|
--- |
|
license: gemma |
|
base_model: google/gemma-2-2b |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: collapse_gemma-2-2b_hs2_accumulate_iter20_sftsd0 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# collapse_gemma-2-2b_hs2_accumulate_iter20_sftsd0 |
|
|
|
This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1003 |
|
- Num Input Tokens Seen: 104630832 |
|
|
|
## 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: 8e-06 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 16 |
|
- seed: 0 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen | |
|
|:-------------:|:------:|:----:|:---------------:|:-----------------:| |
|
| No log | 0 | 0 | 1.3909 | 0 | |
|
| 1.716 | 0.0026 | 5 | 1.3911 | 274624 | |
|
| 1.6101 | 0.0052 | 10 | 1.3844 | 547320 | |
|
| 1.7213 | 0.0078 | 15 | 1.3668 | 817472 | |
|
| 1.6165 | 0.0104 | 20 | 1.3385 | 1085312 | |
|
| 1.6294 | 0.0130 | 25 | 1.3026 | 1356488 | |
|
| 1.4567 | 0.0156 | 30 | 1.2614 | 1625688 | |
|
| 1.4254 | 0.0182 | 35 | 1.2384 | 1894504 | |
|
| 1.2948 | 0.0208 | 40 | 1.2166 | 2171736 | |
|
| 1.1986 | 0.0233 | 45 | 1.2016 | 2443368 | |
|
| 1.0781 | 0.0259 | 50 | 1.2154 | 2710632 | |
|
| 0.9945 | 0.0285 | 55 | 1.2453 | 2979272 | |
|
| 0.8182 | 0.0311 | 60 | 1.2642 | 3249136 | |
|
| 0.7713 | 0.0337 | 65 | 1.3092 | 3520200 | |
|
| 0.5869 | 0.0363 | 70 | 1.3296 | 3792432 | |
|
| 0.3992 | 0.0389 | 75 | 1.4041 | 4067168 | |
|
| 0.4067 | 0.0415 | 80 | 1.3654 | 4329528 | |
|
| 0.3497 | 0.0441 | 85 | 1.3315 | 4600696 | |
|
| 0.3717 | 0.0467 | 90 | 1.3212 | 4874896 | |
|
| 0.3023 | 0.0493 | 95 | 1.2923 | 5147640 | |
|
| 0.2258 | 0.0519 | 100 | 1.2600 | 5413224 | |
|
| 0.2768 | 0.0545 | 105 | 1.2478 | 5685832 | |
|
| 0.2578 | 0.0571 | 110 | 1.2341 | 5957256 | |
|
| 0.2309 | 0.0597 | 115 | 1.2365 | 6225408 | |
|
| 0.2345 | 0.0623 | 120 | 1.2183 | 6499672 | |
|
| 0.1605 | 0.0649 | 125 | 1.2223 | 6769456 | |
|
| 0.1797 | 0.0674 | 130 | 1.2252 | 7038128 | |
|
| 0.2308 | 0.0700 | 135 | 1.2081 | 7309376 | |
|
| 0.1066 | 0.0726 | 140 | 1.2171 | 7579760 | |
|
| 0.148 | 0.0752 | 145 | 1.2080 | 7855136 | |
|
| 0.2081 | 0.0778 | 150 | 1.2019 | 8128928 | |
|
| 0.1838 | 0.0804 | 155 | 1.1987 | 8400680 | |
|
| 0.1415 | 0.0830 | 160 | 1.1975 | 8675064 | |
|
| 0.1379 | 0.0856 | 165 | 1.1964 | 8950944 | |
|
| 0.2083 | 0.0882 | 170 | 1.1948 | 9223752 | |
|
| 0.2306 | 0.0908 | 175 | 1.1878 | 9494608 | |
|
| 0.1422 | 0.0934 | 180 | 1.1856 | 9764504 | |
|
| 0.249 | 0.0960 | 185 | 1.2066 | 10039928 | |
|
| 0.1691 | 0.0986 | 190 | 1.1943 | 10308352 | |
