mlplayer-top5 / train.log
davidquarel's picture
Upload folder using huggingface_hub
be4085b verified
type train | step 10 | loss 79.4517 136.0367 286.7418 387.6865 | lr 1.3e-05 | norm 152.7835 | dt 0.025
type train | step 20 | loss 79.1497 135.3098 281.3571 382.6047 | lr 2.7e-05 | norm 151.8013 | dt 0.024
type train | step 30 | loss 77.4791 133.4711 279.5826 379.5257 | lr 4.0e-05 | norm 152.1443 | dt 0.024
type train | step 40 | loss 76.4947 132.3980 273.0417 372.5096 | lr 5.3e-05 | norm 143.3912 | dt 0.024
type train | step 50 | loss 74.2192 129.2680 271.9122 368.1317 | lr 6.7e-05 | norm 146.3264 | dt 0.024
type train | step 60 | loss 73.0394 126.0161 267.1283 361.3440 | lr 8.0e-05 | norm 144.2204 | dt 0.024
type train | step 70 | loss 70.5887 122.4443 258.7792 353.8127 | lr 9.3e-05 | norm 139.9278 | dt 0.024
type train | step 80 | loss 68.6779 119.8116 249.9142 342.3100 | lr 1.1e-04 | norm 130.6477 | dt 0.024
type train | step 90 | loss 65.6993 114.9073 243.9401 331.8090 | lr 1.2e-04 | norm 130.2916 | dt 0.024
type train | step 100 | loss 62.9905 109.7489 234.7911 321.5562 | lr 1.3e-04 | norm 127.4656 | dt 0.024
type train | step 110 | loss 59.2526 104.8775 225.7866 306.6556 | lr 1.5e-04 | norm 119.2637 | dt 0.024
type train | step 120 | loss 56.3041 100.7336 213.9078 294.9911 | lr 1.6e-04 | norm 110.6407 | dt 0.024
type train | step 130 | loss 52.9905 94.7257 206.3387 284.3115 | lr 1.7e-04 | norm 107.2698 | dt 0.024
type train | step 140 | loss 50.6309 90.5040 195.4298 269.3315 | lr 1.9e-04 | norm 98.3439 | dt 0.024
type train | step 150 | loss 46.9019 85.1798 186.1556 256.1884 | lr 2.0e-04 | norm 95.1244 | dt 0.024
type train | step 160 | loss 44.1146 79.5231 174.4114 240.7520 | lr 2.1e-04 | norm 89.2351 | dt 0.024
type train | step 170 | loss 40.5852 74.5412 164.3555 227.0880 | lr 2.3e-04 | norm 83.6467 | dt 0.024
type train | step 180 | loss 38.0229 70.0960 154.3314 215.2932 | lr 2.4e-04 | norm 74.3083 | dt 0.024
type train | step 190 | loss 34.5324 64.7609 144.9963 203.5314 | lr 2.5e-04 | norm 68.9837 | dt 0.024
type train | step 200 | loss 32.3126 60.8775 136.8374 191.9165 | lr 2.7e-04 | norm 61.7718 | dt 0.024
type train | step 210 | loss 29.7620 56.3866 128.0650 180.0396 | lr 2.8e-04 | norm 56.7384 | dt 0.024
type train | step 220 | loss 27.2159 52.2948 120.1332 169.2647 | lr 2.9e-04 | norm 51.5705 | dt 0.025
type train | step 230 | loss 24.8215 48.7775 112.9968 158.6509 | lr 3.1e-04 | norm 46.1216 | dt 0.024
type train | step 240 | loss 22.9987 46.3235 106.1083 151.6174 | lr 3.2e-04 | norm 39.5283 | dt 0.024
type train | step 250 | loss 21.0092 42.5904 99.4725 143.3105 | lr 3.3e-04 | norm 34.9961 | dt 0.024
type train | step 10 | loss 88.8158 140.8022 283.3437 405.1750 | lr 1.3e-05 | norm 172.1770 | dt 0.079
type train | step 20 | loss 87.6677 139.8809 279.1584 402.8867 | lr 2.7e-05 | norm 172.3862 | dt 0.079
type train | step 30 | loss 86.5094 138.4950 275.5913 397.6230 | lr 4.0e-05 | norm 173.5393 | dt 0.080
type train | step 40 | loss 84.9471 136.1175 272.9260 389.5343 | lr 5.3e-05 | norm 160.9897 | dt 0.079
type train | step 50 | loss 83.4492 133.6090 267.7346 387.2372 | lr 6.7e-05 | norm 166.7573 | dt 0.080
type train | step 60 | loss 81.1418 130.3328 262.8170 378.9498 | lr 8.0e-05 | norm 162.2952 | dt 0.080
type train | step 70 | loss 78.4984 126.9039 256.4213 369.9240 | lr 9.3e-05 | norm 157.8208 | dt 0.080
type train | step 80 | loss 75.9770 123.6498 248.5792 357.4372 | lr 1.1e-04 | norm 146.2193 | dt 0.080
type train | step 90 | loss 73.1938 119.0609 239.5252 348.2194 | lr 1.2e-04 | norm 147.1289 | dt 0.080
type train | step 100 | loss 69.6783 114.5634 232.3235 336.0013 | lr 1.3e-04 | norm 144.7186 | dt 0.081
type train | step 110 | loss 65.7442 108.3448 221.8240 322.8744 | lr 1.5e-04 | norm 135.6794 | dt 0.081
type train | step 120 | loss 62.1308 103.8339 213.3640 307.4771 | lr 1.6e-04 | norm 123.7534 | dt 0.081
type train | step 130 | loss 58.7745 97.7479 203.1346 296.4079 | lr 1.7e-04 | norm 119.4382 | dt 0.080
type train | step 140 | loss 55.0716 93.3574 194.0715 282.7425 | lr 1.9e-04 | norm 110.2255 | dt 0.080
type train | step 150 | loss 51.4467 87.4175 182.9263 266.6889 | lr 2.0e-04 | norm 105.3970 | dt 0.081
type train | step 160 | loss 47.6873 82.4257 171.0446 251.6782 | lr 2.1e-04 | norm 99.6393 | dt 0.081
type train | step 170 | loss 44.0746 77.1765 160.6825 237.6995 | lr 2.3e-04 | norm 94.8070 | dt 0.082
type train | step 180 | loss 40.8392 72.3891 152.5509 223.1505 | lr 2.4e-04 | norm 82.4296 | dt 0.082
type train | step 190 | loss 37.1066 66.7968 143.7157 211.6906 | lr 2.5e-04 | norm 76.7540 | dt 0.081
type train | step 200 | loss 34.4490 62.5053 135.1291 199.1410 | lr 2.7e-04 | norm 68.4613 | dt 0.081
type train | step 210 | loss 31.4578 57.9858 125.3632 186.5767 | lr 2.8e-04 | norm 62.1819 | dt 0.082
type train | step 220 | loss 28.6281 53.7601 117.4130 175.2859 | lr 2.9e-04 | norm 57.0875 | dt 0.082
type train | step 230 | loss 26.0586 49.8864 109.9113 164.8928 | lr 3.1e-04 | norm 50.8501 | dt 0.083
type train | step 240 | loss 24.0570 47.1357 104.6472 156.0832 | lr 3.2e-04 | norm 43.0619 | dt 0.082
type train | step 250 | loss 22.0183 43.5655 97.0624 146.5490 | lr 3.3e-04 | norm 37.4284 | dt 0.083
type train | step 260 | loss 20.1469 40.8034 92.0043 138.1505 | lr 3.5e-04 | norm 32.2951 | dt 0.083
type train | step 270 | loss 18.7564 38.6015 87.1289 130.6970 | lr 3.6e-04 | norm 27.3875 | dt 0.084
type train | step 280 | loss 17.3846 36.4890 83.0474 124.9948 | lr 3.7e-04 | norm 22.9429 | dt 0.084
type train | step 290 | loss 15.8261 34.1079 78.2293 117.8796 | lr 3.9e-04 | norm 19.1404 | dt 0.083
type train | step 300 | loss 14.8081 32.6004 75.1589 113.3990 | lr 4.0e-04 | norm 16.1985 | dt 0.083
type train | step 310 | loss 13.9670 30.8431 71.5368 108.9061 | lr 4.1e-04 | norm 14.1076 | dt 0.083
type train | step 320 | loss 13.0181 28.8978 68.0980 103.7403 | lr 4.3e-04 | norm 12.4833 | dt 0.084
type train | step 10 | loss 75.9573 155.3842 292.9563 401.4576 | lr 1.3e-05 | norm 169.2650 | dt 0.024
type train | step 20 | loss 75.0772 153.5141 289.0566 397.3254 | lr 2.7e-05 | norm 167.7868 | dt 0.024
type train | step 30 | loss 74.8831 153.4297 285.6019 392.8721 | lr 4.0e-05 | norm 169.5378 | dt 0.024
type train | step 40 | loss 72.9626 150.6099 279.4004 385.3763 | lr 5.3e-05 | norm 157.9200 | dt 0.024
type train | step 50 | loss 71.7116 148.2549 277.1435 380.6562 | lr 6.7e-05 | norm 161.8604 | dt 0.025
type train | step 60 | loss 69.8817 144.3430 272.3960 373.7104 | lr 8.0e-05 | norm 159.8772 | dt 0.024
type train | step 70 | loss 67.6416 139.9863 266.5853 363.2805 | lr 9.3e-05 | norm 154.6880 | dt 0.024
type train | step 80 | loss 65.3155 136.1000 255.6237 350.9536 | lr 1.1e-04 | norm 143.1331 | dt 0.024
type train | step 90 | loss 63.0129 132.1352 249.5422 342.3550 | lr 1.2e-04 | norm 144.5298 | dt 0.024
type train | step 100 | loss 60.2221 126.3450 239.8036 330.7666 | lr 1.3e-04 | norm 141.8430 | dt 0.024
type train | step 110 | loss 56.8346 120.5243 230.1906 318.3144 | lr 1.5e-04 | norm 133.2180 | dt 0.024
type train | step 120 | loss 53.8026 114.8466 220.9717 305.4750 | lr 1.6e-04 | norm 124.0184 | dt 0.024
type train | step 130 | loss 50.6128 108.7037 212.4535 291.2957 | lr 1.7e-04 | norm 119.4547 | dt 0.025
type train | step 140 | loss 47.9348 102.8337 201.2367 277.0923 | lr 1.9e-04 | norm 109.5000 | dt 0.024
type train | step 150 | loss 44.8255 97.4138 190.8025 265.0717 | lr 2.0e-04 | norm 105.8757 | dt 0.024
type train | step 160 | loss 41.7486 91.0017 178.3283 247.3149 | lr 2.1e-04 | norm 99.1486 | dt 0.024
type train | step 170 | loss 38.7074 85.1338 167.9214 233.9026 | lr 2.3e-04 | norm 94.1106 | dt 0.024
type train | step 180 | loss 35.9303 79.8792 160.3172 221.2061 | lr 2.4e-04 | norm 84.1552 | dt 0.024
type train | step 190 | loss 32.8660 73.6270 149.4235 208.4873 | lr 2.5e-04 | norm 77.4790 | dt 0.024
type train | step 200 | loss 30.7198 68.6409 140.6784 196.7432 | lr 2.7e-04 | norm 69.6499 | dt 0.024
type train | step 210 | loss 28.1217 63.7749 130.9720 183.6166 | lr 2.8e-04 | norm 63.7406 | dt 0.024
type train | step 220 | loss 25.7165 59.0880 123.0950 172.6194 | lr 2.9e-04 | norm 58.6135 | dt 0.024
type train | step 230 | loss 23.6218 54.4052 115.3393 162.1836 | lr 3.1e-04 | norm 52.9461 | dt 0.024
type train | step 240 | loss 21.9813 51.4004 109.8118 154.9494 | lr 3.2e-04 | norm 45.5950 | dt 0.024
type train | step 250 | loss 20.2432 47.1332 102.2578 144.6796 | lr 3.3e-04 | norm 40.1754 | dt 0.025
type train | step 260 | loss 18.8302 43.9534 96.2643 137.0030 | lr 3.5e-04 | norm 34.4982 | dt 0.024
type train | step 270 | loss 17.6107 41.2925 90.4817 128.8070 | lr 3.6e-04 | norm 29.0413 | dt 0.025
type train | step 280 | loss 16.4248 39.1666 86.1532 123.5791 | lr 3.7e-04 | norm 24.9740 | dt 0.025
type train | step 290 | loss 15.1962 36.2011 80.9638 116.2807 | lr 3.9e-04 | norm 21.1516 | dt 0.024
type train | step 300 | loss 14.3474 34.5706 77.3933 111.8618 | lr 4.0e-04 | norm 17.9640 | dt 0.024
type train | step 310 | loss 13.4452 32.5006 73.7073 107.0802 | lr 4.1e-04 | norm 15.5816 | dt 0.025
type train | step 320 | loss 12.5995 30.6455 69.4140 102.1441 | lr 4.3e-04 | norm 13.3480 | dt 0.025
type train | step 330 | loss 11.7104 28.9116 66.4980 97.9052 | lr 4.4e-04 | norm 11.8312 | dt 0.024
type train | step 340 | loss 10.8282 27.1890 62.5716 93.5110 | lr 4.5e-04 | norm 11.0524 | dt 0.025
type train | step 350 | loss 10.1960 25.7475 59.8932 89.9644 | lr 4.7e-04 | norm 10.2333 | dt 0.024
type train | step 360 | loss 9.4377 24.3499 56.6434 85.8864 | lr 4.8e-04 | norm 9.6898 | dt 0.024
type train | step 370 | loss 8.7510 23.0853 54.7073 83.5357 | lr 4.9e-04 | norm 9.1806 | dt 0.025
type train | step 380 | loss 8.2785 22.2145 53.0669 81.6812 | lr 5.1e-04 | norm 8.3853 | dt 0.025
type train | step 390 | loss 7.4867 20.6467 49.9051 77.8994 | lr 5.2e-04 | norm 8.0258 | dt 0.024
type train | step 400 | loss 6.9464 19.4795 47.0563 74.1963 | lr 5.3e-04 | norm 7.6541 | dt 0.024
type train | step 410 | loss 6.4311 18.6872 45.3797 71.9372 | lr 5.5e-04 | norm 6.9429 | dt 0.025
type train | step 420 | loss 5.9530 17.7954 43.4191 68.8926 | lr 5.6e-04 | norm 6.9376 | dt 0.024
type train | step 430 | loss 5.4172 16.7674 41.7006 66.9177 | lr 5.7e-04 | norm 6.2000 | dt 0.024
type train | step 10 | loss 75.8349 149.0699 272.3273 384.6906 | lr 1.3e-05 | norm 143.8028 | dt 0.025
type train | step 20 | loss 74.7374 146.7620 269.2999 379.3058 | lr 2.7e-05 | norm 142.2105 | dt 0.024
type train | step 30 | loss 74.0294 145.4525 264.6707 376.5620 | lr 4.0e-05 | norm 143.8070 | dt 0.024
type train | step 40 | loss 72.9365 143.3066 260.3184 371.1556 | lr 5.3e-05 | norm 135.9863 | dt 0.024
type train | step 50 | loss 71.1446 141.3472 259.7588 365.0731 | lr 6.7e-05 | norm 138.7336 | dt 0.024
type train | step 60 | loss 69.4765 138.3783 252.7388 357.9761 | lr 8.0e-05 | norm 134.4331 | dt 0.024
type train | step 70 | loss 67.2592 134.7115 247.1428 350.2148 | lr 9.3e-05 | norm 131.7578 | dt 0.024
type train | step 80 | loss 64.9539 129.0575 239.9870 340.5560 | lr 1.1e-04 | norm 123.7113 | dt 0.024
type train | step 90 | loss 62.6637 125.6978 231.4630 329.4371 | lr 1.2e-04 | norm 124.6236 | dt 0.024
type train | step 100 | loss 59.8502 119.5747 223.4362 316.5853 | lr 1.3e-04 | norm 119.3498 | dt 0.024
type train | step 110 | loss 56.3321 115.0126 215.3926 305.5972 | lr 1.5e-04 | norm 113.7821 | dt 0.024
type train | step 120 | loss 53.4757 110.2631 206.6777 294.5030 | lr 1.6e-04 | norm 105.8552 | dt 0.024
type train | step 130 | loss 50.5973 104.8445 196.5845 282.8062 | lr 1.7e-04 | norm 101.6543 | dt 0.024
type train | step 140 | loss 47.5992 98.8083 188.0146 268.6167 | lr 1.9e-04 | norm 93.5924 | dt 0.024
type train | step 150 | loss 44.5018 93.3510 178.1086 256.5907 | lr 2.0e-04 | norm 90.9652 | dt 0.024
type train | step 160 | loss 41.2053 86.9325 166.1847 240.2181 | lr 2.1e-04 | norm 83.8496 | dt 0.024
type train | step 170 | loss 38.4550 81.7559 157.1635 225.7650 | lr 2.3e-04 | norm 79.8006 | dt 0.024
type train | step 180 | loss 35.7797 76.8306 149.0800 216.3343 | lr 2.4e-04 | norm 71.2442 | dt 0.024
type train | step 190 | loss 32.7253 71.0675 139.4324 203.8283 | lr 2.5e-04 | norm 65.9824 | dt 0.024
type train | step 200 | loss 30.4260 66.4695 131.9381 191.6095 | lr 2.7e-04 | norm 59.2601 | dt 0.024
type train | step 210 | loss 27.8953 61.3593 123.4645 180.6730 | lr 2.8e-04 | norm 53.7900 | dt 0.024
type train | step 220 | loss 25.4664 57.0269 115.4372 168.2141 | lr 2.9e-04 | norm 48.9288 | dt 0.024
type train | step 230 | loss 23.3175 52.8585 108.4760 158.8113 | lr 3.1e-04 | norm 43.7944 | dt 0.024
type train | step 240 | loss 21.7050 49.9226 103.2484 151.7350 | lr 3.2e-04 | norm 38.1137 | dt 0.024
type train | step 10 | loss 81.0568 141.5371 269.7250 395.4062 | lr 1.3e-05 | norm 148.4295 | dt 0.024
type train | step 20 | loss 79.8134 139.8085 267.0679 392.2639 | lr 2.7e-05 | norm 148.2219 | dt 0.024
type train | step 30 | loss 78.6829 138.9196 265.5274 388.8335 | lr 4.0e-05 | norm 149.3777 | dt 0.024
type train | step 40 | loss 77.5751 136.3679 260.5955 383.0863 | lr 5.3e-05 | norm 140.2436 | dt 0.024
type train | step 50 | loss 75.9518 134.0268 256.4670 378.4830 | lr 6.7e-05 | norm 143.2906 | dt 0.024
type train | step 60 | loss 73.9268 131.0462 249.9833 371.1044 | lr 8.0e-05 | norm 139.9148 | dt 0.024
type train | step 70 | loss 71.5518 127.0443 245.1814 360.9999 | lr 9.3e-05 | norm 136.4246 | dt 0.024
type train | step 80 | loss 69.0767 123.0239 238.5121 347.8100 | lr 1.1e-04 | norm 127.1495 | dt 0.024
type train | step 90 | loss 66.5646 119.4943 231.9939 339.3709 | lr 1.2e-04 | norm 127.8051 | dt 0.025
type train | step 100 | loss 63.6301 114.2338 221.7170 327.2088 | lr 1.3e-04 | norm 123.9869 | dt 0.024
type train | step 110 | loss 59.9589 108.8465 214.5246 316.5510 | lr 1.5e-04 | norm 117.9020 | dt 0.024
type train | step 120 | loss 57.0970 103.9162 205.3355 304.0794 | lr 1.6e-04 | norm 109.0562 | dt 0.024
type train | step 130 | loss 53.6206 98.3105 194.8685 289.1057 | lr 1.7e-04 | norm 104.4432 | dt 0.024
type train | step 140 | loss 51.0286 93.3803 188.6116 278.9889 | lr 1.9e-04 | norm 98.3710 | dt 0.025
type train | step 150 | loss 47.2279 87.9352 176.6435 264.3781 | lr 2.0e-04 | norm 93.3483 | dt 0.024
type train | step 160 | loss 44.0474 82.4909 165.3663 247.3201 | lr 2.1e-04 | norm 87.7995 | dt 0.024
type train | step 170 | loss 40.6443 77.0679 156.5301 234.2598 | lr 2.3e-04 | norm 82.9265 | dt 0.024
type train | step 180 | loss 37.9305 72.5248 147.7520 222.2291 | lr 2.4e-04 | norm 73.6308 | dt 0.024
type train | step 190 | loss 34.4389 66.7393 138.6086 209.3321 | lr 2.5e-04 | norm 68.4056 | dt 0.024
type train | step 200 | loss 32.2756 62.2587 131.5490 198.4589 | lr 2.7e-04 | norm 61.8961 | dt 0.025
type train | step 210 | loss 29.4464 57.7694 123.1817 185.7102 | lr 2.8e-04 | norm 56.2023 | dt 0.024
type train | step 220 | loss 26.8979 53.8248 114.7502 174.3583 | lr 2.9e-04 | norm 51.3712 | dt 0.024
type train | step 230 | loss 24.6592 49.7837 107.5032 164.5697 | lr 3.1e-04 | norm 45.7710 | dt 0.024
type train | step 240 | loss 22.8621 47.1290 102.4295 156.6706 | lr 3.2e-04 | norm 39.2684 | dt 0.024
type train | step 250 | loss 21.0360 43.3612 96.0350 146.9777 | lr 3.3e-04 | norm 34.5768 | dt 0.025
type train | step 260 | loss 19.4601 40.5876 90.7528 139.0672 | lr 3.5e-04 | norm 29.7989 | dt 0.024
type train | step 270 | loss 18.1473 38.3431 86.4430 131.4350 | lr 3.6e-04 | norm 25.5237 | dt 0.025
type train | step 280 | loss 16.9335 36.2349 82.1787 126.2339 | lr 3.7e-04 | norm 21.5226 | dt 0.024
type train | step 290 | loss 15.6152 33.8531 77.3244 119.1598 | lr 3.9e-04 | norm 18.4383 | dt 0.024
type train | step 300 | loss 14.6620 32.4143 74.3848 114.3975 | lr 4.0e-04 | norm 15.9092 | dt 0.024
type train | step 310 | loss 13.7958 30.4698 70.7804 109.4564 | lr 4.1e-04 | norm 13.9111 | dt 0.024
type train | step 320 | loss 12.8497 28.7538 67.2135 104.2475 | lr 4.3e-04 | norm 12.4836 | dt 0.025
type train | step 330 | loss 11.9068 27.3142 64.3699 100.0802 | lr 4.4e-04 | norm 11.2652 | dt 0.025
type train | step 340 | loss 10.9532 25.7298 60.6959 95.6177 | lr 4.5e-04 | norm 10.6197 | dt 0.024
type train | step 350 | loss 10.2318 24.3861 58.2578 92.2683 | lr 4.7e-04 | norm 9.8777 | dt 0.025
type train | step 360 | loss 9.4906 22.9938 55.0709 88.2605 | lr 4.8e-04 | norm 9.4316 | dt 0.025
type train | step 370 | loss 8.7291 21.9330 53.1128 85.8993 | lr 4.9e-04 | norm 8.8493 | dt 0.024
type train | step 380 | loss 8.2914 21.0569 51.8298 83.3431 | lr 5.1e-04 | norm 8.1069 | dt 0.025
type train | step 390 | loss 7.4402 19.6774 48.6616 79.8152 | lr 5.2e-04 | norm 7.8469 | dt 0.024
type train | step 400 | loss 6.9309 18.5843 45.8506 75.4046 | lr 5.3e-04 | norm 7.4021 | dt 0.024
type train | step 410 | loss 6.4076 17.7750 44.3635 73.6170 | lr 5.5e-04 | norm 6.8037 | dt 0.024
type train | step 420 | loss 6.0117 16.9714 42.2301 70.6498 | lr 5.6e-04 | norm 6.7652 | dt 0.025
type train | step 430 | loss 5.4328 16.0718 40.5578 68.7621 | lr 5.7e-04 | norm 6.1270 | dt 0.024
type train | step 440 | loss 4.9640 15.0394 38.6467 66.0892 | lr 5.9e-04 | norm 5.7624 | dt 0.025
type train | step 450 | loss 4.6414 14.4455 37.6145 64.2348 | lr 6.0e-04 | norm 5.2811 | dt 0.025
type train | step 460 | loss 4.2596 13.4474 34.8839 60.2841 | lr 6.1e-04 | norm 5.1701 | dt 0.024
type train | step 470 | loss 4.0184 13.1590 34.7679 60.2875 | lr 6.3e-04 | norm 4.6611 | dt 0.024
type train | step 480 | loss 3.6304 12.5268 32.5795 58.1373 | lr 6.4e-04 | norm 4.4027 | dt 0.025
type train | step 490 | loss 3.2662 11.8507 31.1481 56.3438 | lr 6.5e-04 | norm 4.1824 | dt 0.024
type train | step 500 | loss 3.0506 11.4448 30.5079 54.8563 | lr 6.7e-04 | norm 3.9641 | dt 0.024
type train | step 510 | loss 2.7631 10.8702 29.5997 54.3682 | lr 6.8e-04 | norm 3.7475 | dt 0.025
type train | step 520 | loss 2.5112 10.2736 28.2151 52.4127 | lr 6.9e-04 | norm 3.7125 | dt 0.025
type train | step 530 | loss 2.4154 10.0838 27.9663 52.2073 | lr 7.1e-04 | norm 3.3515 | dt 0.025
type train | step 540 | loss 2.0800 9.4135 25.4229 48.6979 | lr 7.2e-04 | norm 3.1543 | dt 0.025
type train | step 550 | loss 1.8878 9.1583 24.8435 48.3404 | lr 7.3e-04 | norm 3.1121 | dt 0.024
type train | step 560 | loss 1.8854 8.8792 24.7447 47.1767 | lr 7.5e-04 | norm 3.2714 | dt 0.025
type train | step 570 | loss 1.6703 8.4868 24.1853 47.9795 | lr 7.6e-04 | norm 2.8793 | dt 0.025
type train | step 580 | loss 1.5205 8.1429 22.2603 44.3837 | lr 7.7e-04 | norm 3.1103 | dt 0.024
type train | step 590 | loss 1.4163 7.8417 22.6101 45.5385 | lr 7.9e-04 | norm 2.7722 | dt 0.025
type train | step 600 | loss 1.2060 7.4722 20.6585 42.5256 | lr 8.0e-04 | norm 2.4583 | dt 0.025
type train | step 610 | loss 1.1766 7.2484 20.6646 42.9515 | lr 8.1e-04 | norm 2.5724 | dt 0.026
type train | step 620 | loss 1.0804 6.9794 19.8892 41.8818 | lr 8.3e-04 | norm 2.2386 | dt 0.025
type train | step 630 | loss 0.9927 6.8465 19.9265 42.5650 | lr 8.4e-04 | norm 2.4038 | dt 0.024
type train | step 640 | loss 0.9373 6.4002 18.6674 40.1027 | lr 8.5e-04 | norm 2.3444 | dt 0.025
type train | step 650 | loss 0.9810 6.4863 19.6481 41.9585 | lr 8.7e-04 | norm 2.6162 | dt 0.025
type train | step 660 | loss 0.7961 6.0724 17.5002 38.3280 | lr 8.8e-04 | norm 2.2482 | dt 0.025
type train | step 670 | loss 0.7248 5.7696 17.0918 38.2671 | lr 8.9e-04 | norm 2.0344 | dt 0.025
type train | step 680 | loss 0.6792 5.6874 16.8572 37.7175 | lr 9.1e-04 | norm 1.8682 | dt 0.025
type train | step 690 | loss 0.6896 5.7386 17.9045 40.2647 | lr 9.2e-04 | norm 2.3030 | dt 0.025
type train | step 700 | loss 0.6395 5.3496 16.2905 36.9843 | lr 9.3e-04 | norm 2.0755 | dt 0.025
type train | step 710 | loss 0.5700 5.0568 15.6962 36.4244 | lr 9.5e-04 | norm 1.8714 | dt 0.025
type train | step 720 | loss 0.5749 5.1178 15.5735 36.0813 | lr 9.6e-04 | norm 1.9692 | dt 0.025
type train | step 730 | loss 0.5486 5.0256 15.4517 35.7336 | lr 9.7e-04 | norm 2.1607 | dt 0.025
type train | step 740 | loss 0.4978 4.7418 14.9152 35.6742 | lr 9.9e-04 | norm 1.9414 | dt 0.025
type train | step 750 | loss 0.5677 4.9990 16.1338 37.2282 | lr 1.0e-03 | norm 3.2004 | dt 0.025
type train | step 760 | loss 0.4790 4.6300 14.7370 35.3568 | lr 1.0e-03 | norm 2.1320 | dt 0.026
type train | step 770 | loss 0.4342 4.4618 14.4752 35.1954 | lr 1.0e-03 | norm 1.9216 | dt 0.026
type train | step 780 | loss 0.4206 4.4266 13.8740 33.7575 | lr 1.0e-03 | norm 1.9380 | dt 0.025
type train | step 790 | loss 0.4143 4.3917 14.1528 34.6856 | lr 1.0e-03 | norm 2.1170 | dt 0.026
type train | step 800 | loss 0.3894 4.2014 13.7391 34.1202 | lr 1.0e-03 | norm 2.1986 | dt 0.026
type train | step 810 | loss 0.4075 4.3075 14.3128 35.5229 | lr 1.0e-03 | norm 2.1551 | dt 0.025
type train | step 820 | loss 0.3833 4.0862 13.4227 34.0888 | lr 1.0e-03 | norm 2.0041 | dt 0.025
type train | step 830 | loss 0.3590 3.9501 13.0533 33.3416 | lr 1.0e-03 | norm 1.7751 | dt 0.026
type train | step 840 | loss 0.3347 3.9182 12.7841 32.6557 | lr 1.0e-03 | norm 1.7470 | dt 0.025
type train | step 850 | loss 0.3503 3.9987 13.2353 33.6221 | lr 1.0e-03 | norm 2.0963 | dt 0.025
type train | step 860 | loss 0.3281 3.7167 12.3196 32.1520 | lr 1.0e-03 | norm 1.8191 | dt 0.026
type train | step 870 | loss 0.3184 3.7053 12.5137 32.3250 | lr 1.0e-03 | norm 1.7764 | dt 0.025
type train | step 880 | loss 0.3303 3.6741 12.2929 32.4402 | lr 1.0e-03 | norm 1.7109 | dt 0.026
type train | step 890 | loss 0.3329 3.6669 12.5332 33.0129 | lr 1.0e-03 | norm 2.0194 | dt 0.026
type train | step 900 | loss 0.3044 3.5088 11.8031 31.4773 | lr 1.0e-03 | norm 1.9102 | dt 0.025
type train | step 910 | loss 0.3082 3.6825 12.3201 32.0123 | lr 1.0e-03 | norm 2.1581 | dt 0.025
type train | step 920 | loss 0.3033 3.4515 11.8900 32.0334 | lr 1.0e-03 | norm 2.1102 | dt 0.026
type train | step 930 | loss 0.2914 3.3856 11.8297 31.5533 | lr 1.0e-03 | norm 1.9313 | dt 0.026
type train | step 940 | loss 0.2941 3.4036 11.9246 32.3640 | lr 1.0e-03 | norm 1.5329 | dt 0.025
type train | step 950 | loss 0.2815 3.3028 11.6160 31.7177 | lr 1.0e-03 | norm 1.6065 | dt 0.025
type train | step 960 | loss 0.2904 3.3094 11.3749 31.2188 | lr 1.0e-03 | norm 1.9736 | dt 0.026
type train | step 970 | loss 0.2772 3.1752 11.0063 30.3581 | lr 1.0e-03 | norm 1.9625 | dt 0.025
type train | step 980 | loss 0.2740 3.2472 11.1479 30.8324 | lr 1.0e-03 | norm 2.0218 | dt 0.025
type train | step 990 | loss 0.2834 3.2870 11.5058 31.5090 | lr 1.0e-03 | norm 2.0021 | dt 0.026
type train | step 1000 | loss 0.2643 3.1592 11.3768 31.5718 | lr 1.0e-03 | norm 1.6654 | dt 0.025
type train | step 1010 | loss 0.2792 3.1181 10.9015 30.2065 | lr 1.0e-03 | norm 1.7572 | dt 0.025
type train | step 1020 | loss 0.2709 3.1206 10.9129 30.4778 | lr 1.0e-03 | norm 1.5969 | dt 0.026
type train | step 1030 | loss 0.2693 3.1023 10.8200 30.4073 | lr 1.0e-03 | norm 2.1744 | dt 0.026
type train | step 1040 | loss 0.2619 3.1015 10.9945 30.8171 | lr 1.0e-03 | norm 1.7045 | dt 0.026
type train | step 1050 | loss 0.2542 2.9757 10.7137 30.1693 | lr 1.0e-03 | norm 1.8877 | dt 0.026
type train | step 1060 | loss 0.2597 3.0178 10.8142 30.7549 | lr 1.0e-03 | norm 1.5306 | dt 0.026
type train | step 1070 | loss 0.2511 2.9070 10.2452 29.1492 | lr 1.0e-03 | norm 1.7881 | dt 0.026
type train | step 1080 | loss 0.2595 2.9482 10.7236 30.3522 | lr 1.0e-03 | norm 1.6541 | dt 0.026
type train | step 1090 | loss 0.2509 2.9362 10.6021 30.2647 | lr 1.0e-03 | norm 1.6251 | dt 0.026
type train | step 1100 | loss 0.2520 2.9231 10.6449 30.1168 | lr 1.0e-03 | norm 1.7199 | dt 0.026
type train | step 1110 | loss 0.2532 2.8979 10.4870 30.1071 | lr 1.0e-03 | norm 1.9169 | dt 0.026
type train | step 1120 | loss 0.2464 2.8977 10.6632 30.8583 | lr 1.0e-03 | norm 1.6397 | dt 0.026
type train | step 1130 | loss 0.2428 2.8331 10.5648 30.6110 | lr 1.0e-03 | norm 1.8785 | dt 0.026
type train | step 1140 | loss 0.2515 2.8544 10.6150 30.7113 | lr 1.0e-03 | norm 1.7328 | dt 0.026
type train | step 1150 | loss 0.2358 2.7645 10.0251 29.0365 | lr 1.0e-03 | norm 1.5980 | dt 0.026
type train | step 1160 | loss 0.2368 2.8147 10.2332 29.6795 | lr 1.0e-03 | norm 1.8647 | dt 0.026
type train | step 1170 | loss 0.2450 2.7912 10.2559 29.4151 | lr 1.0e-03 | norm 2.0910 | dt 0.026
type train | step 1180 | loss 0.2377 2.8054 10.5769 31.0248 | lr 1.0e-03 | norm 1.7265 | dt 0.026
type train | step 1190 | loss 0.2482 2.7627 9.9112 28.9699 | lr 1.0e-03 | norm 2.1385 | dt 0.026
type train | step 1200 | loss 0.2363 2.7438 10.2493 30.1821 | lr 1.0e-03 | norm 1.9361 | dt 0.025
type train | step 1210 | loss 0.2263 2.6515 9.7922 28.5982 | lr 1.0e-03 | norm 1.5582 | dt 0.026
type train | step 1220 | loss 0.2330 2.6887 10.1551 29.8798 | lr 1.0e-03 | norm 1.8997 | dt 0.027
type train | step 1230 | loss 0.2285 2.6761 9.9300 29.4271 | lr 1.0e-03 | norm 1.5425 | dt 0.027
type train | step 1240 | loss 0.2293 2.6889 10.1179 30.0235 | lr 1.0e-03 | norm 1.6772 | dt 0.026
type train | step 1250 | loss 0.2305 2.5929 9.5891 28.6962 | lr 1.0e-03 | norm 1.7360 | dt 0.026
type train | step 1260 | loss 0.2403 2.6868 10.1549 29.9277 | lr 1.0e-03 | norm 2.0268 | dt 0.025
type train | step 1270 | loss 0.2270 2.6167 9.5331 28.2407 | lr 1.0e-03 | norm 1.7519 | dt 0.026
type train | step 1280 | loss 0.2266 2.5659 9.7225 28.8822 | lr 1.0e-03 | norm 1.7359 | dt 0.026
type train | step 1290 | loss 0.2216 2.5764 9.4921 28.3374 | lr 1.0e-03 | norm 1.4222 | dt 0.026
type train | step 1300 | loss 0.2302 2.6850 10.3589 30.6585 | lr 1.0e-03 | norm 1.8263 | dt 0.026
type train | step 1310 | loss 0.2286 2.5692 9.5300 28.6603 | lr 1.0e-03 | norm 1.7093 | dt 0.026
type train | step 1320 | loss 0.2196 2.4799 9.2961 28.1320 | lr 1.0e-03 | norm 1.6361 | dt 0.026
type train | step 1330 | loss 0.2262 2.5526 9.5846 28.5343 | lr 1.0e-03 | norm 1.6938 | dt 0.026
type train | step 1340 | loss 0.2307 2.5842 9.4457 28.1126 | lr 1.0e-03 | norm 1.8563 | dt 0.026
