| 2024:11:09-10:06:53:(508946) |CCL_WARN| value of CCL_ATL_TRANSPORT changed to be ofi (default:mpi) | |
| 2024:11:09-10:06:53:(508946) |CCL_WARN| value of CCL_LOCAL_RANK changed to be 0 (default:-1) | |
| 2024:11:09-10:06:53:(508946) |CCL_WARN| value of CCL_LOCAL_SIZE changed to be 16 (default:-1) | |
| 2024:11:09-10:06:53:(508946) |CCL_WARN| value of CCL_PROCESS_LAUNCHER changed to be none (default:hydra) | |
| ['id', 'url', 'title', 'text'] | |
| The model has 240.08M parameters. | |
| Step 0 | |
| Running loss: 11.7923 | |
| Batch loss: 11.7923 | |
| Average epoch loss: 11.7923 | |
| Step 500 | |
| Running loss: 3.3656 | |
| Batch loss: 3.2935 | |
| Average epoch loss: 3.9321 | |
| Step 1000 | |
| Running loss: 3.0827 | |
| Batch loss: 3.2471 | |
| Average epoch loss: 3.5621 | |
| Step 1500 | |
| Running loss: 3.0817 | |
| Batch loss: 3.4774 | |
| Average epoch loss: 3.4071 | |
| Step 2000 | |
| Running loss: 3.0423 | |
| Batch loss: 3.1888 | |
| Average epoch loss: 3.3143 | |
| Step 2500 | |
| Running loss: 3.0551 | |
| Batch loss: 3.1329 | |
| Average epoch loss: 3.2569 | |
| Step 3000 | |
| Running loss: 2.9979 | |
| Batch loss: 3.0741 | |
| Average epoch loss: 3.2136 | |
| Step 3500 | |
| Running loss: 2.9536 | |
| Batch loss: 3.0002 | |
| Average epoch loss: 3.1790 | |
| Step 4000 | |
| Running loss: 2.9903 | |
| Batch loss: 2.7348 | |
| Average epoch loss: 3.1555 | |
| Step 4500 | |
| Running loss: 2.9500 | |
| Batch loss: 2.9907 | |
| Average epoch loss: 3.1365 | |
| Step 5000 | |
| Running loss: 2.9900 | |
| Batch loss: 3.0119 | |
| Average epoch loss: 3.1215 | |
| Step 5500 | |
| Running loss: 2.9919 | |
| Batch loss: 2.9734 | |
| Average epoch loss: 3.1076 | |
| Step 6000 | |
| Running loss: 2.9535 | |
| Batch loss: 3.1941 | |
| Average epoch loss: 3.0943 | |
| Step 6500 | |
| Running loss: 2.9669 | |
| Batch loss: 3.3493 | |
| Average epoch loss: 3.0833 | |
| Step 7000 | |
| Running loss: 2.9665 | |
| Batch loss: 3.1670 | |
| Average epoch loss: 3.0740 | |
| Step 7500 | |
| Running loss: 2.9439 | |
| Batch loss: 2.8684 | |
| Average epoch loss: 3.0661 | |
| Step 8000 | |
| Running loss: 2.9325 | |
| Batch loss: 2.7675 | |
| Average epoch loss: 3.0580 | |
| Step 8500 | |
| Running loss: 2.9384 | |
| Batch loss: 3.1707 | |
| Average epoch loss: 3.0509 | |
| Step 9000 | |
| Running loss: 2.9533 | |
| Batch loss: 2.7907 | |
| Average epoch loss: 3.0457 | |
| Step 9500 | |
| Running loss: 2.9469 | |
| Batch loss: 2.6352 | |
| Average epoch loss: 3.0406 | |
| Step 10000 | |
| Running loss: 2.9262 | |
| Batch loss: 3.0176 | |
| Average epoch loss: 3.0355 | |
| Step 10500 | |
| Running loss: 2.9755 | |
| Batch loss: 3.3512 | |
| Average epoch loss: 3.0312 | |
| Step 11000 | |
| Running loss: 2.9398 | |
| Batch loss: 2.6666 | |
| Average epoch loss: 3.0283 | |
| Step 11500 | |
| Running loss: 2.8770 | |
| Batch loss: 2.5651 | |
| Average epoch loss: 3.0237 | |
| Step 12000 | |
| Running loss: 2.9571 | |
| Batch loss: 2.8708 | |
| Average epoch loss: 3.0212 | |
| Step 12500 | |
| Running loss: 2.9249 | |
| Batch loss: 2.9836 | |
| Average epoch loss: 3.0184 | |
| Step 13000 | |
| Running loss: 2.9492 | |
| Batch loss: 3.0248 | |
| Average epoch loss: 3.0155 | |
| Step 13500 | |
| Running loss: 2.9257 | |
| Batch loss: 2.6260 | |
| Average epoch loss: 3.0130 | |
| Step 14000 | |
| Running loss: 2.9606 | |
| Batch loss: 3.1519 | |
| Average epoch loss: 3.0106 | |
| Step 14500 | |
| Running loss: 2.9850 | |
| Batch loss: 3.2653 | |
| Average epoch loss: 3.0087 | |
| Step 15000 | |
| Running loss: 2.9863 | |
| Batch loss: 3.0859 | |
| Average epoch loss: 3.0070 | |
| Step 15500 | |
| Running loss: 2.9696 | |
| Batch loss: 3.1891 | |
| Average epoch loss: 3.0049 | |
| Step 16000 | |
| Running loss: 2.9176 | |
| Batch loss: 3.3047 | |
| Average epoch loss: 3.0028 | |
| Step 16500 | |
| Running loss: 2.9824 | |
| Batch loss: 2.8600 | |
| Average epoch loss: 3.0012 | |
| Step 17000 | |
| Running loss: 2.9248 | |
| Batch loss: 2.8825 | |
| Average epoch loss: 2.9994 | |
| Step 17500 | |
| Running loss: 2.9647 | |
| Batch loss: 3.1768 | |
| Average epoch loss: 2.9981 | |
| Step 18000 | |
| Running loss: 2.9498 | |
| Batch loss: 2.9701 | |
| Average epoch loss: 2.9964 | |
| Step 18500 | |
| Running loss: 2.9083 | |
| Batch loss: 3.1874 | |
| Average epoch loss: 2.9948 | |
| Step 19000 | |
| Running loss: 2.9352 | |
| Batch loss: 3.0794 | |
| Average epoch loss: 2.9936 | |
| Step 19500 | |
| Running loss: 2.9605 | |
| Batch loss: 3.1238 | |
| Average epoch loss: 2.9925 | |
| Step 20000 | |
| Running loss: 2.9561 | |
| Batch loss: 3.1286 | |
| Average epoch loss: 2.9911 | |
| Step 20500 | |
| Running loss: 2.9351 | |
| Batch loss: 2.9636 | |
| Average epoch loss: 2.9898 | |
| Step 21000 | |
| Running loss: 2.9488 | |
| Batch loss: 2.9922 | |
| Average epoch loss: 2.9891 | |
| Step 21500 | |
| Running loss: 2.9463 | |
| Batch loss: 3.3220 | |
| Average epoch loss: 2.9879 | |
| Step 22000 | |
| Running loss: 2.9371 | |
| Batch loss: 2.9049 | |
| Average epoch loss: 2.9867 | |
| Step 22500 | |
| Running loss: 2.9307 | |
| Batch loss: 2.9283 | |
| Average epoch loss: 2.9856 | |
| Step 23000 | |
| Running loss: 2.9306 | |
| Batch loss: 3.1469 | |
| Average epoch loss: 2.9843 | |
| Step 23500 | |
| Running loss: 2.9348 | |
| Batch loss: 2.8675 | |
| Average epoch loss: 2.9832 | |
| Step 24000 | |
| Running loss: 2.9564 | |
| Batch loss: 3.3677 | |
| Average epoch loss: 2.9822 | |
| Step 24500 | |
| Running loss: 2.9542 | |
| Batch loss: 3.0585 | |
| Average epoch loss: 2.9815 | |
| Step 25000 | |
| Running loss: 2.9246 | |
| Batch loss: 2.4103 | |
| Average epoch loss: 2.9805 | |
| Step 25500 | |
| Running loss: 2.9643 | |
| Batch loss: 2.8754 | |
| Average epoch loss: 2.9798 | |
| Step 26000 | |
| Running loss: 2.9664 | |
| Batch loss: 3.0242 | |
| Average epoch loss: 2.9791 | |
| Step 26500 | |
| Running loss: 2.9557 | |
| Batch loss: 2.6959 | |
| Average epoch loss: 2.9786 | |
| Step 27000 | |
| Running loss: 2.9607 | |
| Batch loss: 3.0604 | |
| Average epoch loss: 2.9779 | |
| Step 27500 | |
| Running loss: 2.9223 | |
| Batch loss: 2.8239 | |
| Average epoch loss: 2.9772 | |
| Step 28000 | |
| Running loss: 2.9646 | |
| Batch loss: 2.9401 | |
| Average epoch loss: 2.9768 | |
| Step 28500 | |
| Running loss: 2.9035 | |
| Batch loss: 2.8699 | |
| Average epoch loss: 2.9760 | |
| Step 29000 | |
| Running loss: 2.9335 | |
| Batch loss: 2.6242 | |
| Average epoch loss: 2.9753 | |
| Step 29500 | |
| Running loss: 2.9684 | |
| Batch loss: 2.5832 | |
| Average epoch loss: 2.9746 | |
| Step 30000 | |
| Running loss: 2.9712 | |
| Batch loss: 3.2953 | |
| Average epoch loss: 2.9743 | |
| Step 30500 | |
| Running loss: 2.9476 | |
| Batch loss: 2.9520 | |
| Average epoch loss: 2.9740 | |
| Step 31000 | |
| Running loss: 2.9195 | |
| Batch loss: 2.7239 | |
| Average epoch loss: 2.9733 | |
| Step 31500 | |
| Running loss: 2.9349 | |
| Batch loss: 3.1235 | |
| Average epoch loss: 2.9729 | |
| Step 32000 | |
| Running loss: 2.9371 | |
| Batch loss: 2.8214 | |
| Average epoch loss: 2.9724 | |
| Step 32500 | |
| Running loss: 2.9166 | |
| Batch loss: 2.9788 | |
| Average epoch loss: 2.9718 | |
| Step 33000 | |
| Running loss: 2.9239 | |
| Batch loss: 2.9541 | |
| Average epoch loss: 2.9712 | |
| Step 33500 | |
| Running loss: 2.9516 | |
| Batch loss: 2.9943 | |
| Average epoch loss: 2.9708 | |
| Step 34000 | |
| Running loss: 2.9543 | |
| Batch loss: 2.9360 | |
| Average epoch loss: 2.9703 | |
| Step 34500 | |
| Running loss: 2.9387 | |
| Batch loss: 2.8120 | |
| Average epoch loss: 2.9698 | |
| Step 35000 | |
| Running loss: 2.9314 | |
| Batch loss: 2.4087 | |
| Average epoch loss: 2.9694 | |
| Step 35500 | |
| Running loss: 2.9931 | |
| Batch loss: 3.2395 | |
| Average epoch loss: 2.9692 | |
| Step 36000 | |
| Running loss: 2.9300 | |
| Batch loss: 2.6211 | |
| Average epoch loss: 2.9686 | |
| Step 36500 | |
| Running loss: 2.9586 | |
| Batch loss: 2.9982 | |
| Average epoch loss: 2.9683 | |
| Step 37000 | |
| Running loss: 2.9480 | |
| Batch loss: 2.7632 | |
| Average epoch loss: 2.9678 | |
| Step 37500 | |
| Running loss: 2.9259 | |
| Batch loss: 3.2003 | |
| Average epoch loss: 2.9674 | |
| Step 38000 | |
| Running loss: 2.9658 | |
| Batch loss: 3.3236 | |
| Average epoch loss: 2.9672 | |
| Step 38500 | |
| Running loss: 2.9334 | |
| Batch loss: 3.2784 | |
| Average epoch loss: 2.9669 | |
| Step 39000 | |
| Running loss: 2.9388 | |
| Batch loss: 2.4574 | |
| Average epoch loss: 2.9667 | |
| Step 39500 | |
| Running loss: 2.9343 | |
| Batch loss: 2.7275 | |
| Average epoch loss: 2.9662 | |
| Step 40000 | |
| Running loss: 2.9302 | |
| Batch loss: 2.6218 | |
| Average epoch loss: 2.9658 | |
| Step 40500 | |
| Running loss: 2.9465 | |
| Batch loss: 3.0923 | |
| Average epoch loss: 2.9654 | |
| Step 41000 | |
| Running loss: 2.9531 | |
| Batch loss: 3.0735 | |
| Average epoch loss: 2.9654 | |
| Step 41500 | |
| Running loss: 2.9718 | |
| Batch loss: 3.3168 | |
| Average epoch loss: 2.9651 | |
| Step 42000 | |
| Running loss: 2.9555 | |
| Batch loss: 2.8667 | |
| Average epoch loss: 2.9649 | |
| Step 42500 | |
