Dmitry Chaplinsky commited on
Commit
eacde4b
1 Parent(s): e682bc9

Updated model: 498 splits, 17.79 epochs, min_loss: 1.0166, min_ppl: 2.7639

Browse files
Files changed (2) hide show
  1. best-lm.pt +1 -1
  2. loss.txt +12 -0
best-lm.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5044e2070b4ef48113bfee82a2c068625c169da95219da5c24fb0170ad0e1d96
3
  size 22791455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcc3948c2a2b6b4c21cd4bc72ce1592dd82a62f06d3623aaa1bb592d19419e3
3
  size 22791455
loss.txt CHANGED
@@ -484,3 +484,15 @@
484
  | end of split 64 / 28 | epoch 16 | time: 3248.84s | valid loss 1.0176 | valid ppl 2.7665 | learning rate 5.0000
485
  | end of split 65 / 28 | epoch 16 | time: 3254.15s | valid loss 1.0174 | valid ppl 2.7661 | learning rate 5.0000
486
  | end of split 66 / 28 | epoch 16 | time: 3250.93s | valid loss 1.0175 | valid ppl 2.7663 | learning rate 5.0000
 
 
 
 
 
 
 
 
 
 
 
 
 
484
  | end of split 64 / 28 | epoch 16 | time: 3248.84s | valid loss 1.0176 | valid ppl 2.7665 | learning rate 5.0000
485
  | end of split 65 / 28 | epoch 16 | time: 3254.15s | valid loss 1.0174 | valid ppl 2.7661 | learning rate 5.0000
486
  | end of split 66 / 28 | epoch 16 | time: 3250.93s | valid loss 1.0175 | valid ppl 2.7663 | learning rate 5.0000
487
+ | end of split 67 / 28 | epoch 16 | time: 3248.51s | valid loss 1.0174 | valid ppl 2.7661 | learning rate 5.0000
488
+ | end of split 68 / 28 | epoch 16 | time: 3249.54s | valid loss 1.0175 | valid ppl 2.7662 | learning rate 5.0000
489
+ | end of split 69 / 28 | epoch 16 | time: 3250.81s | valid loss 1.0176 | valid ppl 2.7666 | learning rate 5.0000
490
+ | end of split 70 / 28 | epoch 16 | time: 3247.34s | valid loss 1.0175 | valid ppl 2.7662 | learning rate 5.0000
491
+ | end of split 71 / 28 | epoch 16 | time: 3241.61s | valid loss 1.0174 | valid ppl 2.7661 | learning rate 5.0000
492
+ | end of split 72 / 28 | epoch 16 | time: 3241.40s | valid loss 1.0175 | valid ppl 2.7662 | learning rate 5.0000
493
+ | end of split 73 / 28 | epoch 16 | time: 3241.41s | valid loss 1.0174 | valid ppl 2.7661 | learning rate 5.0000
494
+ | end of split 74 / 28 | epoch 16 | time: 3238.90s | valid loss 1.0174 | valid ppl 2.7660 | learning rate 5.0000
495
+ | end of split 75 / 28 | epoch 16 | time: 950.51s | valid loss 1.0173 | valid ppl 2.7658 | learning rate 5.0000
496
+ | end of split 76 / 28 | epoch 16 | time: 3246.27s | valid loss 1.0175 | valid ppl 2.7663 | learning rate 5.0000
497
+ | end of split 77 / 28 | epoch 16 | time: 3262.21s | valid loss 1.0167 | valid ppl 2.7641 | learning rate 1.2500
498
+ | end of split 78 / 28 | epoch 16 | time: 3268.11s | valid loss 1.0166 | valid ppl 2.7639 | learning rate 1.2500