data: add fine-tuning run results (lr=1e-5, 50 epochs)
val loss 1.24 → 0.80, val perplexity 3.47 → 2.22. Best epoch 50 (no early stop); convergence epoch 30. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,51 @@
|
|||||||
|
epoch,train_loss,val_loss,val_ppl,lr,elapsed_s
|
||||||
|
1,1.185128,1.244704,3.47,8.000000e-06,9.9
|
||||||
|
2,1.129786,1.168368,3.22,9.994161e-06,9.2
|
||||||
|
3,1.074786,1.102074,3.01,9.968238e-06,8.8
|
||||||
|
4,1.004364,1.045185,2.84,9.921690e-06,8.5
|
||||||
|
5,0.963113,0.995150,2.71,9.854709e-06,9.2
|
||||||
|
6,0.903885,0.953348,2.59,9.767574e-06,9.1
|
||||||
|
7,0.867560,0.927149,2.53,9.660647e-06,8.1
|
||||||
|
8,0.848291,0.911215,2.49,9.534372e-06,9.1
|
||||||
|
9,0.817798,0.897135,2.45,9.389272e-06,9.2
|
||||||
|
10,0.815333,0.885900,2.43,9.225950e-06,8.2
|
||||||
|
11,0.804101,0.876820,2.40,9.045085e-06,9.7
|
||||||
|
12,0.791397,0.868702,2.38,8.847427e-06,9.2
|
||||||
|
13,0.778087,0.860407,2.36,8.633796e-06,8.5
|
||||||
|
14,0.771410,0.853698,2.35,8.405079e-06,10.7
|
||||||
|
15,0.768661,0.848427,2.34,8.162227e-06,10.7
|
||||||
|
16,0.762623,0.842908,2.32,7.906247e-06,9.4
|
||||||
|
17,0.749388,0.837927,2.31,7.638201e-06,8.2
|
||||||
|
18,0.745191,0.833950,2.30,7.359203e-06,9.1
|
||||||
|
19,0.745993,0.830711,2.29,7.070412e-06,9.2
|
||||||
|
20,0.726599,0.827279,2.29,6.773024e-06,9.0
|
||||||
|
21,0.722057,0.824505,2.28,6.468277e-06,8.4
|
||||||
|
22,0.723956,0.822224,2.28,6.157433e-06,9.2
|
||||||
|
23,0.721438,0.819970,2.27,5.841785e-06,9.2
|
||||||
|
24,0.717564,0.817087,2.26,5.522642e-06,8.1
|
||||||
|
25,0.711637,0.814592,2.26,5.201330e-06,9.2
|
||||||
|
26,0.712329,0.812606,2.25,4.879181e-06,9.2
|
||||||
|
27,0.705078,0.810716,2.25,4.557534e-06,8.1
|
||||||
|
28,0.697062,0.808805,2.25,4.237724e-06,9.2
|
||||||
|
29,0.700164,0.807415,2.24,3.921079e-06,10.2
|
||||||
|
30,0.695335,0.806321,2.24,3.608913e-06,8.7
|
||||||
|
31,0.687925,0.804961,2.24,3.302521e-06,8.9
|
||||||
|
32,0.691783,0.803864,2.23,3.003177e-06,9.3
|
||||||
|
33,0.690663,0.802969,2.23,2.712123e-06,9.3
|
||||||
|
34,0.692106,0.801836,2.23,2.430566e-06,8.1
|
||||||
|
35,0.691675,0.801080,2.23,2.159676e-06,9.2
|
||||||
|
36,0.678919,0.800619,2.23,1.900578e-06,9.2
|
||||||
|
37,0.682140,0.800421,2.23,1.654347e-06,8.2
|
||||||
|
38,0.689051,0.800192,2.23,1.422005e-06,9.2
|
||||||
|
39,0.686498,0.799934,2.23,1.204517e-06,9.3
|
||||||
|
40,0.690576,0.799613,2.22,1.002786e-06,8.2
|
||||||
|
41,0.684055,0.799269,2.22,8.176493e-07,9.5
|
||||||
|
42,0.685102,0.799062,2.22,6.498753e-07,9.3
|
||||||
|
43,0.689241,0.798999,2.22,5.001606e-07,8.6
|
||||||
|
44,0.689855,0.798879,2.22,3.691268e-07,8.7
|
||||||
|
45,0.679218,0.798795,2.22,2.573178e-07,9.1
|
||||||
|
46,0.680892,0.798748,2.22,1.651979e-07,9.1
|
||||||
|
47,0.688506,0.798713,2.22,9.314937e-08,8.3
|
||||||
|
48,0.684029,0.798699,2.22,4.147145e-08,9.2
|
||||||
|
49,0.685409,0.798693,2.22,1.037863e-08,9.2
|
||||||
|