| Running loss: 2.9539 | |
| Batch loss: 2.7464 | |
| Average epoch loss: 2.9648 | |
| Step 43000 | |
| Running loss: 2.9739 | |
| Batch loss: 2.9998 | |
| Average epoch loss: 2.9645 | |
| Step 43500 | |
| Running loss: 2.9112 | |
| Batch loss: 3.2753 | |
| Average epoch loss: 2.9645 | |
| Step 44000 | |
| Running loss: 2.9246 | |
| Batch loss: 3.1243 | |
| Average epoch loss: 2.9643 | |
| Step 44500 | |
| Running loss: 2.9382 | |
| Batch loss: 2.6558 | |
| Average epoch loss: 2.9640 | |
| Step 45000 | |
| Running loss: 2.9341 | |
| Batch loss: 2.8882 | |
| Average epoch loss: 2.9637 | |
| Step 45500 | |
| Running loss: 2.9334 | |
| Batch loss: 3.1639 | |
| Average epoch loss: 2.9634 | |
| Step 46000 | |
| Running loss: 2.9120 | |
| Batch loss: 2.4497 | |
| Average epoch loss: 2.9632 | |
| Step 46500 | |
| Running loss: 2.9566 | |
| Batch loss: 3.0874 | |
| Average epoch loss: 2.9630 | |
| Step 47000 | |
| Running loss: 2.9329 | |
| Batch loss: 3.0428 | |
| Average epoch loss: 2.9630 | |
| Step 47500 | |
| Running loss: 2.9254 | |
| Batch loss: 2.9440 | |
| Average epoch loss: 2.9628 | |
| Step 48000 | |
| Running loss: 2.9396 | |
| Batch loss: 2.9472 | |
| Average epoch loss: 2.9626 | |
| Step 48500 | |
| Running loss: 2.9395 | |
| Batch loss: 3.0700 | |
| Average epoch loss: 2.9623 | |
| Step 49000 | |
| Running loss: 2.9150 | |
| Batch loss: 2.7340 | |
| Average epoch loss: 2.9621 | |
| Step 49500 | |
| Running loss: 2.9501 | |
| Batch loss: 3.0657 | |
| Average epoch loss: 2.9619 | |
| Step 50000 | |
| Running loss: 2.9618 | |
| Batch loss: 2.9441 | |
| Average epoch loss: 2.9618 | |
| Epoch 1 completed. | |
| Average epoch loss: 2.9618 | |
| Step 50500 | |
| Running loss: 2.9491 | |
| Batch loss: 3.2120 | |
| Average epoch loss: 2.9396 | |
| Step 51000 | |
| Running loss: 2.9118 | |
| Batch loss: 2.7278 | |
| Average epoch loss: 2.9396 | |
| Step 51500 | |
| Running loss: 2.9111 | |
| Batch loss: 2.6636 | |
| Average epoch loss: 2.9332 | |
| Step 52000 | |
| Running loss: 2.9464 | |
| Batch loss: 2.8036 | |
| Average epoch loss: 2.9334 | |
| Step 52500 | |
| Running loss: 2.9548 | |
| Batch loss: 3.0189 | |
| Average epoch loss: 2.9361 | |
| Step 53000 | |
| Running loss: 2.9167 | |
| Batch loss: 3.1873 | |
| Average epoch loss: 2.9356 | |
| Step 53500 | |
| Running loss: 2.9168 | |
| Batch loss: 2.8147 | |
| Average epoch loss: 2.9381 | |
| Step 54000 | |
| Running loss: 2.9441 | |
| Batch loss: 2.7729 | |
| Average epoch loss: 2.9390 | |
| Step 54500 | |
| Running loss: 2.9599 | |
| Batch loss: 3.1481 | |
| Average epoch loss: 2.9391 | |
| Step 55000 | |
| Running loss: 2.9798 | |
| Batch loss: 2.8620 | |
| Average epoch loss: 2.9406 | |
| Step 55500 | |
| Running loss: 2.9372 | |
| Batch loss: 3.1657 | |
| Average epoch loss: 2.9394 | |
| Step 56000 | |
| Running loss: 2.9250 | |
| Batch loss: 2.7892 | |
| Average epoch loss: 2.9389 | |
| Step 56500 | |
| Running loss: 2.8879 | |
| Batch loss: 2.7797 | |
| Average epoch loss: 2.9396 | |
| Step 57000 | |
| Running loss: 2.9362 | |
| Batch loss: 3.0707 | |
| Average epoch loss: 2.9386 | |
| Step 57500 | |
| Running loss: 2.9383 | |
| Batch loss: 2.8079 | |
| Average epoch loss: 2.9391 | |
| Step 58000 | |
| Running loss: 2.9276 | |
| Batch loss: 3.3322 | |
| Average epoch loss: 2.9384 | |
| Step 58500 | |
| Running loss: 2.9135 | |
| Batch loss: 2.9733 | |
| Average epoch loss: 2.9386 | |
| Step 59000 | |
| Running loss: 2.9211 | |
| Batch loss: 3.0028 | |
| Average epoch loss: 2.9381 | |
| Step 59500 | |
| Running loss: 2.9655 | |
| Batch loss: 2.9855 | |
| Average epoch loss: 2.9378 | |
| Step 60000 | |
| Running loss: 2.9018 | |
| Batch loss: 2.6473 | |
| Average epoch loss: 2.9379 | |
| Step 60500 | |
| Running loss: 2.9554 | |
| Batch loss: 2.6419 | |
| Average epoch loss: 2.9375 | |
| Step 61000 | |
| Running loss: 2.9393 | |
| Batch loss: 2.7936 | |
| Average epoch loss: 2.9371 | |
| Step 61500 | |
| Running loss: 2.9458 | |
| Batch loss: 2.8559 | |
| Average epoch loss: 2.9376 | |
| Step 62000 | |
| Running loss: 2.9655 | |
| Batch loss: 2.6120 | |
| Average epoch loss: 2.9387 | |
| Step 62500 | |
| Running loss: 2.9624 | |
| Batch loss: 2.8286 | |
| Average epoch loss: 2.9386 | |
| Step 63000 | |
| Running loss: 2.9176 | |
| Batch loss: 2.6989 | |
| Average epoch loss: 2.9383 | |
| Step 63500 | |
| Running loss: 2.9202 | |
| Batch loss: 2.7307 | |
| Average epoch loss: 2.9380 | |
| Step 64000 | |
| Running loss: 2.9503 | |
| Batch loss: 2.6869 | |
| Average epoch loss: 2.9383 | |
| Step 64500 | |
| Running loss: 2.9528 | |
| Batch loss: 3.2269 | |
| Average epoch loss: 2.9384 | |
| Step 65000 | |
| Running loss: 2.9556 | |
| Batch loss: 3.3411 | |
| Average epoch loss: 2.9384 | |
| Step 65500 | |
| Running loss: 2.9123 | |
| Batch loss: 2.9850 | |
| Average epoch loss: 2.9383 | |
| Step 66000 | |
| Running loss: 2.9233 | |
| Batch loss: 3.1784 | |
| Average epoch loss: 2.9382 | |
| Step 66500 | |
| Running loss: 2.9360 | |
| Batch loss: 2.7863 | |
| Average epoch loss: 2.9390 | |
| Step 67000 | |
| Running loss: 2.9435 | |
| Batch loss: 2.9241 | |
| Average epoch loss: 2.9394 | |
| Step 67500 | |
| Running loss: 2.9634 | |
| Batch loss: 3.5554 | |
| Average epoch loss: 2.9395 | |
| Step 68000 | |
| Running loss: 2.9398 | |
| Batch loss: 3.0257 | |
| Average epoch loss: 2.9397 | |
| Step 68500 | |
| Running loss: 2.9421 | |
| Batch loss: 2.8450 | |
| Average epoch loss: 2.9400 | |
| Step 69000 | |
| Running loss: 2.9438 | |
| Batch loss: 2.9715 | |
| Average epoch loss: 2.9400 | |
| Step 69500 | |
| Running loss: 2.9122 | |
| Batch loss: 3.0280 | |
| Average epoch loss: 2.9397 | |
| Step 70000 | |
| Running loss: 2.9559 | |
| Batch loss: 2.8276 | |
| Average epoch loss: 2.9399 | |
| Step 70500 | |
| Running loss: 2.9243 | |
| Batch loss: 2.8353 | |
| Average epoch loss: 2.9399 | |
| Step 71000 | |
| Running loss: 2.9459 | |
| Batch loss: 2.6684 | |
| Average epoch loss: 2.9401 | |
| Step 71500 | |
| Running loss: 2.9257 | |
| Batch loss: 2.7531 | |
| Average epoch loss: 2.9400 | |
| Step 72000 | |
| Running loss: 2.9807 | |
| Batch loss: 3.6572 | |
| Average epoch loss: 2.9404 | |
| Step 72500 | |
| Running loss: 2.9122 | |
| Batch loss: 2.9153 | |
| Average epoch loss: 2.9402 | |
| Step 73000 | |
| Running loss: 2.9401 | |
| Batch loss: 2.7401 | |
| Average epoch loss: 2.9404 | |
| Step 73500 | |
| Running loss: 2.9245 | |
| Batch loss: 2.9958 | |
| Average epoch loss: 2.9403 | |
| Step 74000 | |
| Running loss: 2.9485 | |
| Batch loss: 2.8896 | |
| Average epoch loss: 2.9406 | |
| Step 74500 | |
| Running loss: 2.9504 | |
| Batch loss: 2.9339 | |
| Average epoch loss: 2.9407 | |
| Step 75000 | |
| Running loss: 2.9228 | |
| Batch loss: 2.8664 | |
| Average epoch loss: 2.9409 | |
| Step 75500 | |
| Running loss: 2.9469 | |
| Batch loss: 2.6861 | |
| Average epoch loss: 2.9409 | |
| Step 76000 | |
| Running loss: 2.9095 | |
| Batch loss: 2.7464 | |
| Average epoch loss: 2.9407 | |
| Step 76500 | |
| Running loss: 2.9289 | |
| Batch loss: 2.6103 | |
| Average epoch loss: 2.9411 | |
| Step 77000 | |
| Running loss: 2.9304 | |
| Batch loss: 3.1342 | |
| Average epoch loss: 2.9413 | |
| Step 77500 | |
| Running loss: 2.9428 | |
| Batch loss: 3.1167 | |
| Average epoch loss: 2.9412 | |
| Step 78000 | |
| Running loss: 2.9560 | |
| Batch loss: 3.0041 | |
| Average epoch loss: 2.9410 | |
| Step 78500 | |
| Running loss: 2.9678 | |
| Batch loss: 3.2073 | |
| Average epoch loss: 2.9409 | |
| Step 79000 | |
| Running loss: 2.9851 | |
| Batch loss: 2.8627 | |
| Average epoch loss: 2.9414 | |
| Step 79500 | |
| Running loss: 2.8956 | |
| Batch loss: 3.2537 | |
| Average epoch loss: 2.9414 | |
| Step 80000 | |
| Running loss: 2.9508 | |
| Batch loss: 2.9628 | |
| Average epoch loss: 2.9417 | |
| Step 80500 | |
| Running loss: 2.9375 | |
| Batch loss: 2.9945 | |
| Average epoch loss: 2.9417 | |
| Step 81000 | |
| Running loss: 2.9317 | |
| Batch loss: 3.3937 | |
| Average epoch loss: 2.9417 | |
| Step 81500 | |
| Running loss: 2.9224 | |
| Batch loss: 2.5205 | |
| Average epoch loss: 2.9416 | |
| Step 82000 | |
| Running loss: 2.9051 | |
| Batch loss: 2.6957 | |
| Average epoch loss: 2.9414 | |
| Step 82500 | |
| Running loss: 2.9142 | |
| Batch loss: 2.8778 | |
| Average epoch loss: 2.9413 | |
| Step 83000 | |
| Running loss: 2.9332 | |
| Batch loss: 3.0838 | |
| Average epoch loss: 2.9413 | |
| Step 83500 | |
| Running loss: 2.9040 | |
| Batch loss: 2.7878 | |
| Average epoch loss: 2.9416 | |
| Step 84000 | |
| Running loss: 2.9818 | |
| Batch loss: 2.8330 | |
| Average epoch loss: 2.9418 | |
| Step 84500 | |
| Running loss: 2.9247 | |
| Batch loss: 3.0401 | |
| Average epoch loss: 2.9416 | |
| Step 85000 | |
| Running loss: 2.9290 | |
| Batch loss: 2.7374 | |
| Average epoch loss: 2.9415 | |
| Step 85500 | |
| Running loss: 2.9592 | |
| Batch loss: 2.9129 | |
| Average epoch loss: 2.9413 | |
| Step 86000 | |
| Running loss: 2.9454 | |
| Batch loss: 3.1122 | |
| Average epoch loss: 2.9414 | |
| Step 86500 | |
| Running loss: 2.9680 | |
| Batch loss: 3.2592 | |
| Average epoch loss: 2.9416 | |
| Step 87000 | |
| Running loss: 2.9291 | |
