helena-balabin
commited on
Commit
•
bc3d3b0
1
Parent(s):
d839843
End of training
Browse files- README.md +256 -0
- config.json +33 -0
- emissions.csv +2 -0
- events.out.tfevents.1712412730.gbw-d-l0134.4020808.0 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: DTAI-KULeuven/robbert-2023-dutch-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: robbert-2023-dutch-base-ft-nlp-xxl
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# robbert-2023-dutch-base-ft-nlp-xxl
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [DTAI-KULeuven/robbert-2023-dutch-base](https://huggingface.co/DTAI-KULeuven/robbert-2023-dutch-base) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.0118
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- training_steps: 2000
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 2.8326 | 0.06 | 10 | 2.6788 |
|
50 |
+
| 2.7533 | 0.12 | 20 | 2.5468 |
|
51 |
+
| 2.4636 | 0.19 | 30 | 2.5083 |
|
52 |
+
| 2.6891 | 0.25 | 40 | 2.4572 |
|
53 |
+
| 2.5285 | 0.31 | 50 | 2.4016 |
|
54 |
+
| 2.5102 | 0.37 | 60 | 2.4493 |
|
55 |
+
| 2.5021 | 0.43 | 70 | 2.3338 |
|
56 |
+
| 2.4623 | 0.5 | 80 | 2.3530 |
|
57 |
+
| 2.3883 | 0.56 | 90 | 2.3881 |
|
58 |
+
| 2.4773 | 0.62 | 100 | 2.3410 |
|
59 |
+
| 2.4389 | 0.68 | 110 | 2.3148 |
|
60 |
+
| 2.3577 | 0.75 | 120 | 2.3326 |
|
61 |
+
| 2.3497 | 0.81 | 130 | 2.3429 |
|
62 |
+
| 2.3806 | 0.87 | 140 | 2.2916 |
|
63 |
+
| 2.433 | 0.93 | 150 | 2.2801 |
|
64 |
+
| 2.4703 | 0.99 | 160 | 2.2703 |
|
65 |
+
| 2.1623 | 1.06 | 170 | 2.3148 |
|
66 |
+
| 2.3273 | 1.12 | 180 | 2.2596 |
|
67 |
+
| 2.2054 | 1.18 | 190 | 2.1914 |
|
68 |
+
| 2.3115 | 1.24 | 200 | 2.2161 |
|
69 |
+
| 2.109 | 1.3 | 210 | 2.1979 |
|
70 |
+
| 2.375 | 1.37 | 220 | 2.2155 |
|
71 |
+
| 2.2816 | 1.43 | 230 | 2.1992 |
|
72 |
+
| 2.3764 | 1.49 | 240 | 2.1825 |
|
73 |
+
| 2.1229 | 1.55 | 250 | 2.2547 |
|
74 |
+
| 2.1761 | 1.61 | 260 | 2.1983 |
|
75 |
+
| 2.2285 | 1.68 | 270 | 2.2590 |
|
76 |
+
| 2.3079 | 1.74 | 280 | 2.1666 |
|
77 |
+
| 2.2963 | 1.8 | 290 | 2.2389 |
|
78 |
+
| 2.3471 | 1.86 | 300 | 2.1583 |
|
79 |
+
| 2.2031 | 1.93 | 310 | 2.2457 |
|
80 |
+
| 2.3073 | 1.99 | 320 | 2.2102 |
|
81 |
+
| 2.1813 | 2.05 | 330 | 2.1898 |
|
82 |
+
| 2.1958 | 2.11 | 340 | 2.2095 |
|
83 |
+
| 2.2239 | 2.17 | 350 | 2.2107 |
|
84 |
+
| 2.1024 | 2.24 | 360 | 2.2168 |
