Hugging Face's logo

stulcrad
/
CNEC1_1_Supertypes_xlm-roberta-large

Token Classification
Transformers
TensorBoard
Safetensors
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
stulcrad commited on
Commit
da2665c
·
verified ·
1 Parent(s): feaba54

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -18
  2. runs/Mar05_23-55-39_n21/events.out.tfevents.1709679351.n21.2238640.1 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8095043015157722
29
  - name: Recall
30
  type: recall
31
- value: 0.8864961866307761
32
  - name: F1
33
  type: f1
34
- value: 0.8462526766595291
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9620984425621609
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: 0.2133
48
- - Precision: 0.8095
49
- - Recall: 0.8865
50
- - F1: 0.8463
51
- - Accuracy: 0.9621
52
 
53
  ## Model description
54
 
@@ -73,20 +73,26 @@ 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: 15
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.4081 | 1.7 | 500 | 0.1879 | 0.7183 | 0.8430 | 0.7756 | 0.9505 |
83
- | 0.1806 | 3.4 | 1000 | 0.1816 | 0.7703 | 0.8681 | 0.8163 | 0.9567 |
84
- | 0.131 | 5.1 | 1500 | 0.1695 | 0.7756 | 0.8712 | 0.8206 | 0.9592 |
85
- | 0.0975 | 6.8 | 2000 | 0.1861 | 0.7640 | 0.8744 | 0.8155 | 0.9571 |
86
- | 0.0778 | 8.5 | 2500 | 0.1908 | 0.7989 | 0.8807 | 0.8378 | 0.9591 |
87
- | 0.0596 | 10.2 | 3000 | 0.1922 | 0.7916 | 0.8829 | 0.8348 | 0.9592 |
88
- | 0.0506 | 11.9 | 3500 | 0.2070 | 0.8016 | 0.8811 | 0.8395 | 0.9598 |
89
- | 0.0407 | 13.61 | 4000 | 0.2133 | 0.8095 | 0.8865 | 0.8463 | 0.9621 |
 
 
 
 
 
 
90
 
91
 
92
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8374155405405406
29
  - name: Recall
30
  type: recall
31
+ value: 0.8896366083445492
32
  - name: F1
33
  type: f1
34
+ value: 0.8627365673265174
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9609274366680979
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: 0.2870
48
+ - Precision: 0.8374
49
+ - Recall: 0.8896
50
+ - F1: 0.8627
51
+ - Accuracy: 0.9609
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: 25
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4362 | 1.7 | 500 | 0.1915 | 0.7142 | 0.8407 | 0.7723 | 0.9498 |
83
+ | 0.1873 | 3.4 | 1000 | 0.1735 | 0.7945 | 0.8793 | 0.8348 | 0.9584 |
84
+ | 0.1395 | 5.1 | 1500 | 0.1774 | 0.7771 | 0.8681 | 0.8201 | 0.9582 |
85
+ | 0.1031 | 6.8 | 2000 | 0.1837 | 0.8025 | 0.8748 | 0.8371 | 0.9582 |
86
+ | 0.0825 | 8.5 | 2500 | 0.1937 | 0.8106 | 0.8852 | 0.8462 | 0.9585 |
87
+ | 0.0671 | 10.2 | 3000 | 0.2007 | 0.8338 | 0.8932 | 0.8625 | 0.9609 |
88
+ | 0.0538 | 11.9 | 3500 | 0.2101 | 0.8222 | 0.8901 | 0.8548 | 0.9603 |
89
+ | 0.0419 | 13.61 | 4000 | 0.2177 | 0.8186 | 0.8905 | 0.8530 | 0.9619 |
90
+ | 0.0361 | 15.31 | 4500 | 0.2299 | 0.8316 | 0.8843 | 0.8571 | 0.9612 |
91
+ | 0.0281 | 17.01 | 5000 | 0.2474 | 0.8300 | 0.8825 | 0.8554 | 0.9610 |
92
+ | 0.0234 | 18.71 | 5500 | 0.2623 | 0.8327 | 0.8843 | 0.8577 | 0.9606 |
93
+ | 0.0194 | 20.41 | 6000 | 0.2702 | 0.8311 | 0.8829 | 0.8562 | 0.9603 |
94
+ | 0.0169 | 22.11 | 6500 | 0.2781 | 0.8358 | 0.8883 | 0.8612 | 0.9608 |
95
+ | 0.0151 | 23.81 | 7000 | 0.2870 | 0.8374 | 0.8896 | 0.8627 | 0.9609 |
96
 
97
 
98
  ### Framework versions
runs/Mar05_23-55-39_n21/events.out.tfevents.1709679351.n21.2238640.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28c7c7e4e45ab58db34d5a0a569757ddd3a319e30dd3a685771d8fdc1acb222d
3
- size 13916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954b403ff1a3337ffab42cfd6d1c560bfb4bbc95dd9b297f0d6fb87a7704577c
3
+ size 14270