type train | step 1350 | loss 0.2190 2.4999 9.3092 28.4115 | lr 1.0e-03 | norm 1.5645 | dt 0.026
type train | step 1360 | loss 0.2455 2.6295 9.5680 29.0816 | lr 1.0e-03 | norm 2.6350 | dt 0.025
type train | step 1370 | loss 0.2294 2.5547 9.5852 28.7834 | lr 1.0e-03 | norm 1.9222 | dt 0.025
type train | step 1380 | loss 0.2199 2.4792 9.4625 28.6867 | lr 1.0e-03 | norm 1.7906 | dt 0.027
type train | step 1390 | loss 0.2178 2.5101 9.3534 28.0052 | lr 1.0e-03 | norm 1.8006 | dt 0.026
type train | step 1400 | loss 0.2198 2.5274 9.4643 28.5316 | lr 1.0e-03 | norm 1.8849 | dt 0.026
type train | step 1410 | loss 0.2180 2.4509 9.3196 28.3457 | lr 1.0e-03 | norm 1.9812 | dt 0.026
type train | step 1420 | loss 0.2295 2.5483 9.6927 29.4123 | lr 1.0e-03 | norm 1.8382 | dt 0.026
type train | step 1430 | loss 0.2211 2.4511 9.2564 28.5012 | lr 1.0e-03 | norm 1.7809 | dt 0.026
type train | step 1440 | loss 0.2143 2.4088 9.2955 28.3448 | lr 1.0e-03 | norm 1.6937 | dt 0.026
type train | step 1450 | loss 0.2071 2.4314 9.2055 28.0567 | lr 1.0e-03 | norm 1.6121 | dt 0.026
type train | step 1460 | loss 0.2214 2.5262 9.4676 28.8212 | lr 1.0e-03 | norm 1.8655 | dt 0.026
type train | step 1470 | loss 0.2105 2.3864 8.9732 27.6230 | lr 1.0e-03 | norm 1.6248 | dt 0.026
type train | step 1480 | loss 0.2073 2.3872 9.1175 28.0179 | lr 1.0e-03 | norm 1.5879 | dt 0.026
type train | step 1490 | loss 0.2179 2.3825 9.0021 27.8354 | lr 1.0e-03 | norm 1.5636 | dt 0.025
type train | step 1500 | loss 0.2169 2.4167 9.2699 28.5755 | lr 1.0e-03 | norm 1.9105 | dt 0.026
type train | step 1510 | loss 0.2083 2.3600 8.9276 27.5617 | lr 1.0e-03 | norm 1.7462 | dt 0.026
type train | step 1520 | loss 0.2144 2.4632 9.2573 27.9359 | lr 1.0e-03 | norm 1.9546 | dt 0.026
type train | step 1530 | loss 0.2110 2.3819 9.0486 28.2212 | lr 1.0e-03 | norm 1.9242 | dt 0.026
type train | step 1540 | loss 0.2056 2.3400 9.1328 27.8669 | lr 1.0e-03 | norm 1.7944 | dt 0.026
type train | step 1550 | loss 0.2098 2.3879 9.2612 28.6234 | lr 1.0e-03 | norm 1.4616 | dt 0.026
type train | step 1560 | loss 0.2033 2.3207 9.1166 28.3725 | lr 1.0e-03 | norm 1.5365 | dt 0.026
type train | step 1570 | loss 0.2083 2.3523 9.0274 28.0803 | lr 1.0e-03 | norm 1.8666 | dt 0.026
type train | step 1580 | loss 0.2055 2.2610 8.7203 27.0554 | lr 1.0e-03 | norm 1.7923 | dt 0.026
type train | step 1590 | loss 0.2041 2.3417 8.8100 27.7473 | lr 1.0e-03 | norm 1.9363 | dt 0.026
type train | step 1600 | loss 0.2100 2.3627 9.0398 28.1266 | lr 1.0e-03 | norm 1.8355 | dt 0.026
type train | step 1610 | loss 0.2004 2.3318 9.2344 28.3926 | lr 1.0e-03 | norm 1.5595 | dt 0.026
type train | step 1620 | loss 0.2102 2.3147 8.8012 27.3934 | lr 1.0e-03 | norm 1.6645 | dt 0.027
type train | step 1630 | loss 0.2046 2.3259 8.8804 27.6576 | lr 1.0e-03 | norm 1.4847 | dt 0.026
type train | step 1640 | loss 0.2068 2.3340 8.8568 27.5902 | lr 1.0e-03 | norm 2.0466 | dt 0.026
type train | step 1650 | loss 0.2057 2.3417 9.0241 28.0552 | lr 1.0e-03 | norm 1.6412 | dt 0.026
type train | step 1660 | loss 0.1993 2.2603 8.7631 27.3706 | lr 1.0e-03 | norm 1.7958 | dt 0.026
type train | step 1670 | loss 0.2066 2.3028 8.9932 27.9766 | lr 9.9e-04 | norm 1.4622 | dt 0.026
type train | step 1680 | loss 0.2004 2.2195 8.4555 26.7905 | lr 9.9e-04 | norm 1.7385 | dt 0.026
type train | step 1690 | loss 0.2024 2.2763 8.8896 27.6905 | lr 9.9e-04 | norm 1.5565 | dt 0.026
type train | step 1700 | loss 0.2015 2.2872 8.9558 27.7735 | lr 9.9e-04 | norm 1.5786 | dt 0.026
type train | step 1710 | loss 0.2024 2.2977 8.9785 27.8386 | lr 9.9e-04 | norm 1.6509 | dt 0.026
type train | step 1720 | loss 0.2032 2.2847 8.8631 27.7764 | lr 9.9e-04 | norm 1.8169 | dt 0.026
type train | step 1730 | loss 0.1997 2.3020 9.0973 28.5076 | lr 9.9e-04 | norm 1.5755 | dt 0.026
type train | step 1740 | loss 0.1987 2.2735 9.0226 28.4125 | lr 9.9e-04 | norm 1.8116 | dt 0.026
type train | step 1750 | loss 0.2004 2.2938 9.0356 28.3617 | lr 9.9e-04 | norm 1.6531 | dt 0.026
type train | step 1760 | loss 0.1916 2.2304 8.6345 26.8593 | lr 9.9e-04 | norm 1.5141 | dt 0.026
type train | step 1770 | loss 0.1959 2.2780 8.8513 27.6116 | lr 9.9e-04 | norm 1.8152 | dt 0.026
type train | step 1780 | loss 0.2000 2.2536 8.8785 27.3603 | lr 9.9e-04 | norm 1.9911 | dt 0.026
type train | step 1790 | loss 0.1963 2.2928 9.1517 28.8446 | lr 9.9e-04 | norm 1.6818 | dt 0.026
type train | step 1800 | loss 0.2046 2.2557 8.5342 27.0572 | lr 9.9e-04 | norm 2.0882 | dt 0.026
type train | step 1810 | loss 0.1952 2.2413 8.8808 28.1791 | lr 9.9e-04 | norm 1.8133 | dt 0.026
type train | step 1820 | loss 0.1897 2.1927 8.6133 26.7871 | lr 9.9e-04 | norm 1.4875 | dt 0.026
type train | step 1830 | loss 0.1930 2.2357 9.0193 28.1484 | lr 9.9e-04 | norm 1.8624 | dt 0.027
type train | step 1840 | loss 0.1923 2.2327 8.8151 27.6386 | lr 9.9e-04 | norm 1.5183 | dt 0.026
type train | step 1850 | loss 0.1927 2.2396 8.9245 28.1951 | lr 9.9e-04 | norm 1.6412 | dt 0.026
type train | step 1860 | loss 0.1946 2.1683 8.4570 27.0404 | lr 9.9e-04 | norm 1.6406 | dt 0.026
type train | step 1870 | loss 0.2004 2.2496 8.8804 27.9673 | lr 9.9e-04 | norm 1.9112 | dt 0.026
type train | step 1880 | loss 0.1915 2.2039 8.4632 26.6765 | lr 9.9e-04 | norm 1.6754 | dt 0.025
type train | step 1890 | loss 0.1919 2.1838 8.7217 27.3389 | lr 9.9e-04 | norm 1.7274 | dt 0.026
type train | step 1900 | loss 0.1893 2.1987 8.4834 26.7061 | lr 9.9e-04 | norm 1.3885 | dt 0.025
type train | step 1910 | loss 0.1958 2.2880 9.1845 28.9467 | lr 9.9e-04 | norm 1.7000 | dt 0.026
type train | step 1920 | loss 0.1933 2.2018 8.5026 27.0913 | lr 9.9e-04 | norm 1.6494 | dt 0.026
type train | step 1930 | loss 0.1869 2.1136 8.3867 26.6352 | lr 9.9e-04 | norm 1.5948 | dt 0.026
type train | step 1940 | loss 0.1943 2.2018 8.6690 27.1640 | lr 9.9e-04 | norm 1.6165 | dt 0.026
type train | step 1950 | loss 0.1966 2.2214 8.5350 26.6990 | lr 9.9e-04 | norm 1.7834 | dt 0.026
type train | step 1960 | loss 0.1882 2.1659 8.3949 26.9013 | lr 9.9e-04 | norm 1.5243 | dt 0.026
type train | step 1970 | loss 0.2118 2.2600 8.5135 27.6229 | lr 9.9e-04 | norm 2.4631 | dt 0.026
type train | step 1980 | loss 0.1960 2.2137 8.7073 27.5148 | lr 9.9e-04 | norm 1.8670 | dt 0.026
type train | step 1990 | loss 0.1876 2.1504 8.6055 27.2786 | lr 9.9e-04 | norm 1.7253 | dt 0.026
type train | step 2000 | loss 0.1882 2.1901 8.5414 26.7488 | lr 9.9e-04 | norm 1.7542 | dt 0.026
type train | step 2010 | loss 0.1911 2.2070 8.6106 27.1507 | lr 9.9e-04 | norm 1.8315 | dt 0.026
type train | step 2020 | loss 0.1895 2.1382 8.5082 27.0145 | lr 9.9e-04 | norm 1.9109 | dt 0.026
type train | step 2030 | loss 0.1986 2.2432 8.7932 28.1454 | lr 9.9e-04 | norm 1.7429 | dt 0.026
type train | step 2040 | loss 0.1916 2.1440 8.4330 27.0715 | lr 9.9e-04 | norm 1.7823 | dt 0.026
type train | step 2050 | loss 0.1854 2.1348 8.5528 27.0997 | lr 9.9e-04 | norm 1.6525 | dt 0.026
type train | step 2060 | loss 0.1815 2.1563 8.5442 26.9017 | lr 9.9e-04 | norm 1.5599 | dt 0.026
type train | step 2070 | loss 0.1938 2.2571 8.7360 27.6444 | lr 9.9e-04 | norm 1.7965 | dt 0.026
type train | step 2080 | loss 0.1844 2.1192 8.2750 26.4224 | lr 9.9e-04 | norm 1.5505 | dt 0.026
type train | step 2090 | loss 0.1822 2.1278 8.4386 26.8903 | lr 9.9e-04 | norm 1.5489 | dt 0.026
type train | step 2100 | loss 0.1911 2.1207 8.2663 26.5776 | lr 9.9e-04 | norm 1.5448 | dt 0.026
type train | step 2110 | loss 0.1893 2.1556 8.5248 27.4086 | lr 9.9e-04 | norm 1.8562 | dt 0.026
type train | step 2120 | loss 0.1836 2.1212 8.2854 26.4420 | lr 9.9e-04 | norm 1.6750 | dt 0.026
type train | step 2130 | loss 0.1892 2.2282 8.6413 26.8065 | lr 9.9e-04 | norm 1.8634 | dt 0.026
type train | step 2140 | loss 0.1863 2.1292 8.3915 27.0970 | lr 9.9e-04 | norm 1.8649 | dt 0.026
type train | step 2150 | loss 0.1824 2.1175 8.4694 26.9493 | lr 9.9e-04 | norm 1.7499 | dt 0.026
type train | step 2160 | loss 0.1852 2.1573 8.6251 27.5570 | lr 9.9e-04 | norm 1.4096 | dt 0.026
type train | step 2170 | loss 0.1790 2.1170 8.5445 27.3267 | lr 9.9e-04 | norm 1.4573 | dt 0.026
type train | step 2180 | loss 0.1840 2.1408 8.4581 27.0083 | lr 9.9e-04 | norm 1.8179 | dt 0.026
type train | step 2190 | loss 0.1813 2.0597 8.1611 26.1059 | lr 9.9e-04 | norm 1.7418 | dt 0.026
type train | step 2200 | loss 0.1816 2.1317 8.2717 26.7413 | lr 9.9e-04 | norm 1.8431 | dt 0.026
type train | step 2210 | loss 0.1878 2.1387 8.4063 27.2397 | lr 9.9e-04 | norm 1.7443 | dt 0.026
type train | step 2220 | loss 0.1783 2.1355 8.6727 27.3987 | lr 9.9e-04 | norm 1.5259 | dt 0.026
type train | step 2230 | loss 0.1860 2.1244 8.2452 26.4427 | lr 9.9e-04 | norm 1.6221 | dt 0.026
type train | step 2240 | loss 0.1827 2.1281 8.3640 26.7750 | lr 9.9e-04 | norm 1.4547 | dt 0.026
type train | step 2250 | loss 0.1841 2.1564 8.3595 26.6216 | lr 9.9e-04 | norm 1.9688 | dt 0.026
type train | step 2260 | loss 0.1828 2.1443 8.5338 27.1201 | lr 9.9e-04 | norm 1.5828 | dt 0.026
type train | step 2270 | loss 0.1788 2.0819 8.2462 26.4818 | lr 9.9e-04 | norm 1.7510 | dt 0.026
type train | step 2280 | loss 0.1844 2.1197 8.4532 26.9946 | lr 9.9e-04 | norm 1.4047 | dt 0.026
type train | step 2290 | loss 0.1789 2.0529 7.9522 25.9226 | lr 9.9e-04 | norm 1.6841 | dt 0.026
type train | step 2300 | loss 0.1811 2.1003 8.3413 26.8314 | lr 9.9e-04 | norm 1.4963 | dt 0.026
type train | step 2310 | loss 0.1802 2.1174 8.4925 26.9671 | lr 9.9e-04 | norm 1.5176 | dt 0.026
type train | step 2320 | loss 0.1819 2.1226 8.5118 27.1051 | lr 9.9e-04 | norm 1.6217 | dt 0.026
type train | step 2330 | loss 0.1832 2.1126 8.3476 27.0209 | lr 9.9e-04 | norm 1.7722 | dt 0.026
type train | step 2340 | loss 0.1792 2.1360 8.5851 27.6804 | lr 9.8e-04 | norm 1.5061 | dt 0.026
type train | step 2350 | loss 0.1799 2.1149 8.5301 27.5706 | lr 9.8e-04 | norm 1.7499 | dt 0.026
type train | step 2360 | loss 0.1798 2.1190 8.5411 27.5736 | lr 9.8e-04 | norm 1.5920 | dt 0.026
type train | step 2370 | loss 0.1736 2.0929 8.1892 26.0752 | lr 9.8e-04 | norm 1.4923 | dt 0.026
type train | step 2380 | loss 0.1759 2.1320 8.4335 26.7776 | lr 9.8e-04 | norm 1.7626 | dt 0.026
type train | step 2390 | loss 0.1811 2.1000 8.3592 26.5983 | lr 9.8e-04 | norm 1.9398 | dt 0.026
type train | step 2400 | loss 0.1769 2.1395 8.6926 27.9900 | lr 9.8e-04 | norm 1.6424 | dt 0.026
type train | step 2410 | loss 0.1854 2.1038 8.1192 26.2872 | lr 9.8e-04 | norm 2.0118 | dt 0.026
type train | step 2420 | loss 0.1767 2.1021 8.3836 27.4257 | lr 9.8e-04 | norm 1.7559 | dt 0.026
type train | step 2430 | loss 0.1723 2.0668 8.2356 26.0577 | lr 9.8e-04 | norm 1.4678 | dt 0.026
type train | step 2440 | loss 0.1750 2.0981 8.6133 27.4708 | lr 9.8e-04 | norm 1.8061 | dt 0.029
type train | step 2450 | loss 0.1735 2.0825 8.4263 26.9706 | lr 9.8e-04 | norm 1.4853 | dt 0.026
type train | step 2460 | loss 0.1747 2.1093 8.4991 27.4890 | lr 9.8e-04 | norm 1.6197 | dt 0.026
type train | step 2470 | loss 0.1780 2.0451 8.0772 26.3471 | lr 9.8e-04 | norm 1.6128 | dt 0.026
type train | step 2480 | loss 0.1818 2.1155 8.4376 27.2425 | lr 9.8e-04 | norm 1.8414 | dt 0.026
type train | step 2490 | loss 0.1745 2.0818 8.1003 25.9685 | lr 9.8e-04 | norm 1.6409 | dt 0.026
type train | step 2500 | loss 0.1746 2.0461 8.3498 26.6942 | lr 9.8e-04 | norm 1.7129 | dt 0.026
type train | step 2510 | loss 0.1732 2.0657 8.1206 26.0677 | lr 9.8e-04 | norm 1.3340 | dt 0.025
type train | step 2520 | loss 0.1784 2.1438 8.7321 28.3398 | lr 9.8e-04 | norm 1.6180 | dt 0.026
type train | step 2530 | loss 0.1764 2.0701 8.1467 26.4777 | lr 9.8e-04 | norm 1.5906 | dt 0.026
type train | step 2540 | loss 0.1702 1.9989 8.0325 25.9860 | lr 9.8e-04 | norm 1.5342 | dt 0.026
type train | step 2550 | loss 0.1781 2.0745 8.3113 26.4953 | lr 9.8e-04 | norm 1.5987 | dt 0.026
type train | step 2560 | loss 0.1792 2.0827 8.1977 26.1593 | lr 9.8e-04 | norm 1.7329 | dt 0.026
type train | step 2570 | loss 0.1727 2.0328 8.0712 26.2244 | lr 9.8e-04 | norm 1.4706 | dt 0.026
type train | step 2580 | loss 0.1914 2.1197 8.0773 26.9446 | lr 9.8e-04 | norm 2.3381 | dt 0.026
type train | step 2590 | loss 0.1803 2.0923 8.3434 26.9697 | lr 9.8e-04 | norm 1.8285 | dt 0.026
type train | step 2600 | loss 0.1717 2.0304 8.2575 26.7221 | lr 9.8e-04 | norm 1.6637 | dt 0.026
type train | step 2610 | loss 0.1737 2.0794 8.2138 26.0902 | lr 9.8e-04 | norm 1.6979 | dt 0.026
type train | step 2620 | loss 0.1744 2.0837 8.2572 26.6150 | lr 9.8e-04 | norm 1.7586 | dt 0.026
type train | step 2630 | loss 0.1733 2.0242 8.1680 26.3800 | lr 9.8e-04 | norm 1.8161 | dt 0.026
type train | step 2640 | loss 0.1819 2.1163 8.3922 27.5715 | lr 9.8e-04 | norm 1.6430 | dt 0.026
type train | step 2650 | loss 0.1757 2.0259 8.0923 26.4489 | lr 9.8e-04 | norm 1.7061 | dt 0.026
type train | step 2660 | loss 0.1699 2.0203 8.2496 26.5276 | lr 9.8e-04 | norm 1.5946 | dt 0.027
type train | step 2670 | loss 0.1658 2.0515 8.2622 26.3171 | lr 9.8e-04 | norm 1.5169 | dt 0.026
type train | step 2680 | loss 0.1764 2.1298 8.4162 27.0890 | lr 9.8e-04 | norm 1.7230 | dt 0.027
type train | step 2690 | loss 0.1689 2.0017 7.9829 25.8532 | lr 9.8e-04 | norm 1.5014 | dt 0.026
type train | step 2700 | loss 0.1669 2.0226 8.1222 26.3971 | lr 9.8e-04 | norm 1.4909 | dt 0.028
type train | step 2710 | loss 0.1742 2.0194 7.9296 26.0206 | lr 9.8e-04 | norm 1.4746 | dt 0.027
type train | step 2720 | loss 0.1728 2.0361 8.2080 26.8627 | lr 9.8e-04 | norm 1.7756 | dt 0.027
type train | step 2730 | loss 0.1679 2.0129 8.0013 25.9164 | lr 9.8e-04 | norm 1.6347 | dt 0.031
type train | step 2740 | loss 0.1722 2.1242 8.3564 26.2889 | lr 9.8e-04 | norm 1.8111 | dt 0.034
type train | step 2750 | loss 0.1700 2.0192 8.1354 26.5100 | lr 9.8e-04 | norm 1.8051 | dt 0.035
type train | step 2760 | loss 0.1673 2.0116 8.1704 26.4665 | lr 9.8e-04 | norm 1.7185 | dt 0.033
type train | step 2770 | loss 0.1695 2.0532 8.3154 26.9871 | lr 9.8e-04 | norm 1.3834 | dt 0.032
type train | step 2780 | loss 0.1640 2.0131 8.2851 26.7969 | lr 9.8e-04 | norm 1.4231 | dt 0.032
type train | step 2790 | loss 0.1691 2.0344 8.2078 26.4701 | lr 9.8e-04 | norm 1.7667 | dt 0.027
type train | step 2800 | loss 0.1654 1.9511 7.8801 25.6618 | lr 9.8e-04 | norm 1.7060 | dt 0.026
type train | step 2810 | loss 0.1660 2.0327 8.0057 26.2033 | lr 9.7e-04 | norm 1.7861 | dt 0.026
type train | step 2820 | loss 0.1719 2.0433 8.1268 26.7978 | lr 9.7e-04 | norm 1.7002 | dt 0.025
type train | step 2830 | loss 0.1630 2.0431 8.3681 26.9289 | lr 9.7e-04 | norm 1.5157 | dt 0.026
type train | step 2840 | loss 0.1716 2.0244 8.0093 25.9549 | lr 9.7e-04 | norm 1.5625 | dt 0.026
type train | step 2850 | loss 0.1672 2.0275 8.0992 26.2534 | lr 9.7e-04 | norm 1.4365 | dt 0.026
type train | step 2860 | loss 0.1684 2.0619 8.1022 26.1910 | lr 9.7e-04 | norm 1.8960 | dt 0.026
type train | step 2870 | loss 0.1675 2.0455 8.2885 26.5989 | lr 9.7e-04 | norm 1.5544 | dt 0.026
type train | step 2880 | loss 0.1635 1.9831 7.9761 25.9489 | lr 9.7e-04 | norm 1.7189 | dt 0.026
type train | step 2890 | loss 0.1681 2.0330 8.1964 26.4845 | lr 9.7e-04 | norm 1.3748 | dt 0.026
type train | step 2900 | loss 0.1652 1.9622 7.7218 25.4479 | lr 9.7e-04 | norm 1.6188 | dt 0.026
type train | step 2910 | loss 0.1655 2.0077 8.0835 26.3603 | lr 9.7e-04 | norm 1.4502 | dt 0.025
type train | step 2920 | loss 0.1653 2.0238 8.2662 26.5191 | lr 9.7e-04 | norm 1.4788 | dt 0.026
type train | step 2930 | loss 0.1670 2.0279 8.2983 26.6767 | lr 9.7e-04 | norm 1.6059 | dt 0.026
type train | step 2940 | loss 0.1673 2.0177 8.0977 26.4832 | lr 9.7e-04 | norm 1.7054 | dt 0.026
type train | step 2950 | loss 0.1639 2.0489 8.3397 27.2096 | lr 9.7e-04 | norm 1.4768 | dt 0.026
type train | step 2960 | loss 0.1653 2.0334 8.2838 27.0875 | lr 9.7e-04 | norm 1.7123 | dt 0.026
type train | step 2970 | loss 0.1639 2.0299 8.2923 27.1634 | lr 9.7e-04 | norm 1.5569 | dt 0.025
type train | step 2980 | loss 0.1601 2.0075 7.9652 25.6195 | lr 9.7e-04 | norm 1.4522 | dt 0.026
type train | step 2990 | loss 0.1620 2.0516 8.2187 26.2488 | lr 9.7e-04 | norm 1.7391 | dt 0.026
type train | step 3000 | loss 0.1658 2.0146 8.1114 26.1319 | lr 9.7e-04 | norm 1.8953 | dt 0.026
type train | step 3010 | loss 0.1625 2.0496 8.4238 27.5460 | lr 9.7e-04 | norm 1.6010 | dt 0.026
type train | step 3020 | loss 0.1711 2.0188 7.9148 25.8499 | lr 9.7e-04 | norm 1.9562 | dt 0.026
type train | step 3030 | loss 0.1620 2.0104 8.1698 26.9361 | lr 9.7e-04 | norm 1.7166 | dt 0.027
type train | step 3040 | loss 0.1586 1.9923 8.0468 25.6543 | lr 9.7e-04 | norm 1.4341 | dt 0.026
type train | step 3050 | loss 0.1614 2.0266 8.3924 27.0492 | lr 9.7e-04 | norm 1.7612 | dt 0.029
type train | step 3060 | loss 0.1599 2.0108 8.1904 26.4921 | lr 9.7e-04 | norm 1.4298 | dt 0.026
type train | step 3070 | loss 0.1607 2.0368 8.2571 27.0517 | lr 9.7e-04 | norm 1.5612 | dt 0.026
type train | step 3080 | loss 0.1635 1.9675 7.8721 25.9023 | lr 9.7e-04 | norm 1.5606 | dt 0.026
type train | step 3090 | loss 0.1671 2.0380 8.2238 26.7843 | lr 9.7e-04 | norm 1.8043 | dt 0.026
type train | step 3100 | loss 0.1621 1.9962 7.9412 25.5676 | lr 9.7e-04 | norm 1.6090 | dt 0.026
type train | step 3110 | loss 0.1611 1.9875 8.1579 26.3025 | lr 9.7e-04 | norm 1.6271 | dt 0.026
type train | step 3120 | loss 0.1606 1.9886 7.9294 25.6254 | lr 9.7e-04 | norm 1.3099 | dt 0.026
type train | step 3130 | loss 0.1654 2.0629 8.5035 27.9316 | lr 9.7e-04 | norm 1.5899 | dt 0.026
type train | step 3140 | loss 0.1636 1.9878 7.9755 26.0652 | lr 9.7e-04 | norm 1.5579 | dt 0.027
type train | step 3150 | loss 0.1568 1.9317 7.8727 25.5900 | lr 9.7e-04 | norm 1.4952 | dt 0.026
type train | step 3160 | loss 0.1660 2.0039 8.1360 26.1283 | lr 9.7e-04 | norm 1.5511 | dt 0.026
type train | step 3170 | loss 0.1661 2.0077 7.9958 25.7525 | lr 9.7e-04 | norm 1.6593 | dt 0.026
type train | step 3180 | loss 0.1603 1.9609 7.9067 25.7465 | lr 9.7e-04 | norm 1.4114 | dt 0.026
type train | step 3190 | loss 0.1755 2.0313 7.8791 26.5201 | lr 9.6e-04 | norm 2.2908 | dt 0.026
type train | step 3200 | loss 0.1673 2.0167 8.1343 26.5688 | lr 9.6e-04 | norm 1.7721 | dt 0.026
type train | step 3210 | loss 0.1575 1.9672 8.0860 26.3114 | lr 9.6e-04 | norm 1.6683 | dt 0.026
type train | step 3220 | loss 0.1610 2.0178 8.0283 25.6851 | lr 9.6e-04 | norm 1.6327 | dt 0.026
type train | step 3230 | loss 0.1604 2.0182 8.0524 26.2224 | lr 9.6e-04 | norm 1.6979 | dt 0.026
type train | step 3240 | loss 0.1617 1.9561 7.9790 25.9111 | lr 9.6e-04 | norm 1.7811 | dt 0.026
type train | step 3250 | loss 0.1682 2.0442 8.1893 27.1328 | lr 9.6e-04 | norm 1.6092 | dt 0.026
type train | step 3260 | loss 0.1628 1.9594 7.9213 26.0541 | lr 9.6e-04 | norm 1.6741 | dt 0.027
type train | step 3270 | loss 0.1570 1.9605 8.0625 26.1116 | lr 9.6e-04 | norm 1.5421 | dt 0.026
type train | step 3280 | loss 0.1539 1.9902 8.0935 25.9076 | lr 9.6e-04 | norm 1.4979 | dt 0.027
type train | step 3290 | loss 0.1648 2.0735 8.2366 26.6636 | lr 9.6e-04 | norm 1.6743 | dt 0.026
type train | step 3300 | loss 0.1587 1.9366 7.8175 25.4421 | lr 9.6e-04 | norm 1.4624 | dt 0.027
type train | step 3310 | loss 0.1546 1.9630 7.9445 26.0303 | lr 9.6e-04 | norm 1.4730 | dt 0.026
type train | step 3320 | loss 0.1626 1.9530 7.7685 25.6453 | lr 9.6e-04 | norm 1.4584 | dt 0.027
type train | step 3330 | loss 0.1616 1.9767 8.0442 26.5036 | lr 9.6e-04 | norm 1.7488 | dt 0.026
type train | step 3340 | loss 0.1580 1.9629 7.8411 25.5370 | lr 9.6e-04 | norm 1.5789 | dt 0.027
type train | step 3350 | loss 0.1627 2.0708 8.1676 25.8867 | lr 9.6e-04 | norm 1.7390 | dt 0.026
type train | step 3360 | loss 0.1608 1.9567 7.9493 26.0923 | lr 9.6e-04 | norm 1.7670 | dt 0.027
type train | step 3370 | loss 0.1577 1.9555 8.0120 26.0949 | lr 9.6e-04 | norm 1.7052 | dt 0.026
type train | step 3380 | loss 0.1594 1.9941 8.1758 26.6167 | lr 9.6e-04 | norm 1.3779 | dt 0.026
type train | step 3390 | loss 0.1537 1.9525 8.1254 26.3965 | lr 9.6e-04 | norm 1.3791 | dt 0.027
type train | step 3400 | loss 0.1596 1.9788 8.0868 26.0763 | lr 9.6e-04 | norm 1.6930 | dt 0.026
type train | step 3410 | loss 0.1565 1.9020 7.7122 25.2956 | lr 9.6e-04 | norm 1.6314 | dt 0.026
type train | step 3420 | loss 0.1568 1.9753 7.8169 25.7743 | lr 9.6e-04 | norm 1.7433 | dt 0.026
type train | step 3430 | loss 0.1610 1.9766 7.9608 26.4181 | lr 9.6e-04 | norm 1.6659 | dt 0.027
type train | step 3440 | loss 0.1537 1.9949 8.2270 26.5594 | lr 9.6e-04 | norm 1.4880 | dt 0.027
type train | step 3450 | loss 0.1616 1.9613 7.8864 25.6263 | lr 9.6e-04 | norm 1.5319 | dt 0.027
type train | step 3460 | loss 0.1579 1.9788 7.9573 25.8749 | lr 9.6e-04 | norm 1.4048 | dt 0.027
type train | step 3470 | loss 0.1601 2.0016 7.9326 25.8058 | lr 9.6e-04 | norm 1.8441 | dt 0.027
type train | step 3480 | loss 0.1588 1.9873 8.1264 26.2279 | lr 9.6e-04 | norm 1.5291 | dt 0.030
type train | step 3490 | loss 0.1540 1.9278 7.8140 25.5350 | lr 9.6e-04 | norm 1.6832 | dt 0.033
type train | step 3500 | loss 0.1592 1.9802 8.0373 26.1061 | lr 9.6e-04 | norm 1.3221 | dt 0.035
type train | step 3510 | loss 0.1566 1.9136 7.6002 25.1060 | lr 9.6e-04 | norm 1.5740 | dt 0.032
type train | step 3520 | loss 0.1564 1.9492 7.9195 26.0027 | lr 9.5e-04 | norm 1.4090 | dt 0.032
type train | step 3530 | loss 0.1569 1.9693 8.1076 26.1496 | lr 9.5e-04 | norm 1.4238 | dt 0.032
type train | step 3540 | loss 0.1595 1.9740 8.1550 26.3074 | lr 9.5e-04 | norm 1.5796 | dt 0.032
type train | step 3550 | loss 0.1590 1.9689 7.9535 26.1061 | lr 9.5e-04 | norm 1.6697 | dt 0.032
type train | step 3560 | loss 0.1557 2.0108 8.1840 26.8658 | lr 9.5e-04 | norm 1.4558 | dt 0.032
type train | step 3570 | loss 0.1573 1.9814 8.1408 26.7613 | lr 9.5e-04 | norm 1.6793 | dt 0.032
type train | step 3580 | loss 0.1554 1.9758 8.1348 26.8183 | lr 9.5e-04 | norm 1.5225 | dt 0.032
type train | step 3590 | loss 0.1523 1.9574 7.8181 25.2542 | lr 9.5e-04 | norm 1.3955 | dt 0.032
type train | step 3600 | loss 0.1534 1.9969 8.0536 25.8925 | lr 9.5e-04 | norm 1.6834 | dt 0.032
type train | step 3610 | loss 0.1582 1.9565 7.9664 25.7917 | lr 9.5e-04 | norm 1.8582 | dt 0.029
type train | step 3620 | loss 0.1531 2.0024 8.2884 27.2222 | lr 9.5e-04 | norm 1.5537 | dt 0.026
type train | step 3630 | loss 0.1630 1.9657 7.7789 25.5188 | lr 9.5e-04 | norm 1.9043 | dt 0.026
type train | step 3640 | loss 0.1546 1.9593 8.0327 26.5966 | lr 9.5e-04 | norm 1.6780 | dt 0.026
type train | step 3650 | loss 0.1512 1.9415 7.8986 25.3251 | lr 9.5e-04 | norm 1.3983 | dt 0.026
type train | step 3660 | loss 0.1532 1.9787 8.2729 26.7220 | lr 9.5e-04 | norm 1.7297 | dt 0.027
type train | step 3670 | loss 0.1524 1.9597 8.0408 26.1136 | lr 9.5e-04 | norm 1.3924 | dt 0.026
type train | step 3680 | loss 0.1522 2.0004 8.1322 26.7296 | lr 9.5e-04 | norm 1.5381 | dt 0.025
type train | step 3690 | loss 0.1557 1.9110 7.7425 25.5711 | lr 9.5e-04 | norm 1.5195 | dt 0.026
type train | step 3700 | loss 0.1592 1.9933 8.0857 26.4486 | lr 9.5e-04 | norm 1.7686 | dt 0.026
type train | step 3710 | loss 0.1546 1.9527 7.8043 25.2706 | lr 9.5e-04 | norm 1.6000 | dt 0.026
type train | step 3720 | loss 0.1531 1.9460 8.0344 26.0094 | lr 9.5e-04 | norm 1.5966 | dt 0.026
type train | step 3730 | loss 0.1529 1.9481 7.7857 25.2865 | lr 9.5e-04 | norm 1.2795 | dt 0.026
type train | step 3740 | loss 0.1574 2.0182 8.3476 27.5660 | lr 9.5e-04 | norm 1.5663 | dt 0.026
type train | step 3750 | loss 0.1564 1.9499 7.8358 25.7523 | lr 9.5e-04 | norm 1.5411 | dt 0.026
type train | step 3760 | loss 0.1487 1.8977 7.7446 25.2728 | lr 9.5e-04 | norm 1.4518 | dt 0.026
type train | step 3770 | loss 0.1596 1.9658 7.9785 25.7942 | lr 9.5e-04 | norm 1.5207 | dt 0.026
type train | step 3780 | loss 0.1595 1.9646 7.8381 25.4306 | lr 9.5e-04 | norm 1.6012 | dt 0.026
type train | step 3790 | loss 0.1534 1.9226 7.7581 25.4310 | lr 9.5e-04 | norm 1.3724 | dt 0.026
type train | step 3800 | loss 0.1663 2.0040 7.7254 26.2233 | lr 9.5e-04 | norm 2.2616 | dt 0.026
type train | step 3810 | loss 0.1606 1.9754 8.0088 26.2319 | lr 9.5e-04 | norm 1.7142 | dt 0.026
type train | step 3820 | loss 0.1504 1.9389 7.9724 25.9951 | lr 9.4e-04 | norm 1.5899 | dt 0.026
type train | step 3830 | loss 0.1539 1.9821 7.9053 25.3899 | lr 9.4e-04 | norm 1.5980 | dt 0.026
type train | step 3840 | loss 0.1527 1.9825 7.8903 25.8940 | lr 9.4e-04 | norm 1.6481 | dt 0.026
type train | step 3850 | loss 0.1555 1.9192 7.8018 25.5950 | lr 9.4e-04 | norm 1.7575 | dt 0.027
type train | step 3860 | loss 0.1611 2.0085 8.0698 26.8111 | lr 9.4e-04 | norm 1.5763 | dt 0.026
type train | step 3870 | loss 0.1562 1.9289 7.7731 25.7725 | lr 9.4e-04 | norm 1.6412 | dt 0.026
type train | step 3880 | loss 0.1501 1.9244 7.9531 25.8149 | lr 9.4e-04 | norm 1.5271 | dt 0.026
type train | step 3890 | loss 0.1473 1.9589 7.9906 25.5813 | lr 9.4e-04 | norm 1.4485 | dt 0.026
type train | step 3900 | loss 0.1574 2.0362 8.0892 26.3246 | lr 9.4e-04 | norm 1.6098 | dt 0.026
type train | step 3910 | loss 0.1526 1.9010 7.6876 25.1371 | lr 9.4e-04 | norm 1.4231 | dt 0.026
type train | step 3920 | loss 0.1487 1.9336 7.8344 25.7251 | lr 9.4e-04 | norm 1.4284 | dt 0.026
type train | step 3930 | loss 0.1560 1.9188 7.6343 25.4091 | lr 9.4e-04 | norm 1.4400 | dt 0.026
type train | step 3940 | loss 0.1548 1.9444 7.9025 26.2142 | lr 9.4e-04 | norm 1.7047 | dt 0.026
type train | step 3950 | loss 0.1520 1.9389 7.7257 25.2639 | lr 9.4e-04 | norm 1.5498 | dt 0.026
type train | step 3960 | loss 0.1564 2.0344 8.0011 25.5528 | lr 9.4e-04 | norm 1.6853 | dt 0.026
type train | step 3970 | loss 0.1551 1.9158 7.8182 25.7870 | lr 9.4e-04 | norm 1.6966 | dt 0.026
type train | step 3980 | loss 0.1516 1.9233 7.8898 25.7995 | lr 9.4e-04 | norm 1.6395 | dt 0.026
type train | step 3990 | loss 0.1522 1.9642 8.0615 26.3306 | lr 9.4e-04 | norm 1.3685 | dt 0.026
type train | step 4000 | loss 0.1477 1.9314 8.0271 26.1422 | lr 9.4e-04 | norm 1.3622 | dt 0.026
type train | step 4010 | loss 0.1532 1.9566 7.9760 25.7637 | lr 9.4e-04 | norm 1.6440 | dt 0.035
type train | step 4020 | loss 0.1498 1.8846 7.5701 24.9561 | lr 9.4e-04 | norm 1.6062 | dt 0.035