|
85 |
+
| 2.1895 | 2.3 | 370 | 2.1944 |
|
86 |
+
| 2.1631 | 2.36 | 380 | 2.2287 |
|
87 |
+
| 2.1258 | 2.42 | 390 | 2.1830 |
|
88 |
+
| 2.236 | 2.48 | 400 | 2.1641 |
|
89 |
+
| 2.1493 | 2.55 | 410 | 2.1377 |
|
90 |
+
| 2.1368 | 2.61 | 420 | 2.1640 |
|
91 |
+
| 2.1932 | 2.67 | 430 | 2.2102 |
|
92 |
+
| 2.2071 | 2.73 | 440 | 2.1461 |
|
93 |
+
| 2.2059 | 2.8 | 450 | 2.2398 |
|
94 |
+
| 2.2088 | 2.86 | 460 | 2.1055 |
|
95 |
+
| 2.2002 | 2.92 | 470 | 2.2272 |
|
96 |
+
| 2.1892 | 2.98 | 480 | 2.1622 |
|
97 |
+
| 2.1382 | 3.04 | 490 | 2.1392 |
|
98 |
+
| 2.0724 | 3.11 | 500 | 2.1669 |
|
99 |
+
| 2.09 | 3.17 | 510 | 2.1585 |
|
100 |
+
| 2.1398 | 3.23 | 520 | 2.1565 |
|
101 |
+
| 2.1023 | 3.29 | 530 | 2.1532 |
|
102 |
+
| 1.9628 | 3.35 | 540 | 2.1312 |
|
103 |
+
| 2.1294 | 3.42 | 550 | 2.1337 |
|
104 |
+
| 2.0734 | 3.48 | 560 | 2.1854 |
|
105 |
+
| 2.0503 | 3.54 | 570 | 2.1351 |
|
106 |
+
| 1.9727 | 3.6 | 580 | 2.1715 |
|
107 |
+
| 2.0652 | 3.66 | 590 | 2.1348 |
|
108 |
+
| 1.9942 | 3.73 | 600 | 2.2555 |
|
109 |
+
| 2.0017 | 3.79 | 610 | 2.1412 |
|
110 |
+
| 2.0962 | 3.85 | 620 | 2.1442 |
|
111 |
+
| 2.1212 | 3.91 | 630 | 2.1866 |
|
112 |
+
| 2.0276 | 3.98 | 640 | 2.0766 |
|
113 |
+
| 2.0726 | 4.04 | 650 | 2.0432 |
|
114 |
+
| 2.0554 | 4.1 | 660 | 2.1925 |
|
115 |
+
| 1.9865 | 4.16 | 670 | 2.1344 |
|
116 |
+
| 1.9676 | 4.22 | 680 | 2.1379 |
|
117 |
+
| 2.0355 | 4.29 | 690 | 2.1465 |
|
118 |
+
| 1.9982 | 4.35 | 700 | 2.0861 |
|
119 |
+
| 2.0307 | 4.41 | 710 | 2.1359 |
|
120 |
+
| 2.1014 | 4.47 | 720 | 2.0703 |
|
121 |
+
| 1.9608 | 4.53 | 730 | 2.0898 |
|
122 |
+
| 2.1068 | 4.6 | 740 | 2.2018 |
|
123 |
+
| 2.0099 | 4.66 | 750 | 2.1502 |
|
124 |
+
| 2.0715 | 4.72 | 760 | 2.0592 |
|
125 |
+
| 2.1272 | 4.78 | 770 | 2.1833 |
|
126 |
+
| 2.1069 | 4.84 | 780 | 2.0944 |
|
127 |
+
| 1.96 | 4.91 | 790 | 2.1344 |
|
128 |
+
| 2.0613 | 4.97 | 800 | 2.1366 |
|
129 |
+
| 1.9297 | 5.03 | 810 | 2.0956 |
|
130 |
+
| 2.0172 | 5.09 | 820 | 2.1792 |
|
131 |
+
| 2.0134 | 5.16 | 830 | 2.0792 |
|
132 |
+
| 1.9867 | 5.22 | 840 | 2.1058 |
|
133 |
+
| 1.9391 | 5.28 | 850 | 2.1820 |
|
134 |
+
| 1.8802 | 5.34 | 860 | 2.1274 |
|
135 |
+
| 1.9789 | 5.4 | 870 | 2.0956 |
|
136 |
+
| 2.0665 | 5.47 | 880 | 2.1209 |
|
137 |
+
| 2.0909 | 5.53 | 890 | 2.1557 |
|
138 |
+
| 1.9261 | 5.59 | 900 | 2.0976 |
|