|
| 0.1571 | 0.1012 | 195 | 1.1828 | 10581752 | |
|
| 0.1375 | 0.1038 | 200 | 1.1918 | 10858712 | |
|
| 0.2177 | 0.1064 | 205 | 1.1849 | 11115328 | |
|
| 0.1689 | 0.1090 | 210 | 1.1810 | 11382664 | |
|
| 0.1722 | 0.1116 | 215 | 1.1812 | 11651744 | |
|
| 0.1735 | 0.1141 | 220 | 1.1746 | 11918512 | |
|
| 0.1676 | 0.1167 | 225 | 1.1743 | 12188408 | |
|
| 0.1613 | 0.1193 | 230 | 1.1839 | 12454216 | |
|
| 0.1049 | 0.1219 | 235 | 1.1764 | 12726848 | |
|
| 0.1178 | 0.1245 | 240 | 1.1777 | 12997584 | |
|
| 0.1308 | 0.1271 | 245 | 1.1817 | 13270656 | |
|
| 0.1152 | 0.1297 | 250 | 1.1700 | 13537704 | |
|
| 0.0899 | 0.1323 | 255 | 1.1725 | 13817400 | |
|
| 0.1247 | 0.1349 | 260 | 1.1739 | 14092904 | |
|
| 0.1018 | 0.1375 | 265 | 1.1681 | 14369256 | |
|
| 0.0765 | 0.1401 | 270 | 1.1706 | 14638784 | |
|
| 0.0989 | 0.1427 | 275 | 1.1768 | 14907256 | |
|
| 0.1702 | 0.1453 | 280 | 1.1690 | 15179376 | |
|
| 0.1135 | 0.1479 | 285 | 1.1630 | 15448752 | |
|
| 0.1303 | 0.1505 | 290 | 1.1673 | 15719304 | |
|
| 0.0822 | 0.1531 | 295 | 1.1640 | 15996104 | |
|
| 0.1483 | 0.1557 | 300 | 1.1649 | 16264816 | |
|
| 0.0884 | 0.1582 | 305 | 1.1655 | 16534424 | |
|
| 0.1559 | 0.1608 | 310 | 1.1637 | 16802488 | |
|
| 0.1557 | 0.1634 | 315 | 1.1603 | 17072088 | |
|
| 0.1241 | 0.1660 | 320 | 1.1640 | 17345400 | |
|
| 0.1277 | 0.1686 | 325 | 1.1573 | 17611776 | |
|
| 0.1005 | 0.1712 | 330 | 1.1590 | 17876584 | |
|
| 0.1254 | 0.1738 | 335 | 1.1616 | 18149144 | |
|
| 0.13 | 0.1764 | 340 | 1.1623 | 18424184 | |
|
| 0.1183 | 0.1790 | 345 | 1.1599 | 18696760 | |
|
| 0.1063 | 0.1816 | 350 | 1.1551 | 18969232 | |
|
| 0.2259 | 0.1842 | 355 | 1.1604 | 19230096 | |
|
| 0.1062 | 0.1868 | 360 | 1.1589 | 19502800 | |
|
| 0.1318 | 0.1894 | 365 | 1.1550 | 19778792 | |
|
| 0.1188 | 0.1920 | 370 | 1.1571 | 20059488 | |
|
| 0.1708 | 0.1946 | 375 | 1.1542 | 20329088 | |
|
| 0.1379 | 0.1972 | 380 | 1.1570 | 20598304 | |
|
| 0.1412 | 0.1998 | 385 | 1.1558 | 20874240 | |
|
| 0.1036 | 0.2023 | 390 | 1.1531 | 21144064 | |
|
| 0.1187 | 0.2049 | 395 | 1.1528 | 21415968 | |
|
| 0.1144 | 0.2075 | 400 | 1.1544 | 21686632 | |
|
| 0.139 | 0.2101 | 405 | 1.1560 | 21958456 | |
|
| 0.1653 | 0.2127 | 410 | 1.1543 | 22231472 | |
|
| 0.0924 | 0.2153 | 415 | 1.1554 | 22507752 | |
|
| 0.181 | 0.2179 | 420 | 1.1506 | 22770488 | |
|
| 0.1406 | 0.2205 | 425 | 1.1502 | 23043440 | |
|
| 0.1473 | 0.2231 | 430 | 1.1517 | 23317896 | |
|
| 0.1212 | 0.2257 | 435 | 1.1502 | 23591584 | |
|
| 0.1757 | 0.2283 | 440 | 1.1481 | 23863856 | |
