Hugging Face's logo

stulcrad
/
mBERT-2

Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
3690ca5
·
verified ·
1 Parent(s): 03a727f

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -21
  2. runs/Feb10_15-31-55_dgx10/events.out.tfevents.1739197917.dgx10.2757791.0 +2 -2
README.md CHANGED
@@ -4,13 +4,13 @@ license: apache-2.0
4
  base_model: bert-base-multilingual-cased
5
  tags:
6
  - generated_from_trainer
 
 
7
  metrics:
8
  - accuracy
9
  model-index:
10
  - name: mBERT-2
11
  results: []
12
- language:
13
- - cs
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,16 +18,16 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # mBERT-2
20
 
21
- This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the CERED(Czech Relationship Extraction dataset)-version-2 dataset. (https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3266?locale-attribute=cs)
22
- It achieves the following results on the test set:
23
- - Loss: 0.9469
24
- - Accuracy: 0.8845
25
- - Micro Precision: 0.8845
26
- - Micro Recall: 0.8845
27
- - Micro F1: 0.8845
28
- - Macro Precision: 0.8512
29
- - Macro Recall: 0.8349
30
- - Macro F1: 0.8398
31
 
32
  ## Model description
33
 
@@ -58,14 +58,14 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 |
60
  |:-------------:|:-----:|:------:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|
61
- | 0.6019 | 1.0 | 30148 | 0.5612 | 0.8398 | 0.8398 | 0.8398 | 0.8398 | 0.8271 | 0.7687 | 0.7761 |
62
- | 0.4904 | 2.0 | 60296 | 0.5216 | 0.8564 | 0.8564 | 0.8564 | 0.8564 | 0.8172 | 0.8079 | 0.8032 |
63
- | 0.3624 | 3.0 | 90444 | 0.5196 | 0.8656 | 0.8656 | 0.8656 | 0.8656 | 0.8374 | 0.8006 | 0.8094 |
64
- | 0.3242 | 4.0 | 120592 | 0.5662 | 0.8720 | 0.8720 | 0.8720 | 0.8720 | 0.8468 | 0.8222 | 0.8275 |
65
- | 0.2522 | 5.0 | 150740 | 0.6456 | 0.8717 | 0.8717 | 0.8717 | 0.8717 | 0.8329 | 0.8374 | 0.8298 |
66
- | 0.1707 | 6.0 | 180888 | 0.7233 | 0.8764 | 0.8764 | 0.8764 | 0.8764 | 0.8442 | 0.8356 | 0.8343 |
67
- | 0.103 | 7.0 | 211036 | 0.8474 | 0.8794 | 0.8794 | 0.8794 | 0.8794 | 0.8440 | 0.8403 | 0.8385 |
68
- | 0.0646 | 8.0 | 241184 | 0.9117 | 0.8836 | 0.8836 | 0.8836 | 0.8836 | 0.8465 | 0.8455 | 0.8423 |
69
 
70
 
71
  ### Framework versions
@@ -73,4 +73,4 @@ The following hyperparameters were used during training:
73
  - Transformers 4.46.2
74
  - Pytorch 2.5.1+cu124
75
  - Datasets 3.1.0
76
- - Tokenizers 0.20.3
 
4
  base_model: bert-base-multilingual-cased
5
  tags:
6
  - generated_from_trainer
7
+ datasets:
8
+ - generator
9
  metrics:
10
  - accuracy
11
  model-index:
12
  - name: mBERT-2
13
  results: []
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
18
 
19
  # mBERT-2
20
 
21
+ This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.6578
24
+ - Accuracy: 0.8836
25
+ - Micro Precision: 0.8836
26
+ - Micro Recall: 0.8836
27
+ - Micro F1: 0.8836
28
+ - Macro Precision: 0.8408
29
+ - Macro Recall: 0.8390
30
+ - Macro F1: 0.8341
31
 
32
  ## Model description
33
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 |
60
  |:-------------:|:-----:|:------:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|
61
+ | 0.6815 | 1.0 | 30148 | 0.6219 | 0.8248 | 0.8248 | 0.8248 | 0.8248 | 0.7812 | 0.7508 | 0.7461 |
62
+ | 0.587 | 2.0 | 60296 | 0.5427 | 0.8544 | 0.8544 | 0.8544 | 0.8544 | 0.8207 | 0.7933 | 0.7966 |
63
+ | 0.4624 | 3.0 | 90444 | 0.5276 | 0.8611 | 0.8611 | 0.8611 | 0.8611 | 0.8415 | 0.8065 | 0.8116 |
64
+ | 0.4268 | 4.0 | 120592 | 0.5558 | 0.8614 | 0.8614 | 0.8614 | 0.8614 | 0.8169 | 0.8178 | 0.8087 |
65
+ | 0.3821 | 5.0 | 150740 | 0.5770 | 0.8681 | 0.8681 | 0.8681 | 0.8681 | 0.8291 | 0.8242 | 0.8190 |
66
+ | 0.3031 | 6.0 | 180888 | 0.5732 | 0.8774 | 0.8774 | 0.8774 | 0.8774 | 0.8323 | 0.8289 | 0.8250 |
67
+ | 0.219 | 7.0 | 211036 | 0.6498 | 0.8764 | 0.8764 | 0.8764 | 0.8764 | 0.8370 | 0.8296 | 0.8274 |
68
+ | 0.1897 | 8.0 | 241184 | 0.6578 | 0.8836 | 0.8836 | 0.8836 | 0.8836 | 0.8408 | 0.8390 | 0.8341 |
69
 
70
 
71
  ### Framework versions
 
73
  - Transformers 4.46.2
74
  - Pytorch 2.5.1+cu124
75
  - Datasets 3.1.0
76
+ - Tokenizers 0.20.3
runs/Feb10_15-31-55_dgx10/events.out.tfevents.1739197917.dgx10.2757791.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41f1d4ed7277cbb0ceddf3ae67d0f591b31f5e03784317562ea0880618c95fa4
3
- size 118139
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8183f1195aa7b20971b50b675707dcefe485f66445da8e9391faeef20d911feb
3
+ size 119168