139 |
+
| 2.0246 | 5.65 | 910 | 2.1127 |
|
140 |
+
| 1.9727 | 5.71 | 920 | 2.1670 |
|
141 |
+
| 1.8429 | 5.78 | 930 | 2.0906 |
|
142 |
+
| 2.001 | 5.84 | 940 | 2.0951 |
|
143 |
+
| 1.9363 | 5.9 | 950 | 2.0593 |
|
144 |
+
| 2.0033 | 5.96 | 960 | 2.0947 |
|
145 |
+
| 1.9868 | 6.02 | 970 | 2.0643 |
|
146 |
+
| 1.9011 | 6.09 | 980 | 2.1598 |
|
147 |
+
| 1.9562 | 6.15 | 990 | 2.0961 |
|
148 |
+
| 1.8923 | 6.21 | 1000 | 2.1436 |
|
149 |
+
| 1.9066 | 6.27 | 1010 | 2.0773 |
|
150 |
+
| 1.9805 | 6.34 | 1020 | 2.1261 |
|
151 |
+
| 1.829 | 6.4 | 1030 | 2.0962 |
|
152 |
+
| 1.8745 | 6.46 | 1040 | 2.0881 |
|
153 |
+
| 1.8518 | 6.52 | 1050 | 2.0200 |
|
154 |
+
| 1.9164 | 6.58 | 1060 | 2.0809 |
|
155 |
+
| 1.7968 | 6.65 | 1070 | 2.1169 |
|
156 |
+
| 1.9029 | 6.71 | 1080 | 2.0290 |
|
157 |
+
| 1.9383 | 6.77 | 1090 | 2.0806 |
|
158 |
+
| 1.8375 | 6.83 | 1100 | 2.0816 |
|
159 |
+
| 1.8289 | 6.89 | 1110 | 2.0660 |
|
160 |
+
| 1.894 | 6.96 | 1120 | 2.0229 |
|
161 |
+
| 1.843 | 7.02 | 1130 | 2.1239 |
|
162 |
+
| 1.8515 | 7.08 | 1140 | 2.0687 |
|
163 |
+
| 1.8899 | 7.14 | 1150 | 2.0832 |
|
164 |
+
| 1.903 | 7.2 | 1160 | 2.0882 |
|
165 |
+
| 1.8505 | 7.27 | 1170 | 2.0213 |
|
166 |
+
| 1.8155 | 7.33 | 1180 | 2.0808 |
|
167 |
+
| 1.9355 | 7.39 | 1190 | 2.0649 |
|
168 |
+
| 1.8213 | 7.45 | 1200 | 2.0817 |
|
169 |
+
| 1.9897 | 7.52 | 1210 | 2.1589 |
|
170 |
+
| 1.8044 | 7.58 | 1220 | 2.1288 |
|
171 |
+
| 1.9347 | 7.64 | 1230 | 2.0927 |
|
172 |
+
| 1.9311 | 7.7 | 1240 | 2.0180 |
|
173 |
+
| 1.922 | 7.76 | 1250 | 2.0163 |
|
174 |
+
| 1.8572 | 7.83 | 1260 | 2.0632 |
|
175 |
+
| 1.8858 | 7.89 | 1270 | 2.0255 |
|
176 |
+
| 1.8692 | 7.95 | 1280 | 2.0807 |
|
177 |
+
| 1.9486 | 8.01 | 1290 | 2.0829 |
|
178 |
+
| 1.8184 | 8.07 | 1300 | 2.0721 |
|
179 |
+
| 1.884 | 8.14 | 1310 | 2.0809 |
|
180 |
+
| 1.7928 | 8.2 | 1320 | 2.0462 |
|
181 |
+
| 1.8337 | 8.26 | 1330 | 2.0486 |
|
182 |
+
| 1.8443 | 8.32 | 1340 | 2.0113 |
|
183 |
+
| 1.8546 | 8.39 | 1350 | 2.0348 |
|
184 |
+
| 1.9359 | 8.45 | 1360 | 1.9960 |
|
185 |
+
| 1.874 | 8.51 | 1370 | 2.0198 |
|
186 |
+
| 1.9366 | 8.57 | 1380 | 2.1198 |
|
187 |
+
| 1.8081 | 8.63 | 1390 | 2.0964 |
|
188 |
+
| 1.8655 | 8.7 | 1400 | 2.0571 |
|
189 |
+
| 1.8357 | 8.76 | 1410 | 2.0432 |
|
190 |
+
| 1.8409 | 8.82 | 1420 | 2.0679 |
|
191 |
+
| 1.7785 | 8.88 | 1430 | 2.0930 |
