Dmitry Chaplinsky
commited on
Commit
•
7a49802
1
Parent(s):
0f0c52b
Updated model: 453 splits, 16.18 epochs, min_loss: 1.018, min_ppl: 2.7676
Browse files- best-lm.pt +1 -1
- loss.txt +19 -0
best-lm.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22791455
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:034a5447d3ab2a0affecb9803e0440039363553b07fcdc472064ca73f8ce405c
|
3 |
size 22791455
|
loss.txt
CHANGED
@@ -432,3 +432,22 @@
|
|
432 |
| end of split 68 / 28 | epoch 14 | time: 997.06s | valid loss 1.0187 | valid ppl 2.7695 | learning rate 5.0000
|
433 |
| end of split 69 / 28 | epoch 14 | time: 3144.91s | valid loss 1.0185 | valid ppl 2.7692 | learning rate 5.0000
|
434 |
| end of split 70 / 28 | epoch 14 | time: 3324.27s | valid loss 1.0184 | valid ppl 2.7687 | learning rate 5.0000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
432 |
| end of split 68 / 28 | epoch 14 | time: 997.06s | valid loss 1.0187 | valid ppl 2.7695 | learning rate 5.0000
|
433 |
| end of split 69 / 28 | epoch 14 | time: 3144.91s | valid loss 1.0185 | valid ppl 2.7692 | learning rate 5.0000
|
434 |
| end of split 70 / 28 | epoch 14 | time: 3324.27s | valid loss 1.0184 | valid ppl 2.7687 | learning rate 5.0000
|
435 |
+
| end of split 71 / 28 | epoch 14 | time: 3377.70s | valid loss 1.0183 | valid ppl 2.7686 | learning rate 5.0000
|
436 |
+
| end of split 72 / 28 | epoch 14 | time: 3379.24s | valid loss 1.0184 | valid ppl 2.7689 | learning rate 5.0000
|
437 |
+
| end of split 73 / 28 | epoch 14 | time: 3373.14s | valid loss 1.0184 | valid ppl 2.7687 | learning rate 5.0000
|
438 |
+
| end of split 74 / 28 | epoch 14 | time: 3342.04s | valid loss 1.0183 | valid ppl 2.7685 | learning rate 5.0000
|
439 |
+
| end of split 75 / 28 | epoch 14 | time: 3338.23s | valid loss 1.0182 | valid ppl 2.7683 | learning rate 5.0000
|
440 |
+
| end of split 76 / 28 | epoch 14 | time: 3336.11s | valid loss 1.0183 | valid ppl 2.7685 | learning rate 5.0000
|
441 |
+
| end of split 77 / 28 | epoch 14 | time: 3338.18s | valid loss 1.0183 | valid ppl 2.7685 | learning rate 5.0000
|
442 |
+
| end of split 78 / 28 | epoch 14 | time: 3336.34s | valid loss 1.0182 | valid ppl 2.7682 | learning rate 5.0000
|
443 |
+
| end of split 79 / 28 | epoch 14 | time: 3294.94s | valid loss 1.0182 | valid ppl 2.7682 | learning rate 5.0000
|
444 |
+
| end of split 80 / 28 | epoch 14 | time: 3131.17s | valid loss 1.0182 | valid ppl 2.7682 | learning rate 5.0000
|
445 |
+
| end of split 81 / 28 | epoch 14 | time: 3078.59s | valid loss 1.0182 | valid ppl 2.7683 | learning rate 5.0000
|
446 |
+
| end of split 82 / 28 | epoch 14 | time: 3077.37s | valid loss 1.0183 | valid ppl 2.7683 | learning rate 5.0000
|
447 |
+
| end of split 83 / 28 | epoch 14 | time: 3079.84s | valid loss 1.0182 | valid ppl 2.7681 | learning rate 5.0000
|
448 |
+
| end of split 84 / 28 | epoch 14 | time: 3077.24s | valid loss 1.0181 | valid ppl 2.7679 | learning rate 5.0000
|
449 |
+
| end of split 85 / 28 | epoch 14 | time: 3074.62s | valid loss 1.0181 | valid ppl 2.7680 | learning rate 5.0000
|
450 |
+
| end of split 86 / 28 | epoch 14 | time: 3074.32s | valid loss 1.0182 | valid ppl 2.7681 | learning rate 5.0000
|
451 |
+
| end of split 87 / 28 | epoch 14 | time: 3076.92s | valid loss 1.0181 | valid ppl 2.7679 | learning rate 5.0000
|
452 |
+
| end of split 60 / 28 | epoch 15 | time: 3077.51s | valid loss 1.0180 | valid ppl 2.7676 | learning rate 5.0000
|
453 |
+
| end of split 61 / 28 | epoch 15 | time: 3082.58s | valid loss 1.0180 | valid ppl 2.7678 | learning rate 5.0000
|