Anixyz commited on
Commit
a9f9e02
·
verified ·
1 Parent(s): f4fafe8

End of training

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5321
23
- - Accuracy: 0.904
24
- - F1: 0.9004
25
 
26
  ## Model description
27
 
@@ -52,29 +52,29 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
55
- | 2.16 | 0.2096 | 100 | 0.9787 | 0.7682 | 0.7606 |
56
- | 0.3656 | 0.4193 | 200 | 0.8287 | 0.8233 | 0.8141 |
57
- | 0.2759 | 0.6289 | 300 | 0.6711 | 0.8473 | 0.8384 |
58
- | 0.2595 | 0.8386 | 400 | 0.5182 | 0.8822 | 0.8789 |
59
- | 0.1272 | 1.0482 | 500 | 0.6159 | 0.8729 | 0.8679 |
60
- | 0.0906 | 1.2579 | 600 | 0.5846 | 0.8782 | 0.8736 |
61
- | 0.0639 | 1.4675 | 700 | 0.5459 | 0.8916 | 0.8880 |
62
- | 0.0564 | 1.6771 | 800 | 0.5548 | 0.8964 | 0.8938 |
63
- | 0.0688 | 1.8868 | 900 | 0.6296 | 0.882 | 0.8770 |
64
- | 0.0524 | 2.0964 | 1000 | 0.6527 | 0.88 | 0.8733 |
65
- | 0.027 | 2.3061 | 1100 | 0.5214 | 0.9007 | 0.8984 |
66
- | 0.029 | 2.5157 | 1200 | 0.5566 | 0.8931 | 0.8886 |
67
- | 0.0284 | 2.7254 | 1300 | 0.5492 | 0.8982 | 0.8940 |
68
- | 0.0218 | 2.9350 | 1400 | 0.4904 | 0.9084 | 0.9059 |
69
- | 0.0155 | 3.1447 | 1500 | 0.4808 | 0.9082 | 0.9057 |
70
- | 0.0073 | 3.3543 | 1600 | 0.5326 | 0.9027 | 0.8990 |
71
- | 0.0065 | 3.5639 | 1700 | 0.5034 | 0.9051 | 0.9018 |
72
- | 0.0105 | 3.7736 | 1800 | 0.5072 | 0.9058 | 0.9027 |
73
- | 0.0057 | 3.9832 | 1900 | 0.5440 | 0.9024 | 0.8983 |
74
- | 0.0007 | 4.1929 | 2000 | 0.5462 | 0.9024 | 0.8983 |
75
- | 0.0022 | 4.4025 | 2100 | 0.5408 | 0.9035 | 0.8995 |
76
- | 0.003 | 4.6122 | 2200 | 0.5383 | 0.9035 | 0.8997 |
77
- | 0.0032 | 4.8218 | 2300 | 0.5321 | 0.904 | 0.9004 |
78
 
79
 
80
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-large](https://huggingface.co/answerdotai/ModernBERT-large) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.4343
23
+ - Accuracy: 0.9149
24
+ - F1: 0.9122
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
55
+ | 2.2837 | 0.2096 | 100 | 0.9484 | 0.7671 | 0.7603 |
56
+ | 0.3814 | 0.4193 | 200 | 0.6216 | 0.8545 | 0.8498 |
57
+ | 0.2401 | 0.6289 | 300 | 0.6264 | 0.8569 | 0.8495 |
58
+ | 0.2168 | 0.8386 | 400 | 0.5532 | 0.872 | 0.8706 |
59
+ | 0.1421 | 1.0482 | 500 | 0.5101 | 0.8875 | 0.8844 |
60
+ | 0.0653 | 1.2579 | 600 | 0.5893 | 0.8824 | 0.8769 |
61
+ | 0.0567 | 1.4675 | 700 | 0.5224 | 0.8935 | 0.8914 |
62
+ | 0.0593 | 1.6771 | 800 | 0.5689 | 0.8849 | 0.8808 |
63
+ | 0.0598 | 1.8868 | 900 | 0.5895 | 0.886 | 0.8827 |
64
+ | 0.0518 | 2.0964 | 1000 | 0.6355 | 0.8767 | 0.8682 |
65
+ | 0.025 | 2.3061 | 1100 | 0.5616 | 0.8915 | 0.8861 |
66
+ | 0.0182 | 2.5157 | 1200 | 0.4563 | 0.9073 | 0.9040 |
67
+ | 0.0241 | 2.7254 | 1300 | 0.4912 | 0.9042 | 0.9011 |
68
+ | 0.0174 | 2.9350 | 1400 | 0.4381 | 0.9135 | 0.9112 |
69
+ | 0.0164 | 3.1447 | 1500 | 0.4792 | 0.9076 | 0.9042 |
70
+ | 0.0091 | 3.3543 | 1600 | 0.5133 | 0.9011 | 0.8969 |
71
+ | 0.0111 | 3.5639 | 1700 | 0.5006 | 0.9044 | 0.8997 |
72
+ | 0.0096 | 3.7736 | 1800 | 0.4089 | 0.9189 | 0.9170 |
73
+ | 0.004 | 3.9832 | 1900 | 0.4024 | 0.9195 | 0.9174 |
74
+ | 0.002 | 4.1929 | 2000 | 0.4174 | 0.9173 | 0.9150 |
75
+ | 0.0023 | 4.4025 | 2100 | 0.4248 | 0.9169 | 0.9145 |
76
+ | 0.0006 | 4.6122 | 2200 | 0.4360 | 0.9149 | 0.9122 |
77
+ | 0.0028 | 4.8218 | 2300 | 0.4343 | 0.9149 | 0.9122 |
78
 
79
 
80
  ### Framework versions