Hugging Face's logo

IParraMartin
/
impossible-llms-german-random

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
IParraMartin commited on
Commit
76aff30
·
verified ·
1 Parent(s): 737f3a2

End of training

Browse files
Files changed (2) hide show
  1. README.md +230 -0
  2. generation_config.json +6 -0
README.md ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: impossible-llms-german-random
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-german-random
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: 6.5580
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
+ | 28.22 | 1.0 | 18 | 9.3927 |
57
+ | 26.7279 | 2.0 | 36 | 8.9499 |
58
+ | 25.6547 | 3.0 | 54 | 8.5507 |
59
+ | 24.3808 | 4.0 | 72 | 8.1185 |
60
+ | 22.881 | 5.0 | 90 | 7.6329 |
61
+ | 21.4807 | 6.0 | 108 | 7.1485 |
62
+ | 20.4576 | 7.0 | 126 | 6.7649 |
63
+ | 19.6282 | 8.0 | 144 | 6.5364 |
64
+ | 19.1997 | 9.0 | 162 | 6.4326 |
65
+ | 18.861 | 10.0 | 180 | 6.3683 |
66
+ | 18.7922 | 11.0 | 198 | 6.3189 |
67
+ | 18.9556 | 12.0 | 216 | 6.2618 |
68
+ | 18.5314 | 13.0 | 234 | 6.2134 |
69
+ | 18.5663 | 14.0 | 252 | 6.1788 |
70
+ | 18.4854 | 15.0 | 270 | 6.1504 |
71
+ | 18.1668 | 16.0 | 288 | 6.1251 |
72
+ | 18.3746 | 17.0 | 306 | 6.1035 |
73
+ | 18.0233 | 18.0 | 324 | 6.0776 |
74
+ | 18.0164 | 19.0 | 342 | 6.0475 |
75
+ | 17.5869 | 20.0 | 360 | 6.0198 |
76
+ | 17.8081 | 21.0 | 378 | 5.9977 |
77
+ | 17.5177 | 22.0 | 396 | 5.9725 |
78
+ | 17.3173 | 23.0 | 414 | 5.9435 |
79
+ | 17.5747 | 24.0 | 432 | 5.9193 |
80
+ | 17.557 | 25.0 | 450 | 5.8967 |
81
+ | 17.2291 | 26.0 | 468 | 5.8753 |
82
+ | 17.422 | 27.0 | 486 | 5.8524 |
83
+ | 17.1727 | 28.0 | 504 | 5.8351 |
84
+ | 17.0568 | 29.0 | 522 | 5.8191 |
85
+ | 17.0573 | 30.0 | 540 | 5.8014 |
86
+ | 16.768 | 31.0 | 558 | 5.7869 |
87
+ | 16.6649 | 32.0 | 576 | 5.7707 |
88
+ | 16.6858 | 33.0 | 594 | 5.7623 |
89
+ | 16.8468 | 34.0 | 612 | 5.7485 |
90
+ | 16.8416 | 35.0 | 630 | 5.7400 |
91
+ | 16.5872 | 36.0 | 648 | 5.7308 |
92
+ | 16.4419 | 37.0 | 666 | 5.7204 |
93
+ | 16.4949 | 38.0 | 684 | 5.7156 |
94
+ | 16.4446 | 39.0 | 702 | 5.7104 |
95
+ | 16.1716 | 40.0 | 720 | 5.7046 |
96
+ | 16.2623 | 41.0 | 738 | 5.6975 |
97
+ | 16.177 | 42.0 | 756 | 5.6957 |
98
+ | 16.2276 | 43.0 | 774 | 5.6947 |
99
+ | 15.9746 | 44.0 | 792 | 5.6945 |
100
+ | 15.9396 | 45.0 | 810 | 5.6915 |
101
+ | 16.0085 | 46.0 | 828 | 5.6887 |
102
+ | 15.9081 | 47.0 | 846 | 5.6941 |
103
+ | 15.7286 | 48.0 | 864 | 5.6940 |
104
+ | 15.7661 | 49.0 | 882 | 5.6973 |
105
+ | 15.6632 | 50.0 | 900 | 5.6976 |
