2020-Q2-50p-filtered
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-2019-90m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5608
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1400
- training_steps: 2400000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 0.03 | 8000 | 2.6645 |
2.8656 | 0.07 | 16000 | 2.6465 |
2.8656 | 0.1 | 24000 | 2.6186 |
2.7946 | 0.13 | 32000 | 2.6235 |
2.7946 | 0.17 | 40000 | 2.6151 |
2.7911 | 0.2 | 48000 | 2.6128 |
2.7911 | 0.24 | 56000 | 2.6010 |
2.7898 | 0.27 | 64000 | 2.6144 |
2.7898 | 0.3 | 72000 | 2.5976 |
2.7791 | 0.34 | 80000 | 2.6006 |
2.7791 | 0.37 | 88000 | 2.5889 |
2.7776 | 0.4 | 96000 | 2.5888 |
2.7776 | 0.44 | 104000 | 2.5842 |
2.7702 | 0.47 | 112000 | 2.5760 |
2.7702 | 0.51 | 120000 | 2.5720 |
2.7661 | 0.54 | 128000 | 2.5710 |
2.7661 | 0.57 | 136000 | 2.5673 |
2.7609 | 0.61 | 144000 | 2.5693 |
2.7609 | 0.64 | 152000 | 2.5623 |
2.7557 | 0.67 | 160000 | 2.5559 |
2.7557 | 0.71 | 168000 | 2.5650 |
2.7584 | 0.74 | 176000 | 2.5584 |
2.7584 | 0.77 | 184000 | 2.5591 |
2.7619 | 0.81 | 192000 | 2.5597 |
2.7619 | 0.84 | 200000 | 2.5650 |
2.7678 | 0.88 | 208000 | 2.5728 |
2.7678 | 0.91 | 216000 | 2.5712 |
2.7735 | 0.94 | 224000 | 2.5729 |
2.7735 | 0.98 | 232000 | 2.5755 |
2.777 | 1.01 | 240000 | 2.5715 |
2.777 | 1.04 | 248000 | 2.5747 |
2.7692 | 1.08 | 256000 | 2.5782 |
2.7692 | 1.11 | 264000 | 2.5841 |
2.7826 | 1.15 | 272000 | 2.5731 |
2.7826 | 1.18 | 280000 | 2.5836 |
2.7845 | 1.21 | 288000 | 2.5841 |
2.7845 | 1.25 | 296000 | 2.5811 |
2.7909 | 1.28 | 304000 | 2.5928 |
2.7909 | 1.31 | 312000 | 2.5977 |
2.7993 | 1.35 | 320000 | 2.6025 |
2.7993 | 1.38 | 328000 | 2.6072 |
2.8107 | 1.41 | 336000 | 2.6110 |
2.8107 | 1.45 | 344000 | 2.6020 |
2.8102 | 1.48 | 352000 | 2.6065 |
2.8102 | 1.52 | 360000 | 2.6207 |
2.8247 | 1.55 | 368000 | 2.6192 |
2.8247 | 1.58 | 376000 | 2.6224 |
2.8271 | 1.62 | 384000 | 2.6205 |
2.8271 | 1.65 | 392000 | 2.6292 |
2.8415 | 1.68 | 400000 | 2.6348 |
2.8415 | 1.72 | 408000 | 2.6518 |
2.842 | 1.75 | 416000 | 2.6465 |
2.842 | 1.79 | 424000 | 2.6434 |
2.8431 | 1.82 | 432000 | 2.6414 |
2.8431 | 1.85 | 440000 | 2.6532 |
2.8599 | 1.89 | 448000 | 2.6645 |