| Batch loss: 2.6773 | |
| Average epoch loss: 2.9417 | |
| Step 87500 | |
| Running loss: 2.9868 | |
| Batch loss: 2.9199 | |
| Average epoch loss: 2.9417 | |
| Step 88000 | |
| Running loss: 2.9410 | |
| Batch loss: 3.1413 | |
| Average epoch loss: 2.9417 | |
| Step 88500 | |
| Running loss: 2.9555 | |
| Batch loss: 2.7997 | |
| Average epoch loss: 2.9417 | |
| Step 89000 | |
| Running loss: 2.9731 | |
| Batch loss: 3.3676 | |
| Average epoch loss: 2.9418 | |
| Step 89500 | |
| Running loss: 2.9240 | |
| Batch loss: 2.9916 | |
| Average epoch loss: 2.9418 | |
| Step 90000 | |
| Running loss: 2.9650 | |
| Batch loss: 3.2611 | |
| Average epoch loss: 2.9420 | |
| Step 90500 | |
| Running loss: 2.9118 | |
| Batch loss: 2.8739 | |
| Average epoch loss: 2.9421 | |
| Step 91000 | |
| Running loss: 2.9492 | |
| Batch loss: 2.5824 | |
| Average epoch loss: 2.9421 | |
| Step 91500 | |
| Running loss: 2.9447 | |
| Batch loss: 2.8586 | |
| Average epoch loss: 2.9421 | |
| Step 92000 | |
| Running loss: 2.9179 | |
| Batch loss: 2.7481 | |
| Average epoch loss: 2.9420 | |
| Step 92500 | |
| Running loss: 2.9111 | |
| Batch loss: 2.7438 | |
| Average epoch loss: 2.9419 | |
| Step 93000 | |
| Running loss: 2.9528 | |
| Batch loss: 2.8458 | |
| Average epoch loss: 2.9420 | |
| Step 93500 | |
| Running loss: 2.9540 | |
| Batch loss: 2.9936 | |
| Average epoch loss: 2.9421 | |
| Step 94000 | |
| Running loss: 2.9108 | |
| Batch loss: 2.9011 | |
| Average epoch loss: 2.9420 | |
| Step 94500 | |
| Running loss: 2.9438 | |
| Batch loss: 2.8753 | |
| Average epoch loss: 2.9419 | |
| Step 95000 | |
| Running loss: 2.9454 | |
| Batch loss: 3.2084 | |
| Average epoch loss: 2.9418 | |
| Step 95500 | |
| Running loss: 2.9274 | |
| Batch loss: 2.4359 | |
| Average epoch loss: 2.9419 | |
| Step 96000 | |
| Running loss: 2.9686 | |
| Batch loss: 2.9880 | |
| Average epoch loss: 2.9420 | |
| Step 96500 | |
| Running loss: 2.9743 | |
| Batch loss: 2.9369 | |
| Average epoch loss: 2.9420 | |
| Step 97000 | |
| Running loss: 2.9253 | |
| Batch loss: 2.9558 | |
| Average epoch loss: 2.9419 | |
| Step 97500 | |
| Running loss: 2.9518 | |
| Batch loss: 3.4542 | |
| Average epoch loss: 2.9419 | |
| Step 98000 | |
| Running loss: 2.9229 | |
| Batch loss: 2.9370 | |
| Average epoch loss: 2.9420 | |
| Step 98500 | |
| Running loss: 2.9680 | |
| Batch loss: 3.0972 | |
| Average epoch loss: 2.9421 | |
| Step 99000 | |
| Running loss: 2.9380 | |
| Batch loss: 2.6924 | |
| Average epoch loss: 2.9421 | |
| Step 99500 | |
| Running loss: 2.9682 | |
| Batch loss: 3.0364 | |
| Average epoch loss: 2.9421 | |
| Step 100000 | |
| Running loss: 2.9262 | |
| Batch loss: 2.6384 | |
| Average epoch loss: 2.9420 | |
| Epoch 2 completed. | |
| Average epoch loss: 2.9420 | |
| Step 100500 | |
| Running loss: 2.9155 | |
| Batch loss: 3.2358 | |
| Average epoch loss: 2.9429 | |
| Step 101000 | |
| Running loss: 2.9648 | |
| Batch loss: 3.0225 | |
| Average epoch loss: 2.9506 | |
| Step 101500 | |
| Running loss: 2.9768 | |
| Batch loss: 3.2425 | |
| Average epoch loss: 2.9535 | |
| Step 102000 | |
| Running loss: 2.9554 | |
| Batch loss: 3.1232 | |
| Average epoch loss: 2.9484 | |
| Step 102500 | |
| Running loss: 2.8943 | |
| Batch loss: 2.8584 | |
| Average epoch loss: 2.9469 | |
| Step 103000 | |
| Running loss: 2.9329 | |
| Batch loss: 2.8093 | |
| Average epoch loss: 2.9471 | |
| Step 103500 | |
| Running loss: 2.9450 | |
| Batch loss: 2.5643 | |
| Average epoch loss: 2.9478 | |
| Step 104000 | |
| Running loss: 2.9494 | |
| Batch loss: 2.9554 | |
| Average epoch loss: 2.9465 | |
| Step 104500 | |
| Running loss: 2.9572 | |
| Batch loss: 2.9052 | |
| Average epoch loss: 2.9454 | |
| Step 105000 | |
| Running loss: 2.9435 | |
| Batch loss: 3.1540 | |
| Average epoch loss: 2.9439 | |
| Step 105500 | |
| Running loss: 2.9515 | |
| Batch loss: 2.5069 | |
| Average epoch loss: 2.9425 | |
| Step 106000 | |
| Running loss: 2.9417 | |
| Batch loss: 3.1149 | |
| Average epoch loss: 2.9434 | |
| Step 106500 | |
| Running loss: 2.9522 | |
| Batch loss: 2.8295 | |
| Average epoch loss: 2.9431 | |
| Step 107000 | |
| Running loss: 2.9797 | |
| Batch loss: 3.1995 | |
| Average epoch loss: 2.9434 | |
| Step 107500 | |
| Running loss: 2.9615 | |
| Batch loss: 2.8726 | |
| Average epoch loss: 2.9435 | |
| Step 108000 | |
| Running loss: 2.9489 | |
| Batch loss: 3.2710 | |
| Average epoch loss: 2.9423 | |
| Step 108500 | |
| Running loss: 2.9132 | |
| Batch loss: 2.7173 | |
| Average epoch loss: 2.9418 | |
| Step 109000 | |
| Running loss: 2.9469 | |
| Batch loss: 2.6496 | |
| Average epoch loss: 2.9416 | |
| Step 109500 | |
| Running loss: 2.9217 | |
| Batch loss: 2.9631 | |
| Average epoch loss: 2.9413 | |
| Step 110000 | |
| Running loss: 2.9459 | |
| Batch loss: 2.6527 | |
| Average epoch loss: 2.9416 | |
| Step 110500 | |
| Running loss: 2.9782 | |
| Batch loss: 2.9503 | |
| Average epoch loss: 2.9419 | |
| Step 111000 | |
| Running loss: 2.9656 | |
| Batch loss: 2.8471 | |
| Average epoch loss: 2.9418 | |
| Step 111500 | |
| Running loss: 2.9770 | |
| Batch loss: 3.0443 | |
| Average epoch loss: 2.9420 | |
| Step 112000 | |
| Running loss: 2.9759 | |
| Batch loss: 2.6987 | |
| Average epoch loss: 2.9422 | |
| Step 112500 | |
| Running loss: 2.9579 | |
| Batch loss: 3.3248 | |
| Average epoch loss: 2.9431 | |
| Step 113000 | |
| Running loss: 2.9297 | |
| Batch loss: 2.8627 | |
| Average epoch loss: 2.9431 | |
| Step 113500 | |
| Running loss: 2.9346 | |
| Batch loss: 2.7215 | |
| Average epoch loss: 2.9427 | |
| Step 114000 | |
| Running loss: 2.9377 | |
| Batch loss: 3.0495 | |
| Average epoch loss: 2.9429 | |
| Step 114500 | |
| Running loss: 2.9582 | |
| Batch loss: 2.9972 | |
| Average epoch loss: 2.9432 | |
| Step 115000 | |
| Running loss: 2.9556 | |
| Batch loss: 2.8303 | |
| Average epoch loss: 2.9429 | |
| Step 115500 | |
| Running loss: 2.9483 | |
| Batch loss: 2.8286 | |
| Average epoch loss: 2.9431 | |
| Step 116000 | |
| Running loss: 2.9251 | |
| Batch loss: 3.3705 | |
| Average epoch loss: 2.9425 | |
| Step 116500 | |
| Running loss: 2.9381 | |
| Batch loss: 3.2444 | |
| Average epoch loss: 2.9424 | |
| Step 117000 | |
| Running loss: 2.9157 | |
| Batch loss: 3.1123 | |
| Average epoch loss: 2.9421 | |
| Step 117500 | |
| Running loss: 2.9667 | |
| Batch loss: 2.6360 | |
| Average epoch loss: 2.9420 | |
| Step 118000 | |
| Running loss: 2.9263 | |
| Batch loss: 2.9314 | |
| Average epoch loss: 2.9417 | |
| Step 118500 | |
| Running loss: 2.9593 | |
| Batch loss: 3.1476 | |
| Average epoch loss: 2.9419 | |
| Step 119000 | |
| Running loss: 2.9583 | |
| Batch loss: 3.3532 | |
| Average epoch loss: 2.9421 | |
| Step 119500 | |
| Running loss: 2.9470 | |
| Batch loss: 2.5916 | |
| Average epoch loss: 2.9422 | |
| Step 120000 | |
| Running loss: 2.9055 | |
| Batch loss: 2.8971 | |
| Average epoch loss: 2.9418 | |
| Step 120500 | |
| Running loss: 2.9548 | |
| Batch loss: 2.8854 | |
| Average epoch loss: 2.9421 | |
| Step 121000 | |
| Running loss: 2.9418 | |
| Batch loss: 2.8381 | |
| Average epoch loss: 2.9421 | |
| Step 121500 | |
| Running loss: 2.9320 | |
| Batch loss: 2.7310 | |
| Average epoch loss: 2.9418 | |
| Step 122000 | |
| Running loss: 2.9354 | |
| Batch loss: 2.7634 | |
| Average epoch loss: 2.9417 | |
| Step 122500 | |
| Running loss: 2.9424 | |
| Batch loss: 3.1069 | |
| Average epoch loss: 2.9420 | |
| Step 123000 | |
| Running loss: 2.9380 | |
| Batch loss: 2.9285 | |
| Average epoch loss: 2.9422 | |
| Step 123500 | |
| Running loss: 2.9620 | |
| Batch loss: 3.0183 | |
| Average epoch loss: 2.9425 | |
| Step 124000 | |
| Running loss: 2.9390 | |
| Batch loss: 2.7973 | |
| Average epoch loss: 2.9426 | |
| Step 124500 | |
| Running loss: 2.9237 | |
| Batch loss: 3.1155 | |
| Average epoch loss: 2.9424 | |
| Step 125000 | |
| Running loss: 2.9332 | |
| Batch loss: 2.7631 | |
| Average epoch loss: 2.9423 | |
| Step 125500 | |
| Running loss: 2.9495 | |
| Batch loss: 2.9688 | |
| Average epoch loss: 2.9421 | |
| Step 126000 | |
| Running loss: 2.9741 | |
| Batch loss: 2.7977 | |
| Average epoch loss: 2.9418 | |
| Step 126500 | |
| Running loss: 2.9641 | |
| Batch loss: 2.8618 | |
| Average epoch loss: 2.9418 | |
| Step 127000 | |
| Running loss: 2.9248 | |
| Batch loss: 3.0174 | |
| Average epoch loss: 2.9416 | |
| Step 127500 | |
| Running loss: 2.9413 | |
| Batch loss: 3.0881 | |
| Average epoch loss: 2.9416 | |
| Step 128000 | |
| Running loss: 2.9406 | |
| Batch loss: 2.7432 | |
| Average epoch loss: 2.9414 | |
| Step 128500 | |
| Running loss: 2.9093 | |
| Batch loss: 2.8617 | |
| Average epoch loss: 2.9414 | |
| Step 129000 | |
| Running loss: 2.9636 | |
| Batch loss: 2.7803 | |
| Average epoch loss: 2.9416 | |
| Step 129500 | |
| Running loss: 2.9509 | |
| Batch loss: 2.7138 | |
| Average epoch loss: 2.9414 | |
| Step 130000 | |
| Running loss: 2.9346 | |
| Batch loss: 3.1758 | |
| Average epoch loss: 2.9412 | |
| Step 130500 | |
| Running loss: 2.9264 | |
| Batch loss: 2.9572 | |
| Average epoch loss: 2.9410 | |
| Step 131000 | |
| Running loss: 2.9151 | |
| Batch loss: 3.0902 | |
| Average epoch loss: 2.9408 | |