|
| 0.1407 | 0.2309 | 445 | 1.1475 | 24133728 | |
|
| 0.1317 | 0.2335 | 450 | 1.1517 | 24400592 | |
|
| 0.1333 | 0.2361 | 455 | 1.1526 | 24676344 | |
|
| 0.1395 | 0.2387 | 460 | 1.1502 | 24940432 | |
|
| 0.1002 | 0.2413 | 465 | 1.1486 | 25210704 | |
|
| 0.1905 | 0.2439 | 470 | 1.1481 | 25487704 | |
|
| 0.1182 | 0.2464 | 475 | 1.1450 | 25763560 | |
|
| 0.136 | 0.2490 | 480 | 1.1453 | 26040216 | |
|
| 0.1636 | 0.2516 | 485 | 1.1461 | 26318032 | |
|
| 0.1372 | 0.2542 | 490 | 1.1444 | 26577160 | |
|
| 0.0943 | 0.2568 | 495 | 1.1422 | 26842672 | |
|
| 0.1635 | 0.2594 | 500 | 1.1444 | 27117024 | |
|
| 0.1525 | 0.2620 | 505 | 1.1427 | 27389600 | |
|
| 0.0912 | 0.2646 | 510 | 1.1422 | 27659760 | |
|
| 0.1092 | 0.2672 | 515 | 1.1417 | 27936376 | |
|
| 0.1229 | 0.2698 | 520 | 1.1425 | 28206544 | |
|
| 0.1342 | 0.2724 | 525 | 1.1465 | 28480784 | |
|
| 0.1564 | 0.2750 | 530 | 1.1446 | 28754720 | |
|
| 0.1526 | 0.2776 | 535 | 1.1403 | 29027288 | |
|
| 0.1248 | 0.2802 | 540 | 1.1412 | 29299416 | |
|
| 0.1321 | 0.2828 | 545 | 1.1432 | 29570464 | |
|
| 0.0992 | 0.2854 | 550 | 1.1418 | 29847200 | |
|
| 0.1759 | 0.2880 | 555 | 1.1376 | 30118616 | |
|
| 0.1364 | 0.2906 | 560 | 1.1368 | 30384424 | |
|
| 0.1066 | 0.2931 | 565 | 1.1412 | 30658728 | |
|
| 0.1283 | 0.2957 | 570 | 1.1395 | 30930936 | |
|
| 0.1477 | 0.2983 | 575 | 1.1354 | 31195504 | |
|
| 0.0926 | 0.3009 | 580 | 1.1404 | 31471360 | |
|
| 0.1215 | 0.3035 | 585 | 1.1416 | 31747584 | |
|
| 0.1759 | 0.3061 | 590 | 1.1383 | 32018632 | |
|
| 0.1114 | 0.3087 | 595 | 1.1375 | 32294872 | |
|
| 0.1902 | 0.3113 | 600 | 1.1384 | 32573936 | |
|
| 0.1495 | 0.3139 | 605 | 1.1367 | 32848552 | |
|
| 0.1661 | 0.3165 | 610 | 1.1359 | 33114904 | |
|
| 0.1025 | 0.3191 | 615 | 1.1360 | 33387616 | |
|
| 0.1273 | 0.3217 | 620 | 1.1363 | 33653504 | |
|
| 0.1328 | 0.3243 | 625 | 1.1354 | 33927704 | |
|
| 0.1382 | 0.3269 | 630 | 1.1344 | 34197568 | |
|
| 0.093 | 0.3295 | 635 | 1.1354 | 34468608 | |
|
| 0.0825 | 0.3321 | 640 | 1.1369 | 34739504 | |
|
| 0.0689 | 0.3347 | 645 | 1.1333 | 35009640 | |
|
| 0.1842 | 0.3372 | 650 | 1.1321 | 35278544 | |
|
| 0.1477 | 0.3398 | 655 | 1.1341 | 35546784 | |
|
| 0.1309 | 0.3424 | 660 | 1.1318 | 35815424 | |
|
| 0.0731 | 0.3450 | 665 | 1.1316 | 36081936 | |
|
| 0.1444 | 0.3476 | 670 | 1.1337 | 36349872 | |
|
| 0.1908 | 0.3502 | 675 | 1.1332 | 36625504 | |
|
| 0.1288 | 0.3528 | 680 | 1.1303 | 36903568 | |
|
| 0.1455 | 0.3554 | 685 | 1.1310 | 37168376 | |
|
| 0.1587 | 0.3580 | 690 | 1.1295 | 37438008 | |
|
