Hugging Face's logo

davanstrien
/
ModernBERT-based-Reasoning-Required

Text Classification
Transformers
TensorBoard
Safetensors
English
modernbert
reasoning
reasoning-datasets-competition
Model card Files
xet
Metrics Community
2
davanstrien HF Staff commited on
Commit
7704acd
·
verified ·
1 Parent(s): 9895a7d

End of training

Browse files
Files changed (2) hide show
  1. README.md +112 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: answerdotai/ModernBERT-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: modernbert-reasoning-required
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # modernbert-reasoning-required
16
+
17
+ This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2034
20
+ - Mse: 0.2034
21
+ - Mae: 0.2578
22
+ - Spearman: 0.6963
23
+ - High Mae: 0.1355
24
+ - High Mse: 0.0831
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 10
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Mse | Mae | Spearman | High Mae | High Mse |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:--------:|:--------:|:--------:|
55
+ | 0.619 | 0.2 | 50 | 0.2932 | 0.2932 | 0.3742 | 0.6209 | 0.2537 | 0.1183 |
56
+ | 0.3229 | 0.4 | 100 | 0.3045 | 0.3045 | 0.4308 | 0.6303 | 0.3396 | 0.1437 |
57
+ | 0.3032 | 0.6 | 150 | 0.2575 | 0.2575 | 0.3473 | 0.6785 | 0.2365 | 0.1040 |
58
+ | 0.2609 | 0.8 | 200 | 0.2513 | 0.2513 | 0.3433 | 0.6764 | 0.2603 | 0.1442 |
59
+ | 0.3414 | 1.0 | 250 | 0.2308 | 0.2308 | 0.3039 | 0.6732 | 0.1798 | 0.0894 |
60
+ | 0.2337 | 1.2 | 300 | 0.2491 | 0.2491 | 0.3620 | 0.6669 | 0.2780 | 0.1358 |
61
+ | 0.2665 | 1.4 | 350 | 0.2522 | 0.2522 | 0.3350 | 0.6803 | 0.2483 | 0.1660 |
62
+ | 0.1984 | 1.6 | 400 | 0.2660 | 0.2660 | 0.3380 | 0.6836 | 0.1872 | 0.0689 |
63
+ | 0.2587 | 1.8 | 450 | 0.2341 | 0.2341 | 0.3284 | 0.6852 | 0.2225 | 0.1109 |
64
+ | 0.1862 | 2.0 | 500 | 0.2146 | 0.2146 | 0.2971 | 0.6927 | 0.1798 | 0.0821 |
65
+ | 0.1218 | 2.2 | 550 | 0.2364 | 0.2364 | 0.3277 | 0.6888 | 0.2408 | 0.1480 |
66
+ | 0.1232 | 2.4 | 600 | 0.2216 | 0.2216 | 0.3226 | 0.7030 | 0.2305 | 0.1221 |
67
+ | 0.1651 | 2.6 | 650 | 0.2219 | 0.2219 | 0.3344 | 0.6868 | 0.2487 | 0.1190 |
68
+ | 0.1631 | 2.8 | 700 | 0.2306 | 0.2306 | 0.3312 | 0.6918 | 0.2533 | 0.1495 |
69
+ | 0.1024 | 3.0 | 750 | 0.2256 | 0.2256 | 0.3368 | 0.6882 | 0.2320 | 0.0966 |
70
+ | 0.0713 | 3.2 | 800 | 0.2189 | 0.2189 | 0.2950 | 0.6878 | 0.1907 | 0.1121 |
71
+ | 0.0608 | 3.4 | 850 | 0.2196 | 0.2196 | 0.2934 | 0.6981 | 0.1933 | 0.1178 |
72
+ | 0.0656 | 3.6 | 900 | 0.2199 | 0.2199 | 0.3018 | 0.7047 | 0.2186 | 0.1358 |
73
+ | 0.0774 | 3.8 | 950 | 0.2034 | 0.2034 | 0.2765 | 0.7033 | 0.1668 | 0.0962 |
74
+ | 0.0507 | 4.0 | 1000 | 0.2142 | 0.2142 | 0.2726 | 0.6607 | 0.1283 | 0.0602 |
75
+ | 0.0383 | 4.2 | 1050 | 0.2260 | 0.2260 | 0.3115 | 0.7006 | 0.1781 | 0.0642 |
76