|
192 |
+
| 1.766 | 8.94 | 1440 | 2.1041 |
|
193 |
+
| 1.8542 | 9.01 | 1450 | 2.0035 |
|
194 |
+
| 1.7403 | 9.07 | 1460 | 2.0662 |
|
195 |
+
| 1.8109 | 9.13 | 1470 | 1.9674 |
|
196 |
+
| 1.8191 | 9.19 | 1480 | 2.0274 |
|
197 |
+
| 1.7713 | 9.25 | 1490 | 2.1420 |
|
198 |
+
| 1.7628 | 9.32 | 1500 | 2.0899 |
|
199 |
+
| 1.8273 | 9.38 | 1510 | 1.9969 |
|
200 |
+
| 1.7786 | 9.44 | 1520 | 2.0089 |
|
201 |
+
| 1.7618 | 9.5 | 1530 | 2.0572 |
|
202 |
+
| 1.8247 | 9.57 | 1540 | 2.0710 |
|
203 |
+
| 1.7363 | 9.63 | 1550 | 1.9818 |
|
204 |
+
| 1.8374 | 9.69 | 1560 | 2.0177 |
|
205 |
+
| 1.8838 | 9.75 | 1570 | 2.0528 |
|
206 |
+
| 1.709 | 9.81 | 1580 | 1.9890 |
|
207 |
+
| 1.8743 | 9.88 | 1590 | 2.0105 |
|
208 |
+
| 1.855 | 9.94 | 1600 | 1.9971 |
|
209 |
+
| 1.8659 | 10.0 | 1610 | 2.0052 |
|
210 |
+
| 1.8172 | 10.06 | 1620 | 2.0004 |
|
211 |
+
| 1.7537 | 10.12 | 1630 | 2.1136 |
|
212 |
+
| 1.7822 | 10.19 | 1640 | 2.0685 |
|
213 |
+
| 1.7855 | 10.25 | 1650 | 2.0326 |
|
214 |
+
| 1.7825 | 10.31 | 1660 | 2.0402 |
|
215 |
+
| 1.7391 | 10.37 | 1670 | 2.0100 |
|
216 |
+
| 1.755 | 10.43 | 1680 | 2.0587 |
|
217 |
+
| 1.7649 | 10.5 | 1690 | 2.0548 |
|
218 |
+
| 1.7742 | 10.56 | 1700 | 2.0025 |
|
219 |
+
| 1.8407 | 10.62 | 1710 | 2.0164 |
|
220 |
+
| 1.828 | 10.68 | 1720 | 1.9975 |
|
221 |
+
| 1.7487 | 10.75 | 1730 | 2.0598 |
|
222 |
+
| 1.7521 | 10.81 | 1740 | 2.0318 |
|
223 |
+
| 1.7253 | 10.87 | 1750 | 2.1049 |
|
224 |
+
| 1.7245 | 10.93 | 1760 | 2.0569 |
|
225 |
+
| 1.8093 | 10.99 | 1770 | 1.9909 |
|
226 |
+
| 1.6967 | 11.06 | 1780 | 2.0660 |
|
227 |
+
| 1.7274 | 11.12 | 1790 | 2.0615 |
|
228 |
+
| 1.901 | 11.18 | 1800 | 2.0775 |
|
229 |
+
| 1.7667 | 11.24 | 1810 | 2.0470 |
|
230 |
+
| 1.8173 | 11.3 | 1820 | 2.0141 |
|
231 |
+
| 1.6841 | 11.37 | 1830 | 2.0541 |
|
232 |
+
| 1.7374 | 11.43 | 1840 | 2.0526 |
|
233 |
+
| 1.7307 | 11.49 | 1850 | 2.0060 |
|
234 |
+
| 1.7778 | 11.55 | 1860 | 2.0601 |
|
235 |
+
| 1.7656 | 11.61 | 1870 | 2.0358 |
|
236 |
+
| 1.7167 | 11.68 | 1880 | 2.1360 |
|
237 |
+
| 1.7 | 11.74 | 1890 | 2.0746 |
|
238 |
+
| 1.833 | 11.8 | 1900 | 2.0382 |
|
239 |
+
| 1.7076 | 11.86 | 1910 | 1.9974 |
|
240 |
+
| 1.7491 | 11.93 | 1920 | 2.0558 |
|
241 |
+
| 1.7912 | 11.99 | 1930 | 2.0598 |
|
242 |
+
| 1.7654 | 12.05 | 1940 | 2.0048 |
|
243 |
+
| 1.6612 | 12.11 | 1950 | 2.0457 |
