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
a208648
•
1 Parent(s): 8d6f0af

Model save

Browse files
Files changed (3) hide show
  1. README.md +18 -22
  2. model.safetensors +1 -1
  3. runs/Feb26_17-29-15_n29/events.out.tfevents.1708964956.n29.26646.4 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8495533615420781
29
  - name: Recall
30
  type: recall
31
- value: 0.896774193548387
32
  - name: F1
33
  type: f1
34
- value: 0.8725253500724288
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9753512880562061
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: 0.1667
48
- - Precision: 0.8496
49
- - Recall: 0.8968
50
- - F1: 0.8725
51
- - Accuracy: 0.9754
52
 
53
  ## Model description
54
 
@@ -73,24 +73,20 @@ The following hyperparameters were used during training:
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 14
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.4608 | 1.12 | 500 | 0.1709 | 0.6984 | 0.8089 | 0.7496 | 0.9579 |
83
- | 0.1492 | 2.24 | 1000 | 0.1188 | 0.7702 | 0.8467 | 0.8066 | 0.9690 |
84
- | 0.0993 | 3.36 | 1500 | 0.1077 | 0.8123 | 0.8804 | 0.8450 | 0.9739 |
85
- | 0.0724 | 4.47 | 2000 | 0.1113 | 0.8156 | 0.8824 | 0.8477 | 0.9759 |
86
- | 0.0603 | 5.59 | 2500 | 0.1337 | 0.8234 | 0.8864 | 0.8537 | 0.9739 |
87
- | 0.045 | 6.71 | 3000 | 0.1386 | 0.8446 | 0.8958 | 0.8695 | 0.9756 |
88
- | 0.0358 | 7.83 | 3500 | 0.1371 | 0.8449 | 0.8978 | 0.8705 | 0.9756 |
89
- | 0.0284 | 8.95 | 4000 | 0.1364 | 0.8390 | 0.8998 | 0.8683 | 0.9756 |
90
- | 0.0229 | 10.07 | 4500 | 0.1479 | 0.8328 | 0.8873 | 0.8592 | 0.9734 |
91
- | 0.0172 | 11.19 | 5000 | 0.1658 | 0.8446 | 0.8958 | 0.8695 | 0.9754 |
92
- | 0.0146 | 12.3 | 5500 | 0.1650 | 0.8448 | 0.8968 | 0.8700 | 0.9749 |
93
- | 0.0126 | 13.42 | 6000 | 0.1667 | 0.8496 | 0.8968 | 0.8725 | 0.9754 |
94
 
95
 
96
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.850375234521576
29
  - name: Recall
30
  type: recall
31
+ value: 0.8997518610421836
32
  - name: F1
33
  type: f1
34
+ value: 0.8743670122980468
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9757611241217798
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: 0.1491
48
+ - Precision: 0.8504
49
+ - Recall: 0.8998
50
+ - F1: 0.8744
51
+ - Accuracy: 0.9758
52
 
53
  ## Model description
54
 
 
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 10
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3272 | 1.12 | 500 | 0.1195 | 0.7391 | 0.8561 | 0.7933 | 0.9679 |
83
+ | 0.1197 | 2.24 | 1000 | 0.1137 | 0.7796 | 0.8655 | 0.8203 | 0.9725 |
84
+ | 0.0859 | 3.36 | 1500 | 0.1169 | 0.7782 | 0.8620 | 0.8180 | 0.9734 |
85
+ | 0.0628 | 4.47 | 2000 | 0.1174 | 0.8147 | 0.8839 | 0.8479 | 0.9744 |
86
+ | 0.0488 | 5.59 | 2500 | 0.1351 | 0.8297 | 0.8898 | 0.8587 | 0.9742 |
87
+ | 0.0361 | 6.71 | 3000 | 0.1330 | 0.8443 | 0.8963 | 0.8695 | 0.9764 |
88
+ | 0.0302 | 7.83 | 3500 | 0.1394 | 0.8519 | 0.9017 | 0.8761 | 0.9764 |
89
+ | 0.0216 | 8.95 | 4000 | 0.1491 | 0.8504 | 0.8998 | 0.8744 | 0.9758 |
 
 
 
 
90
 
91
 
92
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf1aed1e6b7835ec6cd785ac898961da2f6d3c2af4006a2b70b9de4ccbc0a3b5
3
  size 2235473356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fccd78a7b6ecd92e191bae41f4b6ae6b0293383c3745fa7e487221c69d9dd227
3
  size 2235473356
runs/Feb26_17-29-15_n29/events.out.tfevents.1708964956.n29.26646.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94edc0a78c1ea4caa117f9d35811ede201d2ced18d7985b97216531419e3f23e
3
- size 9909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d28df891eb3b5dc3e664c61f7b11236d0a04f0800a0291ec837f0636116125d0
3
+ size 10263