2.8599 | 1.92 | 456000 | 2.6651 |
2.8567 | 1.95 | 464000 | 2.6694 |
2.8567 | 1.99 | 472000 | 2.6610 |
2.8682 | 2.02 | 480000 | 2.6877 |
2.8682 | 2.05 | 488000 | 2.6724 |
2.8693 | 2.09 | 496000 | 2.6839 |
2.8693 | 2.12 | 504000 | 2.6923 |
2.8881 | 2.16 | 512000 | 2.6964 |
2.8881 | 2.19 | 520000 | 2.6982 |
2.8874 | 2.22 | 528000 | 2.6961 |
2.8874 | 2.26 | 536000 | 2.6884 |
2.8899 | 2.29 | 544000 | 2.7055 |
2.8899 | 2.32 | 552000 | 2.6988 |
2.8966 | 2.36 | 560000 | 2.7103 |
2.8966 | 2.39 | 568000 | 2.7100 |
2.9 | 2.43 | 576000 | 2.7169 |
2.9 | 2.46 | 584000 | 2.7180 |
2.9237 | 2.49 | 592000 | 2.7270 |
2.9237 | 2.53 | 600000 | 2.7265 |
2.9236 | 2.56 | 608000 | 2.7323 |
2.9236 | 2.59 | 616000 | 2.7350 |
2.9276 | 2.63 | 624000 | 2.7333 |
2.9276 | 2.66 | 632000 | 2.7345 |
2.9252 | 2.69 | 640000 | 2.7497 |
2.9252 | 2.73 | 648000 | 2.7428 |
2.9364 | 2.76 | 656000 | 2.7392 |
2.9364 | 2.8 | 664000 | 2.7505 |
2.9366 | 2.83 | 672000 | 2.7393 |
2.9366 | 2.86 | 680000 | 2.7372 |
2.9437 | 2.9 | 688000 | 2.7451 |
2.9437 | 2.93 | 696000 | 2.7488 |
2.9483 | 2.96 | 704000 | 2.7586 |
2.9483 | 3.0 | 712000 | 2.7613 |
2.9588 | 3.03 | 720000 | 2.7619 |
2.9588 | 3.07 | 728000 | 2.7680 |
2.9422 | 3.1 | 736000 | 2.7546 |
2.9422 | 3.13 | 744000 | 2.7629 |
2.965 | 3.17 | 752000 | 2.7595 |
2.965 | 3.2 | 760000 | 2.7763 |
2.959 | 3.23 | 768000 | 2.7739 |
2.959 | 3.27 | 776000 | 2.7839 |
2.9604 | 3.3 | 784000 | 2.7681 |
2.9604 | 3.33 | 792000 | 2.7816 |
2.9638 | 3.37 | 800000 | 2.7812 |
2.9638 | 3.4 | 808000 | 2.7846 |
2.9704 | 3.44 | 816000 | 2.7766 |
2.9704 | 3.47 | 824000 | 2.7869 |
2.9684 | 3.5 | 832000 | 2.7741 |
2.9684 | 3.54 | 840000 | 2.7735 |
2.9723 | 3.57 | 848000 | 2.7701 |
2.9723 | 3.6 | 856000 | 2.7780 |
2.9734 | 3.64 | 864000 | 2.7833 |
2.9734 | 3.67 | 872000 | 2.7910 |
2.9806 | 3.71 | 880000 | 2.7941 |
2.9806 | 3.74 | 888000 | 2.7997 |
2.9808 | 3.77 | 896000 | 2.8027 |
2.9808 | 3.81 | 904000 | 2.7972 |
3.0008 | 3.84 | 912000 | 2.8026 |
3.0008 | 3.87 | 920000 | 2.7975 |
2.9934 | 3.91 | 928000 | 2.7971 |
2.9934 | 3.94 | 936000 | 2.8030 |
2.9927 | 3.97 | 944000 | 2.8082 |
2.9927 | 4.01 | 952000 | 2.8208 |