106
+ | 15.8302 | 51.0 | 918 | 5.7014 |
107
+ | 15.735 | 52.0 | 936 | 5.7084 |
108
+ | 15.5396 | 53.0 | 954 | 5.7129 |
109
+ | 15.2283 | 54.0 | 972 | 5.7151 |
110
+ | 15.3666 | 55.0 | 990 | 5.7200 |
111
+ | 15.3172 | 56.0 | 1008 | 5.7237 |
112
+ | 15.208 | 57.0 | 1026 | 5.7329 |
113
+ | 15.4495 | 58.0 | 1044 | 5.7408 |
114
+ | 15.0151 | 59.0 | 1062 | 5.7522 |
115
+ | 15.2973 | 60.0 | 1080 | 5.7577 |
116
+ | 15.0306 | 61.0 | 1098 | 5.7656 |
117
+ | 14.9065 | 62.0 | 1116 | 5.7721 |
118
+ | 14.8622 | 63.0 | 1134 | 5.7840 |
119
+ | 15.0454 | 64.0 | 1152 | 5.7948 |
120
+ | 14.6227 | 65.0 | 1170 | 5.8064 |
121
+ | 14.661 | 66.0 | 1188 | 5.8118 |
122
+ | 14.5349 | 67.0 | 1206 | 5.8224 |
123
+ | 14.577 | 68.0 | 1224 | 5.8362 |
124
+ | 14.4111 | 69.0 | 1242 | 5.8465 |
125
+ | 14.324 | 70.0 | 1260 | 5.8550 |
126
+ | 14.3226 | 71.0 | 1278 | 5.8667 |
127
+ | 14.3473 | 72.0 | 1296 | 5.8785 |
128
+ | 14.293 | 73.0 | 1314 | 5.8909 |
129
+ | 14.3887 | 74.0 | 1332 | 5.9039 |
130
+ | 14.3544 | 75.0 | 1350 | 5.9148 |
131
+ | 14.1185 | 76.0 | 1368 | 5.9321 |
132
+ | 14.0668 | 77.0 | 1386 | 5.9423 |
133
+ | 14.1742 | 78.0 | 1404 | 5.9526 |
134
+ | 13.8125 | 79.0 | 1422 | 5.9667 |
135
+ | 13.9209 | 80.0 | 1440 | 5.9815 |
136
+ | 13.8013 | 81.0 | 1458 | 5.9925 |
137
+ | 13.8491 | 82.0 | 1476 | 6.0041 |
138
+ | 13.6533 | 83.0 | 1494 | 6.0213 |
139
+ | 13.6402 | 84.0 | 1512 | 6.0318 |
140
+ | 13.5231 | 85.0 | 1530 | 6.0379 |
141
+ | 13.5759 | 86.0 | 1548 | 6.0539 |
142
+ | 13.4849 | 87.0 | 1566 | 6.0718 |
143
+ | 13.4543 | 88.0 | 1584 | 6.0866 |
144
+ | 13.2973 | 89.0 | 1602 | 6.0971 |
145
+ | 13.2578 | 90.0 | 1620 | 6.1055 |
146
+ | 13.3011 | 91.0 | 1638 | 6.1199 |
147
+ | 13.163 | 92.0 | 1656 | 6.1289 |
148
+ | 13.178 | 93.0 | 1674 | 6.1399 |
149
+ | 13.3033 | 94.0 | 1692 | 6.1526 |
150
+ | 13.318 | 95.0 | 1710 | 6.1627 |
151
+ | 12.9948 | 96.0 | 1728 | 6.1788 |
152
+ | 12.9897 | 97.0 | 1746 | 6.1916 |
153
+ | 13.0252 | 98.0 | 1764 | 6.2004 |
154
+ | 13.0065 | 99.0 | 1782 | 6.2176 |
155
+ | 12.9862 | 100.0 | 1800 | 6.2253 |
156
+ | 12.9079 | 101.0 | 1818 | 6.2351 |
157
+ | 12.9666 | 102.0 | 1836 | 6.2442 |
158
+ | 12.8916 | 103.0 | 1854 | 6.2537 |
159
+ | 12.7161 | 104.0 | 1872 | 6.2634 |
160
+ | 12.8223 | 105.0 | 1890 | 6.2823 |
161
+ | 12.6665 | 106.0 | 1908 | 6.2882 |
162
+ | 12.6533 | 107.0 | 1926 | 6.2976 |
163
+ | 12.5934 | 108.0 | 1944 | 6.3050 |
164
+ | 12.6871 | 109.0 | 1962 | 6.3143 |
165
+ | 12.6676 | 110.0 | 1980 | 6.3266 |
166
+ | 12.3628 | 111.0 | 1998 | 6.3319 |
167