| Step 131500 | |
| Running loss: 2.9696 | |
| Batch loss: 3.6255 | |
| Average epoch loss: 2.9412 | |
| Step 132000 | |
| Running loss: 2.9592 | |
| Batch loss: 3.3235 | |
| Average epoch loss: 2.9412 | |
| Step 132500 | |
| Running loss: 2.9619 | |
| Batch loss: 2.8041 | |
| Average epoch loss: 2.9414 | |
| Step 133000 | |
| Running loss: 2.9887 | |
| Batch loss: 2.7448 | |
| Average epoch loss: 2.9416 | |
| Step 133500 | |
| Running loss: 2.9727 | |
| Batch loss: 2.7336 | |
| Average epoch loss: 2.9417 | |
| Step 134000 | |
| Running loss: 2.9386 | |
| Batch loss: 2.7160 | |
| Average epoch loss: 2.9415 | |
| Step 134500 | |
| Running loss: 2.9534 | |
| Batch loss: 3.3067 | |
| Average epoch loss: 2.9416 | |
| Step 135000 | |
| Running loss: 2.9522 | |
| Batch loss: 3.1847 | |
| Average epoch loss: 2.9418 | |
| Step 135500 | |
| Running loss: 2.9470 | |
| Batch loss: 3.0888 | |
| Average epoch loss: 2.9418 | |
| Step 136000 | |
| Running loss: 2.9304 | |
| Batch loss: 3.2115 | |
| Average epoch loss: 2.9417 | |
| Step 136500 | |
| Running loss: 2.9034 | |
| Batch loss: 2.9739 | |
| Average epoch loss: 2.9414 | |
| Step 137000 | |
| Running loss: 2.9424 | |
| Batch loss: 3.1310 | |
| Average epoch loss: 2.9411 | |
| Step 137500 | |
| Running loss: 2.9511 | |
| Batch loss: 2.6156 | |
| Average epoch loss: 2.9414 | |
| Step 138000 | |
| Running loss: 2.9325 | |
| Batch loss: 2.9060 | |
| Average epoch loss: 2.9413 | |
| Step 138500 | |
| Running loss: 2.9368 | |
| Batch loss: 2.9598 | |
| Average epoch loss: 2.9414 | |
| Step 139000 | |
| Running loss: 2.9545 | |
| Batch loss: 3.0586 | |
| Average epoch loss: 2.9416 | |
| Step 139500 | |
| Running loss: 2.9086 | |
| Batch loss: 2.9204 | |
| Average epoch loss: 2.9415 | |
| Step 140000 | |
| Running loss: 2.9447 | |
| Batch loss: 2.7101 | |
| Average epoch loss: 2.9415 | |
| Step 140500 | |
| Running loss: 2.9482 | |
| Batch loss: 3.0306 | |
| Average epoch loss: 2.9417 | |
| Step 141000 | |
| Running loss: 2.9246 | |
| Batch loss: 2.8086 | |
| Average epoch loss: 2.9417 | |
| Step 141500 | |
| Running loss: 2.9395 | |
| Batch loss: 2.7763 | |
| Average epoch loss: 2.9417 | |
| Step 142000 | |
| Running loss: 2.9430 | |
| Batch loss: 2.7555 | |
| Average epoch loss: 2.9416 | |
| Step 142500 | |
| Running loss: 2.9303 | |
| Batch loss: 2.7942 | |
| Average epoch loss: 2.9417 | |
| Step 143000 | |
| Running loss: 2.9498 | |
| Batch loss: 3.1108 | |
| Average epoch loss: 2.9417 | |
| Step 143500 | |
| Running loss: 2.9365 | |
| Batch loss: 2.8355 | |
| Average epoch loss: 2.9417 | |
| Step 144000 | |
| Running loss: 2.9656 | |
| Batch loss: 2.8648 | |
| Average epoch loss: 2.9418 | |
| Step 144500 | |
| Running loss: 2.9625 | |
| Batch loss: 3.2211 | |
| Average epoch loss: 2.9418 | |
| Step 145000 | |
| Running loss: 2.9569 | |
| Batch loss: 3.1650 | |
| Average epoch loss: 2.9418 | |
| Step 145500 | |
| Running loss: 2.9446 | |
| Batch loss: 2.9080 | |
| Average epoch loss: 2.9420 | |
| Step 146000 | |
| Running loss: 2.9262 | |
| Batch loss: 2.7511 | |
| Average epoch loss: 2.9421 | |
| Step 146500 | |
| Running loss: 2.9485 | |
| Batch loss: 3.0678 | |
| Average epoch loss: 2.9420 | |
| Step 147000 | |
| Running loss: 2.9571 | |
| Batch loss: 2.7802 | |
| Average epoch loss: 2.9421 | |
| Step 147500 | |
| Running loss: 2.9199 | |
| Batch loss: 3.0210 | |
| Average epoch loss: 2.9421 | |
| Step 148000 | |
| Running loss: 2.9432 | |
| Batch loss: 3.3375 | |
| Average epoch loss: 2.9420 | |
| Step 148500 | |
| Running loss: 2.9078 | |
| Batch loss: 3.0431 | |
| Average epoch loss: 2.9420 | |
| Step 149000 | |
| Running loss: 2.9389 | |
| Batch loss: 2.9250 | |
| Average epoch loss: 2.9422 | |
| Step 149500 | |
| Running loss: 2.9399 | |
| Batch loss: 2.5021 | |
| Average epoch loss: 2.9424 | |
| Step 150000 | |
| Running loss: 2.9267 | |
| Batch loss: 2.9105 | |
| Average epoch loss: 2.9424 | |
| Epoch 3 completed. | |
| Average epoch loss: 2.9425 | |
| Step 150500 | |
| Running loss: 2.9564 | |
| Batch loss: 3.1557 | |
| Average epoch loss: 2.9656 | |
| Step 151000 | |
| Running loss: 2.9215 | |
| Batch loss: 3.1041 | |
| Average epoch loss: 2.9551 | |
| Step 151500 | |
| Running loss: 2.9062 | |
| Batch loss: 3.3228 | |
| Average epoch loss: 2.9465 | |
| Step 152000 | |
| Running loss: 2.9332 | |
| Batch loss: 2.6937 | |
| Average epoch loss: 2.9459 | |
| Step 152500 | |
| Running loss: 2.9562 | |
| Batch loss: 3.1129 | |
| Average epoch loss: 2.9435 | |
| Step 153000 | |
| Running loss: 2.9425 | |
| Batch loss: 3.0589 | |
| Average epoch loss: 2.9402 | |
| Step 153500 | |
| Running loss: 2.9302 | |
| Batch loss: 3.2617 | |
| Average epoch loss: 2.9389 | |
| Step 154000 | |
| Running loss: 2.9521 | |
| Batch loss: 2.6926 | |
| Average epoch loss: 2.9398 | |
| Step 154500 | |
| Running loss: 2.9719 | |
| Batch loss: 2.4848 | |
| Average epoch loss: 2.9396 | |
| Step 155000 | |
| Running loss: 2.9212 | |
| Batch loss: 2.3902 | |
| Average epoch loss: 2.9399 | |
| Step 155500 | |
| Running loss: 2.9659 | |
| Batch loss: 3.3094 | |
| Average epoch loss: 2.9416 | |
| Step 156000 | |
| Running loss: 2.9653 | |
| Batch loss: 2.9304 | |
| Average epoch loss: 2.9427 | |
| Step 156500 | |
| Running loss: 2.9388 | |
| Batch loss: 3.1402 | |
| Average epoch loss: 2.9427 | |
| Step 157000 | |
| Running loss: 2.9225 | |
| Batch loss: 2.8507 | |
| Average epoch loss: 2.9419 | |
| Step 157500 | |
| Running loss: 2.9352 | |
| Batch loss: 3.2160 | |
| Average epoch loss: 2.9415 | |
| Step 158000 | |
| Running loss: 2.9450 | |
| Batch loss: 3.0769 | |
| Average epoch loss: 2.9416 | |
| Step 158500 | |
| Running loss: 2.9049 | |
| Batch loss: 2.8343 | |
| Average epoch loss: 2.9414 | |
| Step 159000 | |
| Running loss: 2.9294 | |
| Batch loss: 2.8401 | |
| Average epoch loss: 2.9415 | |
| Step 159500 | |
| Running loss: 2.9377 | |
| Batch loss: 3.0961 | |
| Average epoch loss: 2.9422 | |
| Step 160000 | |
| Running loss: 2.9213 | |
| Batch loss: 3.2788 | |
| Average epoch loss: 2.9423 | |
| Step 160500 | |
| Running loss: 2.9646 | |
| Batch loss: 3.2358 | |
| Average epoch loss: 2.9425 | |
| Step 161000 | |
| Running loss: 2.9545 | |
| Batch loss: 2.7998 | |
| Average epoch loss: 2.9434 | |
| Step 161500 | |
| Running loss: 2.9467 | |
| Batch loss: 3.1985 | |
| Average epoch loss: 2.9432 | |
| Step 162000 | |
| Running loss: 2.9145 | |
| Batch loss: 3.1316 | |
| Average epoch loss: 2.9426 | |
| Step 162500 | |
| Running loss: 2.9486 | |
| Batch loss: 2.7330 | |
| Average epoch loss: 2.9422 | |
| Step 163000 | |
| Running loss: 2.9553 | |
| Batch loss: 3.0244 | |
| Average epoch loss: 2.9422 | |
| Step 163500 | |
| Running loss: 2.9461 | |
| Batch loss: 3.1776 | |
| Average epoch loss: 2.9423 | |
| Step 164000 | |
| Running loss: 2.9320 | |
| Batch loss: 2.8124 | |
| Average epoch loss: 2.9422 | |
| Step 164500 | |
| Running loss: 2.9395 | |
| Batch loss: 2.9758 | |
| Average epoch loss: 2.9425 | |
| Step 165000 | |
| Running loss: 2.9606 | |
| Batch loss: 2.7490 | |
| Average epoch loss: 2.9428 | |
| Step 165500 | |
| Running loss: 2.9617 | |
| Batch loss: 2.8240 | |
| Average epoch loss: 2.9432 | |
| Step 166000 | |
| Running loss: 2.9561 | |
| Batch loss: 3.1460 | |
| Average epoch loss: 2.9429 | |
| Step 166500 | |
| Running loss: 2.9597 | |
| Batch loss: 3.3176 | |
| Average epoch loss: 2.9428 | |
| Step 167000 | |
| Running loss: 2.9461 | |
| Batch loss: 2.9058 | |
| Average epoch loss: 2.9431 | |
| Step 167500 | |
| Running loss: 2.9693 | |
| Batch loss: 2.8990 | |
| Average epoch loss: 2.9436 | |
| Step 168000 | |
| Running loss: 2.9369 | |
| Batch loss: 2.9870 | |
| Average epoch loss: 2.9435 | |
| Step 168500 | |
| Running loss: 2.9359 | |
| Batch loss: 2.9673 | |
| Average epoch loss: 2.9431 | |
| Step 169000 | |
| Running loss: 2.9740 | |
| Batch loss: 2.9489 | |
| Average epoch loss: 2.9434 | |
| Step 169500 | |
| Running loss: 2.9954 | |
| Batch loss: 2.8415 | |
| Average epoch loss: 2.9439 | |
| Step 170000 | |
| Running loss: 2.9412 | |
| Batch loss: 3.0077 | |
| Average epoch loss: 2.9442 | |
| Step 170500 | |
| Running loss: 2.9267 | |
| Batch loss: 3.1778 | |
| Average epoch loss: 2.9437 | |
| Step 171000 | |
| Running loss: 2.9154 | |
| Batch loss: 2.7705 | |
| Average epoch loss: 2.9437 | |
| Step 171500 | |
| Running loss: 2.9186 | |
| Batch loss: 2.7800 | |
| Average epoch loss: 2.9437 | |
| Step 172000 | |
| Running loss: 2.9503 | |
| Batch loss: 3.1539 | |
| Average epoch loss: 2.9436 | |
| Step 172500 | |
| Running loss: 2.9598 | |
| Batch loss: 2.8952 | |
| Average epoch loss: 2.9440 | |
| Step 173000 | |
| Running loss: 2.9031 | |
| Batch loss: 2.9620 | |
| Average epoch loss: 2.9439 | |
| Step 173500 | |
| Running loss: 2.9638 | |
| Batch loss: 3.3369 | |
| Average epoch loss: 2.9438 | |
| Step 174000 | |
| Running loss: 2.9150 | |
| Batch loss: 2.8530 | |
| Average epoch loss: 2.9437 | |
| Step 174500 | |
| Running loss: 2.9461 | |
| Batch loss: 3.1431 | |
| Average epoch loss: 2.9435 | |
| Step 175000 | |
| Running loss: 2.9474 | |
| Batch loss: 2.5670 | |
| Average epoch loss: 2.9438 | |
| Step 175500 | |