type train | step 4030 | loss 0.1502 1.9456 7.7003 25.4858 | lr 9.4e-04 | norm 1.6871 | dt 0.035
type train | step 4040 | loss 0.1552 1.9488 7.8273 26.1936 | lr 9.4e-04 | norm 1.6413 | dt 0.035
type train | step 4050 | loss 0.1473 1.9708 8.1059 26.2893 | lr 9.4e-04 | norm 1.4265 | dt 0.035
type train | step 4060 | loss 0.1565 1.9387 7.7798 25.3433 | lr 9.4e-04 | norm 1.5340 | dt 0.035
type train | step 4070 | loss 0.1520 1.9530 7.8501 25.5780 | lr 9.4e-04 | norm 1.3583 | dt 0.035
type train | step 4080 | loss 0.1544 1.9778 7.7791 25.5339 | lr 9.4e-04 | norm 1.7851 | dt 0.035
type train | step 4090 | loss 0.1523 1.9657 7.9967 25.9552 | lr 9.3e-04 | norm 1.4728 | dt 0.035
type train | step 4100 | loss 0.1483 1.9064 7.7043 25.2125 | lr 9.3e-04 | norm 1.6457 | dt 0.035
type train | step 4110 | loss 0.1532 1.9593 7.9322 25.8804 | lr 9.3e-04 | norm 1.2990 | dt 0.035
type train | step 4120 | loss 0.1497 1.8960 7.5058 24.8491 | lr 9.3e-04 | norm 1.5540 | dt 0.035
type train | step 4130 | loss 0.1505 1.9284 7.8259 25.7482 | lr 9.3e-04 | norm 1.3859 | dt 0.035
type train | step 4140 | loss 0.1509 1.9535 7.9702 25.8613 | lr 9.3e-04 | norm 1.3960 | dt 0.035
type train | step 4150 | loss 0.1527 1.9585 8.0523 26.0266 | lr 9.3e-04 | norm 1.5157 | dt 0.034
type train | step 4160 | loss 0.1532 1.9466 7.8543 25.8446 | lr 9.3e-04 | norm 1.6463 | dt 0.034
type train | step 4170 | loss 0.1495 1.9936 8.0689 26.6417 | lr 9.3e-04 | norm 1.4229 | dt 0.034
type train | step 4180 | loss 0.1518 1.9662 8.0488 26.4818 | lr 9.3e-04 | norm 1.6676 | dt 0.034
type train | step 4190 | loss 0.1491 1.9621 8.0310 26.5510 | lr 9.3e-04 | norm 1.4684 | dt 0.034
type train | step 4200 | loss 0.1462 1.9450 7.7213 25.0016 | lr 9.3e-04 | norm 1.3736 | dt 0.033
type train | step 4210 | loss 0.1475 1.9784 7.9416 25.6559 | lr 9.3e-04 | norm 1.6373 | dt 0.033
type train | step 4220 | loss 0.1524 1.9323 7.8662 25.5328 | lr 9.3e-04 | norm 1.8249 | dt 0.034
type train | step 4230 | loss 0.1471 1.9918 8.1865 26.9441 | lr 9.3e-04 | norm 1.5197 | dt 0.033
type train | step 4240 | loss 0.1570 1.9467 7.7034 25.2824 | lr 9.3e-04 | norm 1.8653 | dt 0.029
type train | step 4250 | loss 0.1481 1.9416 7.9417 26.3341 | lr 9.3e-04 | norm 1.6373 | dt 0.027
type train | step 4260 | loss 0.1461 1.9347 7.8106 25.0597 | lr 9.3e-04 | norm 1.3696 | dt 0.026
type train | step 4270 | loss 0.1485 1.9756 8.1822 26.4895 | lr 9.3e-04 | norm 1.6892 | dt 0.028
type train | step 4280 | loss 0.1468 1.9473 7.9466 25.8529 | lr 9.3e-04 | norm 1.3852 | dt 0.026
type train | step 4290 | loss 0.1460 1.9846 8.0373 26.4557 | lr 9.3e-04 | norm 1.4955 | dt 0.026
type train | step 4300 | loss 0.1500 1.8934 7.6687 25.2694 | lr 9.3e-04 | norm 1.4991 | dt 0.026
type train | step 4310 | loss 0.1538 1.9734 7.9976 26.1719 | lr 9.3e-04 | norm 1.7367 | dt 0.026
type train | step 4320 | loss 0.1491 1.9420 7.7032 24.9997 | lr 9.3e-04 | norm 1.5410 | dt 0.026
type train | step 4330 | loss 0.1474 1.9352 7.9402 25.7790 | lr 9.3e-04 | norm 1.5803 | dt 0.026
type train | step 4340 | loss 0.1475 1.9396 7.7024 25.0543 | lr 9.2e-04 | norm 1.2542 | dt 0.026
type train | step 4350 | loss 0.1520 1.9967 8.2766 27.2939 | lr 9.2e-04 | norm 1.5243 | dt 0.026
type train | step 4360 | loss 0.1509 1.9348 7.7774 25.5076 | lr 9.2e-04 | norm 1.5191 | dt 0.026
type train | step 4370 | loss 0.1435 1.8867 7.6538 25.0037 | lr 9.2e-04 | norm 1.4246 | dt 0.026
type train | step 4380 | loss 0.1535 1.9528 7.8887 25.5435 | lr 9.2e-04 | norm 1.4786 | dt 0.026
type train | step 4390 | loss 0.1535 1.9522 7.7168 25.1418 | lr 9.2e-04 | norm 1.5742 | dt 0.026
type train | step 4400 | loss 0.1481 1.9131 7.6768 25.2307 | lr 9.2e-04 | norm 1.3497 | dt 0.026
type train | step 4410 | loss 0.1597 1.9783 7.6625 25.9534 | lr 9.2e-04 | norm 2.2375 | dt 0.026
type train | step 4420 | loss 0.1549 1.9594 7.9181 26.0210 | lr 9.2e-04 | norm 1.6923 | dt 0.027
type train | step 4430 | loss 0.1453 1.9304 7.8925 25.7689 | lr 9.2e-04 | norm 1.5492 | dt 0.026
type train | step 4440 | loss 0.1480 1.9732 7.8280 25.1275 | lr 9.2e-04 | norm 1.5662 | dt 0.027
type train | step 4450 | loss 0.1476 1.9755 7.7805 25.6057 | lr 9.2e-04 | norm 1.6004 | dt 0.026
type train | step 4460 | loss 0.1509 1.9081 7.7164 25.4085 | lr 9.2e-04 | norm 1.7035 | dt 0.026
type train | step 4470 | loss 0.1549 1.9868 8.0028 26.5603 | lr 9.2e-04 | norm 1.5070 | dt 0.026
type train | step 4480 | loss 0.1493 1.9117 7.7097 25.5786 | lr 9.2e-04 | norm 1.6139 | dt 0.026
type train | step 4490 | loss 0.1435 1.9110 7.8613 25.5644 | lr 9.2e-04 | norm 1.4630 | dt 0.026
type train | step 4500 | loss 0.1400 1.9449 7.9125 25.3406 | lr 9.2e-04 | norm 1.3977 | dt 0.026
type train | step 4510 | loss 0.1495 2.0217 7.9913 26.0382 | lr 9.2e-04 | norm 1.5684 | dt 0.027
type train | step 4520 | loss 0.1452 1.8897 7.6030 24.9060 | lr 9.2e-04 | norm 1.4227 | dt 0.027
type train | step 4530 | loss 0.1419 1.9213 7.7706 25.5166 | lr 9.2e-04 | norm 1.4238 | dt 0.027
type train | step 4540 | loss 0.1475 1.9037 7.5883 25.2043 | lr 9.2e-04 | norm 1.4234 | dt 0.026
type train | step 4550 | loss 0.1479 1.9281 7.8217 25.9912 | lr 9.2e-04 | norm 1.6678 | dt 0.027
type train | step 4560 | loss 0.1445 1.9247 7.6470 25.0342 | lr 9.2e-04 | norm 1.5232 | dt 0.027
type train | step 4570 | loss 0.1481 2.0235 7.9091 25.2684 | lr 9.2e-04 | norm 1.6444 | dt 0.027
type train | step 4580 | loss 0.1478 1.9025 7.7570 25.5474 | lr 9.1e-04 | norm 1.6776 | dt 0.027
type train | step 4590 | loss 0.1442 1.9025 7.8223 25.5545 | lr 9.1e-04 | norm 1.6206 | dt 0.027
type train | step 4600 | loss 0.1449 1.9490 7.9990 26.1519 | lr 9.1e-04 | norm 1.3315 | dt 0.027
type train | step 4610 | loss 0.1403 1.9161 7.9563 25.8963 | lr 9.1e-04 | norm 1.3506 | dt 0.027
type train | step 4620 | loss 0.1454 1.9361 7.8854 25.5621 | lr 9.1e-04 | norm 1.5826 | dt 0.027
type train | step 4630 | loss 0.1421 1.8692 7.4804 24.7186 | lr 9.1e-04 | norm 1.5550 | dt 0.026
type train | step 4640 | loss 0.1437 1.9271 7.6089 25.2933 | lr 9.1e-04 | norm 1.6588 | dt 0.027
type train | step 4650 | loss 0.1483 1.9281 7.7440 26.0299 | lr 9.1e-04 | norm 1.6154 | dt 0.027
type train | step 4660 | loss 0.1396 1.9545 8.0382 26.1289 | lr 9.1e-04 | norm 1.3998 | dt 0.027
type train | step 4670 | loss 0.1499 1.9103 7.7263 25.1396 | lr 9.1e-04 | norm 1.5175 | dt 0.027
type train | step 4680 | loss 0.1441 1.9324 7.7936 25.3708 | lr 9.1e-04 | norm 1.3519 | dt 0.026
type train | step 4690 | loss 0.1471 1.9506 7.6903 25.3019 | lr 9.1e-04 | norm 1.7442 | dt 0.026
type train | step 4700 | loss 0.1451 1.9547 7.9114 25.7490 | lr 9.1e-04 | norm 1.4203 | dt 0.027
type train | step 4710 | loss 0.1415 1.8893 7.6428 25.0388 | lr 9.1e-04 | norm 1.6166 | dt 0.027
type train | step 4720 | loss 0.1458 1.9390 7.8456 25.7038 | lr 9.1e-04 | norm 1.2984 | dt 0.026
type train | step 4730 | loss 0.1431 1.8730 7.4626 24.6818 | lr 9.1e-04 | norm 1.5260 | dt 0.027
type train | step 4740 | loss 0.1436 1.9072 7.7589 25.5557 | lr 9.1e-04 | norm 1.3888 | dt 0.026
type train | step 4750 | loss 0.1444 1.9316 7.8781 25.6382 | lr 9.1e-04 | norm 1.3469 | dt 0.027
type train | step 4760 | loss 0.1450 1.9436 7.9672 25.8401 | lr 9.1e-04 | norm 1.4853 | dt 0.029
type train | step 4770 | loss 0.1465 1.9310 7.7909 25.6716 | lr 9.1e-04 | norm 1.6068 | dt 0.029
type train | step 4780 | loss 0.1426 1.9698 7.9973 26.4302 | lr 9.1e-04 | norm 1.3837 | dt 0.035
type train | step 4790 | loss 0.1448 1.9364 7.9861 26.2290 | lr 9.1e-04 | norm 1.6343 | dt 0.036
type train | step 4800 | loss 0.1417 1.9342 7.9605 26.3804 | lr 9.1e-04 | norm 1.4661 | dt 0.035
type train | step 4810 | loss 0.1398 1.9258 7.6348 24.8133 | lr 9.0e-04 | norm 1.3634 | dt 0.035
type train | step 4820 | loss 0.1402 1.9604 7.8572 25.4627 | lr 9.0e-04 | norm 1.5768 | dt 0.036
type train | step 4830 | loss 0.1462 1.9057 7.7981 25.3508 | lr 9.0e-04 | norm 1.8003 | dt 0.035
type train | step 4840 | loss 0.1399 1.9692 8.1074 26.7865 | lr 9.0e-04 | norm 1.4962 | dt 0.035
type train | step 4850 | loss 0.1495 1.9239 7.6333 25.0651 | lr 9.0e-04 | norm 1.8473 | dt 0.035
type train | step 4860 | loss 0.1415 1.9205 7.8656 26.1601 | lr 9.0e-04 | norm 1.6003 | dt 0.035
type train | step 4870 | loss 0.1386 1.9190 7.7138 24.9019 | lr 9.0e-04 | norm 1.3556 | dt 0.035
type train | step 4880 | loss 0.1420 1.9449 8.1215 26.2949 | lr 9.0e-04 | norm 1.6537 | dt 0.037
type train | step 4890 | loss 0.1396 1.9218 7.8804 25.6595 | lr 9.0e-04 | norm 1.3796 | dt 0.035
type train | step 4900 | loss 0.1390 1.9640 7.9785 26.2571 | lr 9.0e-04 | norm 1.4742 | dt 0.036
type train | step 4910 | loss 0.1425 1.8652 7.6204 25.0359 | lr 9.0e-04 | norm 1.4610 | dt 0.035
type train | step 4920 | loss 0.1464 1.9485 7.9187 25.9989 | lr 9.0e-04 | norm 1.7108 | dt 0.035
type train | step 4930 | loss 0.1422 1.9195 7.6108 24.8155 | lr 9.0e-04 | norm 1.5091 | dt 0.036
type train | step 4940 | loss 0.1405 1.9161 7.8718 25.6160 | lr 9.0e-04 | norm 1.5151 | dt 0.035
type train | step 4950 | loss 0.1401 1.9197 7.6318 24.9056 | lr 9.0e-04 | norm 1.2256 | dt 0.035
type train | step 4960 | loss 0.1457 1.9751 8.1975 27.1379 | lr 9.0e-04 | norm 1.4837 | dt 0.035
type train | step 4970 | loss 0.1442 1.9093 7.7353 25.2973 | lr 9.0e-04 | norm 1.4966 | dt 0.035
type train | step 4980 | loss 0.1364 1.8658 7.5925 24.8381 | lr 9.0e-04 | norm 1.3936 | dt 0.035
type train | step 4990 | loss 0.1456 1.9335 7.8147 25.3517 | lr 9.0e-04 | norm 1.4410 | dt 0.035
type train | step 5000 | loss 0.1467 1.9278 7.6635 24.9792 | lr 9.0e-04 | norm 1.5337 | dt 0.035
type train | step 5010 | loss 0.1408 1.8912 7.5999 25.0405 | lr 9.0e-04 | norm 1.3408 | dt 0.033
type train | step 5020 | loss 0.1516 1.9489 7.6056 25.7841 | lr 9.0e-04 | norm 2.1884 | dt 0.033
type train | step 5030 | loss 0.1478 1.9389 7.8474 25.8645 | lr 8.9e-04 | norm 1.6697 | dt 0.033
type train | step 5040 | loss 0.1380 1.9004 7.8251 25.6091 | lr 8.9e-04 | norm 1.5070 | dt 0.032
type train | step 5050 | loss 0.1404 1.9542 7.7476 24.9615 | lr 8.9e-04 | norm 1.5287 | dt 0.033
type train | step 5060 | loss 0.1403 1.9474 7.6962 25.4136 | lr 8.9e-04 | norm 1.5712 | dt 0.032
type train | step 5070 | loss 0.1443 1.8850 7.6514 25.2183 | lr 8.9e-04 | norm 1.6897 | dt 0.032
type train | step 5080 | loss 0.1471 1.9569 7.9627 26.4271 | lr 8.9e-04 | norm 1.5048 | dt 0.032
type train | step 5090 | loss 0.1432 1.8900 7.6439 25.5118 | lr 8.9e-04 | norm 1.5758 | dt 0.033
type train | step 5100 | loss 0.1380 1.8963 7.7880 25.4260 | lr 8.9e-04 | norm 1.4470 | dt 0.029
type train | step 5110 | loss 0.1352 1.9286 7.8426 25.1841 | lr 8.9e-04 | norm 1.3962 | dt 0.026
type train | step 5120 | loss 0.1442 1.9929 7.9123 25.8554 | lr 8.9e-04 | norm 1.5369 | dt 0.026
type train | step 5130 | loss 0.1400 1.8654 7.5388 24.7456 | lr 8.9e-04 | norm 1.3607 | dt 0.026
type train | step 5140 | loss 0.1368 1.8965 7.6876 25.3528 | lr 8.9e-04 | norm 1.4050 | dt 0.026
type train | step 5150 | loss 0.1430 1.8826 7.5200 25.0822 | lr 8.9e-04 | norm 1.4064 | dt 0.026
type train | step 5160 | loss 0.1430 1.8996 7.7507 25.8398 | lr 8.9e-04 | norm 1.6370 | dt 0.025
type train | step 5170 | loss 0.1400 1.8964 7.5753 24.8987 | lr 8.9e-04 | norm 1.4786 | dt 0.026
type train | step 5180 | loss 0.1434 1.9884 7.8244 25.1221 | lr 8.9e-04 | norm 1.6169 | dt 0.026
type train | step 5190 | loss 0.1427 1.8834 7.6765 25.4101 | lr 8.9e-04 | norm 1.6571 | dt 0.026
type train | step 5200 | loss 0.1394 1.8818 7.7416 25.4476 | lr 8.9e-04 | norm 1.5890 | dt 0.026
type train | step 5210 | loss 0.1404 1.9321 7.9361 26.0144 | lr 8.9e-04 | norm 1.3078 | dt 0.026
type train | step 5220 | loss 0.1356 1.9005 7.8996 25.7423 | lr 8.9e-04 | norm 1.3232 | dt 0.026
type train | step 5230 | loss 0.1409 1.9052 7.8166 25.4102 | lr 8.8e-04 | norm 1.5583 | dt 0.026
type train | step 5240 | loss 0.1377 1.8496 7.4218 24.5738 | lr 8.8e-04 | norm 1.5178 | dt 0.026
type train | step 5250 | loss 0.1389 1.9104 7.5341 25.1604 | lr 8.8e-04 | norm 1.6334 | dt 0.027
type train | step 5260 | loss 0.1440 1.9061 7.6860 25.8947 | lr 8.8e-04 | norm 1.5870 | dt 0.026
type train | step 5270 | loss 0.1353 1.9377 7.9665 26.0363 | lr 8.8e-04 | norm 1.3796 | dt 0.026
type train | step 5280 | loss 0.1455 1.8945 7.6783 25.0015 | lr 8.8e-04 | norm 1.4730 | dt 0.026
type train | step 5290 | loss 0.1386 1.9099 7.7273 25.2408 | lr 8.8e-04 | norm 1.3271 | dt 0.026
type train | step 5300 | loss 0.1430 1.9317 7.6346 25.1546 | lr 8.8e-04 | norm 1.7174 | dt 0.025
type train | step 5310 | loss 0.1407 1.9353 7.8439 25.6123 | lr 8.8e-04 | norm 1.4062 | dt 0.026
type train | step 5320 | loss 0.1375 1.8745 7.5917 24.9087 | lr 8.8e-04 | norm 1.6136 | dt 0.026
type train | step 5330 | loss 0.1417 1.9230 7.7875 25.6134 | lr 8.8e-04 | norm 1.2831 | dt 0.026
type train | step 5340 | loss 0.1385 1.8511 7.4162 24.5772 | lr 8.8e-04 | norm 1.4963 | dt 0.028
type train | step 5350 | loss 0.1395 1.8822 7.7197 25.4517 | lr 8.8e-04 | norm 1.3730 | dt 0.036
type train | step 5360 | loss 0.1402 1.9160 7.8265 25.5132 | lr 8.8e-04 | norm 1.3294 | dt 0.035
type train | step 5370 | loss 0.1411 1.9232 7.9147 25.6978 | lr 8.8e-04 | norm 1.4712 | dt 0.035
type train | step 5380 | loss 0.1422 1.9168 7.7547 25.5458 | lr 8.8e-04 | norm 1.5902 | dt 0.035
type train | step 5390 | loss 0.1385 1.9569 7.9361 26.3015 | lr 8.8e-04 | norm 1.3665 | dt 0.035
type train | step 5400 | loss 0.1406 1.9194 7.9541 26.0826 | lr 8.8e-04 | norm 1.5969 | dt 0.035
type train | step 5410 | loss 0.1381 1.9173 7.9041 26.2838 | lr 8.8e-04 | norm 1.4508 | dt 0.035
type train | step 5420 | loss 0.1350 1.9101 7.5780 24.7084 | lr 8.8e-04 | norm 1.3496 | dt 0.035
type train | step 5430 | loss 0.1358 1.9498 7.8017 25.3327 | lr 8.8e-04 | norm 1.5697 | dt 0.035
type train | step 5440 | loss 0.1415 1.8902 7.7552 25.2739 | lr 8.7e-04 | norm 1.7860 | dt 0.035
type train | step 5450 | loss 0.1359 1.9544 8.0465 26.6377 | lr 8.7e-04 | norm 1.4715 | dt 0.035
type train | step 5460 | loss 0.1449 1.9146 7.5939 24.9595 | lr 8.7e-04 | norm 1.8154 | dt 0.035
type train | step 5470 | loss 0.1371 1.9004 7.8080 26.0848 | lr 8.7e-04 | norm 1.5627 | dt 0.035
type train | step 5480 | loss 0.1344 1.9084 7.6580 24.8156 | lr 8.7e-04 | norm 1.3429 | dt 0.035
type train | step 5490 | loss 0.1376 1.9387 8.0731 26.1364 | lr 8.7e-04 | norm 1.6374 | dt 0.037
type train | step 5500 | loss 0.1359 1.9118 7.8420 25.5557 | lr 8.7e-04 | norm 1.3564 | dt 0.036
type train | step 5510 | loss 0.1350 1.9506 7.9256 26.1416 | lr 8.7e-04 | norm 1.4597 | dt 0.026
type train | step 5520 | loss 0.1383 1.8544 7.5661 24.9321 | lr 8.7e-04 | norm 1.4300 | dt 0.026
type train | step 5530 | loss 0.1419 1.9313 7.8572 25.9190 | lr 8.7e-04 | norm 1.6790 | dt 0.026
type train | step 5540 | loss 0.1381 1.9077 7.5554 24.7124 | lr 8.7e-04 | norm 1.4702 | dt 0.025
type train | step 5550 | loss 0.1364 1.9045 7.8264 25.5240 | lr 8.7e-04 | norm 1.5084 | dt 0.026
type train | step 5560 | loss 0.1365 1.9083 7.5923 24.7789 | lr 8.7e-04 | norm 1.2171 | dt 0.026
type train | step 5570 | loss 0.1415 1.9626 8.1518 26.9988 | lr 8.7e-04 | norm 1.4592 | dt 0.027
type train | step 5580 | loss 0.1397 1.8975 7.6769 25.1986 | lr 8.7e-04 | norm 1.4873 | dt 0.026
type train | step 5590 | loss 0.1323 1.8507 7.5363 24.7362 | lr 8.7e-04 | norm 1.3443 | dt 0.026
type train | step 5600 | loss 0.1406 1.9204 7.7760 25.2221 | lr 8.7e-04 | norm 1.4366 | dt 0.026
type train | step 5610 | loss 0.1432 1.9084 7.6116 24.9041 | lr 8.7e-04 | norm 1.5246 | dt 0.026
type train | step 5620 | loss 0.1370 1.8769 7.5515 24.9233 | lr 8.7e-04 | norm 1.3249 | dt 0.026
type train | step 5630 | loss 0.1482 1.9262 7.5655 25.6757 | lr 8.6e-04 | norm 2.1463 | dt 0.026
type train | step 5640 | loss 0.1437 1.9258 7.8082 25.7432 | lr 8.6e-04 | norm 1.6336 | dt 0.026
type train | step 5650 | loss 0.1341 1.8836 7.7667 25.5384 | lr 8.6e-04 | norm 1.4753 | dt 0.026
type train | step 5660 | loss 0.1363 1.9411 7.7016 24.8659 | lr 8.6e-04 | norm 1.5272 | dt 0.026
type train | step 5670 | loss 0.1362 1.9314 7.6509 25.3291 | lr 8.6e-04 | norm 1.5367 | dt 0.026
type train | step 5680 | loss 0.1398 1.8754 7.6225 25.0892 | lr 8.6e-04 | norm 1.6736 | dt 0.026
type train | step 5690 | loss 0.1436 1.9374 7.9149 26.3089 | lr 8.6e-04 | norm 1.4734 | dt 0.026
type train | step 5700 | loss 0.1392 1.8776 7.5884 25.4216 | lr 8.6e-04 | norm 1.5557 | dt 0.026
type train | step 5710 | loss 0.1337 1.8756 7.7322 25.3439 | lr 8.6e-04 | norm 1.3896 | dt 0.026
type train | step 5720 | loss 0.1313 1.9204 7.7814 25.0797 | lr 8.6e-04 | norm 1.3453 | dt 0.026
type train | step 5730 | loss 0.1400 1.9768 7.8522 25.7690 | lr 8.6e-04 | norm 1.5085 | dt 0.026
type train | step 5740 | loss 0.1364 1.8528 7.4997 24.6729 | lr 8.6e-04 | norm 1.3458 | dt 0.026
type train | step 5750 | loss 0.1332 1.8707 7.6260 25.2878 | lr 8.6e-04 | norm 1.3916 | dt 0.026
type train | step 5760 | loss 0.1392 1.8676 7.4631 24.9530 | lr 8.6e-04 | norm 1.3787 | dt 0.028
type train | step 5770 | loss 0.1390 1.8806 7.6862 25.7547 | lr 8.6e-04 | norm 1.6130 | dt 0.027
type train | step 5780 | loss 0.1361 1.8777 7.5276 24.8104 | lr 8.6e-04 | norm 1.4574 | dt 0.027
type train | step 5790 | loss 0.1397 1.9698 7.7783 25.0344 | lr 8.6e-04 | norm 1.6083 | dt 0.027
type train | step 5800 | loss 0.1389 1.8657 7.6277 25.3208 | lr 8.6e-04 | norm 1.6585 | dt 0.027
type train | step 5810 | loss 0.1359 1.8547 7.6998 25.3789 | lr 8.6e-04 | norm 1.5742 | dt 0.027
type train | step 5820 | loss 0.1361 1.9132 7.8887 25.9061 | lr 8.5e-04 | norm 1.2865 | dt 0.027
type train | step 5830 | loss 0.1321 1.8791 7.8364 25.6199 | lr 8.5e-04 | norm 1.2929 | dt 0.033
type train | step 5840 | loss 0.1367 1.8936 7.7551 25.3314 | lr 8.5e-04 | norm 1.5246 | dt 0.036
type train | step 5850 | loss 0.1342 1.8353 7.3819 24.4597 | lr 8.5e-04 | norm 1.5242 | dt 0.035
type train | step 5860 | loss 0.1349 1.8966 7.4828 25.0836 | lr 8.5e-04 | norm 1.6503 | dt 0.035
type train | step 5870 | loss 0.1400 1.8881 7.6427 25.7948 | lr 8.5e-04 | norm 1.5816 | dt 0.035
type train | step 5880 | loss 0.1316 1.9183 7.9210 25.9296 | lr 8.5e-04 | norm 1.3647 | dt 0.035
type train | step 5890 | loss 0.1417 1.8774 7.6437 24.9034 | lr 8.5e-04 | norm 1.4818 | dt 0.036
type train | step 5900 | loss 0.1341 1.8903 7.6771 25.1604 | lr 8.5e-04 | norm 1.3263 | dt 0.035
type train | step 5910 | loss 0.1392 1.9119 7.5937 25.0604 | lr 8.5e-04 | norm 1.7079 | dt 0.035
type train | step 5920 | loss 0.1369 1.9198 7.7978 25.5347 | lr 8.5e-04 | norm 1.3954 | dt 0.035
type train | step 5930 | loss 0.1341 1.8491 7.5329 24.8078 | lr 8.5e-04 | norm 1.5822 | dt 0.035
type train | step 5940 | loss 0.1378 1.9050 7.7537 25.5131 | lr 8.5e-04 | norm 1.2449 | dt 0.035
type train | step 5950 | loss 0.1349 1.8414 7.3697 24.4731 | lr 8.5e-04 | norm 1.4687 | dt 0.036
type train | step 5960 | loss 0.1351 1.8561 7.6783 25.3982 | lr 8.5e-04 | norm 1.3653 | dt 0.035
type train | step 5970 | loss 0.1368 1.9024 7.7885 25.4291 | lr 8.5e-04 | norm 1.3103 | dt 0.035
type train | step 5980 | loss 0.1371 1.9083 7.8667 25.5999 | lr 8.5e-04 | norm 1.4502 | dt 0.035
type train | step 5990 | loss 0.1386 1.8831 7.7135 25.4331 | lr 8.5e-04 | norm 1.5773 | dt 0.035
type train | step 6000 | loss 0.1345 1.9369 7.9025 26.2119 | lr 8.4e-04 | norm 1.3497 | dt 0.035
type train | step 6010 | loss 0.1368 1.8962 7.9102 25.9918 | lr 8.4e-04 | norm 1.5863 | dt 0.033
type train | step 6020 | loss 0.1342 1.8890 7.8596 26.2300 | lr 8.4e-04 | norm 1.4122 | dt 0.032
type train | step 6030 | loss 0.1310 1.8867 7.5294 24.6211 | lr 8.4e-04 | norm 1.3235 | dt 0.033
type train | step 6040 | loss 0.1320 1.9334 7.7573 25.2519 | lr 8.4e-04 | norm 1.5488 | dt 0.033
type train | step 6050 | loss 0.1384 1.8641 7.7059 25.2345 | lr 8.4e-04 | norm 1.7496 | dt 0.030
type train | step 6060 | loss 0.1321 1.9295 7.9946 26.5147 | lr 8.4e-04 | norm 1.4574 | dt 0.031
type train | step 6070 | loss 0.1407 1.8936 7.5381 24.9172 | lr 8.4e-04 | norm 1.7931 | dt 0.028
type train | step 6080 | loss 0.1336 1.8708 7.7659 26.0111 | lr 8.4e-04 | norm 1.5463 | dt 0.026
type train | step 6090 | loss 0.1304 1.8936 7.6070 24.7184 | lr 8.4e-04 | norm 1.3235 | dt 0.026
type train | step 6100 | loss 0.1338 1.9126 8.0370 26.0694 | lr 8.4e-04 | norm 1.6477 | dt 0.027
type train | step 6110 | loss 0.1318 1.8856 7.8046 25.4861 | lr 8.4e-04 | norm 1.3656 | dt 0.026
type train | step 6120 | loss 0.1314 1.9237 7.8933 26.0688 | lr 8.4e-04 | norm 1.4596 | dt 0.026
type train | step 6130 | loss 0.1347 1.8338 7.5240 24.8685 | lr 8.4e-04 | norm 1.4213 | dt 0.026
type train | step 6140 | loss 0.1380 1.9091 7.8111 25.8652 | lr 8.4e-04 | norm 1.6605 | dt 0.026
type train | step 6150 | loss 0.1340 1.8805 7.5173 24.6360 | lr 8.4e-04 | norm 1.4508 | dt 0.026
type train | step 6160 | loss 0.1324 1.8880 7.7759 25.4424 | lr 8.4e-04 | norm 1.4923 | dt 0.026
type train | step 6170 | loss 0.1335 1.8844 7.5560 24.6952 | lr 8.4e-04 | norm 1.2272 | dt 0.026
type train | step 6180 | loss 0.1381 1.9421 8.1203 26.9303 | lr 8.3e-04 | norm 1.4562 | dt 0.026
type train | step 6190 | loss 0.1362 1.8819 7.6336 25.1551 | lr 8.3e-04 | norm 1.4521 | dt 0.026
type train | step 6200 | loss 0.1292 1.8314 7.5016 24.6785 | lr 8.3e-04 | norm 1.3254 | dt 0.026
type train | step 6210 | loss 0.1366 1.9017 7.7350 25.1292 | lr 8.3e-04 | norm 1.3920 | dt 0.026
type train | step 6220 | loss 0.1398 1.8926 7.5757 24.8665 | lr 8.3e-04 | norm 1.4951 | dt 0.026
type train | step 6230 | loss 0.1337 1.8587 7.5134 24.8662 | lr 8.3e-04 | norm 1.3068 | dt 0.026
type train | step 6240 | loss 0.1462 1.9023 7.5416 25.5964 | lr 8.3e-04 | norm 2.1089 | dt 0.026
type train | step 6250 | loss 0.1409 1.9062 7.7614 25.6904 | lr 8.3e-04 | norm 1.6079 | dt 0.026
type train | step 6260 | loss 0.1315 1.8745 7.7407 25.4778 | lr 8.3e-04 | norm 1.4597 | dt 0.026
type train | step 6270 | loss 0.1325 1.9212 7.6720 24.8008 | lr 8.3e-04 | norm 1.4722 | dt 0.027
type train | step 6280 | loss 0.1332 1.9186 7.6177 25.2798 | lr 8.3e-04 | norm 1.5205 | dt 0.027
type train | step 6290 | loss 0.1366 1.8561 7.5813 25.0279 | lr 8.3e-04 | norm 1.6445 | dt 0.027
type train | step 6300 | loss 0.1409 1.9245 7.8620 26.2304 | lr 8.3e-04 | norm 1.4595 | dt 0.026
type train | step 6310 | loss 0.1366 1.8670 7.5430 25.3709 | lr 8.3e-04 | norm 1.5476 | dt 0.026
type train | step 6320 | loss 0.1313 1.8654 7.7214 25.2807 | lr 8.3e-04 | norm 1.3684 | dt 0.027
type train | step 6330 | loss 0.1286 1.9055 7.7442 24.9985 | lr 8.3e-04 | norm 1.3271 | dt 0.026
type train | step 6340 | loss 0.1374 1.9640 7.8293 25.6989 | lr 8.3e-04 | norm 1.4991 | dt 0.027
type train | step 6350 | loss 0.1334 1.8447 7.4702 24.6314 | lr 8.2e-04 | norm 1.3584 | dt 0.027
type train | step 6360 | loss 0.1308 1.8605 7.5896 25.2245 | lr 8.2e-04 | norm 1.3952 | dt 0.027
type train | step 6370 | loss 0.1360 1.8574 7.4407 24.8922 | lr 8.2e-04 | norm 1.3615 | dt 0.027
type train | step 6380 | loss 0.1361 1.8722 7.6521 25.6831 | lr 8.2e-04 | norm 1.5969 | dt 0.027
type train | step 6390 | loss 0.1330 1.8624 7.4866 24.7497 | lr 8.2e-04 | norm 1.4425 | dt 0.027
type train | step 6400 | loss 0.1367 1.9593 7.7341 24.9817 | lr 8.2e-04 | norm 1.5928 | dt 0.027
type train | step 6410 | loss 0.1360 1.8576 7.5879 25.2817 | lr 8.2e-04 | norm 1.6711 | dt 0.032
type train | step 6420 | loss 0.1336 1.8522 7.6561 25.3257 | lr 8.2e-04 | norm 1.5596 | dt 0.035
type train | step 6430 | loss 0.1338 1.9056 7.8577 25.8375 | lr 8.2e-04 | norm 1.2888 | dt 0.035
type train | step 6440 | loss 0.1295 1.8758 7.8060 25.5629 | lr 8.2e-04 | norm 1.2772 | dt 0.035
type train | step 6450 | loss 0.1337 1.8884 7.7219 25.2720 | lr 8.2e-04 | norm 1.5200 | dt 0.036
type train | step 6460 | loss 0.1320 1.8262 7.3689 24.4202 | lr 8.2e-04 | norm 1.5120 | dt 0.035
type train | step 6470 | loss 0.1320 1.8961 7.4418 25.0536 | lr 8.2e-04 | norm 1.6565 | dt 0.035
type train | step 6480 | loss 0.1370 1.8789 7.6109 25.7226 | lr 8.2e-04 | norm 1.5502 | dt 0.036
type train | step 6490 | loss 0.1290 1.9139 7.8800 25.8609 | lr 8.2e-04 | norm 1.3575 | dt 0.035
type train | step 6500 | loss 0.1393 1.8768 7.6137 24.8575 | lr 8.2e-04 | norm 1.4792 | dt 0.035
type train | step 6510 | loss 0.1314 1.8908 7.6385 25.1392 | lr 8.2e-04 | norm 1.2922 | dt 0.035
type train | step 6520 | loss 0.1374 1.9091 7.5592 24.9933 | lr 8.1e-04 | norm 1.6702 | dt 0.034
type train | step 6530 | loss 0.1338 1.9197 7.7520 25.4753 | lr 8.1e-04 | norm 1.4031 | dt 0.034
type train | step 6540 | loss 0.1317 1.8485 7.5048 24.7613 | lr 8.1e-04 | norm 1.5658 | dt 0.034
type train | step 6550 | loss 0.1356 1.9061 7.7237 25.4553 | lr 8.1e-04 | norm 1.2332 | dt 0.034
type train | step 6560 | loss 0.1328 1.8414 7.3413 24.4354 | lr 8.1e-04 | norm 1.4771 | dt 0.034
type train | step 6570 | loss 0.1328 1.8577 7.6551 25.3687 | lr 8.1e-04 | norm 1.3502 | dt 0.033
type train | step 6580 | loss 0.1339 1.9003 7.7589 25.3774 | lr 8.1e-04 | norm 1.3040 | dt 0.035
type train | step 6590 | loss 0.1350 1.9093 7.8225 25.5561 | lr 8.1e-04 | norm 1.4339 | dt 0.034
type train | step 6600 | loss 0.1367 1.8848 7.6820 25.3926 | lr 8.1e-04 | norm 1.5519 | dt 0.034
type train | step 6610 | loss 0.1322 1.9394 7.8707 26.1607 | lr 8.1e-04 | norm 1.3508 | dt 0.033
type train | step 6620 | loss 0.1340 1.9040 7.8854 25.9600 | lr 8.1e-04 | norm 1.5684 | dt 0.033
type train | step 6630 | loss 0.1320 1.8896 7.8299 26.2224 | lr 8.1e-04 | norm 1.4047 | dt 0.033
type train | step 6640 | loss 0.1286 1.8924 7.4790 24.5571 | lr 8.1e-04 | norm 1.3250 | dt 0.033
type train | step 6650 | loss 0.1294 1.9439 7.7286 25.2208 | lr 8.1e-04 | norm 1.5509 | dt 0.034
type train | step 6660 | loss 0.1367 1.8586 7.6832 25.2327 | lr 8.1e-04 | norm 1.7301 | dt 0.033
type train | step 6670 | loss 0.1301 1.9362 7.9745 26.4700 | lr 8.1e-04 | norm 1.4447 | dt 0.033
type train | step 6680 | loss 0.1388 1.9047 7.5003 24.8896 | lr 8.1e-04 | norm 1.7915 | dt 0.034
type train | step 6690 | loss 0.1313 1.8747 7.7358 25.9603 | lr 8.0e-04 | norm 1.5477 | dt 0.033
type train | step 6700 | loss 0.1284 1.8943 7.5652 24.6805 | lr 8.0e-04 | norm 1.3184 | dt 0.030
