Hugging Face's logo

fabikru
/
trainer

Fill-Mask
Transformers
Safetensors
modernbert
Generated from Trainer
Model card Files
xet
Community
fabikru commited on
Commit
9dbe894
·
verified ·
1 Parent(s): 251a692

model_5M_large_ds_masking_0.6_predicted_hparamas

Browse files
Files changed (3) hide show
  1. README.md +39 -25
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1606
20
- - Accuracy: 0.9442
21
 
22
  ## Model description
23
 
@@ -52,29 +52,43 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | No log | 0 | 0 | 4.5171 | 0.0026 |
56
- | No log | 0.0044 | 122 | 0.7823 | 0.7600 |
57
- | No log | 0.0087 | 244 | 0.4773 | 0.8451 |
58
- | No log | 0.0131 | 366 | 0.4435 | 0.8554 |
59
- | No log | 0.0175 | 488 | 0.3739 | 0.8770 |
60
- | 6.7174 | 0.0218 | 610 | 0.3468 | 0.8851 |
61
- | 6.7174 | 0.0262 | 732 | 0.3011 | 0.9001 |
62
- | 6.7174 | 0.0306 | 854 | 0.2789 | 0.9067 |
63
- | 6.7174 | 0.0349 | 976 | 0.2546 | 0.9135 |
64
- | 2.7623 | 0.0393 | 1098 | 0.2348 | 0.9200 |
65
- | 2.7623 | 0.0437 | 1220 | 0.2193 | 0.9256 |
66
- | 2.7623 | 0.0480 | 1342 | 0.2050 | 0.9300 |
67
- | 2.7623 | 0.0524 | 1464 | 0.1958 | 0.9331 |
68
- | 1.8687 | 0.0568 | 1586 | 0.1918 | 0.9348 |
69
- | 1.8687 | 0.0611 | 1708 | 0.1862 | 0.9363 |
70
- | 1.8687 | 0.0655 | 1830 | 0.1852 | 0.9362 |
71
- | 1.8687 | 0.0699 | 1952 | 0.1795 | 0.9385 |
72
- | 1.587 | 0.0743 | 2074 | 0.1719 | 0.9406 |
73
- | 1.587 | 0.0786 | 2196 | 0.1682 | 0.9420 |
74
- | 1.587 | 0.0830 | 2318 | 0.1672 | 0.9421 |
75
- | 1.587 | 0.0874 | 2440 | 0.1610 | 0.9441 |
76
- | 1.4413 | 0.0917 | 2562 | 0.1606 | 0.9447 |
77
- | 1.4413 | 0.0961 | 2684 | 0.1599 | 0.9447 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5105
20
+ - Accuracy: 0.8309
21
 
22
  ## Model description
23
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | No log | 0 | 0 | 4.4023 | 0.0066 |
56
+ | No log | 0.0044 | 122 | 1.2619 | 0.6163 |
57
+ | No log | 0.0087 | 244 | 1.0124 | 0.6795 |
58
+ | No log | 0.0131 | 366 | 0.8866 | 0.7158 |
59
+ | No log | 0.0175 | 488 | 0.8865 | 0.7166 |
60
+ | 10.5295 | 0.0218 | 610 | 0.8234 | 0.7347 |
61
+ | 10.5295 | 0.0262 | 732 | 0.7646 | 0.7519 |
62
+ | 10.5295 | 0.0306 | 854 | 0.7361 | 0.7603 |
63
+ | 10.5295 | 0.0349 | 976 | 0.7118 | 0.7680 |
64
+ | 6.5692 | 0.0393 | 1098 | 0.6775 | 0.7784 |
65
+ | 6.5692 | 0.0437 | 1220 | 0.6562 | 0.7858 |
66
+ | 6.5692 | 0.0480 | 1342 | 0.6391 | 0.7905 |
67
+ | 6.5692 | 0.0524 | 1464 | 0.6223 | 0.7956 |
68
+ | 5.4485 | 0.0568 | 1586 | 0.6140 | 0.7983 |
69
+ | 5.4485 | 0.0611 | 1708 | 0.6021 | 0.8018 |
70
+ | 5.4485 | 0.0655 | 1830 | 0.5968 | 0.8039 |
71
+ | 5.4485 | 0.0699 | 1952 | 0.5881 | 0.8065 |
72
+ | 4.9395 | 0.0743 | 2074 | 0.5793 | 0.8094 |
73
+ | 4.9395 | 0.0786 | 2196 | 0.5739 | 0.8109 |
74
+ | 4.9395 | 0.0830 | 2318 | 0.5707 | 0.8120 |
75
+ | 4.9395 | 0.0874 | 2440 | 0.5638 | 0.8139 |
76
+ | 4.6796 | 0.0917 | 2562 | 0.5605 | 0.8150 |
77
+ | 4.6796 | 0.0961 | 2684 | 0.5514 | 0.8179 |
78
+ | 4.6796 | 0.1005 | 2806 | 0.5520 | 0.8177 |
79
+ | 4.6796 | 0.1048 | 2928 | 0.5496 | 0.8189 |
80
+ | 4.5172 | 0.1092 | 3050 | 0.5424 | 0.8207 |
81
+ | 4.5172 | 0.1136 | 3172 | 0.5391 | 0.8221 |
82
+ | 4.5172 | 0.1179 | 3294 | 0.5362 | 0.8228 |
83
+ | 4.5172 | 0.1223 | 3416 | 0.5327 | 0.8241 |
84
+ | 4.3971 | 0.1267 | 3538 | 0.5295 | 0.8248 |
85
+ | 4.3971 | 0.1310 | 3660 | 0.5259 | 0.8260 |
86
+ | 4.3971 | 0.1354 | 3782 | 0.5238 | 0.8267 |
87
+ | 4.3971 | 0.1398 | 3904 | 0.5195 | 0.8278 |
88
+ | 4.3028 | 0.1441 | 4026 | 0.5200 | 0.8278 |
89
+ | 4.3028 | 0.1485 | 4148 | 0.5150 | 0.8295 |
90
+ | 4.3028 | 0.1529 | 4270 | 0.5160 | 0.8294 |
91
+ | 4.3028 | 0.1572 | 4392 | 0.5140 | 0.8298 |
92
 
93
 
94
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe7643f397b632e3b16b77d6540378ff1d7180ec4fe194929231ff59b1334da9
3
  size 18195880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d7aea7006ec800dae97a3783fa1cdf6c27e1fb1126c6d0a79c8ac015643490
3
  size 18195880
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ff875155df15d0af1b09c5af9c4d074f8b9147e963c136e7a9da5c6ef930829
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17fd9ea669ce7a724261a1d10a58c196aa0f95f6e5e105d7c2f1e6849e2a1e8
3
  size 5905