.8938 | 212.0 | 1696 | 7.2527 |
268
+ | 20.8835 | 213.0 | 1704 | 7.2560 |
269
+ | 20.8416 | 214.0 | 1712 | 7.2649 |
270
+ | 20.9264 | 215.0 | 1720 | 7.2681 |
271
+ | 20.7855 | 216.0 | 1728 | 7.2841 |
272
+ | 20.7273 | 217.0 | 1736 | 7.2881 |
273
+ | 20.6209 | 218.0 | 1744 | 7.2950 |
274
+ | 20.6245 | 219.0 | 1752 | 7.2968 |
275
+ | 20.5751 | 220.0 | 1760 | 7.3022 |
276
+ | 20.4651 | 221.0 | 1768 | 7.3177 |
277
+ | 20.421 | 222.0 | 1776 | 7.3193 |
278
+ | 20.396 | 223.0 | 1784 | 7.3280 |
279
+ | 20.2115 | 224.0 | 1792 | 7.3324 |
280
+ | 20.2426 | 225.0 | 1800 | 7.3388 |
281
+ | 20.1705 | 226.0 | 1808 | 7.3447 |
282
+ | 20.0706 | 227.0 | 1816 | 7.3593 |
283
+ | 20.0526 | 228.0 | 1824 | 7.3586 |
284
+ | 19.9699 | 229.0 | 1832 | 7.3730 |
285
+ | 19.9693 | 230.0 | 1840 | 7.3714 |
286
+ | 19.8774 | 231.0 | 1848 | 7.3788 |
287
+ | 19.7865 | 232.0 | 1856 | 7.3833 |
288
+ | 19.8824 | 233.0 | 1864 | 7.3846 |
289
+ | 19.6696 | 234.0 | 1872 | 7.3839 |
290
+ | 19.6567 | 235.0 | 1880 | 7.4056 |
291
+ | 19.5757 | 236.0 | 1888 | 7.4100 |
292
+ | 19.6795 | 237.0 | 1896 | 7.4117 |
293
+ | 19.6425 | 238.0 | 1904 | 7.4162 |
294
+ | 19.5103 | 239.0 | 1912 | 7.4196 |
295
+ | 19.4417 | 240.0 | 1920 | 7.4329 |
296
+ | 19.4904 | 241.0 | 1928 | 7.4365 |
297
+ | 19.3839 | 242.0 | 1936 | 7.4469 |
298
+ | 19.375 | 243.0 | 1944 | 7.4422 |
299
+ | 19.2889 | 244.0 | 1952 | 7.4488 |
300
+ | 19.2558 | 245.0 | 1960 | 7.4567 |
301
+ | 19.2278 | 246.0 | 1968 | 7.4600 |
302
+ | 19.1181 | 247.0 | 1976 | 7.4692 |
303
+ | 19.0961 | 248.0 | 1984 | 7.4738 |
304
+ | 19.0715 | 249.0 | 1992 | 7.4740 |
305
+ | 19.0496 | 250.0 | 2000 | 7.4824 |
306
+ | 19.0083 | 251.0 | 2008 | 7.4835 |
307
+ | 18.9141 | 252.0 | 2016 | 7.4959 |
308
+ | 18.9221 | 253.0 | 2024 | 7.4904 |
309
+ | 18.9279 | 254.0 | 2032 | 7.5009 |
310
+ | 18.8651 | 255.0 | 2040 | 7.4973 |
311
+ | 18.7985 | 256.0 | 2048 | 7.5030 |
312
+ | 18.7127 | 257.0 | 2056 | 7.5099 |
313
+ | 18.773 | 258.0 | 2064 | 7.5165 |
314
+ | 18.6578 | 259.0 | 2072 | 7.5124 |
315
+ | 18.6339 | 260.0 | 2080 | 7.5202 |
316
+ | 18.6373 | 261.0 | 2088 | 7.5244 |
317
+ | 18.6085 | 262.0 | 2096 | 7.5311 |
318
+ | 18.5759 | 263.0 | 2104 | 7.5326 |
319
+ | 18.604 | 264.0 | 2112 | 7.5401 |
320
+ | 18.5656 | 265.0 | 2120 | 7.5444 |
321
+ | 18.4235 | 266.0 | 2128 | 7.5528 |
322
+ | 18.5318 | 267.0 | 2136 | 7.5496 |
323