type train | step 6710 | loss 0.1315 1.9201 8.0116 26.0401 | lr 8.0e-04 | norm 1.6026 | dt 0.036
type train | step 6720 | loss 0.1295 1.8879 7.7707 25.4636 | lr 8.0e-04 | norm 1.3332 | dt 0.033
type train | step 6730 | loss 0.1293 1.9289 7.8702 26.0199 | lr 8.0e-04 | norm 1.4320 | dt 0.032
type train | step 6740 | loss 0.1328 1.8445 7.4962 24.8216 | lr 8.0e-04 | norm 1.4440 | dt 0.033
type train | step 6750 | loss 0.1361 1.9127 7.7845 25.8623 | lr 8.0e-04 | norm 1.6533 | dt 0.033
type train | step 6760 | loss 0.1314 1.8898 7.4908 24.5915 | lr 8.0e-04 | norm 1.4349 | dt 0.027
type train | step 6770 | loss 0.1296 1.8888 7.7347 25.3812 | lr 8.0e-04 | norm 1.4441 | dt 0.026
type train | step 6780 | loss 0.1306 1.8877 7.5169 24.6626 | lr 8.0e-04 | norm 1.1884 | dt 0.026
type train | step 6790 | loss 0.1357 1.9444 8.0853 26.8792 | lr 8.0e-04 | norm 1.4240 | dt 0.026
type train | step 6800 | loss 0.1338 1.8877 7.5906 25.1160 | lr 8.0e-04 | norm 1.4437 | dt 0.026
type train | step 6810 | loss 0.1270 1.8256 7.4875 24.6600 | lr 8.0e-04 | norm 1.3147 | dt 0.026
type train | step 6820 | loss 0.1339 1.9018 7.7074 25.0717 | lr 8.0e-04 | norm 1.3737 | dt 0.026
type train | step 6830 | loss 0.1370 1.8976 7.5535 24.8343 | lr 8.0e-04 | norm 1.4774 | dt 0.026
type train | step 6840 | loss 0.1317 1.8546 7.4700 24.8305 | lr 8.0e-04 | norm 1.3080 | dt 0.026
type train | step 6850 | loss 0.1438 1.8912 7.5257 25.5056 | lr 7.9e-04 | norm 2.0770 | dt 0.026
type train | step 6860 | loss 0.1391 1.9036 7.7333 25.6400 | lr 7.9e-04 | norm 1.6188 | dt 0.026
type train | step 6870 | loss 0.1298 1.8600 7.7272 25.4406 | lr 7.9e-04 | norm 1.4226 | dt 0.026
type train | step 6880 | loss 0.1301 1.9154 7.6437 24.7729 | lr 7.9e-04 | norm 1.4627 | dt 0.026
type train | step 6890 | loss 0.1311 1.9098 7.5931 25.2271 | lr 7.9e-04 | norm 1.5025 | dt 0.025
type train | step 6900 | loss 0.1342 1.8507 7.5301 25.0168 | lr 7.9e-04 | norm 1.6442 | dt 0.026
type train | step 6910 | loss 0.1385 1.9238 7.8268 26.1801 | lr 7.9e-04 | norm 1.4366 | dt 0.026
type train | step 6920 | loss 0.1343 1.8629 7.5208 25.3212 | lr 7.9e-04 | norm 1.5003 | dt 0.026
type train | step 6930 | loss 0.1288 1.8574 7.6956 25.2453 | lr 7.9e-04 | norm 1.3467 | dt 0.026
type train | step 6940 | loss 0.1257 1.8932 7.6948 24.9855 | lr 7.9e-04 | norm 1.3238 | dt 0.026
type train | step 6950 | loss 0.1355 1.9609 7.7839 25.6368 | lr 7.9e-04 | norm 1.4882 | dt 0.026
type train | step 6960 | loss 0.1310 1.8364 7.4290 24.6291 | lr 7.9e-04 | norm 1.3380 | dt 0.026
type train | step 6970 | loss 0.1287 1.8569 7.5555 25.1732 | lr 7.9e-04 | norm 1.3890 | dt 0.026
type train | step 6980 | loss 0.1344 1.8462 7.4072 24.8671 | lr 7.9e-04 | norm 1.3418 | dt 0.026
type train | step 6990 | loss 0.1341 1.8562 7.6090 25.6425 | lr 7.9e-04 | norm 1.5806 | dt 0.026
type train | step 7000 | loss 0.1307 1.8473 7.4633 24.7682 | lr 7.9e-04 | norm 1.4381 | dt 0.027
type train | step 7010 | loss 0.1347 1.9462 7.6850 24.9337 | lr 7.8e-04 | norm 1.5806 | dt 0.035
type train | step 7020 | loss 0.1332 1.8423 7.5573 25.2664 | lr 7.8e-04 | norm 1.6379 | dt 0.035
type train | step 7030 | loss 0.1316 1.8423 7.6130 25.3021 | lr 7.8e-04 | norm 1.5269 | dt 0.035
type train | step 7040 | loss 0.1315 1.8905 7.8332 25.7868 | lr 7.8e-04 | norm 1.2853 | dt 0.035
type train | step 7050 | loss 0.1272 1.8645 7.7692 25.5444 | lr 7.8e-04 | norm 1.2752 | dt 0.035
type train | step 7060 | loss 0.1312 1.8705 7.6801 25.2508 | lr 7.8e-04 | norm 1.5037 | dt 0.036
type train | step 7070 | loss 0.1296 1.8084 7.3240 24.3944 | lr 7.8e-04 | norm 1.4931 | dt 0.035
type train | step 7080 | loss 0.1296 1.8766 7.4126 25.0688 | lr 7.8e-04 | norm 1.6168 | dt 0.035
type train | step 7090 | loss 0.1349 1.8649 7.5675 25.6774 | lr 7.8e-04 | norm 1.5279 | dt 0.035
type train | step 7100 | loss 0.1270 1.8958 7.8421 25.8342 | lr 7.8e-04 | norm 1.3404 | dt 0.035
type train | step 7110 | loss 0.1371 1.8632 7.5659 24.8573 | lr 7.8e-04 | norm 1.4625 | dt 0.035
type train | step 7120 | loss 0.1295 1.8733 7.6073 25.1314 | lr 7.8e-04 | norm 1.2769 | dt 0.036
type train | step 7130 | loss 0.1351 1.8901 7.5085 24.9863 | lr 7.8e-04 | norm 1.6536 | dt 0.035
type train | step 7140 | loss 0.1319 1.8953 7.7256 25.4829 | lr 7.8e-04 | norm 1.4154 | dt 0.035
type train | step 7150 | loss 0.1296 1.8229 7.4659 24.7544 | lr 7.8e-04 | norm 1.5406 | dt 0.035
type train | step 7160 | loss 0.1339 1.8854 7.6931 25.4271 | lr 7.8e-04 | norm 1.2418 | dt 0.035
type train | step 7170 | loss 0.1303 1.8178 7.2894 24.4022 | lr 7.7e-04 | norm 1.4756 | dt 0.035
type train | step 7180 | loss 0.1307 1.8318 7.6063 25.3716 | lr 7.7e-04 | norm 1.3516 | dt 0.035
type train | step 7190 | loss 0.1316 1.8788 7.7067 25.3667 | lr 7.7e-04 | norm 1.2935 | dt 0.035
type train | step 7200 | loss 0.1332 1.8850 7.7888 25.5484 | lr 7.7e-04 | norm 1.4358 | dt 0.035
type train | step 7210 | loss 0.1341 1.8650 7.6402 25.3788 | lr 7.7e-04 | norm 1.5378 | dt 0.035
type train | step 7220 | loss 0.1303 1.9120 7.8284 26.1181 | lr 7.7e-04 | norm 1.3347 | dt 0.035
type train | step 7230 | loss 0.1320 1.8781 7.8503 25.9668 | lr 7.7e-04 | norm 1.5770 | dt 0.035
type train | step 7240 | loss 0.1299 1.8675 7.7902 26.1958 | lr 7.7e-04 | norm 1.3962 | dt 0.035
type train | step 7250 | loss 0.1271 1.8695 7.4160 24.5296 | lr 7.7e-04 | norm 1.3065 | dt 0.035
type train | step 7260 | loss 0.1281 1.9124 7.6843 25.2553 | lr 7.7e-04 | norm 1.5327 | dt 0.033
type train | step 7270 | loss 0.1350 1.8354 7.6429 25.1873 | lr 7.7e-04 | norm 1.7070 | dt 0.032
type train | step 7280 | loss 0.1278 1.9117 7.9446 26.4526 | lr 7.7e-04 | norm 1.4308 | dt 0.029
type train | step 7290 | loss 0.1370 1.8763 7.4650 24.8914 | lr 7.7e-04 | norm 1.7968 | dt 0.029
type train | step 7300 | loss 0.1294 1.8488 7.6958 25.8936 | lr 7.7e-04 | norm 1.5502 | dt 0.026
type train | step 7310 | loss 0.1268 1.8590 7.5048 24.6661 | lr 7.7e-04 | norm 1.3117 | dt 0.026
type train | step 7320 | loss 0.1296 1.9034 7.9550 26.0436 | lr 7.7e-04 | norm 1.6072 | dt 0.027
type train | step 7330 | loss 0.1283 1.8684 7.7259 25.4170 | lr 7.6e-04 | norm 1.3164 | dt 0.025
type train | step 7340 | loss 0.1272 1.9022 7.8486 25.9982 | lr 7.6e-04 | norm 1.4108 | dt 0.025
type train | step 7350 | loss 0.1304 1.8212 7.4558 24.7918 | lr 7.6e-04 | norm 1.4096 | dt 0.026
type train | step 7360 | loss 0.1339 1.8862 7.7372 25.8395 | lr 7.6e-04 | norm 1.6427 | dt 0.026
type train | step 7370 | loss 0.1290 1.8669 7.4401 24.5817 | lr 7.6e-04 | norm 1.4188 | dt 0.026
type train | step 7380 | loss 0.1270 1.8668 7.7013 25.3568 | lr 7.6e-04 | norm 1.4285 | dt 0.026
type train | step 7390 | loss 0.1281 1.8602 7.4862 24.6516 | lr 7.6e-04 | norm 1.1950 | dt 0.026
type train | step 7400 | loss 0.1334 1.9301 8.0434 26.8747 | lr 7.6e-04 | norm 1.4066 | dt 0.026
type train | step 7410 | loss 0.1306 1.8642 7.5498 25.0908 | lr 7.6e-04 | norm 1.4373 | dt 0.026
type train | step 7420 | loss 0.1246 1.8073 7.4602 24.6538 | lr 7.6e-04 | norm 1.2893 | dt 0.026
type train | step 7430 | loss 0.1312 1.8795 7.6556 25.0755 | lr 7.6e-04 | norm 1.3577 | dt 0.026
type train | step 7440 | loss 0.1344 1.8778 7.5191 24.7873 | lr 7.6e-04 | norm 1.4724 | dt 0.026
type train | step 7450 | loss 0.1291 1.8360 7.4310 24.8253 | lr 7.6e-04 | norm 1.2787 | dt 0.026
type train | step 7460 | loss 0.1405 1.8745 7.4762 25.4695 | lr 7.6e-04 | norm 2.0411 | dt 0.026
type train | step 7470 | loss 0.1354 1.8887 7.6984 25.6157 | lr 7.6e-04 | norm 1.5884 | dt 0.026
type train | step 7480 | loss 0.1268 1.8474 7.7002 25.4385 | lr 7.5e-04 | norm 1.4060 | dt 0.026
type train | step 7490 | loss 0.1272 1.8938 7.6040 24.7654 | lr 7.5e-04 | norm 1.4485 | dt 0.026
type train | step 7500 | loss 0.1286 1.8918 7.5653 25.2022 | lr 7.5e-04 | norm 1.4949 | dt 0.026
type train | step 7510 | loss 0.1305 1.8379 7.4829 25.0244 | lr 7.5e-04 | norm 1.6482 | dt 0.035
type train | step 7520 | loss 0.1357 1.9126 7.7840 26.1411 | lr 7.5e-04 | norm 1.4325 | dt 0.035
type train | step 7530 | loss 0.1318 1.8533 7.5002 25.3147 | lr 7.5e-04 | norm 1.4916 | dt 0.035
type train | step 7540 | loss 0.1254 1.8425 7.6689 25.2454 | lr 7.5e-04 | norm 1.3258 | dt 0.035
type train | step 7550 | loss 0.1228 1.8786 7.6554 25.0065 | lr 7.5e-04 | norm 1.2781 | dt 0.035
type train | step 7560 | loss 0.1324 1.9556 7.7386 25.5852 | lr 7.5e-04 | norm 1.4688 | dt 0.035
type train | step 7570 | loss 0.1280 1.8207 7.3776 24.6289 | lr 7.5e-04 | norm 1.3232 | dt 0.035
type train | step 7580 | loss 0.1258 1.8476 7.5213 25.1039 | lr 7.5e-04 | norm 1.3525 | dt 0.035
type train | step 7590 | loss 0.1315 1.8412 7.3745 24.8478 | lr 7.5e-04 | norm 1.3253 | dt 0.035
type train | step 7600 | loss 0.1315 1.8466 7.5811 25.6026 | lr 7.5e-04 | norm 1.5695 | dt 0.035
type train | step 7610 | loss 0.1282 1.8379 7.4395 24.7758 | lr 7.5e-04 | norm 1.4314 | dt 0.035
type train | step 7620 | loss 0.1314 1.9378 7.6556 24.9238 | lr 7.5e-04 | norm 1.5919 | dt 0.035
type train | step 7630 | loss 0.1306 1.8278 7.5197 25.2536 | lr 7.4e-04 | norm 1.6187 | dt 0.035
type train | step 7640 | loss 0.1292 1.8343 7.5694 25.2814 | lr 7.4e-04 | norm 1.5257 | dt 0.035
type train | step 7650 | loss 0.1287 1.8927 7.8120 25.7907 | lr 7.4e-04 | norm 1.2727 | dt 0.035
type train | step 7660 | loss 0.1244 1.8534 7.7475 25.5524 | lr 7.4e-04 | norm 1.2712 | dt 0.035
type train | step 7670 | loss 0.1280 1.8685 7.6367 25.2795 | lr 7.4e-04 | norm 1.4729 | dt 0.035
type train | step 7680 | loss 0.1272 1.7915 7.2964 24.3867 | lr 7.4e-04 | norm 1.4735 | dt 0.035
type train | step 7690 | loss 0.1268 1.8740 7.3638 25.0587 | lr 7.4e-04 | norm 1.5978 | dt 0.035
type train | step 7700 | loss 0.1320 1.8528 7.5390 25.6310 | lr 7.4e-04 | norm 1.5082 | dt 0.035
type train | step 7710 | loss 0.1237 1.8889 7.8143 25.8157 | lr 7.4e-04 | norm 1.3246 | dt 0.035
type train | step 7720 | loss 0.1330 1.8510 7.5378 24.8751 | lr 7.4e-04 | norm 1.4506 | dt 0.035
type train | step 7730 | loss 0.1264 1.8618 7.5836 25.1072 | lr 7.4e-04 | norm 1.2545 | dt 0.035
type train | step 7740 | loss 0.1307 1.8848 7.4862 24.9575 | lr 7.4e-04 | norm 1.6592 | dt 0.035
type train | step 7750 | loss 0.1285 1.8850 7.6934 25.4652 | lr 7.4e-04 | norm 1.3809 | dt 0.035
type train | step 7760 | loss 0.1263 1.8175 7.4334 24.7628 | lr 7.4e-04 | norm 1.5244 | dt 0.034
type train | step 7770 | loss 0.1311 1.8802 7.6677 25.4011 | lr 7.4e-04 | norm 1.2269 | dt 0.033
type train | step 7780 | loss 0.1262 1.8138 7.2651 24.3888 | lr 7.3e-04 | norm 1.4674 | dt 0.033
type train | step 7790 | loss 0.1274 1.8230 7.5783 25.3698 | lr 7.3e-04 | norm 1.3466 | dt 0.034
type train | step 7800 | loss 0.1284 1.8736 7.6807 25.3740 | lr 7.3e-04 | norm 1.2830 | dt 0.033
type train | step 7810 | loss 0.1300 1.8822 7.7576 25.5376 | lr 7.3e-04 | norm 1.4307 | dt 0.033
type train | step 7820 | loss 0.1315 1.8544 7.6270 25.3803 | lr 7.3e-04 | norm 1.5268 | dt 0.033
type train | step 7830 | loss 0.1271 1.9081 7.7993 26.0916 | lr 7.3e-04 | norm 1.3188 | dt 0.031
type train | step 7840 | loss 0.1283 1.8741 7.8385 25.9754 | lr 7.3e-04 | norm 1.5777 | dt 0.030
type train | step 7850 | loss 0.1266 1.8653 7.7749 26.1598 | lr 7.3e-04 | norm 1.3853 | dt 0.027
type train | step 7860 | loss 0.1236 1.8629 7.3874 24.5161 | lr 7.3e-04 | norm 1.3093 | dt 0.026
type train | step 7870 | loss 0.1242 1.9024 7.6582 25.2476 | lr 7.3e-04 | norm 1.5147 | dt 0.026
type train | step 7880 | loss 0.1319 1.8318 7.6161 25.1565 | lr 7.3e-04 | norm 1.6911 | dt 0.026
type train | step 7890 | loss 0.1248 1.9148 7.9166 26.4569 | lr 7.3e-04 | norm 1.4238 | dt 0.026
type train | step 7900 | loss 0.1312 1.8746 7.4448 24.8665 | lr 7.3e-04 | norm 1.7899 | dt 0.026
type train | step 7910 | loss 0.1260 1.8487 7.6861 25.8461 | lr 7.3e-04 | norm 1.5369 | dt 0.026
type train | step 7920 | loss 0.1226 1.8581 7.4865 24.6532 | lr 7.3e-04 | norm 1.2774 | dt 0.026
type train | step 7930 | loss 0.1256 1.8973 7.9411 26.0430 | lr 7.2e-04 | norm 1.5903 | dt 0.027
type train | step 7940 | loss 0.1246 1.8660 7.6993 25.4021 | lr 7.2e-04 | norm 1.3033 | dt 0.026
type train | step 7950 | loss 0.1242 1.8983 7.8343 25.9839 | lr 7.2e-04 | norm 1.4064 | dt 0.026
type train | step 7960 | loss 0.1267 1.8163 7.4458 24.7609 | lr 7.2e-04 | norm 1.4120 | dt 0.026
type train | step 7970 | loss 0.1312 1.8782 7.7255 25.8116 | lr 7.2e-04 | norm 1.6292 | dt 0.026
type train | step 7980 | loss 0.1252 1.8569 7.4265 24.5917 | lr 7.2e-04 | norm 1.3908 | dt 0.026
type train | step 7990 | loss 0.1234 1.8625 7.6861 25.3395 | lr 7.2e-04 | norm 1.4094 | dt 0.026
type train | step 8000 | loss 0.1252 1.8595 7.4594 24.6476 | lr 7.2e-04 | norm 1.1540 | dt 0.026
type train | step 8010 | loss 0.1298 1.9267 8.0152 26.8376 | lr 7.2e-04 | norm 1.3909 | dt 0.031
type train | step 8020 | loss 0.1260 1.8598 7.5177 25.0597 | lr 7.2e-04 | norm 1.4463 | dt 0.027
type train | step 8030 | loss 0.1218 1.7990 7.4394 24.6242 | lr 7.2e-04 | norm 1.2651 | dt 0.026
type train | step 8040 | loss 0.1273 1.8762 7.6335 25.0595 | lr 7.2e-04 | norm 1.3356 | dt 0.026
type train | step 8050 | loss 0.1307 1.8752 7.5035 24.7559 | lr 7.2e-04 | norm 1.4562 | dt 0.026
type train | step 8060 | loss 0.1262 1.8354 7.4163 24.8048 | lr 7.2e-04 | norm 1.3083 | dt 0.026
type train | step 8070 | loss 0.1359 1.8663 7.4507 25.4510 | lr 7.2e-04 | norm 2.0211 | dt 0.026
type train | step 8080 | loss 0.1311 1.8832 7.6765 25.6000 | lr 7.1e-04 | norm 1.5935 | dt 0.026
type train | step 8090 | loss 0.1238 1.8381 7.6766 25.4090 | lr 7.1e-04 | norm 1.3894 | dt 0.026
type train | step 8100 | loss 0.1238 1.8913 7.5905 24.7630 | lr 7.1e-04 | norm 1.4312 | dt 0.026
type train | step 8110 | loss 0.1261 1.8852 7.5420 25.1816 | lr 7.1e-04 | norm 1.4685 | dt 0.026
type train | step 8120 | loss 0.1264 1.8366 7.4632 25.0387 | lr 7.1e-04 | norm 1.6439 | dt 0.026
type train | step 8130 | loss 0.1321 1.9040 7.7548 26.1105 | lr 7.1e-04 | norm 1.4197 | dt 0.026
type train | step 8140 | loss 0.1284 1.8477 7.4721 25.3077 | lr 7.1e-04 | norm 1.4799 | dt 0.026
type train | step 8150 | loss 0.1230 1.8312 7.6522 25.2146 | lr 7.1e-04 | norm 1.3275 | dt 0.026
type train | step 8160 | loss 0.1205 1.8772 7.6337 25.0156 | lr 7.1e-04 | norm 1.2782 | dt 0.026
type train | step 8170 | loss 0.1293 1.9534 7.7237 25.5366 | lr 7.1e-04 | norm 1.4708 | dt 0.026
type train | step 8180 | loss 0.1247 1.8152 7.3501 24.6304 | lr 7.1e-04 | norm 1.3229 | dt 0.026
type train | step 8190 | loss 0.1229 1.8381 7.4981 25.0730 | lr 7.1e-04 | norm 1.3388 | dt 0.026
type train | step 8200 | loss 0.1279 1.8356 7.3561 24.8338 | lr 7.1e-04 | norm 1.3045 | dt 0.026
type train | step 8210 | loss 0.1284 1.8393 7.5709 25.5761 | lr 7.1e-04 | norm 1.5678 | dt 0.026
type train | step 8220 | loss 0.1257 1.8311 7.4161 24.7365 | lr 7.1e-04 | norm 1.4331 | dt 0.026
type train | step 8230 | loss 0.1273 1.9295 7.6423 24.9115 | lr 7.0e-04 | norm 1.5793 | dt 0.026
type train | step 8240 | loss 0.1278 1.8180 7.5064 25.2449 | lr 7.0e-04 | norm 1.6424 | dt 0.026
type train | step 8250 | loss 0.1263 1.8223 7.5406 25.2667 | lr 7.0e-04 | norm 1.5033 | dt 0.026
type train | step 8260 | loss 0.1250 1.8844 7.7930 25.7869 | lr 7.0e-04 | norm 1.2673 | dt 0.026
type train | step 8270 | loss 0.1218 1.8482 7.7310 25.5582 | lr 7.0e-04 | norm 1.2728 | dt 0.027
type train | step 8280 | loss 0.1251 1.8647 7.6140 25.2627 | lr 7.0e-04 | norm 1.4651 | dt 0.027
type train | step 8290 | loss 0.1244 1.7832 7.2798 24.3748 | lr 7.0e-04 | norm 1.4651 | dt 0.027
type train | step 8300 | loss 0.1233 1.8620 7.3469 25.0475 | lr 7.0e-04 | norm 1.6005 | dt 0.027
type train | step 8310 | loss 0.1284 1.8417 7.5162 25.6114 | lr 7.0e-04 | norm 1.4924 | dt 0.027
type train | step 8320 | loss 0.1209 1.8796 7.8056 25.7995 | lr 7.0e-04 | norm 1.3367 | dt 0.027
type train | step 8330 | loss 0.1296 1.8448 7.5174 24.8695 | lr 7.0e-04 | norm 1.4685 | dt 0.033
type train | step 8340 | loss 0.1234 1.8544 7.5665 25.0747 | lr 7.0e-04 | norm 1.2509 | dt 0.035
type train | step 8350 | loss 0.1274 1.8757 7.4727 24.9039 | lr 7.0e-04 | norm 1.6508 | dt 0.035
type train | step 8360 | loss 0.1256 1.8738 7.6758 25.4877 | lr 7.0e-04 | norm 1.3727 | dt 0.035
type train | step 8370 | loss 0.1235 1.8048 7.4083 24.7634 | lr 6.9e-04 | norm 1.5194 | dt 0.035
type train | step 8380 | loss 0.1276 1.8674 7.6406 25.3739 | lr 6.9e-04 | norm 1.2237 | dt 0.035
type train | step 8390 | loss 0.1229 1.8095 7.2542 24.3566 | lr 6.9e-04 | norm 1.4653 | dt 0.035
type train | step 8400 | loss 0.1242 1.8185 7.5607 25.3478 | lr 6.9e-04 | norm 1.3399 | dt 0.035
type train | step 8410 | loss 0.1254 1.8643 7.6563 25.3656 | lr 6.9e-04 | norm 1.2904 | dt 0.035
type train | step 8420 | loss 0.1262 1.8734 7.7467 25.5013 | lr 6.9e-04 | norm 1.4205 | dt 0.035
type train | step 8430 | loss 0.1275 1.8487 7.6093 25.3671 | lr 6.9e-04 | norm 1.5285 | dt 0.035
type train | step 8440 | loss 0.1241 1.8953 7.7782 26.0806 | lr 6.9e-04 | norm 1.3069 | dt 0.035
type train | step 8450 | loss 0.1247 1.8694 7.8169 25.9628 | lr 6.9e-04 | norm 1.5942 | dt 0.035
type train | step 8460 | loss 0.1232 1.8496 7.7579 26.1371 | lr 6.9e-04 | norm 1.3670 | dt 0.035
type train | step 8470 | loss 0.1203 1.8593 7.3673 24.5151 | lr 6.9e-04 | norm 1.2692 | dt 0.035
type train | step 8480 | loss 0.1219 1.8871 7.6490 25.2474 | lr 6.9e-04 | norm 1.5246 | dt 0.035
type train | step 8490 | loss 0.1281 1.8238 7.5953 25.1557 | lr 6.9e-04 | norm 1.6957 | dt 0.035
type train | step 8500 | loss 0.1217 1.9020 7.8946 26.4384 | lr 6.9e-04 | norm 1.3932 | dt 0.036
type train | step 8510 | loss 0.1274 1.8734 7.4354 24.8365 | lr 6.8e-04 | norm 1.7797 | dt 0.035
type train | step 8520 | loss 0.1227 1.8365 7.6728 25.8139 | lr 6.8e-04 | norm 1.5308 | dt 0.035
type train | step 8530 | loss 0.1197 1.8472 7.4687 24.6372 | lr 6.8e-04 | norm 1.2678 | dt 0.035
type train | step 8540 | loss 0.1220 1.8814 7.9293 26.0196 | lr 6.8e-04 | norm 1.5703 | dt 0.038
type train | step 8550 | loss 0.1216 1.8546 7.6802 25.3873 | lr 6.8e-04 | norm 1.2843 | dt 0.036
type train | step 8560 | loss 0.1212 1.8836 7.8056 25.9619 | lr 6.8e-04 | norm 1.3813 | dt 0.036
type train | step 8570 | loss 0.1234 1.8180 7.4357 24.7343 | lr 6.8e-04 | norm 1.3904 | dt 0.034
type train | step 8580 | loss 0.1271 1.8663 7.7047 25.8022 | lr 6.8e-04 | norm 1.6182 | dt 0.034
type train | step 8590 | loss 0.1221 1.8446 7.4189 24.5788 | lr 6.8e-04 | norm 1.3711 | dt 0.035
type train | step 8600 | loss 0.1202 1.8516 7.6646 25.3174 | lr 6.8e-04 | norm 1.4150 | dt 0.035
type train | step 8610 | loss 0.1219 1.8509 7.4566 24.6501 | lr 6.8e-04 | norm 1.1520 | dt 0.035
type train | step 8620 | loss 0.1265 1.9153 8.0039 26.7995 | lr 6.8e-04 | norm 1.3842 | dt 0.033
type train | step 8630 | loss 0.1224 1.8509 7.5066 25.0482 | lr 6.8e-04 | norm 1.4338 | dt 0.034
type train | step 8640 | loss 0.1189 1.7889 7.4272 24.5983 | lr 6.8e-04 | norm 1.2334 | dt 0.034
type train | step 8650 | loss 0.1239 1.8674 7.6134 25.0613 | lr 6.8e-04 | norm 1.3310 | dt 0.034
type train | step 8660 | loss 0.1271 1.8673 7.4722 24.7461 | lr 6.7e-04 | norm 1.4371 | dt 0.034
type train | step 8670 | loss 0.1230 1.8246 7.4012 24.7920 | lr 6.7e-04 | norm 1.2777 | dt 0.034
type train | step 8680 | loss 0.1311 1.8604 7.4333 25.4302 | lr 6.7e-04 | norm 2.0051 | dt 0.034
type train | step 8690 | loss 0.1267 1.8776 7.6521 25.5735 | lr 6.7e-04 | norm 1.5685 | dt 0.033
type train | step 8700 | loss 0.1212 1.8257 7.6543 25.3888 | lr 6.7e-04 | norm 1.3563 | dt 0.034
type train | step 8710 | loss 0.1209 1.8847 7.5763 24.7503 | lr 6.7e-04 | norm 1.4126 | dt 0.031
type train | step 8720 | loss 0.1225 1.8823 7.5162 25.1619 | lr 6.7e-04 | norm 1.4587 | dt 0.035
type train | step 8730 | loss 0.1232 1.8338 7.4552 25.0475 | lr 6.7e-04 | norm 1.6451 | dt 0.033
type train | step 8740 | loss 0.1282 1.8973 7.7332 26.0834 | lr 6.7e-04 | norm 1.4044 | dt 0.034
type train | step 8750 | loss 0.1248 1.8404 7.4551 25.2867 | lr 6.7e-04 | norm 1.4521 | dt 0.034
type train | step 8760 | loss 0.1205 1.8257 7.6268 25.1963 | lr 6.7e-04 | norm 1.3037 | dt 0.033
type train | step 8770 | loss 0.1180 1.8743 7.6096 25.0016 | lr 6.7e-04 | norm 1.2643 | dt 0.033
type train | step 8780 | loss 0.1260 1.9485 7.7117 25.5147 | lr 6.7e-04 | norm 1.4778 | dt 0.033
type train | step 8790 | loss 0.1221 1.8099 7.3316 24.6171 | lr 6.7e-04 | norm 1.3307 | dt 0.032
type train | step 8800 | loss 0.1199 1.8288 7.4810 25.0227 | lr 6.6e-04 | norm 1.3353 | dt 0.034
type train | step 8810 | loss 0.1246 1.8274 7.3356 24.8166 | lr 6.6e-04 | norm 1.3058 | dt 0.033
type train | step 8820 | loss 0.1249 1.8343 7.5452 25.5421 | lr 6.6e-04 | norm 1.5117 | dt 0.033
type train | step 8830 | loss 0.1224 1.8227 7.3973 24.7120 | lr 6.6e-04 | norm 1.4031 | dt 0.033
type train | step 8840 | loss 0.1237 1.9226 7.6334 24.8937 | lr 6.6e-04 | norm 1.5670 | dt 0.032
type train | step 8850 | loss 0.1246 1.8099 7.4871 25.2243 | lr 6.6e-04 | norm 1.6333 | dt 0.031
type train | step 8860 | loss 0.1231 1.8144 7.5235 25.2801 | lr 6.6e-04 | norm 1.5019 | dt 0.031
type train | step 8870 | loss 0.1219 1.8801 7.7736 25.7769 | lr 6.6e-04 | norm 1.2589 | dt 0.031
type train | step 8880 | loss 0.1188 1.8471 7.7094 25.5463 | lr 6.6e-04 | norm 1.2446 | dt 0.032
type train | step 8890 | loss 0.1217 1.8571 7.5940 25.2638 | lr 6.6e-04 | norm 1.4364 | dt 0.028
type train | step 8900 | loss 0.1214 1.7803 7.2685 24.3568 | lr 6.6e-04 | norm 1.4348 | dt 0.026
type train | step 8910 | loss 0.1203 1.8529 7.3313 25.0239 | lr 6.6e-04 | norm 1.5649 | dt 0.027
type train | step 8920 | loss 0.1249 1.8410 7.5038 25.6168 | lr 6.6e-04 | norm 1.4875 | dt 0.026
type train | step 8930 | loss 0.1180 1.8696 7.7911 25.7789 | lr 6.6e-04 | norm 1.3084 | dt 0.026
type train | step 8940 | loss 0.1263 1.8412 7.5076 24.8437 | lr 6.5e-04 | norm 1.4525 | dt 0.026
type train | step 8950 | loss 0.1206 1.8495 7.5505 25.0460 | lr 6.5e-04 | norm 1.2295 | dt 0.026
type train | step 8960 | loss 0.1235 1.8697 7.4480 24.8617 | lr 6.5e-04 | norm 1.6221 | dt 0.026
type train | step 8970 | loss 0.1228 1.8670 7.6667 25.4921 | lr 6.5e-04 | norm 1.3433 | dt 0.026
type train | step 8980 | loss 0.1206 1.8033 7.3948 24.7860 | lr 6.5e-04 | norm 1.4907 | dt 0.026
type train | step 8990 | loss 0.1241 1.8597 7.6324 25.3612 | lr 6.5e-04 | norm 1.2031 | dt 0.026
type train | step 9000 | loss 0.1197 1.8084 7.2381 24.3289 | lr 6.5e-04 | norm 1.4604 | dt 0.026
type train | step 9010 | loss 0.1210 1.8124 7.5411 25.3340 | lr 6.5e-04 | norm 1.2979 | dt 0.027
type train | step 9020 | loss 0.1222 1.8585 7.6493 25.3477 | lr 6.5e-04 | norm 1.2673 | dt 0.028
type train | step 9030 | loss 0.1231 1.8666 7.7363 25.4835 | lr 6.5e-04 | norm 1.3927 | dt 0.033
type train | step 9040 | loss 0.1245 1.8397 7.5823 25.3582 | lr 6.5e-04 | norm 1.5036 | dt 0.035
type train | step 9050 | loss 0.1210 1.8865 7.7610 26.0636 | lr 6.5e-04 | norm 1.2898 | dt 0.035
type train | step 9060 | loss 0.1221 1.8724 7.7995 25.9349 | lr 6.5e-04 | norm 1.5871 | dt 0.035
type train | step 9070 | loss 0.1201 1.8465 7.7527 26.1148 | lr 6.5e-04 | norm 1.3593 | dt 0.035
type train | step 9080 | loss 0.1172 1.8545 7.3605 24.5012 | lr 6.4e-04 | norm 1.2599 | dt 0.035
type train | step 9090 | loss 0.1181 1.8836 7.6383 25.2017 | lr 6.4e-04 | norm 1.4647 | dt 0.035
type train | step 9100 | loss 0.1248 1.8166 7.5772 25.1333 | lr 6.4e-04 | norm 1.6769 | dt 0.035
type train | step 9110 | loss 0.1194 1.8955 7.8787 26.4253 | lr 6.4e-04 | norm 1.3872 | dt 0.035
type train | step 9120 | loss 0.1242 1.8640 7.4284 24.7931 | lr 6.4e-04 | norm 1.7862 | dt 0.035
type train | step 9130 | loss 0.1199 1.8395 7.6659 25.8082 | lr 6.4e-04 | norm 1.5187 | dt 0.035
type train | step 9140 | loss 0.1167 1.8446 7.4666 24.6225 | lr 6.4e-04 | norm 1.2565 | dt 0.035
type train | step 9150 | loss 0.1193 1.8733 7.9325 25.9966 | lr 6.4e-04 | norm 1.5597 | dt 0.036
type train | step 9160 | loss 0.1189 1.8536 7.6638 25.3618 | lr 6.4e-04 | norm 1.2864 | dt 0.035
type train | step 9170 | loss 0.1185 1.8811 7.7833 25.9490 | lr 6.4e-04 | norm 1.3819 | dt 0.035
type train | step 9180 | loss 0.1207 1.8107 7.4259 24.7156 | lr 6.4e-04 | norm 1.3929 | dt 0.035
type train | step 9190 | loss 0.1238 1.8633 7.6913 25.7783 | lr 6.4e-04 | norm 1.6056 | dt 0.035
type train | step 9200 | loss 0.1193 1.8371 7.4002 24.5409 | lr 6.4e-04 | norm 1.3641 | dt 0.035
type train | step 9210 | loss 0.1175 1.8441 7.6470 25.2830 | lr 6.4e-04 | norm 1.3612 | dt 0.035
type train | step 9220 | loss 0.1193 1.8490 7.4494 24.6538 | lr 6.3e-04 | norm 1.1640 | dt 0.035
type train | step 9230 | loss 0.1236 1.9146 7.9850 26.7601 | lr 6.3e-04 | norm 1.3964 | dt 0.035
type train | step 9240 | loss 0.1194 1.8468 7.4973 25.0207 | lr 6.3e-04 | norm 1.4291 | dt 0.035
type train | step 9250 | loss 0.1162 1.7840 7.4065 24.5761 | lr 6.3e-04 | norm 1.2180 | dt 0.036
type train | step 9260 | loss 0.1211 1.8611 7.6063 25.0238 | lr 6.3e-04 | norm 1.3253 | dt 0.034
type train | step 9270 | loss 0.1243 1.8635 7.4649 24.7238 | lr 6.3e-04 | norm 1.4280 | dt 0.035
type train | step 9280 | loss 0.1204 1.8239 7.3918 24.7834 | lr 6.3e-04 | norm 1.2883 | dt 0.034
type train | step 9290 | loss 0.1277 1.8547 7.4218 25.4159 | lr 6.3e-04 | norm 1.9848 | dt 0.031
type train | step 9300 | loss 0.1238 1.8687 7.6370 25.5630 | lr 6.3e-04 | norm 1.5617 | dt 0.026
type train | step 9310 | loss 0.1186 1.8227 7.6397 25.3744 | lr 6.3e-04 | norm 1.3469 | dt 0.026
type train | step 9320 | loss 0.1184 1.8789 7.5627 24.7401 | lr 6.3e-04 | norm 1.4047 | dt 0.026
type train | step 9330 | loss 0.1195 1.8752 7.5027 25.1395 | lr 6.3e-04 | norm 1.4487 | dt 0.026
type train | step 9340 | loss 0.1203 1.8313 7.4508 25.0391 | lr 6.3e-04 | norm 1.6527 | dt 0.026
type train | step 9350 | loss 0.1252 1.8949 7.7140 26.0452 | lr 6.2e-04 | norm 1.4126 | dt 0.026
type train | step 9360 | loss 0.1220 1.8438 7.4371 25.2417 | lr 6.2e-04 | norm 1.4882 | dt 0.026
type train | step 9370 | loss 0.1176 1.8191 7.6032 25.1727 | lr 6.2e-04 | norm 1.2866 | dt 0.026
type train | step 9380 | loss 0.1155 1.8679 7.6065 24.9896 | lr 6.2e-04 | norm 1.2603 | dt 0.026