| 0.1426 | 0.3606 | 695 | 1.1287 | 37706592 | |
|
| 0.1113 | 0.3632 | 700 | 1.1295 | 37971760 | |
|
| 0.0741 | 0.3658 | 705 | 1.1265 | 38240384 | |
|
| 0.0992 | 0.3684 | 710 | 1.1284 | 38511088 | |
|
| 0.1048 | 0.3710 | 715 | 1.1305 | 38779784 | |
|
| 0.147 | 0.3736 | 720 | 1.1280 | 39050104 | |
|
| 0.0875 | 0.3762 | 725 | 1.1268 | 39327024 | |
|
| 0.1869 | 0.3788 | 730 | 1.1316 | 39601640 | |
|
| 0.1136 | 0.3813 | 735 | 1.1307 | 39875080 | |
|
| 0.1675 | 0.3839 | 740 | 1.1290 | 40153784 | |
|
| 0.1276 | 0.3865 | 745 | 1.1274 | 40422520 | |
|
| 0.121 | 0.3891 | 750 | 1.1244 | 40698128 | |
|
| 0.0962 | 0.3917 | 755 | 1.1249 | 40972008 | |
|
| 0.0805 | 0.3943 | 760 | 1.1260 | 41242168 | |
|
| 0.1301 | 0.3969 | 765 | 1.1276 | 41515064 | |
|
| 0.0664 | 0.3995 | 770 | 1.1263 | 41786720 | |
|
| 0.1147 | 0.4021 | 775 | 1.1274 | 42057440 | |
|
| 0.1098 | 0.4047 | 780 | 1.1290 | 42327624 | |
|
| 0.1501 | 0.4073 | 785 | 1.1269 | 42606024 | |
|
| 0.1321 | 0.4099 | 790 | 1.1259 | 42883472 | |
|
| 0.1765 | 0.4125 | 795 | 1.1252 | 43149744 | |
|
| 0.1008 | 0.4151 | 800 | 1.1237 | 43429112 | |
|
| 0.0973 | 0.4177 | 805 | 1.1240 | 43706696 | |
|
| 0.092 | 0.4203 | 810 | 1.1269 | 43982888 | |
|
| 0.106 | 0.4229 | 815 | 1.1265 | 44251248 | |
|
| 0.1341 | 0.4254 | 820 | 1.1249 | 44518760 | |
|
| 0.1963 | 0.4280 | 825 | 1.1235 | 44788128 | |
|
| 0.0904 | 0.4306 | 830 | 1.1242 | 45057480 | |
|
| 0.1111 | 0.4332 | 835 | 1.1256 | 45332024 | |
|
| 0.1538 | 0.4358 | 840 | 1.1240 | 45607080 | |
|
| 0.132 | 0.4384 | 845 | 1.1231 | 45870912 | |
|
| 0.0939 | 0.4410 | 850 | 1.1241 | 46144224 | |
|
| 0.0757 | 0.4436 | 855 | 1.1260 | 46414416 | |
|
| 0.0849 | 0.4462 | 860 | 1.1256 | 46682112 | |
|
| 0.0825 | 0.4488 | 865 | 1.1244 | 46954088 | |
|
| 0.1124 | 0.4514 | 870 | 1.1244 | 47229128 | |
|
| 0.1349 | 0.4540 | 875 | 1.1224 | 47504032 | |
|
| 0.0906 | 0.4566 | 880 | 1.1218 | 47776744 | |
|
| 0.061 | 0.4592 | 885 | 1.1251 | 48041880 | |
|
| 0.1252 | 0.4618 | 890 | 1.1276 | 48314824 | |
|
| 0.0934 | 0.4644 | 895 | 1.1230 | 48588792 | |
|
| 0.101 | 0.4670 | 900 | 1.1194 | 48861976 | |
|
| 0.1211 | 0.4696 | 905 | 1.1208 | 49141304 | |
|
| 0.1301 | 0.4721 | 910 | 1.1215 | 49414184 | |
|
| 0.0991 | 0.4747 | 915 | 1.1192 | 49686016 | |
|
| 0.1117 | 0.4773 | 920 | 1.1203 | 49958448 | |
|
| 0.1183 | 0.4799 | 925 | 1.1219 | 50231936 | |
|
| 0.1051 | 0.4825 | 930 | 1.1232 | 50500288 | |
|
| 0.1583 | 0.4851 | 935 | 1.1237 | 50773264 | |
|
| 0.0738 | 0.4877 | 940 | 1.1208 | 51043168 | |
|
| 0.1193 | 0.4903 | 945 | 1.1206 | 51316464 | |
