Diachronia year prediction
Guess the time when a Polish excerpt was published [ver. 1.0.0]
This is a long list of all submissions, if you want to see only the best, click leaderboard.
| # | submitter | when | ver. | description | dev-0 RMSE | test-A RMSE | |
|---|---|---|---|---|---|---|---|
| 47 | Rebelski | 2023-06-18 20:36 | 1.0.0 | SGD approach | 71.84 | 51.88 | |
| 37 | Wawrzyniak | 2023-06-17 22:34 | 1.0.0 | LSTM network | 27.82 | 23.46 | |
| 38 | Oprus | 2023-06-14 21:39 | 1.0.0 | test solution 1 | 28.69 | 23.85 | |
| 51 | Wawrzyniak | 2023-06-14 10:41 | 1.0.0 | Average | N/A | 55.37 | |
| 40 | Malinowski | 2023-06-14 08:19 | 1.0.0 | diachronia-year-prediction | 32.50 | 27.57 | |
| 41 | Wnuk | 2023-06-13 21:24 | 1.0.0 | wnuk | 34.77 | 28.14 | |
| 25 | Patyk | 2023-06-13 21:10 | 1.0.0 | lunar-jazz-13 | N/A | 17.17 | |
| 43 | Pluciński | 2023-06-13 14:24 | 1.0.0 | Tragedia w 3 aktach | 33.69 | 30.22 | |
| 1 | Kaszuba | 2023-06-13 09:24 | 1.0.0 | test solution | 17.04 | 14.95 | |
| 39 | Serba | 2023-06-12 21:24 | 1.0.0 | model2 | 29.42 | 24.73 | |
| 48 | Henyk | 2023-06-12 17:08 | 1.0.0 | Solution based on probability matrix, 10 epochs | 62.30 | 51.94 | |
| 55 | Henyk | 2023-06-12 17:02 | 1.0.0 | Solution based on probability matrix, 10 epochs | N/A | N/A | |
| 49 | Szyszko | 2023-06-12 16:10 | 1.0.0 | Solution neural-network bert | 56.23 | 52.71 | |
| 54 | Henyk | 2023-06-12 11:22 | 1.0.0 | Solution based on probability matrix, 5 epochs | 65.03 | 59.39 | |
| 53 | Skórzewski | 2023-06-10 16:04 | 1.0.0 | TF-IDF + linear regression | N/A | 56.03 | |
| 35 | Patyk | 2023-06-10 11:28 | 1.0.0 | restful-bush-6 | N/A | 21.53 | |
| 6 | Kaszuba | 2023-06-08 21:18 | 1.0.0 | test solution | 17.38 | 15.28 | |
| 42 | Czerniak | 2023-06-07 11:49 | 1.0.0 | First submission | 37.84 | 29.16 | |
| 44 | Patyk | 2023-06-06 18:18 | 1.0.0 | new submit | 15.63 | 30.34 | |
| 46 | Patyk | 2023-06-06 12:37 | 1.0.0 | random results | 29.71 | 40.92 | |
| 32 | Antkowiak | 2023-05-31 10:34 | 1.0.0 | transformers | 19.63 | 20.56 | |
| 45 | Antkowiak | 2023-05-28 12:32 | 1.0.0 | sieć Soplica (korpus: Pan Tadeusz) tf tokenization | 46.12 | 40.09 | |
| 4 | zrostek | 2023-05-25 09:22 | 1.0.0 | pretrained nanoT5 (adafactor, legacy) summarization (50 GB), step 70000 out of 364210 (plus 0.5 year) epochs=3 no-pretrained t5 | 16.15 | 15.22 | |
| 8 | zrostek | 2023-05-25 09:19 | 1.0.0 | pretrained nanoT5 (adafactor, legacy) summarization (50 GB), step 70000 out of 364210 epochs=1.8 no-pretrained t5 | 16.00 | 15.59 | |
| 5 | zrostek | 2023-05-25 08:49 | 1.0.0 | pretrained nanoT5 (adafactor, legacy) summarization (50 GB), step 70000 out of 364210 epochs=3 no-pretrained t5 | 16.09 | 15.23 | |
| 16 | zrostek | 2023-05-24 08:19 | 1.0.0 | plT5-base summarization, year with spaces with month name epochs=3 t5 | 16.86 | 16.08 | |
| 10 | zrostek | 2023-05-23 08:23 | 1.0.0 | pretrained nanoT5 summarization with month name (50 GB), step 60000 out of 364210 epochs=2,89 no-pretrained t5 | 16.53 | 15.78 | |
| 13 | zrostek | 2023-05-23 07:15 | 1.0.0 | pretrained nanoT5 summarization (50 GB), step 60000 out of 364210 epochs=3 no-pretrained t5 | 16.49 | 15.90 | |
| 19 | zrostek | 2023-05-12 11:37 | 1.0.0 | pretrained nanoT5 (50 GB) summarization epochs=2.75 no-pretrained t5 | 19.38 | 16.32 | |
| 3 | zrostek | 2023-05-08 07:09 | 1.0.0 | plT5-large summarization with spaces epochs=3 large t5 | 15.21 | 15.00 | |