| Running loss: 2.9495 | |
| Batch loss: 3.3526 | |
| Average epoch loss: 2.9438 | |
| Step 176000 | |
| Running loss: 2.9417 | |
| Batch loss: 2.6791 | |
| Average epoch loss: 2.9439 | |
| Step 176500 | |
| Running loss: 2.9568 | |
| Batch loss: 2.9608 | |
| Average epoch loss: 2.9438 | |
| Step 177000 | |
| Running loss: 2.9490 | |
| Batch loss: 2.8889 | |
| Average epoch loss: 2.9437 | |
| Step 177500 | |
| Running loss: 2.9653 | |
| Batch loss: 2.8927 | |
| Average epoch loss: 2.9438 | |
| Step 178000 | |
| Running loss: 2.9421 | |
| Batch loss: 2.8154 | |
| Average epoch loss: 2.9439 | |
| Step 178500 | |
| Running loss: 2.9526 | |
| Batch loss: 2.7549 | |
| Average epoch loss: 2.9440 | |
| Step 179000 | |
| Running loss: 2.9184 | |
| Batch loss: 3.0188 | |
| Average epoch loss: 2.9439 | |
| Step 179500 | |
| Running loss: 2.9364 | |
| Batch loss: 2.9402 | |
| Average epoch loss: 2.9441 | |
| Step 180000 | |
| Running loss: 2.8763 | |
| Batch loss: 3.0046 | |
| Average epoch loss: 2.9438 | |
| Step 180500 | |
| Running loss: 2.9879 | |
| Batch loss: 2.9668 | |
| Average epoch loss: 2.9440 | |
| Step 181000 | |
| Running loss: 2.9318 | |
| Batch loss: 2.8255 | |
| Average epoch loss: 2.9439 | |
| Step 181500 | |
| Running loss: 2.9655 | |
| Batch loss: 3.0208 | |
| Average epoch loss: 2.9439 | |
| Step 182000 | |
| Running loss: 2.9165 | |
| Batch loss: 3.0341 | |
| Average epoch loss: 2.9439 | |
| Step 182500 | |
| Running loss: 2.9251 | |
| Batch loss: 2.9712 | |
| Average epoch loss: 2.9436 | |
| Step 183000 | |
| Running loss: 2.9651 | |
| Batch loss: 3.0678 | |
| Average epoch loss: 2.9435 | |
| Step 183500 | |
| Running loss: 2.9367 | |
| Batch loss: 2.7992 | |
| Average epoch loss: 2.9435 | |
| Step 184000 | |
| Running loss: 2.9332 | |
| Batch loss: 2.8240 | |
| Average epoch loss: 2.9435 | |
| Step 184500 | |
| Running loss: 2.9411 | |
| Batch loss: 2.6892 | |
| Average epoch loss: 2.9435 | |
| Step 185000 | |
| Running loss: 2.9247 | |
| Batch loss: 2.5427 | |
| Average epoch loss: 2.9436 | |
| Step 185500 | |
| Running loss: 2.9547 | |
| Batch loss: 2.9854 | |
| Average epoch loss: 2.9438 | |
| Step 186000 | |
| Running loss: 2.9362 | |
| Batch loss: 3.1528 | |
| Average epoch loss: 2.9439 | |
| Step 186500 | |
| Running loss: 2.9747 | |
| Batch loss: 2.8146 | |
| Average epoch loss: 2.9439 | |
| Step 187000 | |
| Running loss: 2.9982 | |
| Batch loss: 3.3214 | |
| Average epoch loss: 2.9441 | |
| Step 187500 | |
| Running loss: 2.9468 | |
| Batch loss: 3.4083 | |
| Average epoch loss: 2.9441 | |
| Step 188000 | |
| Running loss: 2.9316 | |
| Batch loss: 3.2157 | |
| Average epoch loss: 2.9439 | |
| Step 188500 | |
| Running loss: 2.9460 | |
| Batch loss: 2.8767 | |
| Average epoch loss: 2.9438 | |
| Step 189000 | |
| Running loss: 2.9610 | |
| Batch loss: 3.2154 | |
| Average epoch loss: 2.9438 | |
| Step 189500 | |
| Running loss: 2.9067 | |
| Batch loss: 3.0325 | |
| Average epoch loss: 2.9436 | |
| Step 190000 | |
| Running loss: 2.8859 | |
| Batch loss: 2.5800 | |
| Average epoch loss: 2.9434 | |
| Step 190500 | |
| Running loss: 2.9800 | |
| Batch loss: 3.0535 | |
| Average epoch loss: 2.9437 | |
| Step 191000 | |
| Running loss: 2.9269 | |
| Batch loss: 3.3987 | |
| Average epoch loss: 2.9435 | |
| Step 191500 | |
| Running loss: 2.9576 | |
| Batch loss: 2.7609 | |
| Average epoch loss: 2.9435 | |
| Step 192000 | |
| Running loss: 2.9595 | |
| Batch loss: 2.8083 | |
| Average epoch loss: 2.9435 | |
| Step 192500 | |
| Running loss: 2.9821 | |
| Batch loss: 3.1185 | |
| Average epoch loss: 2.9435 | |
| Step 193000 | |
| Running loss: 2.9037 | |
| Batch loss: 3.0375 | |
| Average epoch loss: 2.9434 | |
| Step 193500 | |
| Running loss: 2.9343 | |
| Batch loss: 2.8598 | |
| Average epoch loss: 2.9433 | |
| Step 194000 | |
| Running loss: 2.9685 | |
| Batch loss: 3.0807 | |
| Average epoch loss: 2.9432 | |
| Step 194500 | |
| Running loss: 2.9199 | |
| Batch loss: 3.1039 | |
| Average epoch loss: 2.9433 | |
| Step 195000 | |
| Running loss: 2.9586 | |
| Batch loss: 2.5298 | |
| Average epoch loss: 2.9435 | |
| Step 195500 | |
| Running loss: 2.9513 | |
| Batch loss: 2.8460 | |
| Average epoch loss: 2.9434 | |
| Step 196000 | |
| Running loss: 2.9461 | |
| Batch loss: 2.6522 | |
| Average epoch loss: 2.9434 | |
| Step 196500 | |
| Running loss: 2.9350 | |
| Batch loss: 2.4073 | |
| Average epoch loss: 2.9435 | |
| Step 197000 | |
| Running loss: 2.9714 | |
| Batch loss: 3.0423 | |
| Average epoch loss: 2.9434 | |
| Step 197500 | |
| Running loss: 2.9087 | |
| Batch loss: 2.9814 | |
| Average epoch loss: 2.9433 | |
| Step 198000 | |
| Running loss: 2.9385 | |
| Batch loss: 2.9731 | |
| Average epoch loss: 2.9434 | |
| Step 198500 | |
| Running loss: 2.9560 | |
| Batch loss: 3.0354 | |
| Average epoch loss: 2.9432 | |
| Step 199000 | |
| Running loss: 2.9388 | |
| Batch loss: 2.8670 | |
| Average epoch loss: 2.9432 | |
| Step 199500 | |
| Running loss: 2.9584 | |
| Batch loss: 3.0511 | |
| Average epoch loss: 2.9432 | |
| Step 200000 | |
| Running loss: 2.9513 | |
| Batch loss: 2.8311 | |
| Average epoch loss: 2.9430 | |
| Epoch 4 completed. | |
| Average epoch loss: 2.9431 | |
| Step 200500 | |
| Running loss: 2.9121 | |
| Batch loss: 2.7981 | |
| Average epoch loss: 2.9205 | |
| Step 201000 | |
| Running loss: 2.9060 | |
| Batch loss: 3.0067 | |
| Average epoch loss: 2.9275 | |
| Step 201500 | |
| Running loss: 2.9608 | |
| Batch loss: 3.3741 | |
| Average epoch loss: 2.9314 | |
| Step 202000 | |
| Running loss: 2.9445 | |
| Batch loss: 2.9082 | |
| Average epoch loss: 2.9387 | |
| Step 202500 | |
| Running loss: 2.9580 | |
| Batch loss: 2.7243 | |
| Average epoch loss: 2.9439 | |
| Step 203000 | |
| Running loss: 2.9538 | |
| Batch loss: 2.9398 | |
| Average epoch loss: 2.9437 | |
| Step 203500 | |
| Running loss: 2.9346 | |
| Batch loss: 2.7461 | |
| Average epoch loss: 2.9440 | |
| Step 204000 | |
| Running loss: 2.9313 | |
| Batch loss: 2.7932 | |
| Average epoch loss: 2.9418 | |
| Step 204500 | |
| Running loss: 2.9590 | |
| Batch loss: 3.2848 | |
| Average epoch loss: 2.9426 | |
| Step 205000 | |
| Running loss: 2.9495 | |
| Batch loss: 2.7123 | |
| Average epoch loss: 2.9427 | |
| Step 205500 | |
| Running loss: 2.9576 | |
| Batch loss: 2.6668 | |
| Average epoch loss: 2.9415 | |
| Step 206000 | |
| Running loss: 2.9480 | |
| Batch loss: 2.8293 | |
| Average epoch loss: 2.9409 | |
| Step 206500 | |
| Running loss: 2.9217 | |
| Batch loss: 2.8910 | |
| Average epoch loss: 2.9403 | |
| Step 207000 | |
| Running loss: 2.9362 | |
| Batch loss: 2.8238 | |
| Average epoch loss: 2.9403 | |
| Step 207500 | |
| Running loss: 2.8979 | |
| Batch loss: 3.0769 | |
| Average epoch loss: 2.9399 | |
| Step 208000 | |
| Running loss: 2.9598 | |
| Batch loss: 3.0455 | |
| Average epoch loss: 2.9400 | |
| Step 208500 | |
| Running loss: 2.9396 | |
| Batch loss: 2.7116 | |
| Average epoch loss: 2.9405 | |
| Step 209000 | |
| Running loss: 2.9448 | |
| Batch loss: 3.0919 | |
| Average epoch loss: 2.9408 | |
| Step 209500 | |
| Running loss: 2.8930 | |
| Batch loss: 2.7241 | |
| Average epoch loss: 2.9405 | |
| Step 210000 | |
| Running loss: 2.9203 | |
| Batch loss: 2.8739 | |
| Average epoch loss: 2.9412 | |
| Step 210500 | |
| Running loss: 2.9770 | |
| Batch loss: 3.3085 | |
| Average epoch loss: 2.9415 | |
| Step 211000 | |
| Running loss: 2.9446 | |
| Batch loss: 2.6658 | |
| Average epoch loss: 2.9417 | |
| Step 211500 | |
| Running loss: 2.9150 | |
| Batch loss: 2.9073 | |
| Average epoch loss: 2.9419 | |
| Step 212000 | |
| Running loss: 2.9385 | |
| Batch loss: 3.1894 | |
| Average epoch loss: 2.9414 | |
| Step 212500 | |
| Running loss: 2.9158 | |
| Batch loss: 3.1059 | |
| Average epoch loss: 2.9416 | |
| Step 213000 | |
| Running loss: 2.9653 | |
| Batch loss: 3.0103 | |
| Average epoch loss: 2.9421 | |
| Step 213500 | |
| Running loss: 2.9534 | |
| Batch loss: 3.1832 | |
| Average epoch loss: 2.9422 | |
| Step 214000 | |
| Running loss: 2.9624 | |
| Batch loss: 2.9504 | |
| Average epoch loss: 2.9427 | |
| Step 214500 | |
| Running loss: 2.9494 | |
| Batch loss: 2.5730 | |
| Average epoch loss: 2.9432 | |
| Step 215000 | |
| Running loss: 2.9397 | |
| Batch loss: 2.5186 | |
| Average epoch loss: 2.9428 | |
| Step 215500 | |
| Running loss: 2.9404 | |
| Batch loss: 3.1341 | |
| Average epoch loss: 2.9427 | |
| Step 216000 | |
| Running loss: 2.9490 | |
| Batch loss: 2.9746 | |
| Average epoch loss: 2.9427 | |
| Step 216500 | |
| Running loss: 2.9424 | |
| Batch loss: 2.7425 | |
| Average epoch loss: 2.9428 | |
| Step 217000 | |
| Running loss: 2.9337 | |
| Batch loss: 2.8519 | |
| Average epoch loss: 2.9424 | |
| Step 217500 | |
| Running loss: 2.9594 | |
| Batch loss: 2.8271 | |
| Average epoch loss: 2.9425 | |
| Step 218000 | |
| Running loss: 2.9443 | |
| Batch loss: 3.3315 | |
| Average epoch loss: 2.9427 | |
| Step 218500 | |
| Running loss: 2.9349 | |
| Batch loss: 2.6903 | |
| Average epoch loss: 2.9431 | |
| Step 219000 | |
| Running loss: 2.9549 | |
| Batch loss: 3.1145 | |
| Average epoch loss: 2.9433 | |
| Step 219500 | |
| Running loss: 2.9361 | |
| Batch loss: 2.9810 | |
