Updated model: 514 splits, 18.36 epochs, min_loss: 1.0164, min_ppl: 2.7632

best-lm.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bcc3948c2a2b6b4c21cd4bc72ce1592dd82a62f06d3623aaa1bb592d19419e3
+oid sha256:43a896302f954ed5900cb4ac3eefd96189d368a32a3eda428cbce25990d4b54d
 size 22791455

loss.txt

@@ -496,3 +496,19 @@
 | end of split  76 / 28 | epoch  16 | time: 3246.27s | valid loss 1.0175 | valid ppl 2.7663 | learning rate 5.0000
 | end of split  77 / 28 | epoch  16 | time: 3262.21s | valid loss 1.0167 | valid ppl 2.7641 | learning rate 1.2500
 | end of split  78 / 28 | epoch  16 | time: 3268.11s | valid loss 1.0166 | valid ppl 2.7639 | learning rate 1.2500
+| end of split  79 / 28 | epoch  16 | time: 3269.38s | valid loss 1.0167 | valid ppl 2.7639 | learning rate 1.2500
+| end of split  80 / 28 | epoch  16 | time: 3269.47s | valid loss 1.0166 | valid ppl 2.7638 | learning rate 1.2500
+| end of split  81 / 28 | epoch  16 | time: 3258.11s | valid loss 1.0166 | valid ppl 2.7637 | learning rate 1.2500
+| end of split  82 / 28 | epoch  16 | time: 3255.05s | valid loss 1.0165 | valid ppl 2.7636 | learning rate 1.2500
+| end of split  83 / 28 | epoch  16 | time: 3267.27s | valid loss 1.0165 | valid ppl 2.7635 | learning rate 1.2500
+| end of split  84 / 28 | epoch  16 | time: 3267.39s | valid loss 1.0165 | valid ppl 2.7634 | learning rate 1.2500
+| end of split  85 / 28 | epoch  16 | time: 3268.88s | valid loss 1.0165 | valid ppl 2.7635 | learning rate 1.2500
+| end of split  86 / 28 | epoch  16 | time: 3271.95s | valid loss 1.0165 | valid ppl 2.7634 | learning rate 1.2500
+| end of split  87 / 28 | epoch  16 | time: 3211.88s | valid loss 1.0165 | valid ppl 2.7635 | learning rate 1.2500
+| end of split  60 / 28 | epoch  17 | time: 3260.00s | valid loss 1.0164 | valid ppl 2.7632 | learning rate 1.2500
+| end of split  61 / 28 | epoch  17 | time: 3331.83s | valid loss 1.0164 | valid ppl 2.7632 | learning rate 1.2500
+| end of split  62 / 28 | epoch  17 | time: 3266.91s | valid loss 1.0164 | valid ppl 2.7632 | learning rate 1.2500
+| end of split  63 / 28 | epoch  17 | time: 3267.75s | valid loss 1.0164 | valid ppl 2.7633 | learning rate 1.2500
+| end of split  64 / 28 | epoch  17 | time: 3265.47s | valid loss 1.0164 | valid ppl 2.7633 | learning rate 1.2500
+| end of split  65 / 28 | epoch  17 | time: 3253.35s | valid loss 1.0164 | valid ppl 2.7632 | learning rate 1.2500
+| end of split  66 / 28 | epoch  17 | time: 3263.04s | valid loss 1.0164 | valid ppl 2.7633 | learning rate 1.2500