+ | 18.4513 | 268.0 | 2144 | 7.5502 |
324
+ | 18.3522 | 269.0 | 2152 | 7.5572 |
325
+ | 18.3817 | 270.0 | 2160 | 7.5672 |
326
+ | 18.3282 | 271.0 | 2168 | 7.5695 |
327
+ | 18.3291 | 272.0 | 2176 | 7.5691 |
328
+ | 18.2408 | 273.0 | 2184 | 7.5721 |
329
+ | 18.2657 | 274.0 | 2192 | 7.5742 |
330
+ | 18.2421 | 275.0 | 2200 | 7.5738 |
331
+ | 18.1431 | 276.0 | 2208 | 7.5764 |
332
+ | 18.1671 | 277.0 | 2216 | 7.5875 |
333
+ | 18.1461 | 278.0 | 2224 | 7.5894 |
334
+ | 18.0641 | 279.0 | 2232 | 7.5881 |
335
+ | 18.0364 | 280.0 | 2240 | 7.5972 |
336
+ | 18.0405 | 281.0 | 2248 | 7.5952 |
337
+ | 18.1256 | 282.0 | 2256 | 7.5977 |
338
+ | 17.9734 | 283.0 | 2264 | 7.6080 |
339
+ | 17.9075 | 284.0 | 2272 | 7.6076 |
340
+ | 17.9187 | 285.0 | 2280 | 7.6069 |
341
+ | 17.9586 | 286.0 | 2288 | 7.6043 |
342
+ | 17.882 | 287.0 | 2296 | 7.6186 |
343
+ | 17.8672 | 288.0 | 2304 | 7.6214 |
344
+ | 17.8878 | 289.0 | 2312 | 7.6164 |
345
+ | 17.8852 | 290.0 | 2320 | 7.6237 |
346
+ | 17.8945 | 291.0 | 2328 | 7.6245 |
347
+ | 17.7953 | 292.0 | 2336 | 7.6297 |
348
+ | 17.7679 | 293.0 | 2344 | 7.6304 |
349
+ | 17.7104 | 294.0 | 2352 | 7.6286 |
350
+ | 17.7274 | 295.0 | 2360 | 7.6329 |
351
+ | 17.8378 | 296.0 | 2368 | 7.6313 |
352
+ | 17.7059 | 297.0 | 2376 | 7.6407 |
353
+ | 17.6694 | 298.0 | 2384 | 7.6439 |
354
+ | 17.6471 | 299.0 | 2392 | 7.6410 |
355
+ | 17.6261 | 300.0 | 2400 | 7.6451 |
356
+ | 17.6186 | 301.0 | 2408 | 7.6494 |
357
+ | 17.6226 | 302.0 | 2416 | 7.6481 |
358
+ | 17.5872 | 303.0 | 2424 | 7.6518 |
359
+ | 17.539 | 304.0 | 2432 | 7.6539 |
360
+ | 17.5774 | 305.0 | 2440 | 7.6555 |
361
+ | 17.5556 | 306.0 | 2448 | 7.6611 |
362
+ | 17.5351 | 307.0 | 2456 | 7.6561 |
363
+ | 17.4769 | 308.0 | 2464 | 7.6581 |
364
+ | 17.5185 | 309.0 | 2472 | 7.6641 |
365
+ | 17.4876 | 310.0 | 2480 | 7.6592 |
366
+ | 17.4532 | 311.0 | 2488 | 7.6637 |
367
+ | 17.4323 | 312.0 | 2496 | 7.6661 |
368
+ | 17.4594 | 313.0 | 2504 | 7.6679 |
369
+ | 17.4059 | 314.0 | 2512 | 7.6667 |
370
+ | 17.4346 | 315.0 | 2520 | 7.6785 |
371
+ | 17.4066 | 316.0 | 2528 | 7.6736 |
372
+ | 17.4681 | 317.0 | 2536 | 7.6786 |
373
+ | 17.432 | 318.0 | 2544 | 7.6754 |
374
+ | 17.3969 | 319.0 | 2552 | 7.6804 |
375
+ | 17.4143 | 320.0 | 2560 | 7.6799 |
376
+ | 17.3367 | 321.0 | 2568 | 7.6818 |
377
+ | 17.3314 | 322.0 | 2576 | 7.6851 |
378
+ | 17.3424 | 323.0 | 2584 | 7.6841 |
379
+ | 17.4023 | 324.0 | 2592 | 7.6839 |