| Average epoch loss: 2.9431 | |
| Step 220000 | |
| Running loss: 2.9424 | |
| Batch loss: 3.0899 | |
| Average epoch loss: 2.9433 | |
| Step 220500 | |
| Running loss: 2.9531 | |
| Batch loss: 2.9372 | |
| Average epoch loss: 2.9432 | |
| Step 221000 | |
| Running loss: 2.9148 | |
| Batch loss: 2.7178 | |
| Average epoch loss: 2.9431 | |
| Step 221500 | |
| Running loss: 2.9518 | |
| Batch loss: 2.9936 | |
| Average epoch loss: 2.9434 | |
| Step 222000 | |
| Running loss: 2.9169 | |
| Batch loss: 3.0488 | |
| Average epoch loss: 2.9434 | |
| Step 222500 | |
| Running loss: 2.9213 | |
| Batch loss: 2.9938 | |
| Average epoch loss: 2.9432 | |
| Step 223000 | |
| Running loss: 2.9558 | |
| Batch loss: 2.9017 | |
| Average epoch loss: 2.9434 | |
| Step 223500 | |
| Running loss: 2.9165 | |
| Batch loss: 3.0350 | |
| Average epoch loss: 2.9432 | |
| Step 224000 | |
| Running loss: 2.9494 | |
| Batch loss: 3.2996 | |
| Average epoch loss: 2.9431 | |
| Step 224500 | |
| Running loss: 2.9105 | |
| Batch loss: 3.0436 | |
| Average epoch loss: 2.9428 | |
| Step 225000 | |
| Running loss: 2.9507 | |
| Batch loss: 2.7310 | |
| Average epoch loss: 2.9429 | |
| Step 225500 | |
| Running loss: 2.9321 | |
| Batch loss: 2.9168 | |
| Average epoch loss: 2.9427 | |
| Step 226000 | |
| Running loss: 2.9244 | |
| Batch loss: 3.1298 | |
| Average epoch loss: 2.9426 | |
| Step 226500 | |
| Running loss: 2.9064 | |
| Batch loss: 3.2016 | |
| Average epoch loss: 2.9424 | |
| Step 227000 | |
| Running loss: 3.0057 | |
| Batch loss: 3.0171 | |
| Average epoch loss: 2.9427 | |
| Step 227500 | |
| Running loss: 2.9260 | |
| Batch loss: 3.0309 | |
| Average epoch loss: 2.9426 | |
| Step 228000 | |
| Running loss: 2.9203 | |
| Batch loss: 3.0772 | |
| Average epoch loss: 2.9423 | |
| Step 228500 | |
| Running loss: 2.9589 | |
| Batch loss: 2.9839 | |
| Average epoch loss: 2.9419 | |
| Step 229000 | |
| Running loss: 2.9615 | |
| Batch loss: 3.4255 | |
| Average epoch loss: 2.9418 | |
| Step 229500 | |
| Running loss: 2.9439 | |
| Batch loss: 2.9329 | |
| Average epoch loss: 2.9417 | |
| Step 230000 | |
| Running loss: 2.9638 | |
| Batch loss: 2.7203 | |
| Average epoch loss: 2.9418 | |
| Step 230500 | |
| Running loss: 2.9536 | |
| Batch loss: 2.7863 | |
| Average epoch loss: 2.9421 | |
| Step 231000 | |
| Running loss: 2.9633 | |
| Batch loss: 3.1998 | |
| Average epoch loss: 2.9420 | |
| Step 231500 | |
| Running loss: 2.9579 | |
| Batch loss: 3.1888 | |
| Average epoch loss: 2.9423 | |
| Step 232000 | |
| Running loss: 2.9319 | |
| Batch loss: 3.0275 | |
| Average epoch loss: 2.9423 | |
| Step 232500 | |
| Running loss: 2.9509 | |
| Batch loss: 2.7985 | |
| Average epoch loss: 2.9422 | |
| Step 233000 | |
| Running loss: 2.9256 | |
| Batch loss: 2.7160 | |
| Average epoch loss: 2.9420 | |
| Step 233500 | |
| Running loss: 2.9484 | |
| Batch loss: 3.2076 | |
| Average epoch loss: 2.9419 | |
| Step 234000 | |
| Running loss: 2.9571 | |
| Batch loss: 3.2150 | |
| Average epoch loss: 2.9419 | |
| Step 234500 | |
| Running loss: 2.9495 | |
| Batch loss: 3.0010 | |
| Average epoch loss: 2.9420 | |
| Step 235000 | |
| Running loss: 2.8985 | |
| Batch loss: 2.4138 | |
| Average epoch loss: 2.9421 | |
| Step 235500 | |
| Running loss: 2.9183 | |
| Batch loss: 3.0038 | |
| Average epoch loss: 2.9421 | |
| Step 236000 | |
| Running loss: 2.9245 | |
| Batch loss: 2.9919 | |
| Average epoch loss: 2.9421 | |
| Step 236500 | |
| Running loss: 2.9417 | |
| Batch loss: 2.8677 | |
| Average epoch loss: 2.9423 | |
| Step 237000 | |
| Running loss: 2.9188 | |
| Batch loss: 2.8755 | |
| Average epoch loss: 2.9423 | |
| Step 237500 | |
| Running loss: 2.9768 | |
| Batch loss: 3.1052 | |
| Average epoch loss: 2.9424 | |
| Step 238000 | |
| Running loss: 2.9190 | |
| Batch loss: 3.0177 | |
| Average epoch loss: 2.9424 | |
| Step 238500 | |
| Running loss: 2.9417 | |
| Batch loss: 3.1225 | |
| Average epoch loss: 2.9425 | |
| Step 239000 | |
| Running loss: 2.9301 | |
| Batch loss: 2.7949 | |
| Average epoch loss: 2.9426 | |
| Step 239500 | |
| Running loss: 2.9179 | |
| Batch loss: 3.1141 | |
| Average epoch loss: 2.9427 | |
| Step 240000 | |
| Running loss: 2.9474 | |
| Batch loss: 2.8198 | |
| Average epoch loss: 2.9427 | |
| Step 240500 | |
| Running loss: 2.8891 | |
| Batch loss: 2.7526 | |
| Average epoch loss: 2.9426 | |
| Step 241000 | |
| Running loss: 2.9501 | |
| Batch loss: 2.9670 | |
| Average epoch loss: 2.9426 | |
| Step 241500 | |
| Running loss: 2.9619 | |
| Batch loss: 2.6681 | |
| Average epoch loss: 2.9427 | |
| Step 242000 | |
| Running loss: 2.9260 | |
| Batch loss: 3.0840 | |
| Average epoch loss: 2.9427 | |
| Step 242500 | |
| Running loss: 2.9691 | |
| Batch loss: 2.9948 | |
| Average epoch loss: 2.9428 | |
| Step 243000 | |
| Running loss: 2.9355 | |
| Batch loss: 2.7183 | |
| Average epoch loss: 2.9428 | |
| Step 243500 | |
| Running loss: 2.9395 | |
| Batch loss: 2.9271 | |
| Average epoch loss: 2.9429 | |
| Step 244000 | |
| Running loss: 2.9553 | |
| Batch loss: 2.8409 | |
| Average epoch loss: 2.9430 | |
| Step 244500 | |
| Running loss: 2.9714 | |
| Batch loss: 2.7731 | |
| Average epoch loss: 2.9430 | |
| Step 245000 | |
| Running loss: 2.9609 | |
| Batch loss: 2.8004 | |
| Average epoch loss: 2.9432 | |
| Step 245500 | |
| Running loss: 2.9157 | |
| Batch loss: 2.9865 | |
| Average epoch loss: 2.9430 | |
| Step 246000 | |
| Running loss: 2.9495 | |
| Batch loss: 3.0036 | |
| Average epoch loss: 2.9431 | |
| Step 246500 | |
| Running loss: 2.9736 | |
| Batch loss: 2.8773 | |
| Average epoch loss: 2.9431 | |
| Step 247000 | |
| Running loss: 2.9268 | |
| Batch loss: 3.0590 | |
| Average epoch loss: 2.9431 | |
| Step 247500 | |
| Running loss: 2.9561 | |
| Batch loss: 3.3984 | |
| Average epoch loss: 2.9432 | |
| Step 248000 | |
| Running loss: 2.9743 | |
| Batch loss: 3.1262 | |
| Average epoch loss: 2.9435 | |
| Step 248500 | |
| Running loss: 2.9503 | |
| Batch loss: 3.2844 | |
| Average epoch loss: 2.9435 | |
| Step 249000 | |
| Running loss: 2.9181 | |
| Batch loss: 2.7847 | |
| Average epoch loss: 2.9434 | |
| Step 249500 | |
| Running loss: 2.9485 | |
| Batch loss: 3.1284 | |
| Average epoch loss: 2.9435 | |
| Step 250000 | |
| Running loss: 2.9286 | |
| Batch loss: 2.4978 | |
| Average epoch loss: 2.9435 | |
| Epoch 5 completed. | |
| Average epoch loss: 2.9436 | |
| Step 250500 | |
| Running loss: 2.9113 | |
| Batch loss: 3.3179 | |
| Average epoch loss: 2.9247 | |
| Step 251000 | |
| Running loss: 2.9768 | |
| Batch loss: 3.1721 | |
| Average epoch loss: 2.9361 | |
| Step 251500 | |
| Running loss: 2.9479 | |
| Batch loss: 2.7964 | |
| Average epoch loss: 2.9354 | |
| Step 252000 | |
| Running loss: 2.9638 | |
| Batch loss: 3.1067 | |
| Average epoch loss: 2.9410 | |
| Step 252500 | |
| Running loss: 2.8998 | |
| Batch loss: 3.3829 | |
| Average epoch loss: 2.9413 | |
| Step 253000 | |
| Running loss: 2.9308 | |
| Batch loss: 2.8719 | |
| Average epoch loss: 2.9418 | |
| Step 253500 | |
| Running loss: 3.0017 | |
| Batch loss: 3.0819 | |
| Average epoch loss: 2.9433 | |
| Step 254000 | |
| Running loss: 2.9587 | |
| Batch loss: 2.9656 | |
| Average epoch loss: 2.9443 | |
| Step 254500 | |
| Running loss: 2.9689 | |
| Batch loss: 2.9555 | |
| Average epoch loss: 2.9442 | |
| Step 255000 | |
| Running loss: 2.9550 | |
| Batch loss: 2.9712 | |
| Average epoch loss: 2.9432 | |
| Step 255500 | |
| Running loss: 2.9487 | |
| Batch loss: 3.1263 | |
| Average epoch loss: 2.9434 | |
| Step 256000 | |
| Running loss: 2.8925 | |
| Batch loss: 2.7029 | |
| Average epoch loss: 2.9423 | |
| Step 256500 | |
| Running loss: 2.9828 | |
| Batch loss: 3.1138 | |
| Average epoch loss: 2.9421 | |
| Step 257000 | |
| Running loss: 2.9371 | |
| Batch loss: 3.0946 | |
| Average epoch loss: 2.9431 | |
| Step 257500 | |
| Running loss: 2.9530 | |
| Batch loss: 3.0340 | |
| Average epoch loss: 2.9438 | |
| Step 258000 | |
| Running loss: 2.9173 | |
| Batch loss: 3.1016 | |
| Average epoch loss: 2.9433 | |
| Step 258500 | |
| Running loss: 2.9269 | |
| Batch loss: 2.8028 | |
| Average epoch loss: 2.9430 | |
| Step 259000 | |
| Running loss: 2.9581 | |
| Batch loss: 3.0016 | |
| Average epoch loss: 2.9433 | |
| Step 259500 | |
| Running loss: 2.9321 | |
| Batch loss: 3.1088 | |
| Average epoch loss: 2.9434 | |
| Step 260000 | |
| Running loss: 2.9677 | |
| Batch loss: 2.6386 | |
| Average epoch loss: 2.9439 | |
| Step 260500 | |
| Running loss: 2.9368 | |
| Batch loss: 2.8435 | |
| Average epoch loss: 2.9433 | |
| Step 261000 | |
| Running loss: 2.9193 | |
| Batch loss: 2.9137 | |
| Average epoch loss: 2.9433 | |
| Step 261500 | |
| Running loss: 2.9220 | |
| Batch loss: 2.7597 | |
| Average epoch loss: 2.9430 | |
| Step 262000 | |
| Running loss: 2.8940 | |
| Batch loss: 2.5941 | |
| Average epoch loss: 2.9427 | |
| Step 262500 | |
| Running loss: 2.9337 | |
| Batch loss: 3.0090 | |
| Average epoch loss: 2.9429 | |
| Step 263000 | |
| Running loss: 2.9711 | |
| Batch loss: 3.0482 | |
| Average epoch loss: 2.9433 | |
| Step 263500 | |
| Running loss: 2.9400 | |
| Batch loss: 3.0208 | |
| Average epoch loss: 2.9432 | |