3.0013 | 4.04 | 960000 | 2.8129 |
3.0013 | 4.08 | 968000 | 2.8236 |
2.9996 | 4.11 | 976000 | 2.8226 |
2.9996 | 4.14 | 984000 | 2.8273 |
3.0125 | 4.18 | 992000 | 2.8161 |
3.0125 | 4.21 | 1000000 | 2.8249 |
3.0086 | 4.24 | 1008000 | 2.8320 |
3.0086 | 4.28 | 1016000 | 2.8313 |
3.0077 | 4.31 | 1024000 | 2.8321 |
3.0077 | 4.35 | 1032000 | 2.8332 |
3.0186 | 4.38 | 1040000 | 2.8288 |
3.0186 | 4.41 | 1048000 | 2.8392 |
3.0311 | 4.45 | 1056000 | 2.8243 |
3.0311 | 4.48 | 1064000 | 2.8524 |
3.0199 | 4.51 | 1072000 | 2.8347 |
3.0199 | 4.55 | 1080000 | 2.8438 |
3.0198 | 4.58 | 1088000 | 2.8415 |
3.0198 | 4.61 | 1096000 | 2.8460 |
3.0279 | 4.65 | 1104000 | 2.8551 |
3.0279 | 4.68 | 1112000 | 2.8528 |
3.0319 | 4.72 | 1120000 | 2.8601 |
3.0319 | 4.75 | 1128000 | 2.8544 |
3.0371 | 4.78 | 1136000 | 2.8553 |
3.0371 | 4.82 | 1144000 | 2.8597 |
3.038 | 4.85 | 1152000 | 2.8653 |
3.038 | 4.88 | 1160000 | 2.8560 |
3.0318 | 4.92 | 1168000 | 2.8602 |
3.0318 | 4.95 | 1176000 | 2.8484 |
3.0449 | 4.99 | 1184000 | 2.8612 |
3.0449 | 5.02 | 1192000 | 2.8598 |
3.0384 | 5.05 | 1200000 | 2.8581 |
3.0384 | 5.09 | 1208000 | 2.8481 |
3.0243 | 5.12 | 1216000 | 2.8458 |
3.0243 | 5.15 | 1224000 | 2.8494 |
3.0345 | 5.19 | 1232000 | 2.8544 |
3.0345 | 5.22 | 1240000 | 2.8488 |
3.0251 | 5.25 | 1248000 | 2.8453 |
3.0251 | 5.29 | 1256000 | 2.8464 |
3.0234 | 5.32 | 1264000 | 2.8486 |
3.0234 | 5.36 | 1272000 | 2.8436 |
3.0205 | 5.39 | 1280000 | 2.8476 |
3.0205 | 5.42 | 1288000 | 2.8327 |
3.0228 | 5.46 | 1296000 | 2.8452 |
3.0228 | 5.49 | 1304000 | 2.8372 |
3.0063 | 5.52 | 1312000 | 2.8306 |
3.0063 | 5.56 | 1320000 | 2.8411 |
3.0068 | 5.59 | 1328000 | 2.8273 |
3.0068 | 5.63 | 1336000 | 2.8343 |
3.0109 | 5.66 | 1344000 | 2.8328 |
3.0109 | 5.69 | 1352000 | 2.8431 |
3.0068 | 5.73 | 1360000 | 2.8332 |
3.0068 | 5.76 | 1368000 | 2.8275 |
3.002 | 5.79 | 1376000 | 2.8314 |
3.002 | 5.83 | 1384000 | 2.8324 |
3.0037 | 5.86 | 1392000 | 2.8394 |
3.0037 | 5.89 | 1400000 | 2.8338 |
3.0086 | 5.93 | 1408000 | 2.8448 |
3.0086 | 5.96 | 1416000 | 2.8326 |
2.9977 | 6.0 | 1424000 | 2.8311 |
2.9977 | 6.03 | 1432000 | 2.8410 |
2.9984 | 6.06 | 1440000 | 2.8359 |
2.9984 | 6.1 | 1448000 | 2.8393 |