+ | 0.0481 | 4.4 | 1100 | 0.2198 | 0.2198 | 0.3510 | 0.6998 | 0.2959 | 0.1498 |
77
+ | 0.0466 | 4.6 | 1150 | 0.2121 | 0.2121 | 0.3278 | 0.6813 | 0.2356 | 0.0976 |
78
+ | 0.029 | 4.8 | 1200 | 0.2055 | 0.2055 | 0.2710 | 0.7043 | 0.1522 | 0.0857 |
79
+ | 0.0355 | 5.0 | 1250 | 0.2016 | 0.2016 | 0.2751 | 0.7064 | 0.1707 | 0.0989 |
80
+ | 0.0178 | 5.2 | 1300 | 0.2108 | 0.2108 | 0.2926 | 0.6538 | 0.1835 | 0.1015 |
81
+ | 0.0321 | 5.4 | 1350 | 0.2053 | 0.2053 | 0.2824 | 0.7000 | 0.1876 | 0.1124 |
82
+ | 0.0167 | 5.6 | 1400 | 0.1993 | 0.1993 | 0.2622 | 0.7052 | 0.1473 | 0.0886 |
83
+ | 0.0243 | 5.8 | 1450 | 0.2052 | 0.2052 | 0.3119 | 0.6965 | 0.2269 | 0.1081 |
84
+ | 0.0169 | 6.0 | 1500 | 0.2058 | 0.2058 | 0.2565 | 0.6841 | 0.1239 | 0.0734 |
85
+ | 0.0103 | 6.2 | 1550 | 0.2006 | 0.2006 | 0.2639 | 0.6926 | 0.1496 | 0.0907 |
86
+ | 0.0136 | 6.4 | 1600 | 0.2039 | 0.2039 | 0.2859 | 0.6873 | 0.1846 | 0.1002 |
87
+ | 0.0093 | 6.6 | 1650 | 0.1995 | 0.1995 | 0.2685 | 0.7040 | 0.1654 | 0.1001 |
88
+ | 0.0093 | 6.8 | 1700 | 0.2065 | 0.2065 | 0.2604 | 0.6920 | 0.1416 | 0.0932 |
89
+ | 0.0095 | 7.0 | 1750 | 0.2056 | 0.2056 | 0.2618 | 0.7007 | 0.1476 | 0.0956 |
90
+ | 0.0062 | 7.2 | 1800 | 0.2043 | 0.2043 | 0.2637 | 0.6919 | 0.1470 | 0.0918 |
91
+ | 0.0052 | 7.4 | 1850 | 0.2018 | 0.2018 | 0.2593 | 0.6920 | 0.1453 | 0.0927 |
92
+ | 0.0078 | 7.6 | 1900 | 0.2043 | 0.2043 | 0.2571 | 0.6849 | 0.1243 | 0.0699 |
93
+ | 0.0064 | 7.8 | 1950 | 0.2094 | 0.2094 | 0.2565 | 0.6845 | 0.1156 | 0.0650 |
94
+ | 0.0063 | 8.0 | 2000 | 0.2047 | 0.2047 | 0.2556 | 0.6861 | 0.1232 | 0.0703 |
95
+ | 0.0038 | 8.2 | 2050 | 0.2056 | 0.2056 | 0.2541 | 0.6923 | 0.1245 | 0.0787 |
96
+ | 0.0027 | 8.4 | 2100 | 0.2069 | 0.2069 | 0.2587 | 0.6908 | 0.1315 | 0.0792 |
97
+ | 0.0025 | 8.6 | 2150 | 0.2041 | 0.2041 | 0.2576 | 0.6960 | 0.1351 | 0.0835 |
98
+ | 0.0034 | 8.8 | 2200 | 0.2023 | 0.2023 | 0.2633 | 0.6974 | 0.1511 | 0.0920 |
99
+ | 0.0029 | 9.0 | 2250 | 0.2034 | 0.2034 | 0.2589 | 0.6950 | 0.1369 | 0.0833 |
100
+ | 0.002 | 9.2 | 2300 | 0.2029 | 0.2029 | 0.2591 | 0.6985 | 0.1398 | 0.0861 |
101
+ | 0.0025 | 9.4 | 2350 | 0.2033 | 0.2033 | 0.2575 | 0.6969 | 0.1346 | 0.0824 |
102
+ | 0.0011 | 9.6 | 2400 | 0.2042 | 0.2042 | 0.2572 | 0.6958 | 0.1314 | 0.0798 |
103
+ | 0.0023 | 9.8 | 2450 | 0.2034 | 0.2034 | 0.2582 | 0.6951 | 0.1364 | 0.0836 |
104
+ | 0.0006 | 10.0 | 2500 | 0.2034 | 0.2034 | 0.2578 | 0.6963 | 0.1355 | 0.0831 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.51.0
110
+ - Pytorch 2.6.0+cu124
111
+ - Datasets 3.5.0
112
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e06a928ce4cad2d98c457519b71ea9f93201643032fe3f31b56f31441385a9c1
3
  size 598436708
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ac903fa212cf9e088984df906b6000ac3eb4b2ef193599938c5d3602e1f4e5
3
  size 598436708