| Step 264000 | |
| Running loss: 2.9456 | |
| Batch loss: 2.8285 | |
| Average epoch loss: 2.9438 | |
| Step 264500 | |
| Running loss: 2.9076 | |
| Batch loss: 2.7473 | |
| Average epoch loss: 2.9430 | |
| Step 265000 | |
| Running loss: 2.9802 | |
| Batch loss: 3.1843 | |
| Average epoch loss: 2.9439 | |
| Step 265500 | |
| Running loss: 2.9256 | |
| Batch loss: 2.7751 | |
| Average epoch loss: 2.9440 | |
| Step 266000 | |
| Running loss: 2.9484 | |
| Batch loss: 2.7913 | |
| Average epoch loss: 2.9439 | |
| Step 266500 | |
| Running loss: 2.9815 | |
| Batch loss: 2.9242 | |
| Average epoch loss: 2.9443 | |
| Step 267000 | |
| Running loss: 2.9361 | |
| Batch loss: 3.0729 | |
| Average epoch loss: 2.9440 | |
| Step 267500 | |
| Running loss: 2.9534 | |
| Batch loss: 3.0480 | |
| Average epoch loss: 2.9442 | |
| Step 268000 | |
| Running loss: 2.9349 | |
| Batch loss: 3.1642 | |
| Average epoch loss: 2.9441 | |
| Step 268500 | |
| Running loss: 2.9423 | |
| Batch loss: 3.0093 | |
| Average epoch loss: 2.9441 | |
| Step 269000 | |
| Running loss: 2.9546 | |
| Batch loss: 2.9761 | |
| Average epoch loss: 2.9442 | |
| Step 269500 | |
| Running loss: 2.9627 | |
| Batch loss: 3.2358 | |
| Average epoch loss: 2.9445 | |
| Step 270000 | |
| Running loss: 2.9023 | |
| Batch loss: 3.0809 | |
| Average epoch loss: 2.9445 | |
| Step 270500 | |
| Running loss: 2.9853 | |
| Batch loss: 2.9148 | |
| Average epoch loss: 2.9448 | |
| Step 271000 | |
| Running loss: 2.9391 | |
| Batch loss: 3.2628 | |
| Average epoch loss: 2.9447 | |
| Step 271500 | |
| Running loss: 2.9736 | |
| Batch loss: 3.3321 | |
| Average epoch loss: 2.9448 | |
| Step 272000 | |
| Running loss: 2.9412 | |
| Batch loss: 2.8882 | |
| Average epoch loss: 2.9447 | |
| Step 272500 | |
| Running loss: 2.9257 | |
| Batch loss: 2.9686 | |
| Average epoch loss: 2.9447 | |
| Step 273000 | |
| Running loss: 2.9423 | |
| Batch loss: 2.9261 | |
| Average epoch loss: 2.9445 | |
| Step 273500 | |
| Running loss: 2.9542 | |
| Batch loss: 3.2267 | |
| Average epoch loss: 2.9443 | |
| Step 274000 | |
| Running loss: 2.9556 | |
| Batch loss: 3.4395 | |
| Average epoch loss: 2.9445 | |
| Step 274500 | |
| Running loss: 2.9603 | |
| Batch loss: 2.8545 | |
| Average epoch loss: 2.9446 | |
| Step 275000 | |
| Running loss: 2.9399 | |
| Batch loss: 3.2087 | |
| Average epoch loss: 2.9444 | |
| Step 275500 | |
| Running loss: 2.9629 | |
| Batch loss: 3.3634 | |
| Average epoch loss: 2.9446 | |
| Step 276000 | |
| Running loss: 2.9449 | |
| Batch loss: 2.4445 | |
| Average epoch loss: 2.9445 | |
| Step 276500 | |
| Running loss: 2.9767 | |
| Batch loss: 3.1572 | |
| Average epoch loss: 2.9447 | |
| Step 277000 | |
| Running loss: 2.9610 | |
| Batch loss: 3.3276 | |
| Average epoch loss: 2.9447 | |
| Step 277500 | |
| Running loss: 2.9558 | |
| Batch loss: 3.2253 | |
| Average epoch loss: 2.9450 | |
| Step 278000 | |
| Running loss: 2.9316 | |
| Batch loss: 2.5213 | |
| Average epoch loss: 2.9450 | |
| Step 278500 | |
| Running loss: 2.9557 | |
| Batch loss: 2.9831 | |
| Average epoch loss: 2.9449 | |
| Step 279000 | |
| Running loss: 2.9481 | |
| Batch loss: 3.1287 | |
| Average epoch loss: 2.9449 | |
| Step 279500 | |
| Running loss: 2.9387 | |
| Batch loss: 3.0147 | |
| Average epoch loss: 2.9448 | |
| Step 280000 | |
| Running loss: 2.9299 | |
| Batch loss: 2.8073 | |
| Average epoch loss: 2.9446 | |
| Step 280500 | |
| Running loss: 2.9339 | |
| Batch loss: 2.4858 | |
| Average epoch loss: 2.9444 | |
| Step 281000 | |
| Running loss: 2.9336 | |
| Batch loss: 2.8032 | |
| Average epoch loss: 2.9445 | |
| Step 281500 | |
| Running loss: 2.9465 | |
| Batch loss: 3.1049 | |
| Average epoch loss: 2.9444 | |
| Step 282000 | |
| Running loss: 2.9135 | |
| Batch loss: 2.4693 | |
| Average epoch loss: 2.9445 | |
| Step 282500 | |
| Running loss: 2.9900 | |
| Batch loss: 2.8277 | |
| Average epoch loss: 2.9447 | |
| Step 283000 | |
| Running loss: 2.9618 | |
| Batch loss: 2.8386 | |
| Average epoch loss: 2.9449 | |
| Step 283500 | |
| Running loss: 2.9764 | |
| Batch loss: 3.0851 | |
| Average epoch loss: 2.9449 | |
| Step 284000 | |
| Running loss: 2.9650 | |
| Batch loss: 3.2765 | |
| Average epoch loss: 2.9450 | |
| Step 284500 | |
| Running loss: 2.9615 | |
| Batch loss: 2.6453 | |
| Average epoch loss: 2.9450 | |
| Step 285000 | |
| Running loss: 2.9275 | |
| Batch loss: 2.9978 | |
| Average epoch loss: 2.9449 | |
| Step 285500 | |
| Running loss: 2.9214 | |
| Batch loss: 2.8655 | |
| Average epoch loss: 2.9447 | |
| Step 286000 | |
| Running loss: 2.9145 | |
| Batch loss: 3.1816 | |
| Average epoch loss: 2.9446 | |
| Step 286500 | |
| Running loss: 2.9407 | |
| Batch loss: 2.6962 | |
| Average epoch loss: 2.9442 | |
| Step 287000 | |
| Running loss: 2.9402 | |
| Batch loss: 2.9046 | |
| Average epoch loss: 2.9443 | |
| Step 287500 | |
| Running loss: 2.9871 | |
| Batch loss: 3.0893 | |
| Average epoch loss: 2.9445 | |
| Step 288000 | |
| Running loss: 2.9612 | |
| Batch loss: 3.0537 | |
| Average epoch loss: 2.9446 | |
| Step 288500 | |
| Running loss: 2.9318 | |
| Batch loss: 3.2127 | |
| Average epoch loss: 2.9444 | |
| Step 289000 | |
| Running loss: 2.9538 | |
| Batch loss: 2.7891 | |
| Average epoch loss: 2.9443 | |
| Step 289500 | |
| Running loss: 2.9548 | |
| Batch loss: 3.0964 | |
| Average epoch loss: 2.9444 | |
| Step 290000 | |
| Running loss: 2.9277 | |
| Batch loss: 2.9422 | |
| Average epoch loss: 2.9444 | |
| Step 290500 | |
| Running loss: 2.9086 | |
| Batch loss: 2.7414 | |
| Average epoch loss: 2.9442 | |
| Step 291000 | |
| Running loss: 2.9221 | |
| Batch loss: 2.9345 | |
| Average epoch loss: 2.9441 | |
| Step 291500 | |
| Running loss: 2.9571 | |
| Batch loss: 2.8868 | |
| Average epoch loss: 2.9440 | |
| Step 292000 | |
| Running loss: 2.9381 | |
| Batch loss: 2.9505 | |
| Average epoch loss: 2.9439 | |
| Step 292500 | |
| Running loss: 2.9306 | |
| Batch loss: 2.7995 | |
| Average epoch loss: 2.9439 | |
| Step 293000 | |
| Running loss: 2.9866 | |
| Batch loss: 2.8510 | |
| Average epoch loss: 2.9441 | |
| Step 293500 | |
| Running loss: 2.9440 | |
| Batch loss: 3.0075 | |
| Average epoch loss: 2.9443 | |
| Step 294000 | |
| Running loss: 2.9641 | |
| Batch loss: 2.6872 | |
| Average epoch loss: 2.9442 | |
| Step 294500 | |
| Running loss: 2.9523 | |
| Batch loss: 3.0797 | |
| Average epoch loss: 2.9442 | |
| Step 295000 | |
| Running loss: 2.9398 | |
| Batch loss: 2.6084 | |
| Average epoch loss: 2.9441 | |
| Step 295500 | |
| Running loss: 2.9193 | |
| Batch loss: 3.0628 | |
| Average epoch loss: 2.9441 | |
| Step 296000 | |
| Running loss: 2.9487 | |
| Batch loss: 2.9079 | |
| Average epoch loss: 2.9442 | |
| Step 296500 | |
| Running loss: 2.9567 | |
| Batch loss: 2.8253 | |
| Average epoch loss: 2.9442 | |
| Step 297000 | |
| Running loss: 2.9385 | |
| Batch loss: 3.0822 | |
| Average epoch loss: 2.9440 | |
| Step 297500 | |
| Running loss: 2.9247 | |
| Batch loss: 2.9080 | |
| Average epoch loss: 2.9440 | |
| Step 298000 | |
| Running loss: 2.9414 | |
| Batch loss: 2.8154 | |
| Average epoch loss: 2.9440 | |
| Step 298500 | |
| Running loss: 2.9583 | |
| Batch loss: 2.8172 | |
| Average epoch loss: 2.9441 | |
| Step 299000 | |
| Running loss: 2.9466 | |
| Batch loss: 2.9264 | |
| Average epoch loss: 2.9441 | |
| Step 299500 | |
| Running loss: 2.9469 | |
| Batch loss: 3.1462 | |
| Average epoch loss: 2.9442 | |
| Step 300000 | |
| Running loss: 2.9455 | |
| Batch loss: 3.0126 | |
| Average epoch loss: 2.9441 | |
| Epoch 6 completed. | |
| Average epoch loss: 2.9441 | |
| Step 300500 | |
| Running loss: 2.9328 | |
| Batch loss: 2.7379 | |
| Average epoch loss: 2.9263 | |
| Step 301000 | |
| Running loss: 2.9318 | |
| Batch loss: 3.2142 | |
| Average epoch loss: 2.9395 | |
| Step 301500 | |
| Running loss: 2.9937 | |
| Batch loss: 3.0748 | |
| Average epoch loss: 2.9459 | |
| Step 302000 | |
| Running loss: 2.9332 | |
| Batch loss: 3.0018 | |
| Average epoch loss: 2.9427 | |
| Step 302500 | |
| Running loss: 2.9080 | |
| Batch loss: 2.8130 | |
| Average epoch loss: 2.9381 | |
| Step 303000 | |
| Running loss: 2.9326 | |
| Batch loss: 2.7767 | |
| Average epoch loss: 2.9383 | |
| Step 303500 | |
| Running loss: 2.9706 | |
| Batch loss: 2.9422 | |
| Average epoch loss: 2.9400 | |
| Step 304000 | |
| Running loss: 2.9591 | |
| Batch loss: 3.2889 | |
| Average epoch loss: 2.9422 | |
| Step 304500 | |
| Running loss: 2.9500 | |
| Batch loss: 2.4061 | |
| Average epoch loss: 2.9422 | |
| Step 305000 | |
| Running loss: 2.9571 | |
| Batch loss: 2.8458 | |
| Average epoch loss: 2.9433 | |
| Step 305500 | |
| Running loss: 2.9620 | |
| Batch loss: 2.9599 | |
| Average epoch loss: 2.9443 | |
| Step 306000 | |
| Running loss: 2.9552 | |
| Batch loss: 2.9668 | |
| Average epoch loss: 2.9455 | |
| Step 306500 | |
| Running loss: 2.9299 | |
| Batch loss: 2.9835 | |
| Average epoch loss: 2.9455 | |
| Step 307000 | |
| Running loss: 2.9470 | |
| Batch loss: 2.9563 | |
| Average epoch loss: 2.9454 | |
| Step 307500 | |
| Running loss: 2.9276 | |
| Batch loss: 3.1697 | |
| Average epoch loss: 2.9442 | |
| Step 308000 | |
| Running loss: 2.9398 | |