3.0095 | 6.13 | 1456000 | 2.8388 |
3.0095 | 6.16 | 1464000 | 2.8448 |
3.0051 | 6.2 | 1472000 | 2.8472 |
3.0051 | 6.23 | 1480000 | 2.8421 |
3.0142 | 6.27 | 1488000 | 2.8424 |
3.0142 | 6.3 | 1496000 | 2.8477 |
3.0149 | 6.33 | 1504000 | 2.8428 |
3.0149 | 6.37 | 1512000 | 2.8529 |
3.0147 | 6.4 | 1520000 | 2.8541 |
3.0147 | 6.43 | 1528000 | 2.8519 |
3.0205 | 6.47 | 1536000 | 2.8527 |
3.0205 | 6.5 | 1544000 | 2.8471 |
3.029 | 6.53 | 1552000 | 2.8583 |
3.029 | 6.57 | 1560000 | 2.8497 |
3.024 | 6.6 | 1568000 | 2.8653 |
3.024 | 6.64 | 1576000 | 2.8553 |
3.0371 | 6.67 | 1584000 | 2.8653 |
3.0371 | 6.7 | 1592000 | 2.8604 |
3.0319 | 6.74 | 1600000 | 2.8624 |
3.0319 | 6.77 | 1608000 | 2.8657 |
3.0369 | 6.8 | 1616000 | 2.8616 |
3.0369 | 6.84 | 1624000 | 2.8667 |
3.0357 | 6.87 | 1632000 | 2.8660 |
3.0357 | 6.91 | 1640000 | 2.8682 |
3.0342 | 6.94 | 1648000 | 2.8676 |
3.0342 | 6.97 | 1656000 | 2.8815 |
3.0375 | 7.01 | 1664000 | 2.8667 |
3.0375 | 7.04 | 1672000 | 2.8735 |
3.0419 | 7.07 | 1680000 | 2.8788 |
3.0419 | 7.11 | 1688000 | 2.8767 |
3.0403 | 7.14 | 1696000 | 2.8812 |
3.0403 | 7.17 | 1704000 | 2.8795 |
3.0482 | 7.21 | 1712000 | 2.8805 |
3.0482 | 7.24 | 1720000 | 2.8794 |
3.0533 | 7.28 | 1728000 | 2.8788 |
3.0533 | 7.31 | 1736000 | 2.8844 |
3.0453 | 7.34 | 1744000 | 2.8709 |
3.0453 | 7.38 | 1752000 | 2.8835 |
3.0562 | 7.41 | 1760000 | 2.8891 |
3.0562 | 7.44 | 1768000 | 2.8903 |
3.0617 | 7.48 | 1776000 | 2.8849 |
3.0617 | 7.51 | 1784000 | 2.8766 |
3.0539 | 7.55 | 1792000 | 2.8872 |
3.0539 | 7.58 | 1800000 | 2.8981 |
3.0561 | 7.61 | 1808000 | 2.8862 |
3.0561 | 7.65 | 1816000 | 2.8940 |
3.0529 | 7.68 | 1824000 | 2.8874 |
3.0529 | 7.71 | 1832000 | 2.8839 |
3.0484 | 7.75 | 1840000 | 2.8838 |
3.0484 | 7.78 | 1848000 | 2.8856 |
3.0562 | 7.81 | 1856000 | 2.8984 |
3.0562 | 7.85 | 1864000 | 2.8844 |
3.0578 | 7.88 | 1872000 | 2.8874 |
3.0578 | 7.92 | 1880000 | 2.8887 |
3.0553 | 7.95 | 1888000 | 2.8798 |
3.0553 | 7.98 | 1896000 | 2.8789 |
3.0623 | 8.02 | 1904000 | 2.8968 |
3.0623 | 8.05 | 1912000 | 2.8834 |
3.0652 | 8.08 | 1920000 | 2.8902 |
3.0652 | 8.12 | 1928000 | 2.8822 |
3.0487 | 8.15 | 1936000 | 2.8844 |
3.0487 | 8.19 | 1944000 | 2.8909 |