50,0.684188,0.798692,2.22,0.000000e+00,8.1
|
||||||
|
@@ -0,0 +1,67 @@
|
|||||||
|
|
||||||
|
====================================================
|
||||||
|
FINE-TUNING REPORT
|
||||||
|
====================================================
|
||||||
|
Total epochs run : 50
|
||||||
|
Best epoch (val loss) : 50
|
||||||
|
Convergence epoch : 30 (val ≤ best+1 %)
|
||||||
|
Best val loss : 0.7987
|
||||||
|
Best val perplexity : 2.22
|
||||||
|
Final train loss : 0.6842
|
||||||
|
Unique parameters : 1,396,416
|
||||||
|
Checkpoint : checkpoints/finetuned.pt
|
||||||
|
Log CSV : checkpoints/finetuned.log.csv
|
||||||
|
====================================================
|
||||||
|
|
||||||
|
epoch train val ppl lr
|
||||||
|
----- -------- -------- ------- ----------
|
||||||
|
1 1.1851 1.2447 3.47 8.00e-06
|
||||||
|
2 1.1298 1.1684 3.22 9.99e-06
|
||||||
|
3 1.0748 1.1021 3.01 9.97e-06
|
||||||
|
4 1.0044 1.0452 2.84 9.92e-06
|
||||||
|
5 0.9631 0.9951 2.71 9.85e-06
|
||||||
|
6 0.9039 0.9533 2.59 9.77e-06
|
||||||
|
7 0.8676 0.9271 2.53 9.66e-06
|
||||||
|
8 0.8483 0.9112 2.49 9.53e-06
|
||||||
|
9 0.8178 0.8971 2.45 9.39e-06
|
||||||
|
10 0.8153 0.8859 2.43 9.23e-06
|
||||||
|
11 0.8041 0.8768 2.40 9.05e-06
|
||||||
|
12 0.7914 0.8687 2.38 8.85e-06
|
||||||
|
13 0.7781 0.8604 2.36 8.63e-06
|
||||||
|
14 0.7714 0.8537 2.35 8.41e-06
|
||||||
|
15 0.7687 0.8484 2.34 8.16e-06
|
||||||
|
16 0.7626 0.8429 2.32 7.91e-06
|
||||||
|
17 0.7494 0.8379 2.31 7.64e-06
|
||||||
|
18 0.7452 0.8339 2.30 7.36e-06
|
||||||
|
19 0.7460 0.8307 2.29 7.07e-06
|
||||||
|
20 0.7266 0.8273 2.29 6.77e-06
|
||||||
|
21 0.7221 0.8245 2.28 6.47e-06
|
||||||
|
22 0.7240 0.8222 2.28 6.16e-06
|
||||||
|
23 0.7214 0.8200 2.27 5.84e-06
|
||||||
|
24 0.7176 0.8171 2.26 5.52e-06
|
||||||
|
25 0.7116 0.8146 2.26 5.20e-06
|
||||||
|
26 0.7123 0.8126 2.25 4.88e-06
|
||||||
|
27 0.7051 0.8107 2.25 4.56e-06
|
||||||
|
28 0.6971 0.8088 2.25 4.24e-06
|
||||||
|
29 0.7002 0.8074 2.24 3.92e-06
|
||||||
|
30 0.6953 0.8063 2.24 3.61e-06
|
||||||
|
31 0.6879 0.8050 2.24 3.30e-06
|
||||||
|
32 0.6918 0.8039 2.23 3.00e-06
|
||||||
|
33 0.6907 0.8030 2.23 2.71e-06
|
||||||
|
34 0.6921 0.8018 2.23 2.43e-06
|
||||||
|
35 0.6917 0.8011 2.23 2.16e-06
|
||||||
|
36 0.6789 0.8006 2.23 1.90e-06
|
||||||
|
37 0.6821 0.8004 2.23 1.65e-06
|
||||||
|
38 0.6891 0.8002 2.23 1.42e-06
|
||||||
|
39 0.6865 0.7999 2.23 1.20e-06
|
||||||
|
40 0.6906 0.7996 2.22 1.00e-06
|
||||||
|
41 0.6841 0.7993 2.22 8.18e-07
|
||||||
|
42 0.6851 0.7991 2.22 6.50e-07
|
||||||
|
43 0.6892 0.7990 2.22 5.00e-07
|
||||||
|
44 0.6899 0.7989 2.22 3.69e-07
|
||||||
|
45 0.6792 0.7988 2.22 2.57e-07
|
||||||
|
46 0.6809 0.7987 2.22 1.65e-07
|
||||||
|
47 0.6885 0.7987 2.22 9.31e-08
|
||||||
|
48 0.6840 0.7987 2.22 4.15e-08
|
||||||
|
49 0.6854 0.7987 2.22 1.04e-08
|
||||||
|
50 0.6842 0.7987 2.22 0.00e+00 ←
|
||||||
Binary file not shown.
Reference in New Issue
Block a user