type train | step 9390 | loss 0.1230 1.9423 7.7178 25.4930 | lr 6.2e-04 | norm 1.4646 | dt 0.026
type train | step 9400 | loss 0.1190 1.8036 7.3315 24.6058 | lr 6.2e-04 | norm 1.3162 | dt 0.026
type train | step 9410 | loss 0.1177 1.8244 7.4648 24.9909 | lr 6.2e-04 | norm 1.3237 | dt 0.027
type train | step 9420 | loss 0.1221 1.8304 7.3278 24.8054 | lr 6.2e-04 | norm 1.2936 | dt 0.026
type train | step 9430 | loss 0.1219 1.8359 7.5326 25.5127 | lr 6.2e-04 | norm 1.4947 | dt 0.026
type train | step 9440 | loss 0.1200 1.8164 7.3894 24.6957 | lr 6.2e-04 | norm 1.3975 | dt 0.026
type train | step 9450 | loss 0.1209 1.9205 7.6280 24.8867 | lr 6.2e-04 | norm 1.5643 | dt 0.027
type train | step 9460 | loss 0.1215 1.8033 7.4725 25.2184 | lr 6.2e-04 | norm 1.6164 | dt 0.027
type train | step 9470 | loss 0.1206 1.8099 7.5019 25.2764 | lr 6.2e-04 | norm 1.4894 | dt 0.026
type train | step 9480 | loss 0.1193 1.8714 7.7687 25.7769 | lr 6.2e-04 | norm 1.2341 | dt 0.026
type train | step 9490 | loss 0.1162 1.8442 7.6984 25.5287 | lr 6.1e-04 | norm 1.2228 | dt 0.026
type train | step 9500 | loss 0.1194 1.8522 7.5933 25.2493 | lr 6.1e-04 | norm 1.4302 | dt 0.026
type train | step 9510 | loss 0.1190 1.7739 7.2604 24.3371 | lr 6.1e-04 | norm 1.4568 | dt 0.035
type train | step 9520 | loss 0.1180 1.8476 7.3250 24.9711 | lr 6.1e-04 | norm 1.5737 | dt 0.035
type train | step 9530 | loss 0.1223 1.8351 7.4889 25.5749 | lr 6.1e-04 | norm 1.4617 | dt 0.035
type train | step 9540 | loss 0.1158 1.8650 7.7771 25.7667 | lr 6.1e-04 | norm 1.3006 | dt 0.036
type train | step 9550 | loss 0.1234 1.8403 7.4943 24.8193 | lr 6.1e-04 | norm 1.4448 | dt 0.035
type train | step 9560 | loss 0.1184 1.8439 7.5367 25.0279 | lr 6.1e-04 | norm 1.2158 | dt 0.035
type train | step 9570 | loss 0.1204 1.8605 7.4424 24.8460 | lr 6.1e-04 | norm 1.6194 | dt 0.036
type train | step 9580 | loss 0.1203 1.8639 7.6615 25.4799 | lr 6.1e-04 | norm 1.3416 | dt 0.035
type train | step 9590 | loss 0.1181 1.8031 7.3795 24.7726 | lr 6.1e-04 | norm 1.4588 | dt 0.035
type train | step 9600 | loss 0.1218 1.8602 7.6063 25.3464 | lr 6.1e-04 | norm 1.1934 | dt 0.035
type train | step 9610 | loss 0.1179 1.8062 7.2203 24.3011 | lr 6.1e-04 | norm 1.4587 | dt 0.035
type train | step 9620 | loss 0.1194 1.8080 7.5253 25.3250 | lr 6.1e-04 | norm 1.3011 | dt 0.035
type train | step 9630 | loss 0.1195 1.8541 7.6439 25.3328 | lr 6.0e-04 | norm 1.2579 | dt 0.035
type train | step 9640 | loss 0.1210 1.8617 7.7259 25.4479 | lr 6.0e-04 | norm 1.3915 | dt 0.035
type train | step 9650 | loss 0.1223 1.8363 7.5601 25.3358 | lr 6.0e-04 | norm 1.4933 | dt 0.035
type train | step 9660 | loss 0.1195 1.8815 7.7396 26.0548 | lr 6.0e-04 | norm 1.2770 | dt 0.035
type train | step 9670 | loss 0.1199 1.8744 7.7843 25.9101 | lr 6.0e-04 | norm 1.5804 | dt 0.035
type train | step 9680 | loss 0.1182 1.8415 7.7366 26.1002 | lr 6.0e-04 | norm 1.3545 | dt 0.035
type train | step 9690 | loss 0.1150 1.8471 7.3420 24.4879 | lr 6.0e-04 | norm 1.2566 | dt 0.035
type train | step 9700 | loss 0.1162 1.8821 7.6211 25.1490 | lr 6.0e-04 | norm 1.4360 | dt 0.035
type train | step 9710 | loss 0.1229 1.8111 7.5619 25.1007 | lr 6.0e-04 | norm 1.6642 | dt 0.035
type train | step 9720 | loss 0.1173 1.8946 7.8637 26.4383 | lr 6.0e-04 | norm 1.3774 | dt 0.035
type train | step 9730 | loss 0.1221 1.8618 7.4185 24.7708 | lr 6.0e-04 | norm 1.7752 | dt 0.035
type train | step 9740 | loss 0.1173 1.8319 7.6494 25.8023 | lr 6.0e-04 | norm 1.5018 | dt 0.035
type train | step 9750 | loss 0.1150 1.8376 7.4524 24.6094 | lr 6.0e-04 | norm 1.2535 | dt 0.035
type train | step 9760 | loss 0.1177 1.8660 7.9205 25.9805 | lr 6.0e-04 | norm 1.5517 | dt 0.036
type train | step 9770 | loss 0.1172 1.8495 7.6485 25.3524 | lr 5.9e-04 | norm 1.2784 | dt 0.034
type train | step 9780 | loss 0.1166 1.8796 7.7851 25.9384 | lr 5.9e-04 | norm 1.3622 | dt 0.034
type train | step 9790 | loss 0.1190 1.8068 7.4145 24.6850 | lr 5.9e-04 | norm 1.3791 | dt 0.034
type train | step 9800 | loss 0.1216 1.8660 7.6801 25.7589 | lr 5.9e-04 | norm 1.5823 | dt 0.034
type train | step 9810 | loss 0.1178 1.8324 7.3907 24.4819 | lr 5.9e-04 | norm 1.3547 | dt 0.034
type train | step 9820 | loss 0.1159 1.8390 7.6328 25.2578 | lr 5.9e-04 | norm 1.3683 | dt 0.034
type train | step 9830 | loss 0.1175 1.8425 7.4339 24.6468 | lr 5.9e-04 | norm 1.1431 | dt 0.034
type train | step 9840 | loss 0.1211 1.9116 7.9857 26.7399 | lr 5.9e-04 | norm 1.3659 | dt 0.034
type train | step 9850 | loss 0.1175 1.8453 7.4877 24.9984 | lr 5.9e-04 | norm 1.4138 | dt 0.034
type train | step 9860 | loss 0.1146 1.7814 7.3966 24.5667 | lr 5.9e-04 | norm 1.1958 | dt 0.029
type train | step 9870 | loss 0.1193 1.8559 7.5978 24.9981 | lr 5.9e-04 | norm 1.3030 | dt 0.029
type train | step 9880 | loss 0.1223 1.8606 7.4467 24.7064 | lr 5.9e-04 | norm 1.4097 | dt 0.026
type train | step 9890 | loss 0.1182 1.8194 7.3738 24.7639 | lr 5.9e-04 | norm 1.2644 | dt 0.026
type train | step 9900 | loss 0.1251 1.8510 7.4158 25.3844 | lr 5.8e-04 | norm 1.9719 | dt 0.026
type train | step 9910 | loss 0.1217 1.8663 7.6195 25.5354 | lr 5.8e-04 | norm 1.5400 | dt 0.026
type train | step 9920 | loss 0.1173 1.8216 7.6310 25.3496 | lr 5.8e-04 | norm 1.3264 | dt 0.026
type train | step 9930 | loss 0.1167 1.8758 7.5460 24.7127 | lr 5.8e-04 | norm 1.3822 | dt 0.026
type train | step 9940 | loss 0.1172 1.8709 7.4865 25.1211 | lr 5.8e-04 | norm 1.4379 | dt 0.026
type train | step 9950 | loss 0.1182 1.8206 7.4350 25.0303 | lr 5.8e-04 | norm 1.6249 | dt 0.026
type train | step 9960 | loss 0.1228 1.8913 7.6966 26.0153 | lr 5.8e-04 | norm 1.4044 | dt 0.026
type train | step 9970 | loss 0.1204 1.8408 7.4123 25.2234 | lr 5.8e-04 | norm 1.4116 | dt 0.027
type train | step 9980 | loss 0.1162 1.8161 7.6063 25.1676 | lr 5.8e-04 | norm 1.2616 | dt 0.026
type train | step 9990 | loss 0.1142 1.8638 7.6033 24.9651 | lr 5.8e-04 | norm 1.2182 | dt 0.026
type train | step 10000 | loss 0.1210 1.9367 7.7020 25.4684 | lr 5.8e-04 | norm 1.4442 | dt 0.026
type train | step 10010 | loss 0.1171 1.7956 7.3229 24.5802 | lr 5.8e-04 | norm 1.2929 | dt 0.035
type train | step 10020 | loss 0.1160 1.8212 7.4551 24.9603 | lr 5.8e-04 | norm 1.3139 | dt 0.035
type train | step 10030 | loss 0.1202 1.8293 7.3243 24.7825 | lr 5.8e-04 | norm 1.2501 | dt 0.035
type train | step 10040 | loss 0.1198 1.8339 7.5287 25.4979 | lr 5.7e-04 | norm 1.4481 | dt 0.035
type train | step 10050 | loss 0.1183 1.8130 7.3642 24.6643 | lr 5.7e-04 | norm 1.3805 | dt 0.035
type train | step 10060 | loss 0.1186 1.9197 7.6113 24.8845 | lr 5.7e-04 | norm 1.5523 | dt 0.035
type train | step 10070 | loss 0.1199 1.8013 7.4679 25.1809 | lr 5.7e-04 | norm 1.6046 | dt 0.035
type train | step 10080 | loss 0.1187 1.8097 7.4850 25.2631 | lr 5.7e-04 | norm 1.4793 | dt 0.035
type train | step 10090 | loss 0.1181 1.8671 7.7547 25.7537 | lr 5.7e-04 | norm 1.2348 | dt 0.035
type train | step 10100 | loss 0.1146 1.8460 7.6955 25.5346 | lr 5.7e-04 | norm 1.2195 | dt 0.035
type train | step 10110 | loss 0.1177 1.8504 7.5738 25.2170 | lr 5.7e-04 | norm 1.4199 | dt 0.035
type train | step 10120 | loss 0.1170 1.7717 7.2437 24.3330 | lr 5.7e-04 | norm 1.4365 | dt 0.035
type train | step 10130 | loss 0.1163 1.8415 7.3115 24.9257 | lr 5.7e-04 | norm 1.5330 | dt 0.035
type train | step 10140 | loss 0.1208 1.8328 7.4700 25.5337 | lr 5.7e-04 | norm 1.4515 | dt 0.035
type train | step 10150 | loss 0.1146 1.8630 7.7724 25.7410 | lr 5.7e-04 | norm 1.2869 | dt 0.035
type train | step 10160 | loss 0.1217 1.8423 7.4866 24.7989 | lr 5.7e-04 | norm 1.4358 | dt 0.035
type train | step 10170 | loss 0.1168 1.8386 7.5267 25.0212 | lr 5.7e-04 | norm 1.1905 | dt 0.035
type train | step 10180 | loss 0.1191 1.8557 7.4259 24.8229 | lr 5.6e-04 | norm 1.5941 | dt 0.035
type train | step 10190 | loss 0.1187 1.8620 7.6509 25.4601 | lr 5.6e-04 | norm 1.3059 | dt 0.035
type train | step 10200 | loss 0.1170 1.8026 7.3642 24.7646 | lr 5.6e-04 | norm 1.4554 | dt 0.036
type train | step 10210 | loss 0.1200 1.8573 7.5996 25.3465 | lr 5.6e-04 | norm 1.1741 | dt 0.035
type train | step 10220 | loss 0.1159 1.8057 7.2084 24.2847 | lr 5.6e-04 | norm 1.4458 | dt 0.035
type train | step 10230 | loss 0.1177 1.8074 7.5128 25.3191 | lr 5.6e-04 | norm 1.2891 | dt 0.035
type train | step 10240 | loss 0.1181 1.8494 7.6399 25.3126 | lr 5.6e-04 | norm 1.2524 | dt 0.035
type train | step 10250 | loss 0.1196 1.8572 7.7227 25.4293 | lr 5.6e-04 | norm 1.3581 | dt 0.035
type train | step 10260 | loss 0.1210 1.8338 7.5440 25.3287 | lr 5.6e-04 | norm 1.4671 | dt 0.028
type train | step 10270 | loss 0.1177 1.8761 7.7272 26.0588 | lr 5.6e-04 | norm 1.2861 | dt 0.027
type train | step 10280 | loss 0.1183 1.8761 7.7743 25.9132 | lr 5.6e-04 | norm 1.5690 | dt 0.026
type train | step 10290 | loss 0.1168 1.8369 7.7208 26.0766 | lr 5.6e-04 | norm 1.3411 | dt 0.026
type train | step 10300 | loss 0.1137 1.8469 7.3260 24.4771 | lr 5.6e-04 | norm 1.2489 | dt 0.026
type train | step 10310 | loss 0.1149 1.8781 7.6114 25.1088 | lr 5.5e-04 | norm 1.4276 | dt 0.026
type train | step 10320 | loss 0.1212 1.8105 7.5558 25.0838 | lr 5.5e-04 | norm 1.6388 | dt 0.026
type train | step 10330 | loss 0.1158 1.8946 7.8412 26.4416 | lr 5.5e-04 | norm 1.3697 | dt 0.026
type train | step 10340 | loss 0.1207 1.8650 7.4085 24.7596 | lr 5.5e-04 | norm 1.7676 | dt 0.026
type train | step 10350 | loss 0.1160 1.8344 7.6402 25.7975 | lr 5.5e-04 | norm 1.4971 | dt 0.026
type train | step 10360 | loss 0.1135 1.8375 7.4399 24.5963 | lr 5.5e-04 | norm 1.2400 | dt 0.026
type train | step 10370 | loss 0.1161 1.8645 7.9166 25.9698 | lr 5.5e-04 | norm 1.5229 | dt 0.028
type train | step 10380 | loss 0.1160 1.8511 7.6320 25.3540 | lr 5.5e-04 | norm 1.2485 | dt 0.026
type train | step 10390 | loss 0.1148 1.8840 7.7666 25.9379 | lr 5.5e-04 | norm 1.3712 | dt 0.026
type train | step 10400 | loss 0.1175 1.8063 7.4035 24.6816 | lr 5.5e-04 | norm 1.3776 | dt 0.026
type train | step 10410 | loss 0.1202 1.8642 7.6622 25.7476 | lr 5.5e-04 | norm 1.5610 | dt 0.026
type train | step 10420 | loss 0.1161 1.8329 7.3851 24.4582 | lr 5.5e-04 | norm 1.3350 | dt 0.026
type train | step 10430 | loss 0.1146 1.8438 7.6287 25.2457 | lr 5.5e-04 | norm 1.3673 | dt 0.026
type train | step 10440 | loss 0.1161 1.8436 7.4398 24.6320 | lr 5.5e-04 | norm 1.1522 | dt 0.026
type train | step 10450 | loss 0.1194 1.9180 7.9735 26.7288 | lr 5.4e-04 | norm 1.3741 | dt 0.026
type train | step 10460 | loss 0.1157 1.8504 7.4766 24.9995 | lr 5.4e-04 | norm 1.3882 | dt 0.026
type train | step 10470 | loss 0.1133 1.7825 7.3862 24.5547 | lr 5.4e-04 | norm 1.1862 | dt 0.026
type train | step 10480 | loss 0.1179 1.8545 7.5856 24.9974 | lr 5.4e-04 | norm 1.2940 | dt 0.026
type train | step 10490 | loss 0.1208 1.8610 7.4412 24.6699 | lr 5.4e-04 | norm 1.4095 | dt 0.026
type train | step 10500 | loss 0.1170 1.8234 7.3761 24.7606 | lr 5.4e-04 | norm 1.2696 | dt 0.025
type train | step 10510 | loss 0.1235 1.8575 7.3996 25.3532 | lr 5.4e-04 | norm 1.9650 | dt 0.036
type train | step 10520 | loss 0.1205 1.8658 7.6107 25.5309 | lr 5.4e-04 | norm 1.5284 | dt 0.035
type train | step 10530 | loss 0.1162 1.8307 7.6303 25.3254 | lr 5.4e-04 | norm 1.3083 | dt 0.036
type train | step 10540 | loss 0.1156 1.8786 7.5401 24.7032 | lr 5.4e-04 | norm 1.3819 | dt 0.035
type train | step 10550 | loss 0.1163 1.8738 7.4819 25.0963 | lr 5.4e-04 | norm 1.4327 | dt 0.035
type train | step 10560 | loss 0.1172 1.8272 7.4463 24.9898 | lr 5.4e-04 | norm 1.6206 | dt 0.035
type train | step 10570 | loss 0.1218 1.8940 7.6883 25.9910 | lr 5.4e-04 | norm 1.3712 | dt 0.035
type train | step 10580 | loss 0.1191 1.8415 7.4039 25.2110 | lr 5.3e-04 | norm 1.4379 | dt 0.035
type train | step 10590 | loss 0.1149 1.8216 7.5988 25.1471 | lr 5.3e-04 | norm 1.2376 | dt 0.035
type train | step 10600 | loss 0.1128 1.8712 7.6028 24.9511 | lr 5.3e-04 | norm 1.2128 | dt 0.035
type train | step 10610 | loss 0.1199 1.9446 7.7047 25.4394 | lr 5.3e-04 | norm 1.4487 | dt 0.035
type train | step 10620 | loss 0.1161 1.8062 7.3258 24.5582 | lr 5.3e-04 | norm 1.2894 | dt 0.035
type train | step 10630 | loss 0.1147 1.8318 7.4468 24.9530 | lr 5.3e-04 | norm 1.3026 | dt 0.036
type train | step 10640 | loss 0.1184 1.8343 7.3207 24.7660 | lr 5.3e-04 | norm 1.2209 | dt 0.035
type train | step 10650 | loss 0.1187 1.8393 7.5281 25.4722 | lr 5.3e-04 | norm 1.4413 | dt 0.035
type train | step 10660 | loss 0.1171 1.8239 7.3553 24.6379 | lr 5.3e-04 | norm 1.3759 | dt 0.036
type train | step 10670 | loss 0.1173 1.9294 7.6192 24.8652 | lr 5.3e-04 | norm 1.5316 | dt 0.035
type train | step 10680 | loss 0.1186 1.8099 7.4716 25.1749 | lr 5.3e-04 | norm 1.5911 | dt 0.035
type train | step 10690 | loss 0.1175 1.8203 7.4807 25.2452 | lr 5.3e-04 | norm 1.4593 | dt 0.035
type train | step 10700 | loss 0.1164 1.8821 7.7566 25.7408 | lr 5.3e-04 | norm 1.2099 | dt 0.035
type train | step 10710 | loss 0.1137 1.8622 7.6983 25.5312 | lr 5.3e-04 | norm 1.2181 | dt 0.036
type train | step 10720 | loss 0.1165 1.8687 7.5653 25.2056 | lr 5.2e-04 | norm 1.3963 | dt 0.035
type train | step 10730 | loss 0.1160 1.7834 7.2387 24.3180 | lr 5.2e-04 | norm 1.4290 | dt 0.035
type train | step 10740 | loss 0.1152 1.8507 7.3217 24.9121 | lr 5.2e-04 | norm 1.5402 | dt 0.035
type train | step 10750 | loss 0.1197 1.8475 7.4669 25.5192 | lr 5.2e-04 | norm 1.4464 | dt 0.035
type train | step 10760 | loss 0.1133 1.8764 7.7716 25.7322 | lr 5.2e-04 | norm 1.3061 | dt 0.034
type train | step 10770 | loss 0.1209 1.8562 7.4869 24.7988 | lr 5.2e-04 | norm 1.4472 | dt 0.034
type train | step 10780 | loss 0.1155 1.8551 7.5311 25.0134 | lr 5.2e-04 | norm 1.1811 | dt 0.033
type train | step 10790 | loss 0.1179 1.8715 7.4325 24.8030 | lr 5.2e-04 | norm 1.5890 | dt 0.034
type train | step 10800 | loss 0.1178 1.8835 7.6551 25.4513 | lr 5.2e-04 | norm 1.3031 | dt 0.034
type train | step 10810 | loss 0.1162 1.8289 7.3644 24.7472 | lr 5.2e-04 | norm 1.4458 | dt 0.030
type train | step 10820 | loss 0.1190 1.8771 7.6055 25.3396 | lr 5.2e-04 | norm 1.1635 | dt 0.027
type train | step 10830 | loss 0.1149 1.8254 7.2121 24.2747 | lr 5.2e-04 | norm 1.4563 | dt 0.026
type train | step 10840 | loss 0.1170 1.8355 7.5210 25.3100 | lr 5.2e-04 | norm 1.3214 | dt 0.026
type train | step 10850 | loss 0.1170 1.8800 7.6420 25.2956 | lr 5.2e-04 | norm 1.2451 | dt 0.026
type train | step 10860 | loss 0.1189 1.8810 7.7327 25.4307 | lr 5.1e-04 | norm 1.3483 | dt 0.026
type train | step 10870 | loss 0.1199 1.8613 7.5421 25.3046 | lr 5.1e-04 | norm 1.4684 | dt 0.026
type train | step 10880 | loss 0.1164 1.9005 7.7218 26.0544 | lr 5.1e-04 | norm 1.2791 | dt 0.026
type train | step 10890 | loss 0.1171 1.9048 7.7815 25.9242 | lr 5.1e-04 | norm 1.5653 | dt 0.026
type train | step 10900 | loss 0.1156 1.8638 7.7151 26.0739 | lr 5.1e-04 | norm 1.3147 | dt 0.026
type train | step 10910 | loss 0.1124 1.8720 7.3434 24.4684 | lr 5.1e-04 | norm 1.2306 | dt 0.026
type train | step 10920 | loss 0.1139 1.9024 7.6059 25.0993 | lr 5.1e-04 | norm 1.4054 | dt 0.026
type train | step 10930 | loss 0.1201 1.8421 7.5394 25.0722 | lr 5.1e-04 | norm 1.6299 | dt 0.026
type train | step 10940 | loss 0.1152 1.9206 7.8282 26.4427 | lr 5.1e-04 | norm 1.3765 | dt 0.026
type train | step 10950 | loss 0.1196 1.8953 7.4132 24.7345 | lr 5.1e-04 | norm 1.7518 | dt 0.026
type train | step 10960 | loss 0.1152 1.8668 7.6413 25.7924 | lr 5.1e-04 | norm 1.4792 | dt 0.026
type train | step 10970 | loss 0.1126 1.8682 7.4453 24.5997 | lr 5.1e-04 | norm 1.2492 | dt 0.026
type train | step 10980 | loss 0.1156 1.8915 7.9073 25.9714 | lr 5.1e-04 | norm 1.5149 | dt 0.027
type train | step 10990 | loss 0.1152 1.8714 7.6359 25.3610 | lr 5.0e-04 | norm 1.2505 | dt 0.026
type train | step 11000 | loss 0.1137 1.9172 7.7638 25.9377 | lr 5.0e-04 | norm 1.3564 | dt 0.026
type train | step 11010 | loss 0.1164 1.8288 7.4107 24.6723 | lr 5.0e-04 | norm 1.3741 | dt 0.026
type train | step 11020 | loss 0.1190 1.8951 7.6533 25.7367 | lr 5.0e-04 | norm 1.5345 | dt 0.029
type train | step 11030 | loss 0.1152 1.8581 7.3914 24.4483 | lr 5.0e-04 | norm 1.3369 | dt 0.035
type train | step 11040 | loss 0.1138 1.8695 7.6396 25.2398 | lr 5.0e-04 | norm 1.3309 | dt 0.035
type train | step 11050 | loss 0.1154 1.8658 7.4467 24.6390 | lr 5.0e-04 | norm 1.1484 | dt 0.035
type train | step 11060 | loss 0.1184 1.9413 7.9687 26.7203 | lr 5.0e-04 | norm 1.3660 | dt 0.035
type train | step 11070 | loss 0.1148 1.8793 7.4813 25.0030 | lr 5.0e-04 | norm 1.3789 | dt 0.035
type train | step 11080 | loss 0.1126 1.8053 7.3838 24.5485 | lr 5.0e-04 | norm 1.1812 | dt 0.035
type train | step 11090 | loss 0.1169 1.8872 7.5986 24.9903 | lr 5.0e-04 | norm 1.2887 | dt 0.035
type train | step 11100 | loss 0.1200 1.8841 7.4398 24.6352 | lr 5.0e-04 | norm 1.3671 | dt 0.035
type train | step 11110 | loss 0.1165 1.8401 7.3827 24.7563 | lr 5.0e-04 | norm 1.2601 | dt 0.035
type train | step 11120 | loss 0.1220 1.8763 7.3877 25.3461 | lr 5.0e-04 | norm 1.9470 | dt 0.035
type train | step 11130 | loss 0.1196 1.8961 7.6149 25.5313 | lr 4.9e-04 | norm 1.5029 | dt 0.035
type train | step 11140 | loss 0.1153 1.8564 7.6248 25.3128 | lr 4.9e-04 | norm 1.2755 | dt 0.035
type train | step 11150 | loss 0.1147 1.9109 7.5394 24.6853 | lr 4.9e-04 | norm 1.3681 | dt 0.035
type train | step 11160 | loss 0.1153 1.8974 7.4860 25.0792 | lr 4.9e-04 | norm 1.4157 | dt 0.035
type train | step 11170 | loss 0.1164 1.8473 7.4532 24.9856 | lr 4.9e-04 | norm 1.6061 | dt 0.035
type train | step 11180 | loss 0.1211 1.9124 7.6821 25.9811 | lr 4.9e-04 | norm 1.3794 | dt 0.035
type train | step 11190 | loss 0.1183 1.8659 7.4056 25.1914 | lr 4.9e-04 | norm 1.3884 | dt 0.036
type train | step 11200 | loss 0.1141 1.8454 7.6042 25.1310 | lr 4.9e-04 | norm 1.2466 | dt 0.035
type train | step 11210 | loss 0.1118 1.8953 7.6067 24.9485 | lr 4.9e-04 | norm 1.2077 | dt 0.035
type train | step 11220 | loss 0.1196 1.9612 7.7101 25.4343 | lr 4.9e-04 | norm 1.4611 | dt 0.035
type train | step 11230 | loss 0.1152 1.8217 7.3320 24.5512 | lr 4.9e-04 | norm 1.2747 | dt 0.035
type train | step 11240 | loss 0.1133 1.8464 7.4463 24.9392 | lr 4.9e-04 | norm 1.2835 | dt 0.035
type train | step 11250 | loss 0.1175 1.8478 7.3184 24.7727 | lr 4.9e-04 | norm 1.2008 | dt 0.035
type train | step 11260 | loss 0.1179 1.8534 7.5326 25.4641 | lr 4.9e-04 | norm 1.3985 | dt 0.035
type train | step 11270 | loss 0.1162 1.8400 7.3598 24.6272 | lr 4.8e-04 | norm 1.3727 | dt 0.035
type train | step 11280 | loss 0.1165 1.9454 7.6283 24.8444 | lr 4.8e-04 | norm 1.5254 | dt 0.036
type train | step 11290 | loss 0.1178 1.8218 7.4736 25.1700 | lr 4.8e-04 | norm 1.5835 | dt 0.035
type train | step 11300 | loss 0.1164 1.8284 7.4824 25.2358 | lr 4.8e-04 | norm 1.4564 | dt 0.035
type train | step 11310 | loss 0.1157 1.8878 7.7572 25.7367 | lr 4.8e-04 | norm 1.1919 | dt 0.035
type train | step 11320 | loss 0.1126 1.8742 7.6914 25.5240 | lr 4.8e-04 | norm 1.1982 | dt 0.035
type train | step 11330 | loss 0.1157 1.8684 7.5676 25.1892 | lr 4.8e-04 | norm 1.3792 | dt 0.035
type train | step 11340 | loss 0.1152 1.7918 7.2350 24.3028 | lr 4.8e-04 | norm 1.4230 | dt 0.035
type train | step 11350 | loss 0.1144 1.8575 7.3273 24.8964 | lr 4.8e-04 | norm 1.5313 | dt 0.035
type train | step 11360 | loss 0.1188 1.8431 7.4686 25.5207 | lr 4.8e-04 | norm 1.4432 | dt 0.035
type train | step 11370 | loss 0.1124 1.8813 7.7686 25.7377 | lr 4.8e-04 | norm 1.3131 | dt 0.035
type train | step 11380 | loss 0.1199 1.8559 7.4927 24.7910 | lr 4.8e-04 | norm 1.4394 | dt 0.034
type train | step 11390 | loss 0.1149 1.8592 7.5304 25.0038 | lr 4.8e-04 | norm 1.1743 | dt 0.034
type train | step 11400 | loss 0.1172 1.8677 7.4368 24.8009 | lr 4.8e-04 | norm 1.5776 | dt 0.034
type train | step 11410 | loss 0.1169 1.8866 7.6640 25.4410 | lr 4.7e-04 | norm 1.2980 | dt 0.035
type train | step 11420 | loss 0.1154 1.8270 7.3685 24.7376 | lr 4.7e-04 | norm 1.4181 | dt 0.035
type train | step 11430 | loss 0.1183 1.8702 7.6113 25.3325 | lr 4.7e-04 | norm 1.1535 | dt 0.034
type train | step 11440 | loss 0.1138 1.8178 7.2062 24.2675 | lr 4.7e-04 | norm 1.4438 | dt 0.035
type train | step 11450 | loss 0.1158 1.8280 7.5321 25.2965 | lr 4.7e-04 | norm 1.2710 | dt 0.034
type train | step 11460 | loss 0.1164 1.8669 7.6512 25.2845 | lr 4.7e-04 | norm 1.2442 | dt 0.034
type train | step 11470 | loss 0.1183 1.8759 7.7463 25.4287 | lr 4.7e-04 | norm 1.3443 | dt 0.034
type train | step 11480 | loss 0.1195 1.8529 7.5423 25.2906 | lr 4.7e-04 | norm 1.4565 | dt 0.034
type train | step 11490 | loss 0.1160 1.8880 7.7159 26.0568 | lr 4.7e-04 | norm 1.3006 | dt 0.034
type train | step 11500 | loss 0.1162 1.8923 7.7900 25.9159 | lr 4.7e-04 | norm 1.5516 | dt 0.033
type train | step 11510 | loss 0.1150 1.8487 7.7157 26.0562 | lr 4.7e-04 | norm 1.3074 | dt 0.033
type train | step 11520 | loss 0.1118 1.8558 7.3386 24.4667 | lr 4.7e-04 | norm 1.2342 | dt 0.033
type train | step 11530 | loss 0.1132 1.8813 7.6107 25.0926 | lr 4.7e-04 | norm 1.3790 | dt 0.033
type train | step 11540 | loss 0.1194 1.8230 7.5215 25.0596 | lr 4.6e-04 | norm 1.6290 | dt 0.034
type train | step 11550 | loss 0.1143 1.8973 7.8245 26.4404 | lr 4.6e-04 | norm 1.3732 | dt 0.033
type train | step 11560 | loss 0.1189 1.8824 7.4147 24.7175 | lr 4.6e-04 | norm 1.7431 | dt 0.033
type train | step 11570 | loss 0.1143 1.8369 7.6339 25.7878 | lr 4.6e-04 | norm 1.4475 | dt 0.033
type train | step 11580 | loss 0.1118 1.8521 7.4508 24.5910 | lr 4.6e-04 | norm 1.2406 | dt 0.034
type train | step 11590 | loss 0.1146 1.8680 7.9033 25.9570 | lr 4.6e-04 | norm 1.5062 | dt 0.035
type train | step 11600 | loss 0.1143 1.8531 7.6305 25.3554 | lr 4.6e-04 | norm 1.2318 | dt 0.033
type train | step 11610 | loss 0.1129 1.8924 7.7534 25.9455 | lr 4.6e-04 | norm 1.3521 | dt 0.034
type train | step 11620 | loss 0.1155 1.8096 7.3987 24.6627 | lr 4.6e-04 | norm 1.3732 | dt 0.033
type train | step 11630 | loss 0.1185 1.8655 7.6460 25.7359 | lr 4.6e-04 | norm 1.5269 | dt 0.034
type train | step 11640 | loss 0.1144 1.8319 7.3957 24.4433 | lr 4.6e-04 | norm 1.3379 | dt 0.032
type train | step 11650 | loss 0.1130 1.8394 7.6325 25.2360 | lr 4.6e-04 | norm 1.3161 | dt 0.031
type train | step 11660 | loss 0.1146 1.8389 7.4440 24.6342 | lr 4.6e-04 | norm 1.1298 | dt 0.035
type train | step 11670 | loss 0.1176 1.9058 7.9610 26.7205 | lr 4.6e-04 | norm 1.3708 | dt 0.033
type train | step 11680 | loss 0.1141 1.8497 7.4858 25.0026 | lr 4.5e-04 | norm 1.3680 | dt 0.033
type train | step 11690 | loss 0.1115 1.7805 7.3641 24.5440 | lr 4.5e-04 | norm 1.1500 | dt 0.033
type train | step 11700 | loss 0.1165 1.8604 7.5951 24.9774 | lr 4.5e-04 | norm 1.2604 | dt 0.033
type train | step 11710 | loss 0.1190 1.8488 7.4425 24.6206 | lr 4.5e-04 | norm 1.3595 | dt 0.034
type train | step 11720 | loss 0.1155 1.8106 7.3921 24.7544 | lr 4.5e-04 | norm 1.2447 | dt 0.033
type train | step 11730 | loss 0.1212 1.8533 7.3879 25.3347 | lr 4.5e-04 | norm 1.9546 | dt 0.033
type train | step 11740 | loss 0.1189 1.8672 7.6082 25.5213 | lr 4.5e-04 | norm 1.4832 | dt 0.033
type train | step 11750 | loss 0.1145 1.8236 7.6032 25.2903 | lr 4.5e-04 | norm 1.2661 | dt 0.028
type train | step 11760 | loss 0.1141 1.8749 7.5321 24.6809 | lr 4.5e-04 | norm 1.3734 | dt 0.025
type train | step 11770 | loss 0.1149 1.8597 7.4893 25.0725 | lr 4.5e-04 | norm 1.4066 | dt 0.026
type train | step 11780 | loss 0.1156 1.8170 7.4654 24.9739 | lr 4.5e-04 | norm 1.5918 | dt 0.026
type train | step 11790 | loss 0.1203 1.8814 7.6614 25.9655 | lr 4.5e-04 | norm 1.3655 | dt 0.026
type train | step 11800 | loss 0.1175 1.8368 7.4000 25.1792 | lr 4.5e-04 | norm 1.3723 | dt 0.026
type train | step 11810 | loss 0.1133 1.8181 7.5817 25.1173 | lr 4.5e-04 | norm 1.2155 | dt 0.026
type train | step 11820 | loss 0.1111 1.8629 7.5964 24.9295 | lr 4.4e-04 | norm 1.2032 | dt 0.026
type train | step 11830 | loss 0.1185 1.9309 7.7172 25.4118 | lr 4.4e-04 | norm 1.4389 | dt 0.027
type train | step 11840 | loss 0.1145 1.7933 7.3262 24.5443 | lr 4.4e-04 | norm 1.2672 | dt 0.027
type train | step 11850 | loss 0.1129 1.8130 7.4132 24.9305 | lr 4.4e-04 | norm 1.2892 | dt 0.034
type train | step 11860 | loss 0.1168 1.8259 7.2937 24.7538 | lr 4.4e-04 | norm 1.1847 | dt 0.035
type train | step 11870 | loss 0.1174 1.8253 7.5215 25.4618 | lr 4.4e-04 | norm 1.4014 | dt 0.035
type train | step 11880 | loss 0.1154 1.8069 7.3497 24.6056 | lr 4.4e-04 | norm 1.3716 | dt 0.035
type train | step 11890 | loss 0.1156 1.9094 7.6344 24.8267 | lr 4.4e-04 | norm 1.5085 | dt 0.035
type train | step 11900 | loss 0.1168 1.7942 7.4864 25.1476 | lr 4.4e-04 | norm 1.5728 | dt 0.035
type train | step 11910 | loss 0.1157 1.7985 7.4652 25.2299 | lr 4.4e-04 | norm 1.4481 | dt 0.036
type train | step 11920 | loss 0.1148 1.8562 7.7330 25.7343 | lr 4.4e-04 | norm 1.1905 | dt 0.035
type train | step 11930 | loss 0.1118 1.8501 7.6758 25.5180 | lr 4.4e-04 | norm 1.1863 | dt 0.035
type train | step 11940 | loss 0.1146 1.8490 7.5596 25.1807 | lr 4.4e-04 | norm 1.4002 | dt 0.035
type train | step 11950 | loss 0.1144 1.7674 7.2266 24.3122 | lr 4.4e-04 | norm 1.3943 | dt 0.035
type train | step 11960 | loss 0.1134 1.8271 7.3241 24.8876 | lr 4.3e-04 | norm 1.5134 | dt 0.035
type train | step 11970 | loss 0.1182 1.8138 7.4468 25.5025 | lr 4.3e-04 | norm 1.4261 | dt 0.035
type train | step 11980 | loss 0.1117 1.8517 7.7582 25.7456 | lr 4.3e-04 | norm 1.3186 | dt 0.035
type train | step 11990 | loss 0.1189 1.8342 7.4756 24.7897 | lr 4.3e-04 | norm 1.4197 | dt 0.035
type train | step 12000 | loss 0.1140 1.8330 7.5324 24.9951 | lr 4.3e-04 | norm 1.1717 | dt 0.035
type train | step 12010 | loss 0.1168 1.8472 7.4347 24.7802 | lr 4.3e-04 | norm 1.5729 | dt 0.035
type train | step 12020 | loss 0.1159 1.8534 7.6636 25.4416 | lr 4.3e-04 | norm 1.2775 | dt 0.036
type train | step 12030 | loss 0.1149 1.8021 7.3461 24.7376 | lr 4.3e-04 | norm 1.4452 | dt 0.035
type train | step 12040 | loss 0.1173 1.8456 7.5862 25.3349 | lr 4.3e-04 | norm 1.1641 | dt 0.035
