Hugging Face's logo

fabikru
/
trainer

Fill-Mask
Transformers
Safetensors
modernbert
Generated from Trainer
Model card Files
xet
Community
fabikru commited on
Commit
2e33897
·
verified ·
1 Parent(s): f98cafb

model_15M_small_ds_masking_0.2_predicted_hparamas

Browse files
Files changed (3) hide show
  1. README.md +29 -33
  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: 0.2445
20
- - Accuracy: 0.9135
21
 
22
  ## Model description
23
 
@@ -50,37 +50,33 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|
53
- | No log | 0 | 0 | 4.4175 | 0.0125 |
54
- | 0.5685 | 0.4302 | 1953 | 0.4742 | 0.8365 |
55
- | 0.4343 | 0.8604 | 3906 | 0.3988 | 0.8613 |
56
- | 0.3885 | 1.2905 | 5859 | 0.3679 | 0.8716 |
57
- | 0.3663 | 1.7207 | 7812 | 0.3454 | 0.8790 |
58
- | 0.3472 | 2.1509 | 9765 | 0.3319 | 0.8840 |
59
- | 0.3335 | 2.5811 | 11718 | 0.3186 | 0.8881 |
60
- | 0.3242 | 3.0112 | 13671 | 0.3085 | 0.8917 |
61
- | 0.3129 | 3.4414 | 15624 | 0.3026 | 0.8937 |
62
- | 0.3071 | 3.8716 | 17577 | 0.2958 | 0.8957 |
63
- | 0.3002 | 4.3018 | 19530 | 0.2911 | 0.8976 |
64
- | 0.2981 | 4.7319 | 21483 | 0.2861 | 0.8992 |
65
- | 0.2915 | 5.1621 | 23436 | 0.2819 | 0.9006 |
66
- | 0.2882 | 5.5923 | 25389 | 0.2782 | 0.9018 |
67
- | 0.2834 | 6.0225 | 27342 | 0.2731 | 0.9036 |
68
- | 0.2811 | 6.4526 | 29295 | 0.2711 | 0.9043 |
69
- | 0.2756 | 6.8828 | 31248 | 0.2679 | 0.9053 |
70
- | 0.2742 | 7.3130 | 33201 | 0.2663 | 0.9060 |
71
- | 0.2723 | 7.7432 | 35154 | 0.2618 | 0.9075 |
72
- | 0.2679 | 8.1733 | 37107 | 0.2587 | 0.9086 |
73
- | 0.2649 | 8.6035 | 39060 | 0.2585 | 0.9089 |
74
- | 0.2629 | 9.0337 | 41013 | 0.2564 | 0.9092 |
75
- | 0.2619 | 9.4639 | 42966 | 0.2536 | 0.9104 |
76
- | 0.2593 | 9.8941 | 44919 | 0.2514 | 0.9108 |
77
- | 0.2548 | 10.3242 | 46872 | 0.2509 | 0.9111 |
78
- | 0.2567 | 10.7544 | 48825 | 0.2484 | 0.9121 |
79
- | 0.2533 | 11.1846 | 50778 | 0.2487 | 0.9121 |
80
- | 0.2513 | 11.6148 | 52731 | 0.2470 | 0.9122 |
81
- | 0.2509 | 12.0449 | 54684 | 0.2421 | 0.9141 |
82
- | 0.2494 | 12.4751 | 56637 | 0.2456 | 0.9132 |
83
- | 0.2472 | 12.9053 | 58590 | 0.2428 | 0.9139 |
84
 
85
 
86
  ### 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: 0.1261
20
+ - Accuracy: 0.9546
21
 
22
  ## Model description
23
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|
53
+ | No log | 0 | 0 | 4.5785 | 0.0163 |
54
+ | 0.4164 | 0.4302 | 1953 | 0.3256 | 0.8862 |
55
+ | 0.2809 | 0.8604 | 3906 | 0.2521 | 0.9109 |
56
+ | 0.2355 | 1.2905 | 5859 | 0.2174 | 0.9226 |
57
+ | 0.2138 | 1.7207 | 7812 | 0.1972 | 0.9298 |
58
+ | 0.1987 | 2.1509 | 9765 | 0.1861 | 0.9337 |
59
+ | 0.188 | 2.5811 | 11718 | 0.1756 | 0.9371 |
60
+ | 0.1808 | 3.0112 | 13671 | 0.1697 | 0.9397 |
61
+ | 0.1737 | 3.4414 | 15624 | 0.1638 | 0.9413 |
62
+ | 0.1686 | 3.8716 | 17577 | 0.1601 | 0.9426 |
63
+ | 0.1636 | 4.3018 | 19530 | 0.1552 | 0.9444 |
64
+ | 0.1602 | 4.7319 | 21483 | 0.1525 | 0.9453 |
65
+ | 0.1567 | 5.1621 | 23436 | 0.1498 | 0.9463 |
66
+ | 0.1534 | 5.5923 | 25389 | 0.1479 | 0.9466 |
67
+ | 0.1512 | 6.0225 | 27342 | 0.1445 | 0.9481 |
68
+ | 0.1499 | 6.4526 | 29295 | 0.1415 | 0.9493 |
69
+ | 0.1456 | 6.8828 | 31248 | 0.1394 | 0.9500 |
70
+ | 0.1437 | 7.3130 | 33201 | 0.1382 | 0.9502 |
71
+ | 0.1427 | 7.7432 | 35154 | 0.1384 | 0.9503 |
72
+ | 0.1396 | 8.1733 | 37107 | 0.1353 | 0.9514 |
73
+ | 0.1384 | 8.6035 | 39060 | 0.1330 | 0.9519 |
74
+ | 0.1371 | 9.0337 | 41013 | 0.1327 | 0.9522 |
75
+ | 0.1357 | 9.4639 | 42966 | 0.1310 | 0.9528 |
76
+ | 0.1342 | 9.8941 | 44919 | 0.1286 | 0.9536 |
77
+ | 0.1312 | 10.3242 | 46872 | 0.1273 | 0.9543 |
78
+ | 0.132 | 10.7544 | 48825 | 0.1266 | 0.9546 |
79
+ | 0.1303 | 11.1846 | 50778 | 0.1265 | 0.9546 |
 
 
 
 
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:04daea2582129fcfb619b038a5f6975b9e0fdcb7a28c8d4b8eae29576e95afe2
3
  size 60925776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e6655e1e457688f5d6719b9a3475213968034d8e3df9f2e2245696661bc11d
3
  size 60925776
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d08c7c87f1b42e56aeb6f0b627ccead925f157fb3c711e08171861f2405ce60
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29ef52d346e54c9e3e2cf044fbbbb8ba40c8fa85dc365eab8ae247740342405
3
  size 5905