| Batch loss: 3.0600 | |
| Average epoch loss: 2.9434 | |
| Step 308500 | |
| Running loss: 2.9479 | |
| Batch loss: 3.0605 | |
| Average epoch loss: 2.9434 | |
| Step 309000 | |
| Running loss: 2.9456 | |
| Batch loss: 2.9181 | |
| Average epoch loss: 2.9434 | |
| Step 309500 | |
| Running loss: 2.9351 | |
| Batch loss: 3.2009 | |
| Average epoch loss: 2.9436 | |
| Step 310000 | |
| Running loss: 2.9510 | |
| Batch loss: 3.0780 | |
| Average epoch loss: 2.9432 | |
| Step 310500 | |
| Running loss: 2.9169 | |
| Batch loss: 2.7416 | |
| Average epoch loss: 2.9431 | |
| Step 311000 | |
| Running loss: 2.9309 | |
| Batch loss: 2.7509 | |
| Average epoch loss: 2.9429 | |
| Step 311500 | |
| Running loss: 2.9232 | |
| Batch loss: 3.1166 | |
| Average epoch loss: 2.9430 | |
| Step 312000 | |
| Running loss: 2.9316 | |
| Batch loss: 2.8942 | |
| Average epoch loss: 2.9435 | |
| Step 312500 | |
| Running loss: 2.9723 | |
| Batch loss: 2.8425 | |
| Average epoch loss: 2.9441 | |
| Step 313000 | |
| Running loss: 2.9332 | |
| Batch loss: 2.7482 | |
| Average epoch loss: 2.9443 | |
| Step 313500 | |
| Running loss: 2.9524 | |
| Batch loss: 2.8794 | |
| Average epoch loss: 2.9441 | |
| Step 314000 | |
| Running loss: 2.9195 | |
| Batch loss: 2.8446 | |
| Average epoch loss: 2.9433 | |
| Step 314500 | |
| Running loss: 2.9391 | |
| Batch loss: 2.7146 | |
| Average epoch loss: 2.9429 | |
| Step 315000 | |
| Running loss: 2.9605 | |
| Batch loss: 3.2327 | |
| Average epoch loss: 2.9431 | |
| Step 315500 | |
| Running loss: 2.9248 | |
| Batch loss: 2.9638 | |
| Average epoch loss: 2.9428 | |
| Step 316000 | |
| Running loss: 2.9651 | |
| Batch loss: 3.0039 | |
| Average epoch loss: 2.9430 | |
| Step 316500 | |
| Running loss: 2.9683 | |
| Batch loss: 2.8402 | |
| Average epoch loss: 2.9435 | |
| Step 317000 | |
| Running loss: 2.9575 | |
| Batch loss: 2.8157 | |
| Average epoch loss: 2.9437 | |
| Step 317500 | |
| Running loss: 2.9341 | |
| Batch loss: 3.1185 | |
| Average epoch loss: 2.9438 | |
| Step 318000 | |
| Running loss: 2.9507 | |
| Batch loss: 2.7870 | |
| Average epoch loss: 2.9436 | |
| Step 318500 | |
| Running loss: 2.9379 | |
| Batch loss: 3.0190 | |
| Average epoch loss: 2.9435 | |
| Step 319000 | |
| Running loss: 2.9445 | |
| Batch loss: 2.6011 | |
| Average epoch loss: 2.9435 | |
| Step 319500 | |
| Running loss: 2.9391 | |
| Batch loss: 2.7701 | |
| Average epoch loss: 2.9441 | |
| Step 320000 | |
| Running loss: 2.9552 | |
| Batch loss: 2.8577 | |
| Average epoch loss: 2.9444 | |
| Step 320500 | |
| Running loss: 2.9405 | |
| Batch loss: 2.7956 | |
| Average epoch loss: 2.9441 | |
| Step 321000 | |
| Running loss: 2.9515 | |
| Batch loss: 2.6040 | |
| Average epoch loss: 2.9442 | |
| Step 321500 | |
| Running loss: 2.9790 | |
| Batch loss: 3.0194 | |
| Average epoch loss: 2.9444 | |
| Step 322000 | |
| Running loss: 2.9315 | |
| Batch loss: 3.0557 | |
| Average epoch loss: 2.9445 | |
| Step 322500 | |
| Running loss: 2.9143 | |
| Batch loss: 2.9888 | |
| Average epoch loss: 2.9444 | |
| Step 323000 | |
| Running loss: 2.9205 | |
| Batch loss: 2.8676 | |
| Average epoch loss: 2.9445 | |
| Step 323500 | |
| Running loss: 2.9301 | |
| Batch loss: 3.0074 | |
| Average epoch loss: 2.9446 | |
| Step 324000 | |
| Running loss: 2.9513 | |
| Batch loss: 3.1289 | |
| Average epoch loss: 2.9444 | |
| Step 324500 | |
| Running loss: 2.9413 | |
| Batch loss: 2.9877 | |
| Average epoch loss: 2.9445 | |
| Step 325000 | |
| Running loss: 2.9429 | |
| Batch loss: 2.9344 | |
| Average epoch loss: 2.9449 | |
| Step 325500 | |
| Running loss: 2.9359 | |
| Batch loss: 2.5455 | |
| Average epoch loss: 2.9451 | |
| Step 326000 | |
| Running loss: 2.9189 | |
| Batch loss: 3.0073 | |
| Average epoch loss: 2.9450 | |
| Step 326500 | |
| Running loss: 2.9418 | |
| Batch loss: 3.1083 | |
| Average epoch loss: 2.9449 | |
| Step 327000 | |
| Running loss: 2.9784 | |
| Batch loss: 3.3186 | |
| Average epoch loss: 2.9451 | |
| Step 327500 | |
| Running loss: 2.9211 | |
| Batch loss: 2.8693 | |
| Average epoch loss: 2.9450 | |
| Step 328000 | |
| Running loss: 2.9608 | |
| Batch loss: 2.7695 | |
| Average epoch loss: 2.9450 | |
| Step 328500 | |
| Running loss: 2.9339 | |
| Batch loss: 2.9863 | |
| Average epoch loss: 2.9450 | |
| Step 329000 | |
| Running loss: 2.9393 | |
| Batch loss: 2.5218 | |
| Average epoch loss: 2.9451 | |
| Step 329500 | |
| Running loss: 2.9500 | |
| Batch loss: 2.9094 | |
| Average epoch loss: 2.9454 | |
| Step 330000 | |
| Running loss: 2.9195 | |
| Batch loss: 2.7419 | |
| Average epoch loss: 2.9453 | |
| Step 330500 | |
| Running loss: 2.9843 | |
| Batch loss: 2.8572 | |
| Average epoch loss: 2.9454 | |
| Step 331000 | |
| Running loss: 2.9344 | |
| Batch loss: 3.1539 | |
| Average epoch loss: 2.9456 | |
| Step 331500 | |
| Running loss: 2.9245 | |
| Batch loss: 2.6960 | |
| Average epoch loss: 2.9456 | |
| Step 332000 | |
| Running loss: 2.9361 | |
| Batch loss: 2.7934 | |
| Average epoch loss: 2.9456 | |
| Step 332500 | |
| Running loss: 2.9522 | |
| Batch loss: 3.0147 | |
| Average epoch loss: 2.9458 | |
| Step 333000 | |
| Running loss: 2.9385 | |
| Batch loss: 2.7401 | |
| Average epoch loss: 2.9456 | |
| Step 333500 | |
| Running loss: 2.9378 | |
| Batch loss: 2.5856 | |
| Average epoch loss: 2.9457 | |
| Step 334000 | |
| Running loss: 2.9539 | |
| Batch loss: 2.8438 | |
| Average epoch loss: 2.9457 | |
| Step 334500 | |
| Running loss: 2.9283 | |
| Batch loss: 2.8956 | |
| Average epoch loss: 2.9457 | |
| Step 335000 | |
| Running loss: 2.9614 | |
| Batch loss: 3.1633 | |
| Average epoch loss: 2.9455 | |
| Step 335500 | |
| Running loss: 2.9382 | |
| Batch loss: 2.8455 | |
| Average epoch loss: 2.9454 | |
| Step 336000 | |
| Running loss: 2.9602 | |
| Batch loss: 2.9623 | |
| Average epoch loss: 2.9453 | |
| Step 336500 | |
| Running loss: 2.9237 | |
| Batch loss: 3.0215 | |
| Average epoch loss: 2.9454 | |
| Step 337000 | |
| Running loss: 2.9438 | |
| Batch loss: 2.7086 | |
| Average epoch loss: 2.9454 | |
| Step 337500 | |
| Running loss: 2.9230 | |
| Batch loss: 3.1938 | |
| Average epoch loss: 2.9453 | |
| Step 338000 | |
| Running loss: 2.9472 | |
| Batch loss: 2.9973 | |
| Average epoch loss: 2.9454 | |
| Step 338500 | |
| Running loss: 2.9639 | |
| Batch loss: 2.5161 | |
| Average epoch loss: 2.9453 | |
| Step 339000 | |
| Running loss: 2.9565 | |
| Batch loss: 3.1882 | |
| Average epoch loss: 2.9451 | |
| Step 339500 | |
| Running loss: 2.9714 | |
| Batch loss: 3.1228 | |
| Average epoch loss: 2.9452 | |
| Step 340000 | |
| Running loss: 2.9543 | |
| Batch loss: 3.2117 | |
| Average epoch loss: 2.9451 | |
| Step 340500 | |
| Running loss: 2.9437 | |
| Batch loss: 2.8860 | |
| Average epoch loss: 2.9451 | |
| Step 341000 | |
| Running loss: 2.9557 | |
| Batch loss: 2.8797 | |
| Average epoch loss: 2.9450 | |
| Step 341500 | |
| Running loss: 2.9312 | |
| Batch loss: 3.0584 | |
| Average epoch loss: 2.9449 | |
| Step 342000 | |
| Running loss: 2.9317 | |
| Batch loss: 2.6924 | |
| Average epoch loss: 2.9448 | |
| Step 342500 | |
| Running loss: 2.9517 | |
| Batch loss: 3.1028 | |
| Average epoch loss: 2.9446 | |
| Step 343000 | |
| Running loss: 2.9595 | |
| Batch loss: 3.2777 | |
| Average epoch loss: 2.9445 | |
| Step 343500 | |
| Running loss: 2.9220 | |
| Batch loss: 3.2698 | |
| Average epoch loss: 2.9445 | |
| Step 344000 | |
| Running loss: 2.9130 | |
| Batch loss: 2.7796 | |
| Average epoch loss: 2.9443 | |
| Step 344500 | |
| Running loss: 2.9148 | |
| Batch loss: 2.7949 | |
| Average epoch loss: 2.9443 | |
| Step 345000 | |
| Running loss: 2.9205 | |
| Batch loss: 2.8368 | |
| Average epoch loss: 2.9444 | |
| Step 345500 | |
| Running loss: 2.9707 | |
| Batch loss: 2.9889 | |
| Average epoch loss: 2.9446 | |
| Step 346000 | |
| Running loss: 2.9340 | |
| Batch loss: 2.6803 | |
| Average epoch loss: 2.9445 | |
| Step 346500 | |
| Running loss: 2.9491 | |
| Batch loss: 2.9157 | |
| Average epoch loss: 2.9446 | |
| Step 347000 | |
| Running loss: 2.9572 | |
| Batch loss: 3.0248 | |
| Average epoch loss: 2.9446 | |
| Step 347500 | |
| Running loss: 2.9309 | |
| Batch loss: 2.9177 | |
| Average epoch loss: 2.9446 | |
| Step 348000 | |
| Running loss: 2.9591 | |
| Batch loss: 2.8777 | |
| Average epoch loss: 2.9445 | |
| Step 348500 | |
| Running loss: 2.9670 | |
| Batch loss: 2.8642 | |
| Average epoch loss: 2.9445 | |
| Step 349000 | |
| Running loss: 2.9284 | |
| Batch loss: 3.4837 | |
| Average epoch loss: 2.9445 | |
| Step 349500 | |
| Running loss: 2.9378 | |
| Batch loss: 3.0959 | |
| Average epoch loss: 2.9445 | |
| Step 350000 | |
| Running loss: 2.9699 | |
| Batch loss: 2.7136 | |
| Average epoch loss: 2.9444 | |
| Epoch 7 completed. | |
| Average epoch loss: 2.9444 | |
| Step 350500 | |
| Running loss: 2.9318 | |
| Batch loss: 3.1311 | |
| Average epoch loss: 2.9281 | |
| Step 351000 | |
| Running loss: 2.9800 | |
| Batch loss: 3.0993 | |
| Average epoch loss: 2.9545 | |
| write: error: buf 0x7f3dd93ba220, size 394, shift 0 | |
| write: error: buf 0x7f2349dc9060, size 394, shift 0 | |
| write: error: buf 0x7f8b7537ef20, size 394, shift 0 | |