|
| 0.0698 | 0.4929 | 950 | 1.1215 | 51589032 | |
|
| 0.1228 | 0.4955 | 955 | 1.1208 | 51855792 | |
|
| 0.1515 | 0.4981 | 960 | 1.1196 | 52127784 | |
|
| 0.1304 | 0.5007 | 965 | 1.1198 | 52405864 | |
|
| 0.0628 | 0.5033 | 970 | 1.1223 | 52670424 | |
|
| 0.1231 | 0.5059 | 975 | 1.1235 | 52941040 | |
|
| 0.0829 | 0.5085 | 980 | 1.1205 | 53215216 | |
|
| 0.0972 | 0.5111 | 985 | 1.1188 | 53488912 | |
|
| 0.113 | 0.5137 | 990 | 1.1219 | 53765608 | |
|
| 0.1117 | 0.5162 | 995 | 1.1227 | 54031712 | |
|
| 0.1229 | 0.5188 | 1000 | 1.1198 | 54305320 | |
|
| 0.1169 | 0.5214 | 1005 | 1.1204 | 54578760 | |
|
| 0.0884 | 0.5240 | 1010 | 1.1223 | 54850136 | |
|
| 0.1089 | 0.5266 | 1015 | 1.1228 | 55117064 | |
|
| 0.1343 | 0.5292 | 1020 | 1.1176 | 55391736 | |
|
| 0.1224 | 0.5318 | 1025 | 1.1176 | 55657720 | |
|
| 0.0934 | 0.5344 | 1030 | 1.1206 | 55931936 | |
|
| 0.1104 | 0.5370 | 1035 | 1.1188 | 56212208 | |
|
| 0.1026 | 0.5396 | 1040 | 1.1167 | 56478800 | |
|
| 0.133 | 0.5422 | 1045 | 1.1202 | 56742088 | |
|
| 0.1646 | 0.5448 | 1050 | 1.1208 | 57013056 | |
|
| 0.1028 | 0.5474 | 1055 | 1.1182 | 57278840 | |
|
| 0.1191 | 0.5500 | 1060 | 1.1166 | 57546456 | |
|
| 0.1047 | 0.5526 | 1065 | 1.1163 | 57815472 | |
|
| 0.1002 | 0.5552 | 1070 | 1.1166 | 58088736 | |
|
| 0.1291 | 0.5578 | 1075 | 1.1149 | 58361360 | |
|
| 0.0825 | 0.5603 | 1080 | 1.1149 | 58637656 | |
|
| 0.1685 | 0.5629 | 1085 | 1.1157 | 58912096 | |
|
| 0.0975 | 0.5655 | 1090 | 1.1147 | 59187552 | |
|
| 0.1306 | 0.5681 | 1095 | 1.1154 | 59458184 | |
|
| 0.131 | 0.5707 | 1100 | 1.1170 | 59725096 | |
|
| 0.1421 | 0.5733 | 1105 | 1.1159 | 59991136 | |
|
| 0.0415 | 0.5759 | 1110 | 1.1164 | 60258976 | |
|
| 0.1087 | 0.5785 | 1115 | 1.1162 | 60535608 | |
|
| 0.0675 | 0.5811 | 1120 | 1.1163 | 60811120 | |
|
| 0.153 | 0.5837 | 1125 | 1.1161 | 61076968 | |
|
| 0.0661 | 0.5863 | 1130 | 1.1148 | 61345256 | |
|
| 0.1609 | 0.5889 | 1135 | 1.1157 | 61612816 | |
|
| 0.1478 | 0.5915 | 1140 | 1.1156 | 61881160 | |
|
| 0.1493 | 0.5941 | 1145 | 1.1147 | 62155744 | |
|
| 0.213 | 0.5967 | 1150 | 1.1132 | 62424568 | |
|
| 0.1001 | 0.5993 | 1155 | 1.1119 | 62696568 | |
|
| 0.1504 | 0.6019 | 1160 | 1.1129 | 62966448 | |
|
| 0.1081 | 0.6044 | 1165 | 1.1142 | 63241864 | |
|
| 0.1363 | 0.6070 | 1170 | 1.1165 | 63511496 | |
|
| 0.1489 | 0.6096 | 1175 | 1.1165 | 63780824 | |
|
| 0.1227 | 0.6122 | 1180 | 1.1138 | 64048520 | |
|
| 0.0623 | 0.6148 | 1185 | 1.1138 | 64319720 | |
|
| 0.1511 | 0.6174 | 1190 | 1.1137 | 64598184 | |
|