type train | step 12050 | loss 0.1130 1.7975 7.1827 24.2519 | lr 4.3e-04 | norm 1.4111 | dt 0.035
type train | step 12060 | loss 0.1147 1.8048 7.4985 25.2858 | lr 4.3e-04 | norm 1.2714 | dt 0.035
type train | step 12070 | loss 0.1152 1.8431 7.6446 25.2793 | lr 4.3e-04 | norm 1.2343 | dt 0.034
type train | step 12080 | loss 0.1172 1.8549 7.7313 25.4265 | lr 4.3e-04 | norm 1.3360 | dt 0.035
type train | step 12090 | loss 0.1189 1.8361 7.5350 25.2820 | lr 4.3e-04 | norm 1.4597 | dt 0.035
type train | step 12100 | loss 0.1150 1.8658 7.7056 26.0597 | lr 4.2e-04 | norm 1.2992 | dt 0.034
type train | step 12110 | loss 0.1150 1.8732 7.7670 25.9164 | lr 4.2e-04 | norm 1.5401 | dt 0.035
type train | step 12120 | loss 0.1141 1.8249 7.7103 26.0499 | lr 4.2e-04 | norm 1.2960 | dt 0.034
type train | step 12130 | loss 0.1107 1.8304 7.3353 24.4599 | lr 4.2e-04 | norm 1.2331 | dt 0.034
type train | step 12140 | loss 0.1124 1.8605 7.5938 25.0890 | lr 4.2e-04 | norm 1.3631 | dt 0.034
type train | step 12150 | loss 0.1186 1.8043 7.5061 25.0568 | lr 4.2e-04 | norm 1.6150 | dt 0.035
type train | step 12160 | loss 0.1132 1.8715 7.8078 26.4285 | lr 4.2e-04 | norm 1.3532 | dt 0.034
type train | step 12170 | loss 0.1186 1.8603 7.4163 24.6968 | lr 4.2e-04 | norm 1.7263 | dt 0.033
type train | step 12180 | loss 0.1135 1.8149 7.6196 25.7884 | lr 4.2e-04 | norm 1.4428 | dt 0.034
type train | step 12190 | loss 0.1110 1.8222 7.4507 24.5811 | lr 4.2e-04 | norm 1.2517 | dt 0.034
type train | step 12200 | loss 0.1137 1.8561 7.8937 25.9396 | lr 4.2e-04 | norm 1.4916 | dt 0.037
type train | step 12210 | loss 0.1136 1.8369 7.6109 25.3507 | lr 4.2e-04 | norm 1.2288 | dt 0.034
type train | step 12220 | loss 0.1119 1.8737 7.7350 25.9434 | lr 4.2e-04 | norm 1.3583 | dt 0.034
type train | step 12230 | loss 0.1150 1.7919 7.3790 24.6401 | lr 4.2e-04 | norm 1.3502 | dt 0.034
type train | step 12240 | loss 0.1178 1.8385 7.6239 25.7306 | lr 4.2e-04 | norm 1.5175 | dt 0.034
type train | step 12250 | loss 0.1135 1.8155 7.3801 24.4250 | lr 4.1e-04 | norm 1.3312 | dt 0.034
type train | step 12260 | loss 0.1121 1.8227 7.6151 25.2379 | lr 4.1e-04 | norm 1.2785 | dt 0.033
type train | step 12270 | loss 0.1140 1.8232 7.4272 24.6345 | lr 4.1e-04 | norm 1.1187 | dt 0.033
type train | step 12280 | loss 0.1166 1.8921 7.9434 26.7144 | lr 4.1e-04 | norm 1.3562 | dt 0.033
type train | step 12290 | loss 0.1131 1.8378 7.4617 24.9891 | lr 4.1e-04 | norm 1.3318 | dt 0.033
type train | step 12300 | loss 0.1109 1.7694 7.3339 24.5404 | lr 4.1e-04 | norm 1.1430 | dt 0.033
type train | step 12310 | loss 0.1156 1.8486 7.5797 24.9650 | lr 4.1e-04 | norm 1.2687 | dt 0.033
type train | step 12320 | loss 0.1184 1.8351 7.4319 24.5928 | lr 4.1e-04 | norm 1.3535 | dt 0.033
type train | step 12330 | loss 0.1149 1.7941 7.3850 24.7451 | lr 4.1e-04 | norm 1.2394 | dt 0.033
type train | step 12340 | loss 0.1207 1.8402 7.3582 25.3276 | lr 4.1e-04 | norm 1.9577 | dt 0.033
type train | step 12350 | loss 0.1181 1.8589 7.5898 25.5077 | lr 4.1e-04 | norm 1.4554 | dt 0.033
type train | step 12360 | loss 0.1135 1.8138 7.5759 25.2859 | lr 4.1e-04 | norm 1.2524 | dt 0.033
type train | step 12370 | loss 0.1130 1.8650 7.5220 24.6608 | lr 4.1e-04 | norm 1.3686 | dt 0.033
type train | step 12380 | loss 0.1139 1.8429 7.4790 25.0538 | lr 4.1e-04 | norm 1.4078 | dt 0.033
type train | step 12390 | loss 0.1146 1.8078 7.4606 24.9638 | lr 4.0e-04 | norm 1.5871 | dt 0.034
type train | step 12400 | loss 0.1193 1.8703 7.6455 25.9606 | lr 4.0e-04 | norm 1.3638 | dt 0.033
type train | step 12410 | loss 0.1167 1.8242 7.3772 25.1831 | lr 4.0e-04 | norm 1.3603 | dt 0.030
type train | step 12420 | loss 0.1123 1.8100 7.5529 25.1025 | lr 4.0e-04 | norm 1.2168 | dt 0.027
type train | step 12430 | loss 0.1102 1.8552 7.5905 24.9263 | lr 4.0e-04 | norm 1.2033 | dt 0.026
type train | step 12440 | loss 0.1178 1.9147 7.7048 25.3918 | lr 4.0e-04 | norm 1.4227 | dt 0.026
type train | step 12450 | loss 0.1134 1.7844 7.3113 24.5362 | lr 4.0e-04 | norm 1.2635 | dt 0.026
type train | step 12460 | loss 0.1119 1.8032 7.3854 24.9248 | lr 4.0e-04 | norm 1.2715 | dt 0.026
type train | step 12470 | loss 0.1162 1.8140 7.2806 24.7424 | lr 4.0e-04 | norm 1.1747 | dt 0.026
type train | step 12480 | loss 0.1163 1.8175 7.5070 25.4470 | lr 4.0e-04 | norm 1.3923 | dt 0.026
type train | step 12490 | loss 0.1146 1.8023 7.3361 24.5897 | lr 4.0e-04 | norm 1.3552 | dt 0.026
type train | step 12500 | loss 0.1150 1.8997 7.6336 24.8083 | lr 4.0e-04 | norm 1.5065 | dt 0.026
type train | step 12510 | loss 0.1159 1.7868 7.4690 25.1279 | lr 4.0e-04 | norm 1.5520 | dt 0.031
type train | step 12520 | loss 0.1151 1.7865 7.4344 25.2281 | lr 4.0e-04 | norm 1.4507 | dt 0.035
type train | step 12530 | loss 0.1147 1.8484 7.7146 25.7210 | lr 3.9e-04 | norm 1.1894 | dt 0.035
type train | step 12540 | loss 0.1112 1.8421 7.6725 25.5128 | lr 3.9e-04 | norm 1.1957 | dt 0.035
type train | step 12550 | loss 0.1136 1.8407 7.5448 25.1685 | lr 3.9e-04 | norm 1.3931 | dt 0.035
type train | step 12560 | loss 0.1135 1.7604 7.2133 24.3027 | lr 3.9e-04 | norm 1.4104 | dt 0.035
type train | step 12570 | loss 0.1128 1.8175 7.3071 24.8753 | lr 3.9e-04 | norm 1.4929 | dt 0.035
type train | step 12580 | loss 0.1173 1.8033 7.4323 25.4922 | lr 3.9e-04 | norm 1.4319 | dt 0.035
type train | step 12590 | loss 0.1108 1.8419 7.7469 25.7482 | lr 3.9e-04 | norm 1.3039 | dt 0.035
type train | step 12600 | loss 0.1183 1.8253 7.4597 24.7919 | lr 3.9e-04 | norm 1.4133 | dt 0.035
type train | step 12610 | loss 0.1132 1.8329 7.5143 24.9953 | lr 3.9e-04 | norm 1.1627 | dt 0.035
type train | step 12620 | loss 0.1160 1.8419 7.4248 24.7764 | lr 3.9e-04 | norm 1.5804 | dt 0.035
type train | step 12630 | loss 0.1152 1.8403 7.6585 25.4204 | lr 3.9e-04 | norm 1.2526 | dt 0.035
type train | step 12640 | loss 0.1141 1.7880 7.3213 24.7282 | lr 3.9e-04 | norm 1.4192 | dt 0.035
type train | step 12650 | loss 0.1164 1.8364 7.5719 25.3227 | lr 3.9e-04 | norm 1.1464 | dt 0.035
type train | step 12660 | loss 0.1122 1.7902 7.1649 24.2383 | lr 3.9e-04 | norm 1.3967 | dt 0.035
type train | step 12670 | loss 0.1141 1.7971 7.4807 25.2841 | lr 3.9e-04 | norm 1.2505 | dt 0.035
type train | step 12680 | loss 0.1145 1.8309 7.6433 25.2681 | lr 3.8e-04 | norm 1.2400 | dt 0.035
type train | step 12690 | loss 0.1165 1.8426 7.7135 25.4205 | lr 3.8e-04 | norm 1.3227 | dt 0.035
type train | step 12700 | loss 0.1180 1.8259 7.5092 25.2611 | lr 3.8e-04 | norm 1.4450 | dt 0.035
type train | step 12710 | loss 0.1143 1.8574 7.6964 26.0549 | lr 3.8e-04 | norm 1.3108 | dt 0.035
type train | step 12720 | loss 0.1142 1.8617 7.7467 25.9024 | lr 3.8e-04 | norm 1.5401 | dt 0.035
type train | step 12730 | loss 0.1136 1.8164 7.6946 26.0460 | lr 3.8e-04 | norm 1.2838 | dt 0.035
type train | step 12740 | loss 0.1102 1.8214 7.3326 24.4517 | lr 3.8e-04 | norm 1.2334 | dt 0.035
type train | step 12750 | loss 0.1120 1.8463 7.5791 25.0864 | lr 3.8e-04 | norm 1.3522 | dt 0.035
type train | step 12760 | loss 0.1176 1.7950 7.4809 25.0546 | lr 3.8e-04 | norm 1.5986 | dt 0.035
type train | step 12770 | loss 0.1128 1.8646 7.7917 26.4180 | lr 3.8e-04 | norm 1.3747 | dt 0.034
type train | step 12780 | loss 0.1178 1.8513 7.4033 24.6916 | lr 3.8e-04 | norm 1.7190 | dt 0.034
type train | step 12790 | loss 0.1128 1.8110 7.6018 25.7947 | lr 3.8e-04 | norm 1.4264 | dt 0.034
type train | step 12800 | loss 0.1103 1.8127 7.4460 24.5768 | lr 3.8e-04 | norm 1.2411 | dt 0.034
type train | step 12810 | loss 0.1135 1.8409 7.8898 25.9219 | lr 3.8e-04 | norm 1.4948 | dt 0.036
type train | step 12820 | loss 0.1128 1.8278 7.5926 25.3427 | lr 3.8e-04 | norm 1.2199 | dt 0.034
type train | step 12830 | loss 0.1112 1.8657 7.7282 25.9373 | lr 3.7e-04 | norm 1.3666 | dt 0.034
type train | step 12840 | loss 0.1142 1.7807 7.3588 24.6349 | lr 3.7e-04 | norm 1.3099 | dt 0.034
type train | step 12850 | loss 0.1171 1.8252 7.6169 25.7308 | lr 3.7e-04 | norm 1.5084 | dt 0.032
type train | step 12860 | loss 0.1129 1.8089 7.3718 24.4131 | lr 3.7e-04 | norm 1.3358 | dt 0.031
type train | step 12870 | loss 0.1115 1.8100 7.5963 25.2289 | lr 3.7e-04 | norm 1.2689 | dt 0.034
type train | step 12880 | loss 0.1132 1.8177 7.4195 24.6201 | lr 3.7e-04 | norm 1.1115 | dt 0.034
type train | step 12890 | loss 0.1157 1.8818 7.9338 26.7092 | lr 3.7e-04 | norm 1.3548 | dt 0.034
type train | step 12900 | loss 0.1125 1.8207 7.4518 24.9866 | lr 3.7e-04 | norm 1.3106 | dt 0.034
type train | step 12910 | loss 0.1105 1.7645 7.3117 24.5371 | lr 3.7e-04 | norm 1.1407 | dt 0.034
type train | step 12920 | loss 0.1151 1.8416 7.5658 24.9614 | lr 3.7e-04 | norm 1.2630 | dt 0.034
type train | step 12930 | loss 0.1179 1.8276 7.4199 24.5682 | lr 3.7e-04 | norm 1.3345 | dt 0.034
type train | step 12940 | loss 0.1141 1.7927 7.3733 24.7486 | lr 3.7e-04 | norm 1.2302 | dt 0.033
type train | step 12950 | loss 0.1198 1.8348 7.3483 25.3354 | lr 3.7e-04 | norm 1.9465 | dt 0.034
type train | step 12960 | loss 0.1176 1.8515 7.5717 25.4897 | lr 3.7e-04 | norm 1.4360 | dt 0.032
type train | step 12970 | loss 0.1128 1.8086 7.5593 25.2841 | lr 3.7e-04 | norm 1.2430 | dt 0.030
type train | step 12980 | loss 0.1125 1.8570 7.5075 24.6551 | lr 3.6e-04 | norm 1.3517 | dt 0.027
type train | step 12990 | loss 0.1138 1.8378 7.4666 25.0388 | lr 3.6e-04 | norm 1.3997 | dt 0.026
type train | step 13000 | loss 0.1142 1.7965 7.4483 24.9574 | lr 3.6e-04 | norm 1.5680 | dt 0.026
type train | step 13010 | loss 0.1188 1.8656 7.6357 25.9461 | lr 3.6e-04 | norm 1.3581 | dt 0.026
type train | step 13020 | loss 0.1162 1.8146 7.3678 25.1740 | lr 3.6e-04 | norm 1.3584 | dt 0.026
type train | step 13030 | loss 0.1120 1.8010 7.5317 25.0958 | lr 3.6e-04 | norm 1.1989 | dt 0.027
type train | step 13040 | loss 0.1097 1.8460 7.5809 24.9302 | lr 3.6e-04 | norm 1.2036 | dt 0.030
type train | step 13050 | loss 0.1179 1.9055 7.6819 25.3824 | lr 3.6e-04 | norm 1.4266 | dt 0.035
type train | step 13060 | loss 0.1128 1.7765 7.3021 24.5348 | lr 3.6e-04 | norm 1.2598 | dt 0.035
type train | step 13070 | loss 0.1112 1.7971 7.3762 24.9189 | lr 3.6e-04 | norm 1.2768 | dt 0.035
type train | step 13080 | loss 0.1157 1.8094 7.2624 24.7379 | lr 3.6e-04 | norm 1.1723 | dt 0.035
type train | step 13090 | loss 0.1155 1.8182 7.4915 25.4326 | lr 3.6e-04 | norm 1.3737 | dt 0.035
type train | step 13100 | loss 0.1141 1.8011 7.3215 24.5840 | lr 3.6e-04 | norm 1.3558 | dt 0.035
type train | step 13110 | loss 0.1148 1.8914 7.6253 24.7904 | lr 3.6e-04 | norm 1.5042 | dt 0.035
type train | step 13120 | loss 0.1155 1.7883 7.4594 25.1165 | lr 3.6e-04 | norm 1.5458 | dt 0.035
type train | step 13130 | loss 0.1143 1.7835 7.4268 25.2247 | lr 3.5e-04 | norm 1.4553 | dt 0.035
type train | step 13140 | loss 0.1140 1.8416 7.7004 25.7165 | lr 3.5e-04 | norm 1.1740 | dt 0.035
type train | step 13150 | loss 0.1105 1.8297 7.6490 25.5142 | lr 3.5e-04 | norm 1.1792 | dt 0.035
type train | step 13160 | loss 0.1131 1.8409 7.5181 25.1581 | lr 3.5e-04 | norm 1.3809 | dt 0.035
type train | step 13170 | loss 0.1131 1.7472 7.1986 24.2979 | lr 3.5e-04 | norm 1.3786 | dt 0.035
type train | step 13180 | loss 0.1123 1.8191 7.2903 24.8512 | lr 3.5e-04 | norm 1.4887 | dt 0.035
type train | step 13190 | loss 0.1167 1.7980 7.4164 25.5013 | lr 3.5e-04 | norm 1.4223 | dt 0.035
type train | step 13200 | loss 0.1103 1.8361 7.7254 25.7451 | lr 3.5e-04 | norm 1.3048 | dt 0.035
type train | step 13210 | loss 0.1176 1.8172 7.4370 24.7938 | lr 3.5e-04 | norm 1.3988 | dt 0.035
type train | step 13220 | loss 0.1130 1.8257 7.4983 24.9762 | lr 3.5e-04 | norm 1.1381 | dt 0.035
type train | step 13230 | loss 0.1154 1.8349 7.4091 24.7603 | lr 3.5e-04 | norm 1.5665 | dt 0.036
type train | step 13240 | loss 0.1146 1.8368 7.6406 25.4072 | lr 3.5e-04 | norm 1.2482 | dt 0.035
type train | step 13250 | loss 0.1137 1.7865 7.3065 24.7303 | lr 3.5e-04 | norm 1.4094 | dt 0.035
type train | step 13260 | loss 0.1160 1.8321 7.5624 25.3041 | lr 3.5e-04 | norm 1.1436 | dt 0.035
type train | step 13270 | loss 0.1119 1.7734 7.1461 24.2284 | lr 3.5e-04 | norm 1.3699 | dt 0.034
type train | step 13280 | loss 0.1138 1.7983 7.4680 25.2888 | lr 3.4e-04 | norm 1.2555 | dt 0.035
type train | step 13290 | loss 0.1140 1.8260 7.6285 25.2664 | lr 3.4e-04 | norm 1.2322 | dt 0.034
type train | step 13300 | loss 0.1159 1.8408 7.6984 25.4107 | lr 3.4e-04 | norm 1.3146 | dt 0.034
type train | step 13310 | loss 0.1175 1.8189 7.4865 25.2529 | lr 3.4e-04 | norm 1.4366 | dt 0.034
type train | step 13320 | loss 0.1138 1.8546 7.6842 26.0461 | lr 3.4e-04 | norm 1.2971 | dt 0.034
type train | step 13330 | loss 0.1138 1.8505 7.7351 25.8859 | lr 3.4e-04 | norm 1.5193 | dt 0.035
type train | step 13340 | loss 0.1130 1.8147 7.6847 26.0552 | lr 3.4e-04 | norm 1.2661 | dt 0.034
type train | step 13350 | loss 0.1097 1.8150 7.3201 24.4504 | lr 3.4e-04 | norm 1.2478 | dt 0.033
type train | step 13360 | loss 0.1115 1.8459 7.5611 25.0775 | lr 3.4e-04 | norm 1.3497 | dt 0.033
type train | step 13370 | loss 0.1172 1.7911 7.4652 25.0548 | lr 3.4e-04 | norm 1.5866 | dt 0.030
type train | step 13380 | loss 0.1126 1.8610 7.7815 26.4090 | lr 3.4e-04 | norm 1.3497 | dt 0.026
type train | step 13390 | loss 0.1173 1.8429 7.3876 24.6802 | lr 3.4e-04 | norm 1.6946 | dt 0.026
type train | step 13400 | loss 0.1123 1.8141 7.5926 25.8022 | lr 3.4e-04 | norm 1.4296 | dt 0.026
type train | step 13410 | loss 0.1098 1.8060 7.4281 24.5684 | lr 3.4e-04 | norm 1.2236 | dt 0.026
type train | step 13420 | loss 0.1127 1.8327 7.8723 25.9049 | lr 3.4e-04 | norm 1.4712 | dt 0.027
type train | step 13430 | loss 0.1124 1.8198 7.5717 25.3419 | lr 3.3e-04 | norm 1.1888 | dt 0.026
type train | step 13440 | loss 0.1107 1.8589 7.7056 25.9389 | lr 3.3e-04 | norm 1.3418 | dt 0.026
type train | step 13450 | loss 0.1138 1.7761 7.3409 24.6160 | lr 3.3e-04 | norm 1.2928 | dt 0.026
type train | step 13460 | loss 0.1170 1.8247 7.6010 25.7217 | lr 3.3e-04 | norm 1.4979 | dt 0.026
type train | step 13470 | loss 0.1125 1.8072 7.3639 24.4010 | lr 3.3e-04 | norm 1.3294 | dt 0.026
type train | step 13480 | loss 0.1111 1.7990 7.5785 25.2206 | lr 3.3e-04 | norm 1.2429 | dt 0.026
type train | step 13490 | loss 0.1129 1.8091 7.4059 24.6223 | lr 3.3e-04 | norm 1.0955 | dt 0.026
type train | step 13500 | loss 0.1151 1.8770 7.9334 26.6987 | lr 3.3e-04 | norm 1.3754 | dt 0.026
type train | step 13510 | loss 0.1120 1.8090 7.4429 24.9801 | lr 3.3e-04 | norm 1.3042 | dt 0.035
type train | step 13520 | loss 0.1099 1.7573 7.2982 24.5213 | lr 3.3e-04 | norm 1.1316 | dt 0.035
type train | step 13530 | loss 0.1147 1.8292 7.5550 24.9422 | lr 3.3e-04 | norm 1.2459 | dt 0.035
type train | step 13540 | loss 0.1178 1.8173 7.4051 24.5568 | lr 3.3e-04 | norm 1.3404 | dt 0.035
type train | step 13550 | loss 0.1137 1.7800 7.3538 24.7445 | lr 3.3e-04 | norm 1.2175 | dt 0.036
type train | step 13560 | loss 0.1196 1.8263 7.3306 25.3279 | lr 3.3e-04 | norm 1.9547 | dt 0.035
type train | step 13570 | loss 0.1173 1.8420 7.5520 25.4720 | lr 3.3e-04 | norm 1.4008 | dt 0.035
type train | step 13580 | loss 0.1126 1.8008 7.5449 25.2612 | lr 3.3e-04 | norm 1.2349 | dt 0.035
type train | step 13590 | loss 0.1123 1.8466 7.4988 24.6415 | lr 3.2e-04 | norm 1.3603 | dt 0.035
type train | step 13600 | loss 0.1133 1.8208 7.4540 25.0340 | lr 3.2e-04 | norm 1.3971 | dt 0.036
type train | step 13610 | loss 0.1141 1.7920 7.4350 24.9425 | lr 3.2e-04 | norm 1.5745 | dt 0.035
type train | step 13620 | loss 0.1186 1.8548 7.6228 25.9385 | lr 3.2e-04 | norm 1.3554 | dt 0.035
type train | step 13630 | loss 0.1160 1.8034 7.3478 25.1651 | lr 3.2e-04 | norm 1.3383 | dt 0.035
type train | step 13640 | loss 0.1114 1.7966 7.5128 25.0805 | lr 3.2e-04 | norm 1.2159 | dt 0.035
type train | step 13650 | loss 0.1093 1.8321 7.5641 24.9228 | lr 3.2e-04 | norm 1.2030 | dt 0.035
type train | step 13660 | loss 0.1174 1.8921 7.6697 25.3696 | lr 3.2e-04 | norm 1.4125 | dt 0.035
type train | step 13670 | loss 0.1126 1.7649 7.2993 24.5250 | lr 3.2e-04 | norm 1.2475 | dt 0.035
type train | step 13680 | loss 0.1110 1.7885 7.3630 24.9124 | lr 3.2e-04 | norm 1.2642 | dt 0.035
type train | step 13690 | loss 0.1155 1.7959 7.2511 24.7276 | lr 3.2e-04 | norm 1.1794 | dt 0.035
type train | step 13700 | loss 0.1151 1.8082 7.4783 25.4079 | lr 3.2e-04 | norm 1.3706 | dt 0.035
type train | step 13710 | loss 0.1142 1.7845 7.2981 24.5735 | lr 3.2e-04 | norm 1.3519 | dt 0.035
type train | step 13720 | loss 0.1140 1.8734 7.6130 24.7792 | lr 3.2e-04 | norm 1.4957 | dt 0.036
type train | step 13730 | loss 0.1157 1.7731 7.4512 25.1090 | lr 3.2e-04 | norm 1.5499 | dt 0.035
type train | step 13740 | loss 0.1141 1.7739 7.4110 25.2130 | lr 3.2e-04 | norm 1.4425 | dt 0.035
type train | step 13750 | loss 0.1137 1.8319 7.6983 25.6901 | lr 3.1e-04 | norm 1.1667 | dt 0.036
type train | step 13760 | loss 0.1101 1.8161 7.6320 25.5024 | lr 3.1e-04 | norm 1.1817 | dt 0.035
type train | step 13770 | loss 0.1127 1.8253 7.5070 25.1437 | lr 3.1e-04 | norm 1.3782 | dt 0.034
type train | step 13780 | loss 0.1125 1.7372 7.1848 24.2938 | lr 3.1e-04 | norm 1.3575 | dt 0.035
type train | step 13790 | loss 0.1119 1.8056 7.2764 24.8347 | lr 3.1e-04 | norm 1.4841 | dt 0.034
type train | step 13800 | loss 0.1166 1.7805 7.3987 25.4921 | lr 3.1e-04 | norm 1.4288 | dt 0.035
type train | step 13810 | loss 0.1102 1.8303 7.7218 25.7275 | lr 3.1e-04 | norm 1.3224 | dt 0.034
type train | step 13820 | loss 0.1173 1.8033 7.4235 24.7821 | lr 3.1e-04 | norm 1.3857 | dt 0.035
type train | step 13830 | loss 0.1126 1.8120 7.4910 24.9517 | lr 3.1e-04 | norm 1.1367 | dt 0.034
type train | step 13840 | loss 0.1148 1.8204 7.4013 24.7390 | lr 3.1e-04 | norm 1.5735 | dt 0.034
type train | step 13850 | loss 0.1144 1.8252 7.6326 25.3880 | lr 3.1e-04 | norm 1.2497 | dt 0.033
type train | step 13860 | loss 0.1134 1.7709 7.2895 24.7077 | lr 3.1e-04 | norm 1.3994 | dt 0.028
type train | step 13870 | loss 0.1156 1.8214 7.5601 25.2948 | lr 3.1e-04 | norm 1.1542 | dt 0.027
type train | step 13880 | loss 0.1120 1.7642 7.1437 24.2039 | lr 3.1e-04 | norm 1.3901 | dt 0.026
type train | step 13890 | loss 0.1135 1.7895 7.4669 25.2773 | lr 3.1e-04 | norm 1.2792 | dt 0.026
type train | step 13900 | loss 0.1133 1.8146 7.6152 25.2381 | lr 3.1e-04 | norm 1.2160 | dt 0.026
type train | step 13910 | loss 0.1159 1.8269 7.6855 25.3785 | lr 3.0e-04 | norm 1.3234 | dt 0.026
type train | step 13920 | loss 0.1173 1.8101 7.4786 25.2298 | lr 3.0e-04 | norm 1.4445 | dt 0.026
type train | step 13930 | loss 0.1135 1.8452 7.6827 26.0340 | lr 3.0e-04 | norm 1.3078 | dt 0.026
type train | step 13940 | loss 0.1133 1.8434 7.7260 25.8573 | lr 3.0e-04 | norm 1.4959 | dt 0.026
type train | step 13950 | loss 0.1126 1.8052 7.6778 26.0496 | lr 3.0e-04 | norm 1.2499 | dt 0.026
type train | step 13960 | loss 0.1091 1.8048 7.3150 24.4317 | lr 3.0e-04 | norm 1.2276 | dt 0.026
type train | step 13970 | loss 0.1114 1.8330 7.5487 25.0513 | lr 3.0e-04 | norm 1.3333 | dt 0.026
type train | step 13980 | loss 0.1170 1.7801 7.4547 25.0416 | lr 3.0e-04 | norm 1.5816 | dt 0.026
type train | step 13990 | loss 0.1121 1.8482 7.7761 26.3972 | lr 3.0e-04 | norm 1.3419 | dt 0.026
type train | step 14000 | loss 0.1168 1.8316 7.3783 24.6459 | lr 3.0e-04 | norm 1.6713 | dt 0.026
type train | step 14010 | loss 0.1121 1.8034 7.5848 25.7821 | lr 3.0e-04 | norm 1.4165 | dt 0.035
type train | step 14020 | loss 0.1093 1.7933 7.4247 24.5513 | lr 3.0e-04 | norm 1.2355 | dt 0.035
type train | step 14030 | loss 0.1125 1.8204 7.8596 25.8795 | lr 3.0e-04 | norm 1.4554 | dt 0.037
type train | step 14040 | loss 0.1124 1.8106 7.5714 25.3317 | lr 3.0e-04 | norm 1.1877 | dt 0.035
type train | step 14050 | loss 0.1104 1.8536 7.6948 25.9155 | lr 3.0e-04 | norm 1.3364 | dt 0.035
type train | step 14060 | loss 0.1134 1.7607 7.3346 24.5955 | lr 3.0e-04 | norm 1.2836 | dt 0.035
type train | step 14070 | loss 0.1163 1.8198 7.5940 25.7022 | lr 2.9e-04 | norm 1.4778 | dt 0.035
type train | step 14080 | loss 0.1124 1.7926 7.3539 24.3935 | lr 2.9e-04 | norm 1.3292 | dt 0.035
type train | step 14090 | loss 0.1108 1.7964 7.5684 25.2137 | lr 2.9e-04 | norm 1.2257 | dt 0.035
type train | step 14100 | loss 0.1126 1.8021 7.4078 24.6146 | lr 2.9e-04 | norm 1.1171 | dt 0.035
type train | step 14110 | loss 0.1148 1.8678 7.9191 26.6785 | lr 2.9e-04 | norm 1.3596 | dt 0.036
type train | step 14120 | loss 0.1118 1.8006 7.4329 24.9501 | lr 2.9e-04 | norm 1.2734 | dt 0.035
type train | step 14130 | loss 0.1095 1.7481 7.2897 24.5119 | lr 2.9e-04 | norm 1.1289 | dt 0.035
type train | step 14140 | loss 0.1143 1.8196 7.5432 24.9326 | lr 2.9e-04 | norm 1.2446 | dt 0.035
type train | step 14150 | loss 0.1173 1.8045 7.3928 24.5267 | lr 2.9e-04 | norm 1.3257 | dt 0.035
type train | step 14160 | loss 0.1136 1.7730 7.3446 24.7421 | lr 2.9e-04 | norm 1.2330 | dt 0.035
type train | step 14170 | loss 0.1194 1.8182 7.3214 25.3243 | lr 2.9e-04 | norm 1.9431 | dt 0.035
type train | step 14180 | loss 0.1169 1.8306 7.5452 25.4547 | lr 2.9e-04 | norm 1.3833 | dt 0.035
type train | step 14190 | loss 0.1120 1.7940 7.5338 25.2399 | lr 2.9e-04 | norm 1.2326 | dt 0.035
type train | step 14200 | loss 0.1119 1.8378 7.4913 24.6426 | lr 2.9e-04 | norm 1.3521 | dt 0.035
type train | step 14210 | loss 0.1133 1.8138 7.4470 25.0212 | lr 2.9e-04 | norm 1.3865 | dt 0.035
type train | step 14220 | loss 0.1137 1.7815 7.4291 24.9315 | lr 2.9e-04 | norm 1.5617 | dt 0.035
type train | step 14230 | loss 0.1181 1.8456 7.6133 25.9203 | lr 2.9e-04 | norm 1.3572 | dt 0.035
type train | step 14240 | loss 0.1155 1.7949 7.3465 25.1655 | lr 2.8e-04 | norm 1.3343 | dt 0.035
type train | step 14250 | loss 0.1107 1.7873 7.5008 25.0724 | lr 2.8e-04 | norm 1.1824 | dt 0.035
type train | step 14260 | loss 0.1091 1.8242 7.5484 24.8979 | lr 2.8e-04 | norm 1.2111 | dt 0.035
type train | step 14270 | loss 0.1174 1.8837 7.6595 25.3525 | lr 2.8e-04 | norm 1.4132 | dt 0.035
type train | step 14280 | loss 0.1121 1.7592 7.2932 24.5052 | lr 2.8e-04 | norm 1.2609 | dt 0.034
type train | step 14290 | loss 0.1106 1.7809 7.3496 24.9020 | lr 2.8e-04 | norm 1.2522 | dt 0.034
type train | step 14300 | loss 0.1151 1.7828 7.2461 24.7201 | lr 2.8e-04 | norm 1.1577 | dt 0.034
type train | step 14310 | loss 0.1147 1.7979 7.4694 25.3928 | lr 2.8e-04 | norm 1.3579 | dt 0.034
type train | step 14320 | loss 0.1135 1.7744 7.2872 24.5616 | lr 2.8e-04 | norm 1.3364 | dt 0.034
type train | step 14330 | loss 0.1136 1.8646 7.6130 24.7751 | lr 2.8e-04 | norm 1.4868 | dt 0.033
type train | step 14340 | loss 0.1150 1.7624 7.4392 25.0981 | lr 2.8e-04 | norm 1.5393 | dt 0.031
type train | step 14350 | loss 0.1137 1.7670 7.3990 25.1926 | lr 2.8e-04 | norm 1.4338 | dt 0.028
type train | step 14360 | loss 0.1135 1.8250 7.6858 25.6763 | lr 2.8e-04 | norm 1.1726 | dt 0.027
type train | step 14370 | loss 0.1098 1.8116 7.6232 25.4867 | lr 2.8e-04 | norm 1.1654 | dt 0.026
type train | step 14380 | loss 0.1122 1.8143 7.4952 25.1226 | lr 2.8e-04 | norm 1.3693 | dt 0.026
type train | step 14390 | loss 0.1121 1.7288 7.1688 24.2771 | lr 2.8e-04 | norm 1.3610 | dt 0.026
type train | step 14400 | loss 0.1115 1.7941 7.2638 24.8255 | lr 2.8e-04 | norm 1.4895 | dt 0.026
type train | step 14410 | loss 0.1161 1.7728 7.3909 25.4763 | lr 2.7e-04 | norm 1.4054 | dt 0.026
type train | step 14420 | loss 0.1101 1.8252 7.7168 25.7206 | lr 2.7e-04 | norm 1.3315 | dt 0.025
type train | step 14430 | loss 0.1168 1.7970 7.4205 24.7740 | lr 2.7e-04 | norm 1.3728 | dt 0.026
type train | step 14440 | loss 0.1122 1.8055 7.4834 24.9391 | lr 2.7e-04 | norm 1.1342 | dt 0.026
type train | step 14450 | loss 0.1145 1.8118 7.3985 24.7210 | lr 2.7e-04 | norm 1.5584 | dt 0.026
type train | step 14460 | loss 0.1139 1.8205 7.6234 25.3814 | lr 2.7e-04 | norm 1.2493 | dt 0.026
type train | step 14470 | loss 0.1130 1.7671 7.2780 24.6937 | lr 2.7e-04 | norm 1.3817 | dt 0.026
type train | step 14480 | loss 0.1151 1.8144 7.5520 25.2799 | lr 2.7e-04 | norm 1.1467 | dt 0.026
type train | step 14490 | loss 0.1110 1.7549 7.1291 24.1899 | lr 2.7e-04 | norm 1.3460 | dt 0.027
type train | step 14500 | loss 0.1131 1.7850 7.4621 25.2836 | lr 2.7e-04 | norm 1.2315 | dt 0.026
type train | step 14510 | loss 0.1131 1.8078 7.6042 25.2311 | lr 2.7e-04 | norm 1.2451 | dt 0.027
type train | step 14520 | loss 0.1151 1.8197 7.6793 25.3720 | lr 2.7e-04 | norm 1.3069 | dt 0.027
type train | step 14530 | loss 0.1170 1.8032 7.4722 25.2202 | lr 2.7e-04 | norm 1.4170 | dt 0.027
type train | step 14540 | loss 0.1130 1.8407 7.6775 26.0263 | lr 2.7e-04 | norm 1.3108 | dt 0.027
type train | step 14550 | loss 0.1130 1.8372 7.7085 25.8532 | lr 2.7e-04 | norm 1.4912 | dt 0.027
type train | step 14560 | loss 0.1124 1.7973 7.6727 26.0462 | lr 2.7e-04 | norm 1.2487 | dt 0.027
type train | step 14570 | loss 0.1089 1.7986 7.3152 24.4223 | lr 2.7e-04 | norm 1.2225 | dt 0.027
type train | step 14580 | loss 0.1110 1.8302 7.5355 25.0376 | lr 2.6e-04 | norm 1.3257 | dt 0.027
type train | step 14590 | loss 0.1166 1.7746 7.4549 25.0343 | lr 2.6e-04 | norm 1.5682 | dt 0.026
type train | step 14600 | loss 0.1118 1.8421 7.7737 26.3893 | lr 2.6e-04 | norm 1.3420 | dt 0.029
type train | step 14610 | loss 0.1164 1.8217 7.3634 24.6236 | lr 2.6e-04 | norm 1.6491 | dt 0.029
type train | step 14620 | loss 0.1119 1.8013 7.5789 25.7907 | lr 2.6e-04 | norm 1.4106 | dt 0.035
type train | step 14630 | loss 0.1093 1.7859 7.4188 24.5615 | lr 2.6e-04 | norm 1.2397 | dt 0.035
type train | step 14640 | loss 0.1124 1.8128 7.8504 25.8565 | lr 2.6e-04 | norm 1.4498 | dt 0.037
type train | step 14650 | loss 0.1118 1.8058 7.5596 25.3364 | lr 2.6e-04 | norm 1.1691 | dt 0.035
type train | step 14660 | loss 0.1102 1.8473 7.6778 25.9083 | lr 2.6e-04 | norm 1.3383 | dt 0.035
type train | step 14670 | loss 0.1130 1.7532 7.3254 24.5823 | lr 2.6e-04 | norm 1.2560 | dt 0.035
type train | step 14680 | loss 0.1163 1.8181 7.5766 25.7028 | lr 2.6e-04 | norm 1.4861 | dt 0.035
type train | step 14690 | loss 0.1119 1.7943 7.3406 24.3897 | lr 2.6e-04 | norm 1.3120 | dt 0.035