3.0546 | 8.22 | 1952000 | 2.8915 |
3.0546 | 8.25 | 1960000 | 2.8870 |
3.0524 | 8.29 | 1968000 | 2.8828 |
3.0524 | 8.32 | 1976000 | 2.8781 |
3.0491 | 8.35 | 1984000 | 2.8948 |
3.0491 | 8.39 | 1992000 | 2.8904 |
3.0534 | 8.42 | 2000000 | 2.8839 |
3.0534 | 8.45 | 2008000 | 2.8918 |
3.0547 | 8.49 | 2016000 | 2.8739 |
3.0547 | 8.52 | 2024000 | 2.8684 |
3.0544 | 8.56 | 2032000 | 2.8740 |
3.0544 | 8.59 | 2040000 | 2.8784 |
3.0448 | 8.62 | 2048000 | 2.8758 |
3.0448 | 8.66 | 2056000 | 2.8801 |
3.0499 | 8.69 | 2064000 | 2.8793 |
3.0499 | 8.72 | 2072000 | 2.8707 |
3.0368 | 8.76 | 2080000 | 2.8722 |
3.0368 | 8.79 | 2088000 | 2.8752 |
3.0548 | 8.83 | 2096000 | 2.8880 |
3.0548 | 8.86 | 2104000 | 2.8781 |
3.0457 | 8.89 | 2112000 | 2.8825 |
3.0457 | 8.93 | 2120000 | 2.8827 |
3.0377 | 8.96 | 2128000 | 2.8810 |
3.0377 | 8.99 | 2136000 | 2.8727 |
3.0341 | 9.03 | 2144000 | 2.8750 |
3.0341 | 9.06 | 2152000 | 2.8638 |
3.0275 | 9.09 | 2160000 | 2.8690 |
3.0275 | 9.13 | 2168000 | 2.8660 |
3.0413 | 9.16 | 2176000 | 2.8578 |
3.0413 | 9.2 | 2184000 | 2.8692 |
3.0272 | 9.23 | 2192000 | 2.8702 |
3.0272 | 9.26 | 2200000 | 2.8707 |
3.034 | 9.3 | 2208000 | 2.8666 |
3.034 | 9.33 | 2216000 | 2.8734 |
3.0346 | 9.36 | 2224000 | 2.8685 |
3.0346 | 9.4 | 2232000 | 2.8675 |
3.0234 | 9.43 | 2240000 | 2.8662 |
3.0234 | 9.47 | 2248000 | 2.8670 |
3.0256 | 9.5 | 2256000 | 2.8764 |
3.0256 | 9.53 | 2264000 | 2.8664 |
3.0232 | 9.57 | 2272000 | 2.8625 |
3.0232 | 9.6 | 2280000 | 2.8647 |
3.0309 | 9.63 | 2288000 | 2.8561 |
3.0309 | 9.67 | 2296000 | 2.8657 |
3.0254 | 9.7 | 2304000 | 2.8667 |
3.0254 | 9.73 | 2312000 | 2.8618 |
3.0198 | 9.77 | 2320000 | 2.8650 |
3.0198 | 9.8 | 2328000 | 2.8630 |
3.0109 | 9.84 | 2336000 | 2.8533 |
3.0109 | 9.87 | 2344000 | 2.8656 |
3.0316 | 9.9 | 2352000 | 2.8607 |
3.0316 | 9.94 | 2360000 | 2.8572 |
3.0225 | 9.97 | 2368000 | 2.8617 |
3.0225 | 10.0 | 2376000 | 2.8604 |
3.0132 | 10.04 | 2384000 | 2.8577 |
3.0132 | 10.07 | 2392000 | 2.8535 |
3.0202 | 10.11 | 2400000 | 2.8566 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for DouglasPontes/2020-Q2-50p-filtered-random
Base model
cardiffnlp/twitter-roberta-base-2019-90m