| 0.0856 | 0.6200 | 1195 | 1.1138 | 64874736 | |
|
| 0.1107 | 0.6226 | 1200 | 1.1140 | 65153352 | |
|
| 0.1279 | 0.6252 | 1205 | 1.1125 | 65417824 | |
|
| 0.1414 | 0.6278 | 1210 | 1.1117 | 65685816 | |
|
| 0.1748 | 0.6304 | 1215 | 1.1116 | 65963712 | |
|
| 0.0846 | 0.6330 | 1220 | 1.1142 | 66237640 | |
|
| 0.1313 | 0.6356 | 1225 | 1.1129 | 66508248 | |
|
| 0.1576 | 0.6382 | 1230 | 1.1114 | 66772208 | |
|
| 0.0878 | 0.6408 | 1235 | 1.1118 | 67047128 | |
|
| 0.0523 | 0.6434 | 1240 | 1.1114 | 67319360 | |
|
| 0.1038 | 0.6460 | 1245 | 1.1115 | 67598528 | |
|
| 0.1218 | 0.6486 | 1250 | 1.1112 | 67880128 | |
|
| 0.0988 | 0.6511 | 1255 | 1.1120 | 68144176 | |
|
| 0.1595 | 0.6537 | 1260 | 1.1118 | 68414248 | |
|
| 0.1114 | 0.6563 | 1265 | 1.1094 | 68683672 | |
|
| 0.088 | 0.6589 | 1270 | 1.1105 | 68949456 | |
|
| 0.1422 | 0.6615 | 1275 | 1.1095 | 69222944 | |
|
| 0.1483 | 0.6641 | 1280 | 1.1088 | 69495776 | |
|
| 0.0872 | 0.6667 | 1285 | 1.1075 | 69765256 | |
|
| 0.1242 | 0.6693 | 1290 | 1.1073 | 70030464 | |
|
| 0.09 | 0.6719 | 1295 | 1.1101 | 70306592 | |
|
| 0.092 | 0.6745 | 1300 | 1.1128 | 70585120 | |
|
| 0.0747 | 0.6771 | 1305 | 1.1109 | 70858144 | |
|
| 0.1358 | 0.6797 | 1310 | 1.1091 | 71132752 | |
|
| 0.0551 | 0.6823 | 1315 | 1.1081 | 71401184 | |
|
| 0.1157 | 0.6849 | 1320 | 1.1118 | 71674272 | |
|
| 0.1057 | 0.6875 | 1325 | 1.1113 | 71945264 | |
|
| 0.1077 | 0.6901 | 1330 | 1.1075 | 72213728 | |
|
| 0.1014 | 0.6927 | 1335 | 1.1076 | 72489288 | |
|
| 0.1332 | 0.6952 | 1340 | 1.1110 | 72761704 | |
|
| 0.0568 | 0.6978 | 1345 | 1.1108 | 73032896 | |
|
| 0.0769 | 0.7004 | 1350 | 1.1090 | 73306464 | |
|
| 0.1208 | 0.7030 | 1355 | 1.1094 | 73574192 | |
|
| 0.1284 | 0.7056 | 1360 | 1.1101 | 73847024 | |
|
| 0.1122 | 0.7082 | 1365 | 1.1091 | 74118120 | |
|
| 0.1399 | 0.7108 | 1370 | 1.1087 | 74386544 | |
|
| 0.1238 | 0.7134 | 1375 | 1.1076 | 74656936 | |
|
| 0.0894 | 0.7160 | 1380 | 1.1077 | 74929048 | |
|
| 0.101 | 0.7186 | 1385 | 1.1093 | 75202000 | |
|
| 0.119 | 0.7212 | 1390 | 1.1095 | 75478328 | |
|
| 0.1609 | 0.7238 | 1395 | 1.1096 | 75741360 | |
|
| 0.121 | 0.7264 | 1400 | 1.1087 | 76017240 | |
|
| 0.0817 | 0.7290 | 1405 | 1.1075 | 76287216 | |
|
| 0.1366 | 0.7316 | 1410 | 1.1085 | 76563168 | |
|
| 0.0853 | 0.7342 | 1415 | 1.1079 | 76835392 | |
|
| 0.1003 | 0.7368 | 1420 | 1.1082 | 77100568 | |
|
| 0.0783 | 0.7393 | 1425 | 1.1079 | 77370592 | |
|
| 0.1313 | 0.7419 | 1430 | 1.1087 | 77641784 | |
|
| 0.0961 | 0.7445 | 1435 | 1.1089 | 77912760 | |
|
| 0.1182 | 0.7471 | 1440 | 1.1097 | 78186248 | |