type train | step 14700 | loss 0.1105 1.7887 7.5609 25.2054 | lr 2.6e-04 | norm 1.2286 | dt 0.035
type train | step 14710 | loss 0.1125 1.7982 7.3983 24.6126 | lr 2.6e-04 | norm 1.0999 | dt 0.035
type train | step 14720 | loss 0.1142 1.8622 7.9107 26.6787 | lr 2.6e-04 | norm 1.3451 | dt 0.035
type train | step 14730 | loss 0.1113 1.7972 7.4259 24.9411 | lr 2.6e-04 | norm 1.2394 | dt 0.036
type train | step 14740 | loss 0.1093 1.7476 7.2704 24.5130 | lr 2.6e-04 | norm 1.1320 | dt 0.036
type train | step 14750 | loss 0.1141 1.8172 7.5324 24.9238 | lr 2.6e-04 | norm 1.2354 | dt 0.035
type train | step 14760 | loss 0.1168 1.7959 7.3810 24.5098 | lr 2.5e-04 | norm 1.3257 | dt 0.035
type train | step 14770 | loss 0.1131 1.7663 7.3368 24.7356 | lr 2.5e-04 | norm 1.2342 | dt 0.036
type train | step 14780 | loss 0.1192 1.8185 7.3214 25.3199 | lr 2.5e-04 | norm 1.9313 | dt 0.035
type train | step 14790 | loss 0.1165 1.8237 7.5325 25.4418 | lr 2.5e-04 | norm 1.3676 | dt 0.035
type train | step 14800 | loss 0.1116 1.7894 7.5214 25.2388 | lr 2.5e-04 | norm 1.2424 | dt 0.036
type train | step 14810 | loss 0.1119 1.8319 7.4852 24.6304 | lr 2.5e-04 | norm 1.3492 | dt 0.035
type train | step 14820 | loss 0.1130 1.8125 7.4385 25.0237 | lr 2.5e-04 | norm 1.3828 | dt 0.035
type train | step 14830 | loss 0.1134 1.7774 7.4196 24.9288 | lr 2.5e-04 | norm 1.5617 | dt 0.035
type train | step 14840 | loss 0.1179 1.8450 7.6066 25.9131 | lr 2.5e-04 | norm 1.3326 | dt 0.035
type train | step 14850 | loss 0.1151 1.7924 7.3391 25.1581 | lr 2.5e-04 | norm 1.3245 | dt 0.035
type train | step 14860 | loss 0.1103 1.7847 7.4867 25.0685 | lr 2.5e-04 | norm 1.1871 | dt 0.035
type train | step 14870 | loss 0.1089 1.8219 7.5414 24.8918 | lr 2.5e-04 | norm 1.2028 | dt 0.035
type train | step 14880 | loss 0.1171 1.8808 7.6535 25.3535 | lr 2.5e-04 | norm 1.4171 | dt 0.035
type train | step 14890 | loss 0.1118 1.7533 7.2834 24.4989 | lr 2.5e-04 | norm 1.2488 | dt 0.035
type train | step 14900 | loss 0.1104 1.7762 7.3477 24.8976 | lr 2.5e-04 | norm 1.2499 | dt 0.035
type train | step 14910 | loss 0.1148 1.7834 7.2423 24.7139 | lr 2.5e-04 | norm 1.1671 | dt 0.035
type train | step 14920 | loss 0.1139 1.7976 7.4608 25.3817 | lr 2.5e-04 | norm 1.3460 | dt 0.036
type train | step 14930 | loss 0.1129 1.7715 7.2759 24.5507 | lr 2.5e-04 | norm 1.3287 | dt 0.035
type train | step 14940 | loss 0.1136 1.8608 7.6104 24.7744 | lr 2.4e-04 | norm 1.5054 | dt 0.035
type train | step 14950 | loss 0.1148 1.7649 7.4256 25.0999 | lr 2.4e-04 | norm 1.5320 | dt 0.035
type train | step 14960 | loss 0.1136 1.7639 7.3895 25.1865 | lr 2.4e-04 | norm 1.4251 | dt 0.035
type train | step 14970 | loss 0.1131 1.8258 7.6735 25.6622 | lr 2.4e-04 | norm 1.1657 | dt 0.035
type train | step 14980 | loss 0.1094 1.8130 7.6141 25.4900 | lr 2.4e-04 | norm 1.1564 | dt 0.035
type train | step 14990 | loss 0.1119 1.8104 7.4788 25.1005 | lr 2.4e-04 | norm 1.3610 | dt 0.035
type train | step 15000 | loss 0.1117 1.7280 7.1554 24.2772 | lr 2.4e-04 | norm 1.3463 | dt 0.035
type train | step 15010 | loss 0.1113 1.7918 7.2601 24.8269 | lr 2.4e-04 | norm 1.4845 | dt 0.034
type train | step 15020 | loss 0.1159 1.7714 7.3853 25.4732 | lr 2.4e-04 | norm 1.3997 | dt 0.035
type train | step 15030 | loss 0.1096 1.8245 7.7053 25.7125 | lr 2.4e-04 | norm 1.3237 | dt 0.033
type train | step 15040 | loss 0.1166 1.7944 7.4049 24.7670 | lr 2.4e-04 | norm 1.3521 | dt 0.035
type train | step 15050 | loss 0.1117 1.8046 7.4721 24.9284 | lr 2.4e-04 | norm 1.1032 | dt 0.034
type train | step 15060 | loss 0.1141 1.8085 7.3832 24.7110 | lr 2.4e-04 | norm 1.5583 | dt 0.034
type train | step 15070 | loss 0.1135 1.8196 7.6105 25.3803 | lr 2.4e-04 | norm 1.2354 | dt 0.033
type train | step 15080 | loss 0.1128 1.7722 7.2689 24.6808 | lr 2.4e-04 | norm 1.3725 | dt 0.033
type train | step 15090 | loss 0.1149 1.8122 7.5416 25.2753 | lr 2.4e-04 | norm 1.1478 | dt 0.034
type train | step 15100 | loss 0.1105 1.7550 7.1190 24.1851 | lr 2.4e-04 | norm 1.3190 | dt 0.034
type train | step 15110 | loss 0.1125 1.7862 7.4559 25.2766 | lr 2.4e-04 | norm 1.2314 | dt 0.031
type train | step 15120 | loss 0.1127 1.8063 7.5958 25.2212 | lr 2.4e-04 | norm 1.2225 | dt 0.027
type train | step 15130 | loss 0.1148 1.8184 7.6673 25.3621 | lr 2.3e-04 | norm 1.3033 | dt 0.027
type train | step 15140 | loss 0.1170 1.8017 7.4573 25.2151 | lr 2.3e-04 | norm 1.4068 | dt 0.026
type train | step 15150 | loss 0.1129 1.8440 7.6681 26.0309 | lr 2.3e-04 | norm 1.3100 | dt 0.026
type train | step 15160 | loss 0.1128 1.8363 7.6965 25.8516 | lr 2.3e-04 | norm 1.4719 | dt 0.026
type train | step 15170 | loss 0.1123 1.7992 7.6629 26.0454 | lr 2.3e-04 | norm 1.2450 | dt 0.026
type train | step 15180 | loss 0.1084 1.7984 7.3127 24.4286 | lr 2.3e-04 | norm 1.2230 | dt 0.027
type train | step 15190 | loss 0.1105 1.8310 7.5214 25.0357 | lr 2.3e-04 | norm 1.3179 | dt 0.026
type train | step 15200 | loss 0.1163 1.7736 7.4431 25.0288 | lr 2.3e-04 | norm 1.5613 | dt 0.026
type train | step 15210 | loss 0.1117 1.8464 7.7689 26.3835 | lr 2.3e-04 | norm 1.3422 | dt 0.026
type train | step 15220 | loss 0.1162 1.8213 7.3495 24.6210 | lr 2.3e-04 | norm 1.6096 | dt 0.026
type train | step 15230 | loss 0.1117 1.7980 7.5701 25.7867 | lr 2.3e-04 | norm 1.4013 | dt 0.026
type train | step 15240 | loss 0.1087 1.7881 7.4160 24.5573 | lr 2.3e-04 | norm 1.2375 | dt 0.026
type train | step 15250 | loss 0.1119 1.8128 7.8470 25.8471 | lr 2.3e-04 | norm 1.4469 | dt 0.027
type train | step 15260 | loss 0.1114 1.8055 7.5521 25.3300 | lr 2.3e-04 | norm 1.1477 | dt 0.027
type train | step 15270 | loss 0.1100 1.8468 7.6654 25.9095 | lr 2.3e-04 | norm 1.3300 | dt 0.027
type train | step 15280 | loss 0.1125 1.7519 7.3181 24.5745 | lr 2.3e-04 | norm 1.2372 | dt 0.027
type train | step 15290 | loss 0.1157 1.8143 7.5696 25.6960 | lr 2.3e-04 | norm 1.4680 | dt 0.027
type train | step 15300 | loss 0.1114 1.7927 7.3353 24.3929 | lr 2.3e-04 | norm 1.3111 | dt 0.027
type train | step 15310 | loss 0.1101 1.7904 7.5502 25.2041 | lr 2.3e-04 | norm 1.2057 | dt 0.027
type train | step 15320 | loss 0.1118 1.7988 7.3929 24.6089 | lr 2.2e-04 | norm 1.0857 | dt 0.027
type train | step 15330 | loss 0.1142 1.8616 7.8986 26.6715 | lr 2.2e-04 | norm 1.3556 | dt 0.028
type train | step 15340 | loss 0.1111 1.7952 7.4196 24.9314 | lr 2.2e-04 | norm 1.2344 | dt 0.027
type train | step 15350 | loss 0.1087 1.7516 7.2606 24.5067 | lr 2.2e-04 | norm 1.1163 | dt 0.027
type train | step 15360 | loss 0.1137 1.8182 7.5294 24.9175 | lr 2.2e-04 | norm 1.2384 | dt 0.027
type train | step 15370 | loss 0.1169 1.7942 7.3765 24.5070 | lr 2.2e-04 | norm 1.3331 | dt 0.027
type train | step 15380 | loss 0.1131 1.7687 7.3312 24.7277 | lr 2.2e-04 | norm 1.2415 | dt 0.027
type train | step 15390 | loss 0.1191 1.8151 7.3212 25.3173 | lr 2.2e-04 | norm 1.9510 | dt 0.027
type train | step 15400 | loss 0.1162 1.8271 7.5246 25.4360 | lr 2.2e-04 | norm 1.3564 | dt 0.027
type train | step 15410 | loss 0.1112 1.7967 7.5147 25.2284 | lr 2.2e-04 | norm 1.2461 | dt 0.027
type train | step 15420 | loss 0.1114 1.8323 7.4785 24.6262 | lr 2.2e-04 | norm 1.3482 | dt 0.032
type train | step 15430 | loss 0.1127 1.8159 7.4307 25.0251 | lr 2.2e-04 | norm 1.3834 | dt 0.034
type train | step 15440 | loss 0.1129 1.7787 7.4189 24.9198 | lr 2.2e-04 | norm 1.5513 | dt 0.036
type train | step 15450 | loss 0.1178 1.8439 7.6022 25.9108 | lr 2.2e-04 | norm 1.3341 | dt 0.035
type train | step 15460 | loss 0.1148 1.7935 7.3349 25.1519 | lr 2.2e-04 | norm 1.3170 | dt 0.035
type train | step 15470 | loss 0.1099 1.7864 7.4790 25.0605 | lr 2.2e-04 | norm 1.1738 | dt 0.035
type train | step 15480 | loss 0.1083 1.8234 7.5291 24.8831 | lr 2.2e-04 | norm 1.1939 | dt 0.035
type train | step 15490 | loss 0.1164 1.8814 7.6497 25.3459 | lr 2.2e-04 | norm 1.4112 | dt 0.035
type train | step 15500 | loss 0.1116 1.7548 7.2759 24.4931 | lr 2.2e-04 | norm 1.2524 | dt 0.035
type train | step 15510 | loss 0.1101 1.7779 7.3425 24.8907 | lr 2.2e-04 | norm 1.2476 | dt 0.035
type train | step 15520 | loss 0.1147 1.7837 7.2395 24.7174 | lr 2.2e-04 | norm 1.1567 | dt 0.035
type train | step 15530 | loss 0.1137 1.7952 7.4504 25.3770 | lr 2.1e-04 | norm 1.3409 | dt 0.035
type train | step 15540 | loss 0.1127 1.7716 7.2650 24.5450 | lr 2.1e-04 | norm 1.3112 | dt 0.035
type train | step 15550 | loss 0.1130 1.8615 7.6026 24.7688 | lr 2.1e-04 | norm 1.4970 | dt 0.035
type train | step 15560 | loss 0.1146 1.7649 7.4135 25.0937 | lr 2.1e-04 | norm 1.5265 | dt 0.036
type train | step 15570 | loss 0.1133 1.7636 7.3894 25.1739 | lr 2.1e-04 | norm 1.4183 | dt 0.035
type train | step 15580 | loss 0.1130 1.8286 7.6661 25.6540 | lr 2.1e-04 | norm 1.1686 | dt 0.035
type train | step 15590 | loss 0.1092 1.8128 7.6086 25.4738 | lr 2.1e-04 | norm 1.1524 | dt 0.035
type train | step 15600 | loss 0.1116 1.8093 7.4659 25.0854 | lr 2.1e-04 | norm 1.3421 | dt 0.036
type train | step 15610 | loss 0.1111 1.7284 7.1422 24.2697 | lr 2.1e-04 | norm 1.3370 | dt 0.035
type train | step 15620 | loss 0.1111 1.7958 7.2486 24.8237 | lr 2.1e-04 | norm 1.4835 | dt 0.035
type train | step 15630 | loss 0.1159 1.7740 7.3800 25.4647 | lr 2.1e-04 | norm 1.3951 | dt 0.035
type train | step 15640 | loss 0.1094 1.8295 7.6990 25.7081 | lr 2.1e-04 | norm 1.3297 | dt 0.035
type train | step 15650 | loss 0.1162 1.7944 7.3920 24.7627 | lr 2.1e-04 | norm 1.3350 | dt 0.035
type train | step 15660 | loss 0.1113 1.8093 7.4603 24.9184 | lr 2.1e-04 | norm 1.0935 | dt 0.035
type train | step 15670 | loss 0.1137 1.8098 7.3757 24.6999 | lr 2.1e-04 | norm 1.5594 | dt 0.036
type train | step 15680 | loss 0.1134 1.8207 7.6051 25.3659 | lr 2.1e-04 | norm 1.2375 | dt 0.035
type train | step 15690 | loss 0.1127 1.7731 7.2673 24.6780 | lr 2.1e-04 | norm 1.3718 | dt 0.035
type train | step 15700 | loss 0.1152 1.8171 7.5399 25.2713 | lr 2.1e-04 | norm 1.1821 | dt 0.035
type train | step 15710 | loss 0.1104 1.7552 7.1077 24.1755 | lr 2.1e-04 | norm 1.3143 | dt 0.035
type train | step 15720 | loss 0.1125 1.7903 7.4418 25.2675 | lr 2.1e-04 | norm 1.2526 | dt 0.035
type train | step 15730 | loss 0.1127 1.8080 7.5883 25.2162 | lr 2.0e-04 | norm 1.2414 | dt 0.035
type train | step 15740 | loss 0.1149 1.8201 7.6632 25.3481 | lr 2.0e-04 | norm 1.3265 | dt 0.035
type train | step 15750 | loss 0.1169 1.8032 7.4453 25.2053 | lr 2.0e-04 | norm 1.3881 | dt 0.035
type train | step 15760 | loss 0.1129 1.8427 7.6725 26.0207 | lr 2.0e-04 | norm 1.3253 | dt 0.034
type train | step 15770 | loss 0.1124 1.8396 7.6872 25.8426 | lr 2.0e-04 | norm 1.4788 | dt 0.034
type train | step 15780 | loss 0.1119 1.8030 7.6632 26.0349 | lr 2.0e-04 | norm 1.2322 | dt 0.034
type train | step 15790 | loss 0.1081 1.7994 7.3055 24.4265 | lr 2.0e-04 | norm 1.2148 | dt 0.034
type train | step 15800 | loss 0.1104 1.8383 7.5214 25.0352 | lr 2.0e-04 | norm 1.3175 | dt 0.034
type train | step 15810 | loss 0.1159 1.7748 7.4397 25.0275 | lr 2.0e-04 | norm 1.5332 | dt 0.033
type train | step 15820 | loss 0.1114 1.8484 7.7645 26.3814 | lr 2.0e-04 | norm 1.3390 | dt 0.034
type train | step 15830 | loss 0.1165 1.8201 7.3413 24.6084 | lr 2.0e-04 | norm 1.5959 | dt 0.033
type train | step 15840 | loss 0.1114 1.7967 7.5599 25.7738 | lr 2.0e-04 | norm 1.4122 | dt 0.033
type train | step 15850 | loss 0.1084 1.7889 7.4120 24.5571 | lr 2.0e-04 | norm 1.2303 | dt 0.034
type train | step 15860 | loss 0.1117 1.8157 7.8410 25.8449 | lr 2.0e-04 | norm 1.4370 | dt 0.035
type train | step 15870 | loss 0.1112 1.8096 7.5465 25.3255 | lr 2.0e-04 | norm 1.1355 | dt 0.034
type train | step 15880 | loss 0.1098 1.8505 7.6653 25.9007 | lr 2.0e-04 | norm 1.3184 | dt 0.034
type train | step 15890 | loss 0.1121 1.7536 7.3109 24.5709 | lr 2.0e-04 | norm 1.2329 | dt 0.033
type train | step 15900 | loss 0.1155 1.8160 7.5584 25.6900 | lr 2.0e-04 | norm 1.4739 | dt 0.033
type train | step 15910 | loss 0.1111 1.7930 7.3224 24.3869 | lr 2.0e-04 | norm 1.3061 | dt 0.034
type train | step 15920 | loss 0.1101 1.7938 7.5413 25.1967 | lr 2.0e-04 | norm 1.2198 | dt 0.034
type train | step 15930 | loss 0.1117 1.8007 7.3878 24.6082 | lr 2.0e-04 | norm 1.0705 | dt 0.034
type train | step 15940 | loss 0.1140 1.8647 7.8941 26.6704 | lr 2.0e-04 | norm 1.3484 | dt 0.034
type train | step 15950 | loss 0.1107 1.7993 7.4088 24.9217 | lr 1.9e-04 | norm 1.2121 | dt 0.034
type train | step 15960 | loss 0.1083 1.7548 7.2582 24.5045 | lr 1.9e-04 | norm 1.1189 | dt 0.033
type train | step 15970 | loss 0.1138 1.8165 7.5197 24.9095 | lr 1.9e-04 | norm 1.2591 | dt 0.033
type train | step 15980 | loss 0.1164 1.8006 7.3711 24.5073 | lr 1.9e-04 | norm 1.3216 | dt 0.031
type train | step 15990 | loss 0.1128 1.7694 7.3226 24.7188 | lr 1.9e-04 | norm 1.2281 | dt 0.029
type train | step 16000 | loss 0.1191 1.8150 7.3195 25.3080 | lr 1.9e-04 | norm 1.9457 | dt 0.027
type train | step 16010 | loss 0.1160 1.8264 7.5172 25.4321 | lr 1.9e-04 | norm 1.3444 | dt 0.026
type train | step 16020 | loss 0.1111 1.7963 7.5108 25.2288 | lr 1.9e-04 | norm 1.2605 | dt 0.026
type train | step 16030 | loss 0.1113 1.8311 7.4673 24.6237 | lr 1.9e-04 | norm 1.3482 | dt 0.026
type train | step 16040 | loss 0.1124 1.8174 7.4244 25.0212 | lr 1.9e-04 | norm 1.3863 | dt 0.026
type train | step 16050 | loss 0.1126 1.7792 7.4119 24.9168 | lr 1.9e-04 | norm 1.5390 | dt 0.026
type train | step 16060 | loss 0.1176 1.8437 7.5932 25.9014 | lr 1.9e-04 | norm 1.3275 | dt 0.026
type train | step 16070 | loss 0.1145 1.7970 7.3344 25.1485 | lr 1.9e-04 | norm 1.3177 | dt 0.027
type train | step 16080 | loss 0.1096 1.7902 7.4738 25.0498 | lr 1.9e-04 | norm 1.1813 | dt 0.027
type train | step 16090 | loss 0.1081 1.8249 7.5169 24.8689 | lr 1.9e-04 | norm 1.1820 | dt 0.027
type train | step 16100 | loss 0.1164 1.8827 7.6376 25.3346 | lr 1.9e-04 | norm 1.4145 | dt 0.027
type train | step 16110 | loss 0.1114 1.7549 7.2708 24.4885 | lr 1.9e-04 | norm 1.2449 | dt 0.027
type train | step 16120 | loss 0.1099 1.7773 7.3364 24.8845 | lr 1.9e-04 | norm 1.2354 | dt 0.027
type train | step 16130 | loss 0.1141 1.7862 7.2328 24.7138 | lr 1.9e-04 | norm 1.1453 | dt 0.027
type train | step 16140 | loss 0.1131 1.7987 7.4441 25.3623 | lr 1.9e-04 | norm 1.3448 | dt 0.028
type train | step 16150 | loss 0.1123 1.7753 7.2587 24.5313 | lr 1.9e-04 | norm 1.3043 | dt 0.034
type train | step 16160 | loss 0.1128 1.8614 7.5958 24.7670 | lr 1.9e-04 | norm 1.4999 | dt 0.035
type train | step 16170 | loss 0.1143 1.7631 7.4067 25.0896 | lr 1.9e-04 | norm 1.5028 | dt 0.035
type train | step 16180 | loss 0.1132 1.7645 7.3823 25.1704 | lr 1.8e-04 | norm 1.4114 | dt 0.035
type train | step 16190 | loss 0.1126 1.8333 7.6513 25.6486 | lr 1.8e-04 | norm 1.1561 | dt 0.035
type train | step 16200 | loss 0.1090 1.8172 7.6056 25.4718 | lr 1.8e-04 | norm 1.1367 | dt 0.035
type train | step 16210 | loss 0.1113 1.8130 7.4596 25.0759 | lr 1.8e-04 | norm 1.3388 | dt 0.035
type train | step 16220 | loss 0.1111 1.7309 7.1310 24.2675 | lr 1.8e-04 | norm 1.3410 | dt 0.035
type train | step 16230 | loss 0.1108 1.7989 7.2425 24.8135 | lr 1.8e-04 | norm 1.4863 | dt 0.036
type train | step 16240 | loss 0.1157 1.7742 7.3800 25.4574 | lr 1.8e-04 | norm 1.3894 | dt 0.036
type train | step 16250 | loss 0.1094 1.8305 7.6906 25.7011 | lr 1.8e-04 | norm 1.3342 | dt 0.035
type train | step 16260 | loss 0.1160 1.7955 7.3828 24.7549 | lr 1.8e-04 | norm 1.3369 | dt 0.035
type train | step 16270 | loss 0.1108 1.8113 7.4492 24.9014 | lr 1.8e-04 | norm 1.0746 | dt 0.035
type train | step 16280 | loss 0.1136 1.8109 7.3723 24.6946 | lr 1.8e-04 | norm 1.5561 | dt 0.035
type train | step 16290 | loss 0.1130 1.8234 7.5934 25.3590 | lr 1.8e-04 | norm 1.2350 | dt 0.035
type train | step 16300 | loss 0.1121 1.7713 7.2583 24.6754 | lr 1.8e-04 | norm 1.3489 | dt 0.036
type train | step 16310 | loss 0.1144 1.8168 7.5301 25.2672 | lr 1.8e-04 | norm 1.1445 | dt 0.035
type train | step 16320 | loss 0.1101 1.7527 7.1000 24.1602 | lr 1.8e-04 | norm 1.2896 | dt 0.035
type train | step 16330 | loss 0.1122 1.7919 7.4327 25.2659 | lr 1.8e-04 | norm 1.2449 | dt 0.035
type train | step 16340 | loss 0.1121 1.8107 7.5762 25.2112 | lr 1.8e-04 | norm 1.2035 | dt 0.035
type train | step 16350 | loss 0.1145 1.8198 7.6594 25.3435 | lr 1.8e-04 | norm 1.3180 | dt 0.035
type train | step 16360 | loss 0.1166 1.8025 7.4368 25.1978 | lr 1.8e-04 | norm 1.3596 | dt 0.035
type train | step 16370 | loss 0.1127 1.8441 7.6741 26.0167 | lr 1.8e-04 | norm 1.3163 | dt 0.035
type train | step 16380 | loss 0.1121 1.8366 7.6838 25.8317 | lr 1.8e-04 | norm 1.4583 | dt 0.035
type train | step 16390 | loss 0.1114 1.8053 7.6572 26.0287 | lr 1.8e-04 | norm 1.2379 | dt 0.035
type train | step 16400 | loss 0.1078 1.8012 7.3053 24.4202 | lr 1.8e-04 | norm 1.2062 | dt 0.035
type train | step 16410 | loss 0.1101 1.8390 7.5150 25.0308 | lr 1.8e-04 | norm 1.3175 | dt 0.035
type train | step 16420 | loss 0.1155 1.7758 7.4276 25.0177 | lr 1.7e-04 | norm 1.5071 | dt 0.035
type train | step 16430 | loss 0.1111 1.8484 7.7563 26.3787 | lr 1.7e-04 | norm 1.3355 | dt 0.034
type train | step 16440 | loss 0.1157 1.8180 7.3331 24.6037 | lr 1.7e-04 | norm 1.5626 | dt 0.035
type train | step 16450 | loss 0.1110 1.7960 7.5535 25.7729 | lr 1.7e-04 | norm 1.3943 | dt 0.036
type train | step 16460 | loss 0.1079 1.7893 7.4030 24.5466 | lr 1.7e-04 | norm 1.2147 | dt 0.035
type train | step 16470 | loss 0.1113 1.8185 7.8344 25.8441 | lr 1.7e-04 | norm 1.4378 | dt 0.036
type train | step 16480 | loss 0.1110 1.8077 7.5338 25.3226 | lr 1.7e-04 | norm 1.1043 | dt 0.035
type train | step 16490 | loss 0.1094 1.8522 7.6561 25.8925 | lr 1.7e-04 | norm 1.3059 | dt 0.034
type train | step 16500 | loss 0.1118 1.7557 7.3099 24.5585 | lr 1.7e-04 | norm 1.2211 | dt 0.034
type train | step 16510 | loss 0.1151 1.8139 7.5502 25.6839 | lr 1.7e-04 | norm 1.4538 | dt 0.034
type train | step 16520 | loss 0.1106 1.7950 7.3101 24.3814 | lr 1.7e-04 | norm 1.2996 | dt 0.034
type train | step 16530 | loss 0.1091 1.7944 7.5458 25.1971 | lr 1.7e-04 | norm 1.1938 | dt 0.034
type train | step 16540 | loss 0.1112 1.7990 7.3814 24.6053 | lr 1.7e-04 | norm 1.0674 | dt 0.033
type train | step 16550 | loss 0.1137 1.8673 7.8874 26.6707 | lr 1.7e-04 | norm 1.3283 | dt 0.028
type train | step 16560 | loss 0.1102 1.8032 7.4002 24.9136 | lr 1.7e-04 | norm 1.2144 | dt 0.028
type train | step 16570 | loss 0.1078 1.7541 7.2538 24.5029 | lr 1.7e-04 | norm 1.1268 | dt 0.027
type train | step 16580 | loss 0.1131 1.8145 7.5129 24.9053 | lr 1.7e-04 | norm 1.2324 | dt 0.026
type train | step 16590 | loss 0.1161 1.8015 7.3644 24.5143 | lr 1.7e-04 | norm 1.3281 | dt 0.026
type train | step 16600 | loss 0.1127 1.7703 7.3161 24.7132 | lr 1.7e-04 | norm 1.2359 | dt 0.026
type train | step 16610 | loss 0.1187 1.8137 7.3130 25.3051 | lr 1.7e-04 | norm 1.9361 | dt 0.026
type train | step 16620 | loss 0.1158 1.8260 7.5140 25.4220 | lr 1.7e-04 | norm 1.3166 | dt 0.026
type train | step 16630 | loss 0.1103 1.7971 7.5094 25.2302 | lr 1.7e-04 | norm 1.2555 | dt 0.026
type train | step 16640 | loss 0.1108 1.8334 7.4551 24.6225 | lr 1.7e-04 | norm 1.3384 | dt 0.026
type train | step 16650 | loss 0.1120 1.8179 7.4210 25.0229 | lr 1.7e-04 | norm 1.3908 | dt 0.026
type train | step 16660 | loss 0.1121 1.7796 7.4056 24.9180 | lr 1.7e-04 | norm 1.5547 | dt 0.026
type train | step 16670 | loss 0.1172 1.8461 7.5880 25.8945 | lr 1.6e-04 | norm 1.3165 | dt 0.026
type train | step 16680 | loss 0.1143 1.8007 7.3336 25.1472 | lr 1.6e-04 | norm 1.3201 | dt 0.026
type train | step 16690 | loss 0.1091 1.7869 7.4689 25.0543 | lr 1.6e-04 | norm 1.1701 | dt 0.026
type train | step 16700 | loss 0.1075 1.8264 7.5144 24.8564 | lr 1.6e-04 | norm 1.1659 | dt 0.026
type train | step 16710 | loss 0.1163 1.8824 7.6308 25.3376 | lr 1.6e-04 | norm 1.4231 | dt 0.026
type train | step 16720 | loss 0.1110 1.7563 7.2694 24.4847 | lr 1.6e-04 | norm 1.2644 | dt 0.026
type train | step 16730 | loss 0.1096 1.7795 7.3366 24.8822 | lr 1.6e-04 | norm 1.2353 | dt 0.026
type train | step 16740 | loss 0.1138 1.7853 7.2348 24.7136 | lr 1.6e-04 | norm 1.1486 | dt 0.026
type train | step 16750 | loss 0.1126 1.7963 7.4370 25.3646 | lr 1.6e-04 | norm 1.3343 | dt 0.026
type train | step 16760 | loss 0.1117 1.7754 7.2477 24.5216 | lr 1.6e-04 | norm 1.2821 | dt 0.035
type train | step 16770 | loss 0.1124 1.8648 7.5960 24.7666 | lr 1.6e-04 | norm 1.5013 | dt 0.035
type train | step 16780 | loss 0.1140 1.7658 7.4011 25.0826 | lr 1.6e-04 | norm 1.5098 | dt 0.035
type train | step 16790 | loss 0.1129 1.7637 7.3792 25.1645 | lr 1.6e-04 | norm 1.4084 | dt 0.035
type train | step 16800 | loss 0.1122 1.8350 7.6456 25.6513 | lr 1.6e-04 | norm 1.1508 | dt 0.035
type train | step 16810 | loss 0.1085 1.8170 7.6034 25.4608 | lr 1.6e-04 | norm 1.1322 | dt 0.035
type train | step 16820 | loss 0.1110 1.8107 7.4514 25.0666 | lr 1.6e-04 | norm 1.3105 | dt 0.035
type train | step 16830 | loss 0.1105 1.7310 7.1276 24.2569 | lr 1.6e-04 | norm 1.3274 | dt 0.035
type train | step 16840 | loss 0.1103 1.7962 7.2405 24.8130 | lr 1.6e-04 | norm 1.4932 | dt 0.035
type train | step 16850 | loss 0.1155 1.7773 7.3725 25.4552 | lr 1.6e-04 | norm 1.3705 | dt 0.035
type train | step 16860 | loss 0.1091 1.8319 7.6895 25.6982 | lr 1.6e-04 | norm 1.3278 | dt 0.035
type train | step 16870 | loss 0.1155 1.7956 7.3762 24.7407 | lr 1.6e-04 | norm 1.3214 | dt 0.035
type train | step 16880 | loss 0.1101 1.8131 7.4488 24.8940 | lr 1.6e-04 | norm 1.0692 | dt 0.035
type train | step 16890 | loss 0.1129 1.8110 7.3647 24.6925 | lr 1.6e-04 | norm 1.5431 | dt 0.035
type train | step 16900 | loss 0.1128 1.8229 7.5879 25.3507 | lr 1.6e-04 | norm 1.2320 | dt 0.035
type train | step 16910 | loss 0.1116 1.7686 7.2597 24.6760 | lr 1.6e-04 | norm 1.3336 | dt 0.035
type train | step 16920 | loss 0.1140 1.8171 7.5269 25.2618 | lr 1.6e-04 | norm 1.1395 | dt 0.035
type train | step 16930 | loss 0.1096 1.7525 7.0988 24.1495 | lr 1.6e-04 | norm 1.2777 | dt 0.035
type train | step 16940 | loss 0.1117 1.7932 7.4285 25.2658 | lr 1.5e-04 | norm 1.2394 | dt 0.035
type train | step 16950 | loss 0.1116 1.8090 7.5679 25.2087 | lr 1.5e-04 | norm 1.1951 | dt 0.035
type train | step 16960 | loss 0.1140 1.8199 7.6543 25.3409 | lr 1.5e-04 | norm 1.3268 | dt 0.036
type train | step 16970 | loss 0.1161 1.8016 7.4335 25.1910 | lr 1.5e-04 | norm 1.3489 | dt 0.036
type train | step 16980 | loss 0.1123 1.8468 7.6645 26.0151 | lr 1.5e-04 | norm 1.3111 | dt 0.035
type train | step 16990 | loss 0.1118 1.8369 7.6801 25.8262 | lr 1.5e-04 | norm 1.4658 | dt 0.035
type train | step 17000 | loss 0.1110 1.8056 7.6528 26.0268 | lr 1.5e-04 | norm 1.2361 | dt 0.035
type train | step 17010 | loss 0.1073 1.8010 7.2994 24.4119 | lr 1.5e-04 | norm 1.1999 | dt 0.034
type train | step 17020 | loss 0.1097 1.8390 7.5055 25.0232 | lr 1.5e-04 | norm 1.3169 | dt 0.034
type train | step 17030 | loss 0.1150 1.7746 7.4251 25.0186 | lr 1.5e-04 | norm 1.5009 | dt 0.034
type train | step 17040 | loss 0.1107 1.8476 7.7571 26.3830 | lr 1.5e-04 | norm 1.3289 | dt 0.034
type train | step 17050 | loss 0.1156 1.8178 7.3277 24.5989 | lr 1.5e-04 | norm 1.5586 | dt 0.034
type train | step 17060 | loss 0.1106 1.7978 7.5491 25.7711 | lr 1.5e-04 | norm 1.3994 | dt 0.034
type train | step 17070 | loss 0.1077 1.7926 7.3938 24.5421 | lr 1.5e-04 | norm 1.2124 | dt 0.034
type train | step 17080 | loss 0.1110 1.8210 7.8272 25.8420 | lr 1.5e-04 | norm 1.4287 | dt 0.038
type train | step 17090 | loss 0.1104 1.8071 7.5271 25.3160 | lr 1.5e-04 | norm 1.0952 | dt 0.033
type train | step 17100 | loss 0.1091 1.8511 7.6557 25.8802 | lr 1.5e-04 | norm 1.3031 | dt 0.034
type train | step 17110 | loss 0.1114 1.7572 7.3038 24.5560 | lr 1.5e-04 | norm 1.2181 | dt 0.033
type train | step 17120 | loss 0.1146 1.8142 7.5444 25.6874 | lr 1.5e-04 | norm 1.4565 | dt 0.031
type train | step 17130 | loss 0.1105 1.7959 7.3056 24.3789 | lr 1.5e-04 | norm 1.2969 | dt 0.034
type train | step 17140 | loss 0.1087 1.7986 7.5410 25.1931 | lr 1.5e-04 | norm 1.1938 | dt 0.034
type train | step 17150 | loss 0.1108 1.8019 7.3776 24.6066 | lr 1.5e-04 | norm 1.0642 | dt 0.030
type train | step 17160 | loss 0.1135 1.8676 7.8809 26.6647 | lr 1.5e-04 | norm 1.3260 | dt 0.034
type train | step 17170 | loss 0.1100 1.8007 7.3943 24.9082 | lr 1.5e-04 | norm 1.1983 | dt 0.035
type train | step 17180 | loss 0.1075 1.7539 7.2513 24.5005 | lr 1.5e-04 | norm 1.1102 | dt 0.034
type train | step 17190 | loss 0.1125 1.8169 7.5121 24.9107 | lr 1.5e-04 | norm 1.2296 | dt 0.034
type train | step 17200 | loss 0.1158 1.8083 7.3663 24.5133 | lr 1.5e-04 | norm 1.3323 | dt 0.034
type train | step 17210 | loss 0.1123 1.7699 7.3088 24.7208 | lr 1.5e-04 | norm 1.2403 | dt 0.034
type train | step 17220 | loss 0.1187 1.8158 7.3043 25.3070 | lr 1.5e-04 | norm 1.9266 | dt 0.034
type train | step 17230 | loss 0.1154 1.8272 7.5126 25.4132 | lr 1.5e-04 | norm 1.3143 | dt 0.034
type train | step 17240 | loss 0.1098 1.7962 7.5044 25.2266 | lr 1.4e-04 | norm 1.2465 | dt 0.034
type train | step 17250 | loss 0.1106 1.8332 7.4472 24.6196 | lr 1.4e-04 | norm 1.3213 | dt 0.034
type train | step 17260 | loss 0.1114 1.8168 7.4202 25.0218 | lr 1.4e-04 | norm 1.3686 | dt 0.027
type train | step 17270 | loss 0.1117 1.7787 7.4055 24.9132 | lr 1.4e-04 | norm 1.5421 | dt 0.026
type train | step 17280 | loss 0.1170 1.8424 7.5809 25.8918 | lr 1.4e-04 | norm 1.3205 | dt 0.026
type train | step 17290 | loss 0.1141 1.7992 7.3333 25.1489 | lr 1.4e-04 | norm 1.3149 | dt 0.026
type train | step 17300 | loss 0.1088 1.7854 7.4606 25.0487 | lr 1.4e-04 | norm 1.1598 | dt 0.026
type train | step 17310 | loss 0.1074 1.8272 7.5094 24.8629 | lr 1.4e-04 | norm 1.1498 | dt 0.026
type train | step 17320 | loss 0.1159 1.8878 7.6292 25.3406 | lr 1.4e-04 | norm 1.4172 | dt 0.026
type train | step 17330 | loss 0.1107 1.7568 7.2648 24.4904 | lr 1.4e-04 | norm 1.2506 | dt 0.026
type train | step 17340 | loss 0.1094 1.7783 7.3295 24.8784 | lr 1.4e-04 | norm 1.2288 | dt 0.026
type train | step 17350 | loss 0.1135 1.7840 7.2279 24.7114 | lr 1.4e-04 | norm 1.1407 | dt 0.026
