Hugging Face's logo

stulcrad
/
CNEC_extended_xlm-roberta-large

Token Classification
Transformers
TensorBoard
Safetensors
Czech
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
4a32a39
•
1 Parent(s): 107ecc6

Model save

Browse files
Files changed (3) hide show
  1. README.md +18 -39
  2. model.safetensors +1 -1
  3. runs/Feb22_21-02-11_n32/events.out.tfevents.1708632134.n32.1130375.2 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8481132075471698
29
  - name: Recall
30
  type: recall
31
- value: 0.8923076923076924
32
  - name: F1
33
  type: f1
34
- value: 0.8696493349455865
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9768735362997658
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.1540
48
- - Precision: 0.8481
49
- - Recall: 0.8923
50
- - F1: 0.8696
51
- - Accuracy: 0.9769
52
 
53
  ## Model description
54
 
@@ -68,42 +68,21 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 4
72
- - eval_batch_size: 4
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 7
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.3844 | 0.28 | 500 | 0.2098 | 0.6100 | 0.7474 | 0.6717 | 0.9487 |
83
- | 0.2166 | 0.56 | 1000 | 0.1502 | 0.7313 | 0.8065 | 0.7671 | 0.9618 |
84
- | 0.1712 | 0.84 | 1500 | 0.1321 | 0.7447 | 0.8427 | 0.7907 | 0.9653 |
85
- | 0.1646 | 1.12 | 2000 | 0.1227 | 0.7516 | 0.8422 | 0.7943 | 0.9681 |
86
- | 0.1336 | 1.4 | 2500 | 0.1233 | 0.7729 | 0.8447 | 0.8072 | 0.9688 |
87
- | 0.1212 | 1.68 | 3000 | 0.1308 | 0.7989 | 0.8655 | 0.8309 | 0.9714 |
88
- | 0.1268 | 1.96 | 3500 | 0.1298 | 0.7867 | 0.8660 | 0.8245 | 0.9718 |
89
- | 0.0979 | 2.24 | 4000 | 0.1142 | 0.8111 | 0.8844 | 0.8462 | 0.9740 |
90
- | 0.1 | 2.52 | 4500 | 0.1316 | 0.8159 | 0.8799 | 0.8467 | 0.9724 |
91
- | 0.0971 | 2.8 | 5000 | 0.1334 | 0.8228 | 0.8849 | 0.8527 | 0.9737 |
92
- | 0.0912 | 3.08 | 5500 | 0.1348 | 0.8277 | 0.8844 | 0.8551 | 0.9755 |
93
- | 0.0661 | 3.36 | 6000 | 0.1349 | 0.8213 | 0.8849 | 0.8519 | 0.9747 |
94
- | 0.0672 | 3.64 | 6500 | 0.1423 | 0.8301 | 0.8898 | 0.8589 | 0.9735 |
95
- | 0.0721 | 3.92 | 7000 | 0.1242 | 0.8402 | 0.8923 | 0.8655 | 0.9764 |
96
- | 0.0703 | 4.2 | 7500 | 0.1351 | 0.8204 | 0.8794 | 0.8489 | 0.9737 |
97
- | 0.0503 | 4.48 | 8000 | 0.1625 | 0.8273 | 0.8918 | 0.8584 | 0.9747 |
98
- | 0.054 | 4.76 | 8500 | 0.1556 | 0.8276 | 0.8839 | 0.8548 | 0.9745 |
99
- | 0.0452 | 5.04 | 9000 | 0.1454 | 0.8360 | 0.8903 | 0.8623 | 0.9756 |
100
- | 0.0392 | 5.32 | 9500 | 0.1548 | 0.8406 | 0.8923 | 0.8657 | 0.9769 |
101
- | 0.0357 | 5.6 | 10000 | 0.1473 | 0.8446 | 0.8953 | 0.8692 | 0.9770 |
102
- | 0.0389 | 5.88 | 10500 | 0.1463 | 0.8494 | 0.8983 | 0.8731 | 0.9768 |
103
- | 0.0331 | 6.16 | 11000 | 0.1530 | 0.8503 | 0.8938 | 0.8715 | 0.9769 |
104
- | 0.0273 | 6.44 | 11500 | 0.1553 | 0.8483 | 0.8933 | 0.8702 | 0.9770 |
105
- | 0.0315 | 6.72 | 12000 | 0.1537 | 0.8499 | 0.8938 | 0.8713 | 0.9768 |
106
- | 0.0274 | 7.0 | 12500 | 0.1540 | 0.8481 | 0.8923 | 0.8696 | 0.9769 |
107
 
108
 
109
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.862624348649929
29
  - name: Recall
30
  type: recall
31
+ value: 0.9037220843672457
32
  - name: F1
33
  type: f1
34
+ value: 0.8826951042171596
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9778103044496487
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.1070
48
+ - Precision: 0.8626
49
+ - Recall: 0.9037
50
+ - F1: 0.8827
51
+ - Accuracy: 0.9778
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 16
72
+ - eval_batch_size: 16
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 5
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3643 | 1.12 | 500 | 0.1506 | 0.7225 | 0.8452 | 0.7790 | 0.9628 |
83
+ | 0.1213 | 2.24 | 1000 | 0.1073 | 0.7944 | 0.8725 | 0.8316 | 0.9723 |
84
+ | 0.0783 | 3.36 | 1500 | 0.1024 | 0.8424 | 0.8938 | 0.8673 | 0.9763 |
85
+ | 0.0562 | 4.47 | 2000 | 0.1070 | 0.8626 | 0.9037 | 0.8827 | 0.9778 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
86
 
87
 
88
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef988d9210adc4132b3d8f119932458f698b82529773615d9bbe07e7ea27b2bb
3
  size 2235473356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15da1a3fc3b900fb76b48615a9e4b2063a76d4a59297830770856fb81c1826f
3
  size 2235473356
runs/Feb22_21-02-11_n32/events.out.tfevents.1708632134.n32.1130375.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:299bcdffe4484ebf110f7a3ae88c4bfee7c7fab897e078df149a01e0da4c56f5
3
- size 7392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4427080dbf109ea1d1791d184e1d9cb506f9e4f36d930273d18479da704d40
3
+ size 7746