+ | 12.6313 | 112.0 | 2016 | 6.3413 |
168
+ | 12.328 | 113.0 | 2034 | 6.3557 |
169
+ | 12.4958 | 114.0 | 2052 | 6.3611 |
170
+ | 12.5022 | 115.0 | 2070 | 6.3673 |
171
+ | 12.3673 | 116.0 | 2088 | 6.3787 |
172
+ | 12.3613 | 117.0 | 2106 | 6.3904 |
173
+ | 12.4782 | 118.0 | 2124 | 6.3973 |
174
+ | 12.3523 | 119.0 | 2142 | 6.4094 |
175
+ | 12.1093 | 120.0 | 2160 | 6.4166 |
176
+ | 12.2079 | 121.0 | 2178 | 6.4194 |
177
+ | 12.1763 | 122.0 | 2196 | 6.4229 |
178
+ | 12.1662 | 123.0 | 2214 | 6.4335 |
179
+ | 12.256 | 124.0 | 2232 | 6.4407 |
180
+ | 12.1079 | 125.0 | 2250 | 6.4467 |
181
+ | 12.1875 | 126.0 | 2268 | 6.4554 |
182
+ | 12.1299 | 127.0 | 2286 | 6.4605 |
183
+ | 11.9807 | 128.0 | 2304 | 6.4662 |
184
+ | 12.09 | 129.0 | 2322 | 6.4693 |
185
+ | 11.9597 | 130.0 | 2340 | 6.4760 |
186
+ | 11.9942 | 131.0 | 2358 | 6.4824 |
187
+ | 12.0525 | 132.0 | 2376 | 6.4904 |
188
+ | 12.0041 | 133.0 | 2394 | 6.4914 |
189
+ | 11.9356 | 134.0 | 2412 | 6.4995 |
190
+ | 12.07 | 135.0 | 2430 | 6.5004 |
191
+ | 11.8729 | 136.0 | 2448 | 6.5052 |
192
+ | 11.9321 | 137.0 | 2466 | 6.5094 |
193
+ | 11.9413 | 138.0 | 2484 | 6.5114 |
194
+ | 11.9385 | 139.0 | 2502 | 6.5158 |
195
+ | 11.8975 | 140.0 | 2520 | 6.5230 |
196
+ | 11.7267 | 141.0 | 2538 | 6.5264 |
197
+ | 11.9369 | 142.0 | 2556 | 6.5283 |
198
+ | 11.8706 | 143.0 | 2574 | 6.5292 |
199
+ | 11.7837 | 144.0 | 2592 | 6.5352 |
200
+ | 11.6952 | 145.0 | 2610 | 6.5372 |
201
+ | 11.8134 | 146.0 | 2628 | 6.5397 |
202
+ | 11.7266 | 147.0 | 2646 | 6.5439 |
203
+ | 11.7295 | 148.0 | 2664 | 6.5441 |
204
+ | 11.5708 | 149.0 | 2682 | 6.5456 |
205
+ | 11.7177 | 150.0 | 2700 | 6.5479 |
206
+ | 11.7275 | 151.0 | 2718 | 6.5502 |
207
+ | 11.6484 | 152.0 | 2736 | 6.5518 |
208
+ | 11.8526 | 153.0 | 2754 | 6.5529 |
209
+ | 11.7822 | 154.0 | 2772 | 6.5530 |
210
+ | 11.8092 | 155.0 | 2790 | 6.5533 |
211
+ | 11.6373 | 156.0 | 2808 | 6.5540 |
212
+ | 11.7904 | 157.0 | 2826 | 6.5569 |
213
+ | 11.7237 | 158.0 | 2844 | 6.5575 |
214
+ | 11.6092 | 159.0 | 2862 | 6.5569 |
215
+ | 11.6797 | 160.0 | 2880 | 6.5569 |
216
+ | 11.7197 | 161.0 | 2898 | 6.5575 |
217
+ | 11.9107 | 162.0 | 2916 | 6.5581 |
218
+ | 11.7386 | 163.0 | 2934 | 6.5578 |
219
+ | 11.7278 | 164.0 | 2952 | 6.5580 |
220
+ | 11.8036 | 165.0 | 2970 | 6.5580 |
221
+ | 11.6859 | 166.0 | 2988 | 6.5580 |
222
+ | 31.2663 | 166.6906 | 3000 | 6.5580 |
223
+
224
+
225
+ ### Framework versions
226
+
227
+ - Transformers 4.49.0
228
+ - Pytorch 2.4.0+cu121
229
+ - Datasets 3.4.0
230
+ - 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
+ }