Hugging Face's logo

fabikru
/
trainer

Fill-Mask
Transformers
Safetensors
modernbert
Generated from Trainer
Model card Files
xet
Community
fabikru commited on
Commit
284fd81
·
verified ·
1 Parent(s): f48d93e

model_15M_medium_ds_masking_0.7_explicit_hs_predicted_hparamas

Browse files
Files changed (4) hide show
  1. README.md +28 -39
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. 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: 0.3649
20
- - Accuracy: 0.8733
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.003439
40
  - train_batch_size: 256
41
  - eval_batch_size: 256
42
  - seed: 42
@@ -48,44 +48,33 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-------:|:-----:|:---------------:|:--------:|
53
- | No log | 0 | 0 | 4.4509 | 0.0072 |
54
- | 0.7148 | 0.4302 | 1953 | 0.6216 | 0.7885 |
55
- | 0.5807 | 0.8604 | 3906 | 0.5453 | 0.8131 |
56
- | 0.5322 | 1.2905 | 5859 | 0.5084 | 0.8251 |
57
- | 0.5068 | 1.7207 | 7812 | 0.4851 | 0.8328 |
58
- | 0.4855 | 2.1509 | 9765 | 0.4710 | 0.8376 |
59
- | 0.47 | 2.5811 | 11718 | 0.4552 | 0.8433 |
60
- | 0.4589 | 3.0112 | 13671 | 0.4455 | 0.8459 |
61
- | 0.4475 | 3.4414 | 15624 | 0.4383 | 0.8484 |
62
- | 0.4401 | 3.8716 | 17577 | 0.4276 | 0.8515 |
63
- | 0.4329 | 4.3018 | 19530 | 0.4218 | 0.8537 |
64
- | 0.4299 | 4.7319 | 21483 | 0.4167 | 0.8557 |
65
- | 0.423 | 5.1621 | 23436 | 0.4108 | 0.8568 |
66
- | 0.4175 | 5.5923 | 25389 | 0.4081 | 0.8584 |
67
- | 0.4122 | 6.0225 | 27342 | 0.4022 | 0.8607 |
68
- | 0.4095 | 6.4526 | 29295 | 0.3966 | 0.8625 |
69
- | 0.4034 | 6.8828 | 31248 | 0.3962 | 0.8623 |
70
- | 0.4012 | 7.3130 | 33201 | 0.3926 | 0.8636 |
71
- | 0.3984 | 7.7432 | 35154 | 0.3893 | 0.8650 |
72
- | 0.395 | 8.1733 | 37107 | 0.3849 | 0.8663 |
73
- | 0.3904 | 8.6035 | 39060 | 0.3827 | 0.8669 |
74
- | 0.3873 | 9.0337 | 41013 | 0.3797 | 0.8680 |
75
- | 0.3865 | 9.4639 | 42966 | 0.3775 | 0.8691 |
76
- | 0.3839 | 9.8941 | 44919 | 0.3742 | 0.8696 |
77
- | 0.3781 | 10.3242 | 46872 | 0.3757 | 0.8693 |
78
- | 0.3806 | 10.7544 | 48825 | 0.3698 | 0.8713 |
79
- | 0.376 | 11.1846 | 50778 | 0.3703 | 0.8712 |
80
- | 0.3748 | 11.6148 | 52731 | 0.3672 | 0.8720 |
81
- | 0.3743 | 12.0449 | 54684 | 0.3643 | 0.8733 |
82
- | 0.3715 | 12.4751 | 56637 | 0.3662 | 0.8727 |
83
- | 0.3695 | 12.9053 | 58590 | 0.3666 | 0.8724 |
84
 
85
 
86
  ### Framework versions
87
 
88
- - Transformers 4.51.2
89
- - Pytorch 2.8.0.dev20250410+cu128
90
- - Datasets 3.5.0
91
  - Tokenizers 0.21.1
 
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: 0.2317
20
+ - Accuracy: 0.9237
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.005776
40
  - train_batch_size: 256
41
  - eval_batch_size: 256
42
  - seed: 42
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
53
+ | No log | 0 | 0 | 4.4632 | 0.0019 |
54
+ | 0.4564 | 0.2190 | 1953 | 0.3973 | 0.8732 |
55
+ | 0.3637 | 0.4379 | 3906 | 0.3450 | 0.8886 |
56
+ | 0.3313 | 0.6569 | 5859 | 0.3169 | 0.8970 |
57
+ | 0.3101 | 0.8759 | 7812 | 0.2993 | 0.9026 |
58
+ | 0.3062 | 1.0949 | 9765 | 0.2885 | 0.9058 |
59
+ | 0.2852 | 1.3138 | 11718 | 0.2776 | 0.9092 |
60
+ | 0.2754 | 1.5328 | 13671 | 0.2703 | 0.9117 |
61
+ | 0.2689 | 1.7518 | 15624 | 0.2626 | 0.9142 |
62
+ | 0.2624 | 1.9707 | 17577 | 0.2566 | 0.9159 |
63
+ | 0.2574 | 2.1897 | 19530 | 0.2533 | 0.9169 |
64
+ | 0.2547 | 2.4087 | 21483 | 0.2478 | 0.9187 |
65
+ | 0.2495 | 2.6276 | 23436 | 0.2434 | 0.9201 |
66
+ | 0.2447 | 2.8466 | 25389 | 0.2395 | 0.9213 |
67
+ | 0.2416 | 3.0656 | 27342 | 0.2350 | 0.9227 |
68
+ | 0.2383 | 3.2846 | 29295 | 0.2331 | 0.9233 |
69
+ | 0.2363 | 3.5035 | 31248 | 0.2321 | 0.9236 |
70
+ | 0.0 | 3.7225 | 33201 | 0.2309 | 0.9240 |
71
+ | 0.0 | 3.9415 | 35154 | 0.2320 | 0.9237 |
72
+ | 0.0 | 4.1604 | 37107 | 0.2304 | 0.9241 |
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
76
 
77
+ - Transformers 4.52.2
78
+ - Pytorch 2.8.0.dev20250521+cu128
79
+ - Datasets 3.6.0
80
  - Tokenizers 0.21.1
config.json CHANGED
@@ -37,6 +37,6 @@
37
  "sparse_pred_ignore_index": -100,
38
  "sparse_prediction": false,
39
  "torch_dtype": "float32",
40
- "transformers_version": "4.51.2",
41
  "vocab_size": 82
42
  }
 
37
  "sparse_pred_ignore_index": -100,
38
  "sparse_prediction": false,
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.52.2",
41
  "vocab_size": 82
42
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa8f0a3fb8aa1fb113188ec55e7fbe69b46e7eab0cb61755051222e9762bfa4c
3
  size 60925776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcd833fc7ee5f7d40833d741dabd16a251eb928798344e8b76c9113827562a8a
3
  size 60925776
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc81299c0a6ea26b4af7dc8a6953ad6af75dfe1fa70e7d8cfa5a016c89291664
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc10ffd859f1450b05826ac813f49be0f0747e5248bcbc28c5728d5933007bf
3
  size 5905