|
| 0.1139 | 0.7497 | 1445 | 1.1087 | 78456720 | |
|
| 0.1163 | 0.7523 | 1450 | 1.1079 | 78728848 | |
|
| 0.1504 | 0.7549 | 1455 | 1.1090 | 78993960 | |
|
| 0.1127 | 0.7575 | 1460 | 1.1088 | 79262720 | |
|
| 0.084 | 0.7601 | 1465 | 1.1069 | 79536160 | |
|
| 0.1591 | 0.7627 | 1470 | 1.1062 | 79805664 | |
|
| 0.1148 | 0.7653 | 1475 | 1.1062 | 80076272 | |
|
| 0.1601 | 0.7679 | 1480 | 1.1081 | 80345880 | |
|
| 0.1103 | 0.7705 | 1485 | 1.1109 | 80623320 | |
|
| 0.095 | 0.7731 | 1490 | 1.1092 | 80896600 | |
|
| 0.0765 | 0.7757 | 1495 | 1.1066 | 81167936 | |
|
| 0.1369 | 0.7783 | 1500 | 1.1053 | 81436328 | |
|
| 0.098 | 0.7809 | 1505 | 1.1058 | 81715176 | |
|
| 0.1389 | 0.7834 | 1510 | 1.1061 | 81989600 | |
|
| 0.0708 | 0.7860 | 1515 | 1.1040 | 82260328 | |
|
| 0.1061 | 0.7886 | 1520 | 1.1054 | 82533968 | |
|
| 0.1184 | 0.7912 | 1525 | 1.1059 | 82811712 | |
|
| 0.1093 | 0.7938 | 1530 | 1.1054 | 83078272 | |
|
| 0.1408 | 0.7964 | 1535 | 1.1050 | 83352592 | |
|
| 0.1094 | 0.7990 | 1540 | 1.1051 | 83628256 | |
|
| 0.0787 | 0.8016 | 1545 | 1.1054 | 83896128 | |
|
| 0.0894 | 0.8042 | 1550 | 1.1057 | 84170368 | |
|
| 0.1838 | 0.8068 | 1555 | 1.1056 | 84443680 | |
|
| 0.0922 | 0.8094 | 1560 | 1.1053 | 84720936 | |
|
| 0.0878 | 0.8120 | 1565 | 1.1056 | 84991280 | |
|
| 0.119 | 0.8146 | 1570 | 1.1070 | 85266376 | |
|
| 0.134 | 0.8172 | 1575 | 1.1064 | 85527880 | |
|
| 0.083 | 0.8198 | 1580 | 1.1035 | 85803392 | |
|
| 0.086 | 0.8224 | 1585 | 1.1036 | 86069952 | |
|
| 0.1289 | 0.8250 | 1590 | 1.1042 | 86341424 | |
|
| 0.0694 | 0.8276 | 1595 | 1.1046 | 86608888 | |
|
| 0.0916 | 0.8301 | 1600 | 1.1045 | 86880656 | |
|
| 0.1325 | 0.8327 | 1605 | 1.1052 | 87150656 | |
|
| 0.1159 | 0.8353 | 1610 | 1.1048 | 87421992 | |
|
| 0.1611 | 0.8379 | 1615 | 1.1026 | 87689936 | |
|
| 0.0616 | 0.8405 | 1620 | 1.1017 | 87962640 | |
|
| 0.086 | 0.8431 | 1625 | 1.1024 | 88233064 | |
|
| 0.1509 | 0.8457 | 1630 | 1.1031 | 88504904 | |
|
| 0.0949 | 0.8483 | 1635 | 1.1042 | 88778224 | |
|
| 0.141 | 0.8509 | 1640 | 1.1054 | 89049064 | |
|
| 0.1221 | 0.8535 | 1645 | 1.1047 | 89322512 | |
|
| 0.1069 | 0.8561 | 1650 | 1.1037 | 89589672 | |
|
| 0.0911 | 0.8587 | 1655 | 1.1043 | 89865152 | |
|
| 0.1367 | 0.8613 | 1660 | 1.1040 | 90143112 | |
|
| 0.152 | 0.8639 | 1665 | 1.1041 | 90417376 | |
|
| 0.1041 | 0.8665 | 1670 | 1.1042 | 90690424 | |
|
| 0.1947 | 0.8691 | 1675 | 1.1046 | 90966792 | |
|
| 0.1343 | 0.8717 | 1680 | 1.1063 | 91235752 | |
|
| 0.1491 | 0.8742 | 1685 | 1.1057 | 91508464 | |