type train | step 17360 | loss 0.1123 1.7954 7.4360 25.3512 | lr 1.4e-04 | norm 1.3094 | dt 0.025
type train | step 17370 | loss 0.1114 1.7714 7.2408 24.5081 | lr 1.4e-04 | norm 1.2543 | dt 0.026
type train | step 17380 | loss 0.1121 1.8684 7.5880 24.7633 | lr 1.4e-04 | norm 1.5068 | dt 0.026
type train | step 17390 | loss 0.1136 1.7669 7.3930 25.0827 | lr 1.4e-04 | norm 1.4999 | dt 0.026
type train | step 17400 | loss 0.1126 1.7634 7.3712 25.1551 | lr 1.4e-04 | norm 1.4016 | dt 0.026
type train | step 17410 | loss 0.1119 1.8353 7.6407 25.6489 | lr 1.4e-04 | norm 1.1470 | dt 0.025
type train | step 17420 | loss 0.1084 1.8182 7.5962 25.4559 | lr 1.4e-04 | norm 1.1336 | dt 0.026
type train | step 17430 | loss 0.1107 1.8113 7.4455 25.0648 | lr 1.4e-04 | norm 1.2913 | dt 0.026
type train | step 17440 | loss 0.1102 1.7322 7.1263 24.2547 | lr 1.4e-04 | norm 1.3175 | dt 0.026
type train | step 17450 | loss 0.1102 1.7962 7.2327 24.8077 | lr 1.4e-04 | norm 1.4924 | dt 0.026
type train | step 17460 | loss 0.1153 1.7787 7.3682 25.4547 | lr 1.4e-04 | norm 1.3655 | dt 0.026
type train | step 17470 | loss 0.1089 1.8303 7.6794 25.6874 | lr 1.4e-04 | norm 1.3257 | dt 0.025
type train | step 17480 | loss 0.1153 1.7944 7.3689 24.7382 | lr 1.4e-04 | norm 1.3117 | dt 0.026
type train | step 17490 | loss 0.1101 1.8149 7.4402 24.8869 | lr 1.4e-04 | norm 1.0505 | dt 0.026
type train | step 17500 | loss 0.1126 1.8151 7.3586 24.6789 | lr 1.4e-04 | norm 1.5406 | dt 0.026
type train | step 17510 | loss 0.1125 1.8214 7.5882 25.3511 | lr 1.4e-04 | norm 1.2310 | dt 0.035
type train | step 17520 | loss 0.1112 1.7711 7.2528 24.6788 | lr 1.4e-04 | norm 1.3250 | dt 0.035
type train | step 17530 | loss 0.1137 1.8156 7.5279 25.2516 | lr 1.4e-04 | norm 1.1463 | dt 0.035
type train | step 17540 | loss 0.1094 1.7550 7.0938 24.1414 | lr 1.4e-04 | norm 1.2676 | dt 0.035
type train | step 17550 | loss 0.1113 1.7909 7.4250 25.2621 | lr 1.4e-04 | norm 1.2474 | dt 0.035
type train | step 17560 | loss 0.1112 1.8069 7.5623 25.2054 | lr 1.4e-04 | norm 1.1944 | dt 0.035
type train | step 17570 | loss 0.1137 1.8202 7.6538 25.3398 | lr 1.3e-04 | norm 1.3148 | dt 0.035
type train | step 17580 | loss 0.1158 1.8012 7.4255 25.1892 | lr 1.3e-04 | norm 1.3347 | dt 0.035
type train | step 17590 | loss 0.1121 1.8477 7.6569 26.0070 | lr 1.3e-04 | norm 1.3045 | dt 0.035
type train | step 17600 | loss 0.1116 1.8355 7.6712 25.8177 | lr 1.3e-04 | norm 1.4597 | dt 0.035
type train | step 17610 | loss 0.1109 1.8032 7.6501 26.0198 | lr 1.3e-04 | norm 1.2379 | dt 0.035
type train | step 17620 | loss 0.1069 1.8000 7.2960 24.4039 | lr 1.3e-04 | norm 1.1871 | dt 0.035
type train | step 17630 | loss 0.1096 1.8392 7.5021 25.0215 | lr 1.3e-04 | norm 1.3014 | dt 0.035
type train | step 17640 | loss 0.1146 1.7724 7.4169 25.0138 | lr 1.3e-04 | norm 1.4939 | dt 0.035
type train | step 17650 | loss 0.1106 1.8470 7.7545 26.3705 | lr 1.3e-04 | norm 1.3140 | dt 0.035
type train | step 17660 | loss 0.1153 1.8156 7.3213 24.5934 | lr 1.3e-04 | norm 1.5505 | dt 0.035
type train | step 17670 | loss 0.1104 1.7958 7.5407 25.7697 | lr 1.3e-04 | norm 1.3896 | dt 0.035
type train | step 17680 | loss 0.1075 1.7931 7.3861 24.5421 | lr 1.3e-04 | norm 1.2073 | dt 0.035
type train | step 17690 | loss 0.1105 1.8223 7.8190 25.8360 | lr 1.3e-04 | norm 1.4279 | dt 0.036
type train | step 17700 | loss 0.1100 1.8038 7.5203 25.3141 | lr 1.3e-04 | norm 1.0955 | dt 0.035
type train | step 17710 | loss 0.1088 1.8489 7.6510 25.8707 | lr 1.3e-04 | norm 1.2855 | dt 0.035
type train | step 17720 | loss 0.1110 1.7563 7.2979 24.5546 | lr 1.3e-04 | norm 1.2052 | dt 0.035
type train | step 17730 | loss 0.1147 1.8114 7.5378 25.6860 | lr 1.3e-04 | norm 1.4493 | dt 0.035
type train | step 17740 | loss 0.1101 1.7961 7.2949 24.3805 | lr 1.3e-04 | norm 1.2888 | dt 0.035
type train | step 17750 | loss 0.1084 1.7964 7.5361 25.1893 | lr 1.3e-04 | norm 1.1782 | dt 0.035
type train | step 17760 | loss 0.1106 1.8013 7.3781 24.6044 | lr 1.3e-04 | norm 1.0671 | dt 0.035
type train | step 17770 | loss 0.1131 1.8668 7.8848 26.6665 | lr 1.3e-04 | norm 1.3221 | dt 0.033
type train | step 17780 | loss 0.1098 1.8010 7.3835 24.9025 | lr 1.3e-04 | norm 1.2006 | dt 0.034
type train | step 17790 | loss 0.1073 1.7528 7.2515 24.5012 | lr 1.3e-04 | norm 1.1149 | dt 0.034
type train | step 17800 | loss 0.1123 1.8150 7.5019 24.8993 | lr 1.3e-04 | norm 1.2232 | dt 0.034
type train | step 17810 | loss 0.1155 1.8095 7.3647 24.5124 | lr 1.3e-04 | norm 1.3256 | dt 0.032
type train | step 17820 | loss 0.1123 1.7681 7.3026 24.7212 | lr 1.3e-04 | norm 1.2409 | dt 0.034
type train | step 17830 | loss 0.1185 1.8150 7.3028 25.3034 | lr 1.3e-04 | norm 1.9109 | dt 0.034
type train | step 17840 | loss 0.1153 1.8252 7.5052 25.4111 | lr 1.3e-04 | norm 1.3136 | dt 0.033
type train | step 17850 | loss 0.1098 1.7931 7.5012 25.2239 | lr 1.3e-04 | norm 1.2551 | dt 0.034
type train | step 17860 | loss 0.1103 1.8326 7.4397 24.6129 | lr 1.3e-04 | norm 1.3141 | dt 0.032
type train | step 17870 | loss 0.1110 1.8178 7.4194 25.0278 | lr 1.3e-04 | norm 1.3667 | dt 0.035
type train | step 17880 | loss 0.1115 1.7769 7.3987 24.9101 | lr 1.3e-04 | norm 1.5565 | dt 0.033
type train | step 17890 | loss 0.1168 1.8395 7.5748 25.8852 | lr 1.3e-04 | norm 1.3008 | dt 0.033
type train | step 17900 | loss 0.1138 1.7970 7.3277 25.1496 | lr 1.3e-04 | norm 1.3247 | dt 0.033
type train | step 17910 | loss 0.1087 1.7828 7.4632 25.0425 | lr 1.3e-04 | norm 1.1719 | dt 0.033
type train | step 17920 | loss 0.1071 1.8265 7.5010 24.8608 | lr 1.3e-04 | norm 1.1474 | dt 0.034
type train | step 17930 | loss 0.1156 1.8859 7.6253 25.3323 | lr 1.3e-04 | norm 1.4133 | dt 0.033
type train | step 17940 | loss 0.1104 1.7550 7.2657 24.4893 | lr 1.3e-04 | norm 1.2612 | dt 0.034
type train | step 17950 | loss 0.1091 1.7770 7.3247 24.8738 | lr 1.2e-04 | norm 1.2215 | dt 0.033
type train | step 17960 | loss 0.1133 1.7824 7.2280 24.7087 | lr 1.2e-04 | norm 1.1481 | dt 0.034
type train | step 17970 | loss 0.1122 1.7918 7.4340 25.3518 | lr 1.2e-04 | norm 1.3382 | dt 0.034
type train | step 17980 | loss 0.1109 1.7712 7.2387 24.4999 | lr 1.2e-04 | norm 1.2493 | dt 0.030
type train | step 17990 | loss 0.1119 1.8688 7.5862 24.7670 | lr 1.2e-04 | norm 1.4994 | dt 0.027
type train | step 18000 | loss 0.1134 1.7664 7.3849 25.0816 | lr 1.2e-04 | norm 1.4976 | dt 0.026
type train | step 18010 | loss 0.1123 1.7625 7.3747 25.1501 | lr 1.2e-04 | norm 1.3895 | dt 0.026
type train | step 18020 | loss 0.1118 1.8330 7.6323 25.6435 | lr 1.2e-04 | norm 1.1543 | dt 0.026
type train | step 18030 | loss 0.1080 1.8176 7.5938 25.4576 | lr 1.2e-04 | norm 1.1198 | dt 0.026
type train | step 18040 | loss 0.1104 1.8104 7.4365 25.0655 | lr 1.2e-04 | norm 1.2900 | dt 0.026
type train | step 18050 | loss 0.1101 1.7334 7.1227 24.2560 | lr 1.2e-04 | norm 1.3236 | dt 0.026
type train | step 18060 | loss 0.1101 1.7952 7.2314 24.8037 | lr 1.2e-04 | norm 1.4777 | dt 0.026
type train | step 18070 | loss 0.1150 1.7773 7.3627 25.4549 | lr 1.2e-04 | norm 1.3501 | dt 0.027
type train | step 18080 | loss 0.1088 1.8293 7.6784 25.6828 | lr 1.2e-04 | norm 1.3164 | dt 0.027
type train | step 18090 | loss 0.1151 1.7929 7.3646 24.7308 | lr 1.2e-04 | norm 1.3130 | dt 0.026
type train | step 18100 | loss 0.1099 1.8131 7.4379 24.8797 | lr 1.2e-04 | norm 1.0467 | dt 0.027
type train | step 18110 | loss 0.1123 1.8138 7.3573 24.6733 | lr 1.2e-04 | norm 1.5390 | dt 0.030
type train | step 18120 | loss 0.1126 1.8191 7.5849 25.3571 | lr 1.2e-04 | norm 1.2256 | dt 0.035
type train | step 18130 | loss 0.1112 1.7695 7.2458 24.6724 | lr 1.2e-04 | norm 1.3167 | dt 0.035
type train | step 18140 | loss 0.1138 1.8145 7.5250 25.2471 | lr 1.2e-04 | norm 1.1383 | dt 0.036
type train | step 18150 | loss 0.1091 1.7542 7.0910 24.1320 | lr 1.2e-04 | norm 1.2672 | dt 0.035
type train | step 18160 | loss 0.1112 1.7890 7.4230 25.2581 | lr 1.2e-04 | norm 1.2391 | dt 0.036
type train | step 18170 | loss 0.1110 1.8052 7.5581 25.1913 | lr 1.2e-04 | norm 1.1904 | dt 0.035
type train | step 18180 | loss 0.1135 1.8189 7.6542 25.3468 | lr 1.2e-04 | norm 1.3149 | dt 0.035
type train | step 18190 | loss 0.1155 1.7988 7.4165 25.1831 | lr 1.2e-04 | norm 1.3191 | dt 0.035
type train | step 18200 | loss 0.1119 1.8459 7.6547 26.0038 | lr 1.2e-04 | norm 1.3039 | dt 0.035
type train | step 18210 | loss 0.1114 1.8337 7.6715 25.8184 | lr 1.2e-04 | norm 1.4566 | dt 0.035
type train | step 18220 | loss 0.1108 1.8019 7.6451 26.0215 | lr 1.2e-04 | norm 1.2444 | dt 0.035
type train | step 18230 | loss 0.1068 1.7997 7.2905 24.4009 | lr 1.2e-04 | norm 1.1849 | dt 0.035
type train | step 18240 | loss 0.1095 1.8403 7.4990 25.0178 | lr 1.2e-04 | norm 1.3018 | dt 0.035
type train | step 18250 | loss 0.1145 1.7719 7.4202 25.0138 | lr 1.2e-04 | norm 1.4904 | dt 0.035
type train | step 18260 | loss 0.1105 1.8476 7.7520 26.3679 | lr 1.2e-04 | norm 1.3170 | dt 0.035
type train | step 18270 | loss 0.1149 1.8125 7.3192 24.5896 | lr 1.2e-04 | norm 1.5361 | dt 0.035
type train | step 18280 | loss 0.1105 1.7968 7.5365 25.7649 | lr 1.2e-04 | norm 1.4045 | dt 0.034
type train | step 18290 | loss 0.1072 1.7933 7.3866 24.5385 | lr 1.2e-04 | norm 1.2021 | dt 0.030
type train | step 18300 | loss 0.1103 1.8215 7.8173 25.8331 | lr 1.2e-04 | norm 1.4164 | dt 0.038
type train | step 18310 | loss 0.1102 1.8017 7.5183 25.3115 | lr 1.2e-04 | norm 1.1030 | dt 0.035
type train | step 18320 | loss 0.1089 1.8484 7.6513 25.8633 | lr 1.2e-04 | norm 1.2941 | dt 0.035
type train | step 18330 | loss 0.1110 1.7561 7.2943 24.5562 | lr 1.2e-04 | norm 1.2106 | dt 0.034
type train | step 18340 | loss 0.1146 1.8067 7.5347 25.6772 | lr 1.2e-04 | norm 1.4475 | dt 0.035
type train | step 18350 | loss 0.1101 1.7957 7.2900 24.3746 | lr 1.2e-04 | norm 1.2815 | dt 0.034
type train | step 18360 | loss 0.1080 1.7963 7.5366 25.1834 | lr 1.2e-04 | norm 1.1627 | dt 0.034
type train | step 18370 | loss 0.1104 1.8027 7.3798 24.6062 | lr 1.2e-04 | norm 1.0514 | dt 0.034
type train | step 18380 | loss 0.1129 1.8657 7.8797 26.6612 | lr 1.2e-04 | norm 1.3071 | dt 0.034
type train | step 18390 | loss 0.1096 1.8004 7.3824 24.8919 | lr 1.2e-04 | norm 1.1725 | dt 0.034
type train | step 18400 | loss 0.1074 1.7505 7.2491 24.4992 | lr 1.2e-04 | norm 1.1292 | dt 0.034
type train | step 18410 | loss 0.1122 1.8138 7.4995 24.9004 | lr 1.2e-04 | norm 1.2150 | dt 0.034
type train | step 18420 | loss 0.1151 1.8094 7.3578 24.5116 | lr 1.1e-04 | norm 1.3205 | dt 0.034
type train | step 18430 | loss 0.1122 1.7654 7.3014 24.7262 | lr 1.1e-04 | norm 1.2367 | dt 0.033
type train | step 18440 | loss 0.1183 1.8145 7.2961 25.3007 | lr 1.1e-04 | norm 1.9045 | dt 0.034
type train | step 18450 | loss 0.1150 1.8227 7.5000 25.4100 | lr 1.1e-04 | norm 1.2978 | dt 0.033
type train | step 18460 | loss 0.1096 1.7925 7.4960 25.2244 | lr 1.1e-04 | norm 1.2495 | dt 0.034
type train | step 18470 | loss 0.1102 1.8323 7.4327 24.6135 | lr 1.1e-04 | norm 1.2959 | dt 0.033
type train | step 18480 | loss 0.1112 1.8165 7.4194 25.0220 | lr 1.1e-04 | norm 1.3579 | dt 0.034
type train | step 18490 | loss 0.1112 1.7764 7.3913 24.9052 | lr 1.1e-04 | norm 1.5384 | dt 0.033
type train | step 18500 | loss 0.1166 1.8387 7.5746 25.8793 | lr 1.1e-04 | norm 1.2904 | dt 0.033
type train | step 18510 | loss 0.1139 1.7968 7.3334 25.1513 | lr 1.1e-04 | norm 1.3349 | dt 0.027
type train | step 18520 | loss 0.1085 1.7819 7.4561 25.0448 | lr 1.1e-04 | norm 1.1737 | dt 0.026
type train | step 18530 | loss 0.1068 1.8250 7.5019 24.8599 | lr 1.1e-04 | norm 1.1352 | dt 0.026
type train | step 18540 | loss 0.1155 1.8886 7.6197 25.3340 | lr 1.1e-04 | norm 1.4043 | dt 0.026
type train | step 18550 | loss 0.1105 1.7525 7.2646 24.4904 | lr 1.1e-04 | norm 1.2537 | dt 0.026
type train | step 18560 | loss 0.1089 1.7773 7.3221 24.8727 | lr 1.1e-04 | norm 1.2142 | dt 0.025
type train | step 18570 | loss 0.1132 1.7815 7.2289 24.7043 | lr 1.1e-04 | norm 1.1490 | dt 0.026
type train | step 18580 | loss 0.1119 1.7941 7.4302 25.3543 | lr 1.1e-04 | norm 1.3206 | dt 0.026
type train | step 18590 | loss 0.1109 1.7710 7.2381 24.4961 | lr 1.1e-04 | norm 1.2479 | dt 0.026
type train | step 18600 | loss 0.1118 1.8674 7.5813 24.7638 | lr 1.1e-04 | norm 1.4993 | dt 0.027
type train | step 18610 | loss 0.1132 1.7663 7.3854 25.0851 | lr 1.1e-04 | norm 1.4879 | dt 0.026
type train | step 18620 | loss 0.1122 1.7605 7.3707 25.1488 | lr 1.1e-04 | norm 1.3883 | dt 0.026
type train | step 18630 | loss 0.1116 1.8314 7.6278 25.6421 | lr 1.1e-04 | norm 1.1404 | dt 0.026
type train | step 18640 | loss 0.1079 1.8152 7.5910 25.4580 | lr 1.1e-04 | norm 1.1130 | dt 0.026
type train | step 18650 | loss 0.1103 1.8103 7.4309 25.0604 | lr 1.1e-04 | norm 1.2828 | dt 0.026
type train | step 18660 | loss 0.1098 1.7339 7.1195 24.2581 | lr 1.1e-04 | norm 1.3123 | dt 0.027
type train | step 18670 | loss 0.1102 1.7946 7.2272 24.7966 | lr 1.1e-04 | norm 1.4785 | dt 0.026
type train | step 18680 | loss 0.1147 1.7747 7.3597 25.4548 | lr 1.1e-04 | norm 1.3493 | dt 0.027
type train | step 18690 | loss 0.1086 1.8283 7.6738 25.6854 | lr 1.1e-04 | norm 1.3127 | dt 0.027
type train | step 18700 | loss 0.1149 1.7918 7.3633 24.7309 | lr 1.1e-04 | norm 1.3130 | dt 0.027
type train | step 18710 | loss 0.1095 1.8148 7.4334 24.8772 | lr 1.1e-04 | norm 1.0417 | dt 0.026
type train | step 18720 | loss 0.1122 1.8107 7.3571 24.6724 | lr 1.1e-04 | norm 1.5259 | dt 0.026
type train | step 18730 | loss 0.1123 1.8190 7.5873 25.3621 | lr 1.1e-04 | norm 1.2301 | dt 0.026
type train | step 18740 | loss 0.1109 1.7697 7.2457 24.6661 | lr 1.1e-04 | norm 1.3020 | dt 0.027
type train | step 18750 | loss 0.1135 1.8153 7.5220 25.2454 | lr 1.1e-04 | norm 1.1279 | dt 0.027
type train | step 18760 | loss 0.1089 1.7563 7.0906 24.1299 | lr 1.1e-04 | norm 1.2573 | dt 0.036
type train | step 18770 | loss 0.1111 1.7865 7.4198 25.2565 | lr 1.1e-04 | norm 1.2355 | dt 0.036
type train | step 18780 | loss 0.1109 1.8077 7.5549 25.1880 | lr 1.1e-04 | norm 1.1757 | dt 0.036
type train | step 18790 | loss 0.1133 1.8169 7.6501 25.3442 | lr 1.1e-04 | norm 1.3104 | dt 0.036
type train | step 18800 | loss 0.1154 1.7982 7.4144 25.1829 | lr 1.1e-04 | norm 1.3014 | dt 0.037
type train | step 18810 | loss 0.1120 1.8454 7.6545 26.0006 | lr 1.1e-04 | norm 1.3023 | dt 0.036
type train | step 18820 | loss 0.1111 1.8344 7.6657 25.8102 | lr 1.1e-04 | norm 1.4595 | dt 0.036
type train | step 18830 | loss 0.1105 1.8030 7.6451 26.0195 | lr 1.1e-04 | norm 1.2374 | dt 0.036
type train | step 18840 | loss 0.1068 1.7974 7.2871 24.3983 | lr 1.1e-04 | norm 1.1824 | dt 0.035
type train | step 18850 | loss 0.1096 1.8382 7.4964 25.0172 | lr 1.1e-04 | norm 1.3157 | dt 0.037
type train | step 18860 | loss 0.1146 1.7696 7.4123 25.0107 | lr 1.1e-04 | norm 1.4822 | dt 0.035
type train | step 18870 | loss 0.1103 1.8466 7.7512 26.3712 | lr 1.1e-04 | norm 1.3120 | dt 0.036
type train | step 18880 | loss 0.1148 1.8108 7.3169 24.5858 | lr 1.1e-04 | norm 1.5289 | dt 0.036
type train | step 18890 | loss 0.1103 1.7946 7.5339 25.7602 | lr 1.1e-04 | norm 1.3958 | dt 0.035
type train | step 18900 | loss 0.1069 1.7920 7.3860 24.5422 | lr 1.1e-04 | norm 1.1945 | dt 0.033
type train | step 18910 | loss 0.1102 1.8205 7.8178 25.8308 | lr 1.1e-04 | norm 1.4176 | dt 0.036
type train | step 18920 | loss 0.1097 1.7999 7.5137 25.3100 | lr 1.1e-04 | norm 1.0574 | dt 0.028
type train | step 18930 | loss 0.1088 1.8466 7.6470 25.8618 | lr 1.1e-04 | norm 1.2902 | dt 0.026
type train | step 18940 | loss 0.1109 1.7549 7.2903 24.5531 | lr 1.1e-04 | norm 1.2025 | dt 0.026
type train | step 18950 | loss 0.1142 1.8060 7.5329 25.6752 | lr 1.1e-04 | norm 1.4405 | dt 0.026
type train | step 18960 | loss 0.1099 1.7933 7.2849 24.3711 | lr 1.1e-04 | norm 1.2697 | dt 0.026
type train | step 18970 | loss 0.1078 1.7942 7.5323 25.1912 | lr 1.1e-04 | norm 1.1731 | dt 0.027
type train | step 18980 | loss 0.1106 1.8013 7.3751 24.6056 | lr 1.1e-04 | norm 1.0823 | dt 0.027
type train | step 18990 | loss 0.1128 1.8634 7.8760 26.6530 | lr 1.1e-04 | norm 1.3073 | dt 0.027
type train | step 19000 | loss 0.1096 1.7983 7.3816 24.8867 | lr 1.1e-04 | norm 1.1703 | dt 0.027
type train | step 19010 | loss 0.1070 1.7493 7.2444 24.5006 | lr 1.1e-04 | norm 1.1102 | dt 0.027
type train | step 19020 | loss 0.1120 1.8131 7.4955 24.8902 | lr 1.1e-04 | norm 1.2101 | dt 0.028
type train | step 19030 | loss 0.1151 1.8071 7.3623 24.5101 | lr 1.1e-04 | norm 1.3154 | dt 0.036
type train | step 19040 | loss 0.1121 1.7656 7.2921 24.7242 | lr 1.1e-04 | norm 1.2397 | dt 0.036
type train | step 19050 | loss 0.1182 1.8148 7.2970 25.2992 | lr 1.1e-04 | norm 1.9045 | dt 0.037
type train | step 19060 | loss 0.1149 1.8215 7.4953 25.4066 | lr 1.1e-04 | norm 1.2904 | dt 0.035
type train | step 19070 | loss 0.1095 1.7929 7.4927 25.2211 | lr 1.1e-04 | norm 1.2504 | dt 0.036
type train | step 19080 | loss 0.1099 1.8298 7.4288 24.6041 | lr 1.1e-04 | norm 1.3002 | dt 0.035
type train | step 19090 | loss 0.1111 1.8167 7.4139 25.0243 | lr 1.0e-04 | norm 1.3564 | dt 0.036
type train | step 19100 | loss 0.1112 1.7745 7.3923 24.9072 | lr 1.0e-04 | norm 1.5410 | dt 0.036
type train | step 19110 | loss 0.1165 1.8407 7.5748 25.8791 | lr 1.0e-04 | norm 1.2798 | dt 0.036
type train | step 19120 | loss 0.1137 1.7952 7.3316 25.1560 | lr 1.0e-04 | norm 1.3214 | dt 0.035
type train | step 19130 | loss 0.1084 1.7815 7.4518 25.0446 | lr 1.0e-04 | norm 1.1549 | dt 0.036
type train | step 19140 | loss 0.1068 1.8253 7.4983 24.8517 | lr 1.0e-04 | norm 1.1284 | dt 0.036
type train | step 19150 | loss 0.1153 1.8894 7.6140 25.3346 | lr 1.0e-04 | norm 1.4023 | dt 0.035
type train | step 19160 | loss 0.1104 1.7503 7.2585 24.4886 | lr 1.0e-04 | norm 1.2479 | dt 0.035
type train | step 19170 | loss 0.1089 1.7759 7.3230 24.8661 | lr 1.0e-04 | norm 1.2031 | dt 0.036
type train | step 19180 | loss 0.1132 1.7817 7.2223 24.6976 | lr 1.0e-04 | norm 1.1417 | dt 0.035
type train | step 19190 | loss 0.1118 1.7918 7.4230 25.3524 | lr 1.0e-04 | norm 1.3194 | dt 0.035
type train | step 19200 | loss 0.1108 1.7678 7.2319 24.4900 | lr 1.0e-04 | norm 1.2352 | dt 0.036
type train | step 19210 | loss 0.1116 1.8670 7.5800 24.7680 | lr 1.0e-04 | norm 1.4994 | dt 0.036
type train | step 19220 | loss 0.1134 1.7629 7.3826 25.0854 | lr 1.0e-04 | norm 1.4899 | dt 0.036
type train | step 19230 | loss 0.1120 1.7592 7.3632 25.1408 | lr 1.0e-04 | norm 1.3822 | dt 0.036
type train | step 19240 | loss 0.1116 1.8298 7.6244 25.6392 | lr 1.0e-04 | norm 1.1315 | dt 0.035
type train | step 19250 | loss 0.1079 1.8146 7.5912 25.4590 | lr 1.0e-04 | norm 1.1109 | dt 0.036
type train | step 19260 | loss 0.1101 1.8083 7.4268 25.0566 | lr 1.0e-04 | norm 1.2737 | dt 0.033
type train | step 19270 | loss 0.1096 1.7335 7.1167 24.2554 | lr 1.0e-04 | norm 1.3054 | dt 0.032
type train | step 19280 | loss 0.1102 1.7925 7.2221 24.7956 | lr 1.0e-04 | norm 1.4791 | dt 0.032
type train | step 19290 | loss 0.1146 1.7724 7.3545 25.4522 | lr 1.0e-04 | norm 1.3425 | dt 0.029
type train | step 19300 | loss 0.1085 1.8283 7.6719 25.6845 | lr 1.0e-04 | norm 1.3117 | dt 0.027
type train | step 19310 | loss 0.1149 1.7930 7.3575 24.7275 | lr 1.0e-04 | norm 1.3058 | dt 0.026
type train | step 19320 | loss 0.1095 1.8129 7.4283 24.8710 | lr 1.0e-04 | norm 1.0329 | dt 0.026
type train | step 19330 | loss 0.1121 1.8124 7.3537 24.6726 | lr 1.0e-04 | norm 1.5204 | dt 0.026
type train | step 19340 | loss 0.1125 1.8189 7.5818 25.3585 | lr 1.0e-04 | norm 1.2247 | dt 0.026
type train | step 19350 | loss 0.1109 1.7672 7.2396 24.6723 | lr 1.0e-04 | norm 1.3030 | dt 0.026
type train | step 19360 | loss 0.1134 1.8131 7.5173 25.2455 | lr 1.0e-04 | norm 1.1320 | dt 0.026
type train | step 19370 | loss 0.1089 1.7561 7.0877 24.1259 | lr 1.0e-04 | norm 1.2566 | dt 0.026
type train | step 19380 | loss 0.1109 1.7852 7.4165 25.2560 | lr 1.0e-04 | norm 1.2413 | dt 0.026
type train | step 19390 | loss 0.1108 1.8090 7.5515 25.1879 | lr 1.0e-04 | norm 1.1745 | dt 0.026
type train | step 19400 | loss 0.1133 1.8139 7.6458 25.3446 | lr 1.0e-04 | norm 1.3168 | dt 0.026
type train | step 19410 | loss 0.1155 1.7948 7.4089 25.1810 | lr 1.0e-04 | norm 1.3040 | dt 0.026
type train | step 19420 | loss 0.1118 1.8429 7.6498 26.0012 | lr 1.0e-04 | norm 1.2979 | dt 0.026
type train | step 19430 | loss 0.1113 1.8334 7.6593 25.8148 | lr 1.0e-04 | norm 1.4607 | dt 0.026
type train | step 19440 | loss 0.1104 1.8016 7.6370 26.0153 | lr 1.0e-04 | norm 1.2350 | dt 0.026
type train | step 19450 | loss 0.1069 1.7965 7.2852 24.3975 | lr 1.0e-04 | norm 1.1754 | dt 0.026
type train | step 19460 | loss 0.1092 1.8398 7.4946 25.0159 | lr 1.0e-04 | norm 1.3052 | dt 0.026
type train | step 19470 | loss 0.1140 1.7696 7.4077 25.0045 | lr 1.0e-04 | norm 1.4714 | dt 0.026
type train | step 19480 | loss 0.1104 1.8462 7.7492 26.3686 | lr 1.0e-04 | norm 1.3056 | dt 0.025
type train | step 19490 | loss 0.1146 1.8096 7.3126 24.5855 | lr 1.0e-04 | norm 1.5390 | dt 0.026
type train | step 19500 | loss 0.1103 1.7928 7.5313 25.7570 | lr 1.0e-04 | norm 1.3936 | dt 0.026
type train | step 19510 | loss 0.1070 1.7915 7.3797 24.5373 | lr 1.0e-04 | norm 1.1875 | dt 0.035
type train | step 19520 | loss 0.1106 1.8217 7.8133 25.8330 | lr 1.0e-04 | norm 1.4364 | dt 0.037
type train | step 19530 | loss 0.1095 1.7976 7.5128 25.3088 | lr 1.0e-04 | norm 1.0578 | dt 0.035
type train | step 19540 | loss 0.1087 1.8484 7.6434 25.8542 | lr 1.0e-04 | norm 1.2785 | dt 0.035
type train | step 19550 | loss 0.1106 1.7530 7.2909 24.5504 | lr 1.0e-04 | norm 1.2004 | dt 0.035
type train | step 19560 | loss 0.1142 1.8066 7.5263 25.6708 | lr 1.0e-04 | norm 1.4442 | dt 0.036
type train | step 19570 | loss 0.1100 1.7896 7.2797 24.3665 | lr 1.0e-04 | norm 1.2766 | dt 0.035
type train | step 19580 | loss 0.1083 1.7935 7.5307 25.1946 | lr 1.0e-04 | norm 1.1833 | dt 0.036
type train | step 19590 | loss 0.1103 1.7993 7.3717 24.6034 | lr 1.0e-04 | norm 1.0645 | dt 0.036
type train | step 19600 | loss 0.1129 1.8622 7.8739 26.6545 | lr 1.0e-04 | norm 1.3104 | dt 0.035
type train | step 19610 | loss 0.1096 1.7978 7.3783 24.8849 | lr 1.0e-04 | norm 1.1795 | dt 0.036
type train | step 19620 | loss 0.1071 1.7488 7.2416 24.5011 | lr 1.0e-04 | norm 1.1125 | dt 0.035
type train | step 19630 | loss 0.1121 1.8118 7.4930 24.8894 | lr 1.0e-04 | norm 1.2127 | dt 0.035
type train | step 19640 | loss 0.1154 1.8048 7.3650 24.5134 | lr 1.0e-04 | norm 1.3267 | dt 0.035
type train | step 19650 | loss 0.1120 1.7650 7.2941 24.7251 | lr 1.0e-04 | norm 1.2375 | dt 0.035
type train | step 19660 | loss 0.1185 1.8140 7.2925 25.2965 | lr 1.0e-04 | norm 1.9017 | dt 0.035
type train | step 19670 | loss 0.1147 1.8184 7.4919 25.4051 | lr 1.0e-04 | norm 1.2899 | dt 0.035
type train | step 19680 | loss 0.1096 1.7928 7.4884 25.2173 | lr 1.0e-04 | norm 1.2645 | dt 0.035
type train | step 19690 | loss 0.1100 1.8276 7.4261 24.6100 | lr 1.0e-04 | norm 1.2965 | dt 0.035
type train | step 19700 | loss 0.1112 1.8157 7.4151 25.0275 | lr 1.0e-04 | norm 1.3509 | dt 0.035
type train | step 19710 | loss 0.1112 1.7747 7.3912 24.9074 | lr 1.0e-04 | norm 1.5482 | dt 0.036
type train | step 19720 | loss 0.1165 1.8410 7.5727 25.8778 | lr 1.0e-04 | norm 1.2875 | dt 0.035
type train | step 19730 | loss 0.1137 1.7984 7.3293 25.1576 | lr 1.0e-04 | norm 1.3301 | dt 0.035
type train | step 19740 | loss 0.1083 1.7810 7.4532 25.0439 | lr 1.0e-04 | norm 1.1560 | dt 0.035
type train | step 19750 | loss 0.1066 1.8225 7.4925 24.8526 | lr 1.0e-04 | norm 1.1233 | dt 0.035
type train | step 19760 | loss 0.1155 1.8873 7.6122 25.3341 | lr 1.0e-04 | norm 1.4097 | dt 0.031
type train | step 19770 | loss 0.1104 1.7481 7.2613 24.4917 | lr 1.0e-04 | norm 1.2603 | dt 0.030
type train | step 19780 | loss 0.1087 1.7753 7.3215 24.8708 | lr 1.0e-04 | norm 1.2076 | dt 0.026
type train | step 19790 | loss 0.1131 1.7819 7.2227 24.6959 | lr 1.0e-04 | norm 1.1329 | dt 0.026
type train | step 19800 | loss 0.1119 1.7920 7.4255 25.3555 | lr 1.0e-04 | norm 1.3229 | dt 0.026
type train | step 19810 | loss 0.1107 1.7676 7.2288 24.4926 | lr 1.0e-04 | norm 1.2311 | dt 0.026
type train | step 19820 | loss 0.1118 1.8673 7.5799 24.7664 | lr 1.0e-04 | norm 1.5057 | dt 0.026
type train | step 19830 | loss 0.1131 1.7628 7.3792 25.0858 | lr 1.0e-04 | norm 1.4856 | dt 0.026
type train | step 19840 | loss 0.1121 1.7555 7.3610 25.1409 | lr 1.0e-04 | norm 1.3784 | dt 0.026
type train | step 19850 | loss 0.1115 1.8290 7.6202 25.6397 | lr 1.0e-04 | norm 1.1391 | dt 0.026
type train | step 19860 | loss 0.1079 1.8134 7.5887 25.4560 | lr 1.0e-04 | norm 1.1119 | dt 0.026
type train | step 19870 | loss 0.1101 1.8067 7.4224 25.0556 | lr 1.0e-04 | norm 1.2752 | dt 0.026
type train | step 19880 | loss 0.1096 1.7349 7.1118 24.2522 | lr 1.0e-04 | norm 1.3030 | dt 0.026
type train | step 19890 | loss 0.1101 1.7915 7.2202 24.7912 | lr 1.0e-04 | norm 1.4718 | dt 0.026
type train | step 19900 | loss 0.1145 1.7720 7.3543 25.4558 | lr 1.0e-04 | norm 1.3436 | dt 0.025
type train | step 19910 | loss 0.1085 1.8264 7.6707 25.6801 | lr 1.0e-04 | norm 1.3134 | dt 0.026
type train | step 19920 | loss 0.1149 1.7936 7.3585 24.7289 | lr 1.0e-04 | norm 1.3010 | dt 0.026
type train | step 19930 | loss 0.1096 1.8124 7.4230 24.8710 | lr 1.0e-04 | norm 1.0331 | dt 0.026
type train | step 19940 | loss 0.1120 1.8115 7.3503 24.6782 | lr 1.0e-04 | norm 1.5263 | dt 0.026
type train | step 19950 | loss 0.1123 1.8183 7.5810 25.3600 | lr 1.0e-04 | norm 1.2370 | dt 0.026
type train | step 19960 | loss 0.1108 1.7676 7.2373 24.6706 | lr 1.0e-04 | norm 1.2950 | dt 0.026
type train | step 19970 | loss 0.1134 1.8137 7.5203 25.2506 | lr 1.0e-04 | norm 1.1276 | dt 0.026
type train | step 19980 | loss 0.1089 1.7561 7.0855 24.1230 | lr 1.0e-04 | norm 1.2578 | dt 0.026
type train | step 19990 | loss 0.1109 1.7848 7.4157 25.2593 | lr 1.0e-04 | norm 1.2331 | dt 0.026
type train | step 20000 | loss 0.1107 1.8068 7.5495 25.1892 | lr 1.0e-04 | norm 1.1741 | dt 0.026