|
244 |
+
| 1.7856 | 12.17 | 1960 | 2.0841 |
|
245 |
+
| 1.8026 | 12.24 | 1970 | 2.1041 |
|
246 |
+
| 1.696 | 12.3 | 1980 | 2.0776 |
|
247 |
+
| 1.7901 | 12.36 | 1990 | 2.0176 |
|
248 |
+
| 1.7881 | 12.42 | 2000 | 2.0118 |
|
249 |
+
|
250 |
+
|
251 |
+
### Framework versions
|
252 |
+
|
253 |
+
- Transformers 4.38.2
|
254 |
+
- Pytorch 2.1.1+cu121
|
255 |
+
- Datasets 2.15.0
|
256 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DTAI-KULeuven/robbert-2023-dutch-base",
|
3 |
+
"additional_special_tokens_ids": [],
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"cls_token_id": 0,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"hidden_dropout_prob": 0.1,
|
14 |
+
"hidden_size": 768,
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"layer_norm_eps": 1e-05,
|
18 |
+
"mask_token_id": 4,
|
19 |
+
"max_position_embeddings": 514,
|
20 |
+
"model_type": "roberta",
|
21 |
+
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"pad_token_id": 1,
|
24 |
+
"position_embedding_type": "absolute",
|
25 |
+
"sep_token_id": 3,
|
26 |
+
"tokenizer_class": "RobertaTokenizerFast",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.38.2",
|
29 |
+
"type_vocab_size": 1,
|
30 |
+
"unk_token_id": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50000
|
33 |
+
}
|
emissions.csv
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud
|
2 |
+
2024-04-06T16:46:30,codecarbon,f61224a3-98ca-4470-bbbe-2a7572aa726d,2059.3586490154266,0.025141290118237136,0.012208310645771738,0.0,99.248,6.0,0,0.12751597603748557,0.0034282433283328996,0.1309442193658184,Belgium,BEL,flanders,,,Linux-5.15.0-97-generic-x86_64-with-glibc2.31,3.10.4,2,Intel(R) Core(TM) i9-10920X CPU @ 3.50GHz,1,1 x NVIDIA RTX A5000,4.7027,50.8758,16,machine,N
|
events.out.tfevents.1712412730.gbw-d-l0134.4020808.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ef0a7e49b00db099ffa31f9e3c449639c5d8045d409f47acf142e5d26404632
|
3 |
+
size 101644
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b76c43faa3c3a39944af23669b49006b033e1b34351c9a9fc01d86d81505837
|
3 |
+
size 497998808
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "</s>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a1de7ae651d9829a686916dedf5ffa27c5ba5ea0df8f47c0957ee28a033e65d
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|