380
+ | 17.2825 | 325.0 | 2600 | 7.6870 |
381
+ | 17.2865 | 326.0 | 2608 | 7.6857 |
382
+ | 17.3422 | 327.0 | 2616 | 7.6866 |
383
+ | 17.3048 | 328.0 | 2624 | 7.6901 |
384
+ | 17.2966 | 329.0 | 2632 | 7.6886 |
385
+ | 17.2027 | 330.0 | 2640 | 7.6900 |
386
+ | 17.31 | 331.0 | 2648 | 7.6911 |
387
+ | 17.376 | 332.0 | 2656 | 7.6930 |
388
+ | 17.2862 | 333.0 | 2664 | 7.6943 |
389
+ | 17.2696 | 334.0 | 2672 | 7.6960 |
390
+ | 17.2753 | 335.0 | 2680 | 7.6968 |
391
+ | 17.17 | 336.0 | 2688 | 7.6963 |
392
+ | 17.1251 | 337.0 | 2696 | 7.6971 |
393
+ | 17.2253 | 338.0 | 2704 | 7.6966 |
394
+ | 17.2259 | 339.0 | 2712 | 7.6996 |
395
+ | 17.1681 | 340.0 | 2720 | 7.6974 |
396
+ | 17.2241 | 341.0 | 2728 | 7.6990 |
397
+ | 17.2255 | 342.0 | 2736 | 7.6996 |
398
+ | 17.2979 | 343.0 | 2744 | 7.7002 |
399
+ | 17.1608 | 344.0 | 2752 | 7.6985 |
400
+ | 17.1699 | 345.0 | 2760 | 7.7017 |
401
+ | 17.225 | 346.0 | 2768 | 7.7016 |
402
+ | 17.1287 | 347.0 | 2776 | 7.7021 |
403
+ | 17.2054 | 348.0 | 2784 | 7.7034 |
404
+ | 17.2621 | 349.0 | 2792 | 7.7025 |
405
+ | 17.1999 | 350.0 | 2800 | 7.7041 |
406
+ | 17.1437 | 351.0 | 2808 | 7.7053 |
407
+ | 17.1945 | 352.0 | 2816 | 7.7044 |
408
+ | 17.1877 | 353.0 | 2824 | 7.7030 |
409
+ | 17.0871 | 354.0 | 2832 | 7.7059 |
410
+ | 17.1505 | 355.0 | 2840 | 7.7050 |
411
+ | 17.1964 | 356.0 | 2848 | 7.7052 |
412
+ | 17.1234 | 357.0 | 2856 | 7.7060 |
413
+ | 17.2103 | 358.0 | 2864 | 7.7056 |
414
+ | 17.2273 | 359.0 | 2872 | 7.7047 |
415
+ | 17.0804 | 360.0 | 2880 | 7.7061 |
416
+ | 17.0981 | 361.0 | 2888 | 7.7064 |
417
+ | 17.0298 | 362.0 | 2896 | 7.7056 |
418
+ | 17.1634 | 363.0 | 2904 | 7.7053 |
419
+ | 17.0846 | 364.0 | 2912 | 7.7061 |
420
+ | 17.1246 | 365.0 | 2920 | 7.7067 |
421
+ | 17.1628 | 366.0 | 2928 | 7.7064 |
422
+ | 17.2124 | 367.0 | 2936 | 7.7063 |
423
+ | 17.085 | 368.0 | 2944 | 7.7064 |
424
+ | 17.0525 | 369.0 | 2952 | 7.7065 |
425
+ | 17.0698 | 370.0 | 2960 | 7.7065 |
426
+ | 17.1785 | 371.0 | 2968 | 7.7066 |
427
+ | 17.0874 | 372.0 | 2976 | 7.7066 |
428
+ | 17.1582 | 373.0 | 2984 | 7.7066 |
429
+ | 17.1624 | 374.0 | 2992 | 7.7066 |
430
+ | 17.1268 | 375.0 | 3000 | 7.7066 |
431
+
432
+
433
+ ### Framework versions
434
+
435
+ - Transformers 4.49.0
436
+ - Pytorch 2.4.0+cu121
437
+ - Datasets 3.4.0
438
+ - Tokenizers 0.21.0
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.49.0"
6
+ }