| 9 | zrostek | 2023-04-27 07:38 | 1.0.0 | plT5-large summarization with spaces epochs=2.1 large t5 | 15.93 | 15.63 | |
| 12 | zrostek | 2023-04-26 13:18 | 1.0.0 | plT5-large summarization with spaces epochs=1.54 large t5 | 15.56 | 15.87 | |
| 7 | zrostek | 2023-04-26 08:40 | 1.0.0 | plT5-large summarization with spaces epochs=1.29 large t5 | 16.39 | 15.36 | |
| 2 | zrostek | 2023-04-25 10:06 | 1.0.0 | plT5 summarization with spaces epochs=3 t5 | 16.98 | 14.98 | |
| 23 | zrostek | 2023-04-25 10:03 | 1.0.0 | plT5-large summarization with spaces epochs=1.15 large t5 | 16.50 | 16.58 | |
| 15 | zrostek | 2023-04-25 07:44 | 1.0.0 | plT5-large summarization with spaces epochs=0.79 large t5 | 17.10 | 16.05 | |
| 11 | zrostek | 2023-04-21 08:09 | 1.0.0 | plT5 summarization with spaces epochs=2.4 t5 | 17.75 | 15.81 | |
| 24 | zrostek | 2023-04-21 07:25 | 1.0.0 | plT5 summarization with spaces epochs=1.5 t5 | 17.70 | 16.84 | |
| 18 | zrostek | 2023-04-20 12:40 | 1.0.0 | plT5 summarization with spaces (one decimal place) epochs=3 t5 | 17.74 | 16.29 | |
| 20 | zrostek | 2023-04-20 09:42 | 1.0.0 | plT5 summarization with spaces (one decimal place) epochs=2.62 t5 | 17.59 | 16.34 | |
| 14 | zrostek | 2023-04-19 19:34 | 1.0.0 | plT5 summarization epochs=2.45 t5 | 17.74 | 16.05 | |
| 22 | zrostek | 2023-04-19 12:06 | 1.0.0 | plT5 summarization with spaces epochs=1.5 t5 | 17.72 | 16.45 | |
| 36 | zrostek | 2023-04-19 07:59 | 1.0.0 | pretrained nanoT5 (1GB) summarization epochs=3 no-pretrained t5 | 23.83 | 22.62 | |
| 30 | zrostek | 2023-04-13 10:26 | 1.0.0 | Roberta trained from scratch with 50 GB filtered data epochs=1 roberta no-pretrained | 21.17 | 20.00 | |
| 28 | zrostek | 2023-04-11 10:55 | 1.0.0 | Roberta trained from scratch with 50 GB filtered data (checkpoint 94000 from 202000) epochs=1 roberta no-pretrained | 20.31 | 19.41 | |
| 27 | zrostek | 2023-03-09 08:58 | 1.0.0 | Roberta trained from scratch with 6,2 + 19 GB extra filtered Polish text roberta no-pretrained | 20.06 | 18.68 | |
| 33 | zrostek | 2023-02-24 14:36 | 1.0.0 | Roberta trained from scratch with 6,7 GB extra unfiltered Polish text roberta no-pretrained | 22.98 | 20.87 | |
| 29 | zrostek | 2023-02-24 11:07 | 1.0.0 | Roberta trained from scratch with 6,2 GB extra filtered Polish text (6,7 GB before filtering) roberta no-pretrained | 21.50 | 19.84 | |
| 31 | zrostek | 2023-02-23 12:39 | 1.0.0 | Roberta trained from scratch with 6,2 GB extra filtered Polish text (6,7 GB before filtering) roberta no-pretrained | 21.93 | 20.15 | |
| 34 | zrostek | 2023-02-16 08:46 | 1.0.0 | Roberta trained from scratch with 6,7 GB extra unfiltered Polish text roberta no-pretrained | 23.19 | 21.06 | |
| 17 | zrostek | 2022-12-19 08:20 | 1.0.0 | finetuned HerBERT epochs=10 learning-rate=1.0e-6 transformer bert | 17.72 | 16.09 | |
| 21 | zrostek | 2022-12-12 08:08 | 1.0.0 | transformer linear regression linear-regression transformer | 18.75 | 16.41 | |
| 50 | zrostek | 2022-12-05 14:44 | 1.0.0 | linear regression baseline linear-regression tf-idf baseline | 64.45 | 53.32 | |
| 26 | p/tlen | 2022-12-03 20:31 | 1.0.0 | Vowpal Wabbit regression with a small neural network bits=29 nnsize=6 passes=10 vowpal-wabbit | 20.77 | 17.76 | |
| 52 | p/tlen | 2022-11-19 15:24 | 1.0.0 | null-model baseline null-model baseline | 66.69 | 55.70 |