|
| 0.0623 | 0.8768 | 1690 | 1.1030 | 91783680 | |
|
| 0.1136 | 0.8794 | 1695 | 1.1033 | 92052728 | |
|
| 0.1123 | 0.8820 | 1700 | 1.1058 | 92324952 | |
|
| 0.0936 | 0.8846 | 1705 | 1.1057 | 92598744 | |
|
| 0.1418 | 0.8872 | 1710 | 1.1031 | 92873568 | |
|
| 0.1034 | 0.8898 | 1715 | 1.1024 | 93151312 | |
|
| 0.0717 | 0.8924 | 1720 | 1.1016 | 93419920 | |
|
| 0.1187 | 0.8950 | 1725 | 1.1014 | 93686864 | |
|
| 0.1236 | 0.8976 | 1730 | 1.1034 | 93964560 | |
|
| 0.1112 | 0.9002 | 1735 | 1.1048 | 94237456 | |
|
| 0.1082 | 0.9028 | 1740 | 1.1043 | 94508280 | |
|
| 0.1275 | 0.9054 | 1745 | 1.1041 | 94779928 | |
|
| 0.1312 | 0.9080 | 1750 | 1.1028 | 95060512 | |
|
| 0.1151 | 0.9106 | 1755 | 1.1024 | 95331504 | |
|
| 0.0875 | 0.9132 | 1760 | 1.1043 | 95597992 | |
|
| 0.0897 | 0.9158 | 1765 | 1.1056 | 95871088 | |
|
| 0.0904 | 0.9183 | 1770 | 1.1024 | 96143112 | |
|
| 0.0981 | 0.9209 | 1775 | 1.1011 | 96411696 | |
|
| 0.1145 | 0.9235 | 1780 | 1.1032 | 96689832 | |
|
| 0.0778 | 0.9261 | 1785 | 1.1030 | 96954648 | |
|
| 0.1091 | 0.9287 | 1790 | 1.1025 | 97224512 | |
|
| 0.1311 | 0.9313 | 1795 | 1.1020 | 97490656 | |
|
| 0.0952 | 0.9339 | 1800 | 1.1014 | 97756472 | |
|
| 0.0709 | 0.9365 | 1805 | 1.1002 | 98020344 | |
|
| 0.0606 | 0.9391 | 1810 | 1.1015 | 98292480 | |
|
| 0.1449 | 0.9417 | 1815 | 1.1036 | 98563688 | |
|
| 0.1069 | 0.9443 | 1820 | 1.1021 | 98828624 | |
|
| 0.1182 | 0.9469 | 1825 | 1.1006 | 99098296 | |
|
| 0.1127 | 0.9495 | 1830 | 1.1005 | 99361784 | |
|
| 0.126 | 0.9521 | 1835 | 1.1004 | 99626592 | |
|
| 0.1273 | 0.9547 | 1840 | 1.0996 | 99894880 | |
|
| 0.094 | 0.9573 | 1845 | 1.1004 | 100166920 | |
|
| 0.1138 | 0.9599 | 1850 | 1.1008 | 100441200 | |
|
| 0.1154 | 0.9624 | 1855 | 1.1008 | 100720616 | |
|
| 0.0715 | 0.9650 | 1860 | 1.1007 | 100993872 | |
|
| 0.1398 | 0.9676 | 1865 | 1.0997 | 101260832 | |
|
| 0.1156 | 0.9702 | 1870 | 1.0983 | 101535904 | |
|
| 0.055 | 0.9728 | 1875 | 1.0994 | 101804960 | |
|
| 0.0664 | 0.9754 | 1880 | 1.0994 | 102071392 | |
|
| 0.104 | 0.9780 | 1885 | 1.1002 | 102346880 | |
|
| 0.1057 | 0.9806 | 1890 | 1.0986 | 102608816 | |
|
| 0.109 | 0.9832 | 1895 | 1.0978 | 102880240 | |
|
| 0.1497 | 0.9858 | 1900 | 1.0982 | 103155816 | |
|
| 0.0843 | 0.9884 | 1905 | 1.0983 | 103423176 | |
|
| 0.1182 | 0.9910 | 1910 | 1.0992 | 103698136 | |
|
| 0.1218 | 0.9936 | 1915 | 1.0990 | 103974240 | |
|
| 0.0774 | 0.9962 | 1920 | 1.0986 | 104245048 | |
|
| 0.0987 | 0.9988 | 1925 | 1.0997 | 104522816 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
