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
3fa8656
·
verified ·
1 Parent(s): e9a3ab8

Model save

Browse files
Files changed (2) hide show
  1. README.md +21 -24
  2. runs/Mar05_20-39-32_n21/events.out.tfevents.1709667575.n21.1799025.0 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8290241868223519
29
  - name: Recall
30
  type: recall
31
- value: 0.8918797667115298
32
  - name: F1
33
  type: f1
34
- value: 0.859304084720121
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9619032749131504
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: 0.2393
48
- - Precision: 0.8290
49
- - Recall: 0.8919
50
- - F1: 0.8593
51
- - Accuracy: 0.9619
52
 
53
  ## Model description
54
 
@@ -67,29 +67,26 @@ More information needed
67
  ### Training hyperparameters
68
 
69
  The following hyperparameters were used during training:
70
- - learning_rate: 5e-05
71
- - train_batch_size: 8
72
- - eval_batch_size: 8
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
- | 0.5114 | 0.85 | 500 | 0.2247 | 0.7072 | 0.8107 | 0.7554 | 0.9415 |
83
- | 0.2786 | 1.7 | 1000 | 0.2415 | 0.7177 | 0.8439 | 0.7757 | 0.9397 |
84
- | 0.2089 | 2.56 | 1500 | 0.2379 | 0.7460 | 0.8461 | 0.7929 | 0.9453 |
85
- | 0.1777 | 3.41 | 2000 | 0.2023 | 0.7842 | 0.8690 | 0.8244 | 0.9496 |
86
- | 0.1492 | 4.26 | 2500 | 0.1994 | 0.7827 | 0.8708 | 0.8244 | 0.9535 |
87
- | 0.1166 | 5.11 | 3000 | 0.2037 | 0.7966 | 0.8748 | 0.8339 | 0.9548 |
88
- | 0.1022 | 5.96 | 3500 | 0.2032 | 0.8114 | 0.8645 | 0.8371 | 0.9549 |
89
- | 0.0786 | 6.81 | 4000 | 0.2216 | 0.8068 | 0.8883 | 0.8456 | 0.9585 |
90
- | 0.0683 | 7.67 | 4500 | 0.2249 | 0.8103 | 0.8775 | 0.8426 | 0.9593 |
91
- | 0.0491 | 8.52 | 5000 | 0.2224 | 0.8288 | 0.8838 | 0.8554 | 0.9622 |
92
- | 0.0435 | 9.37 | 5500 | 0.2393 | 0.8290 | 0.8919 | 0.8593 | 0.9619 |
93
 
94
 
95
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8294412010008341
29
  - name: Recall
30
  type: recall
31
+ value: 0.892328398384926
32
  - name: F1
33
  type: f1
34
+ value: 0.8597363302355738
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9629571802178071
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: 0.2118
48
+ - Precision: 0.8294
49
+ - Recall: 0.8923
50
+ - F1: 0.8597
51
+ - Accuracy: 0.9630
52
 
53
  ## Model description
54
 
 
67
  ### Training hyperparameters
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: 15
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4103 | 1.7 | 500 | 0.1933 | 0.7270 | 0.8528 | 0.7849 | 0.9513 |
83
+ | 0.1838 | 3.4 | 1000 | 0.1799 | 0.7559 | 0.8573 | 0.8034 | 0.9573 |
84
+ | 0.1312 | 5.1 | 1500 | 0.1710 | 0.7855 | 0.8739 | 0.8274 | 0.9589 |
85
+ | 0.0949 | 6.8 | 2000 | 0.1782 | 0.7917 | 0.8766 | 0.8320 | 0.9605 |
86
+ | 0.0746 | 8.5 | 2500 | 0.1810 | 0.8027 | 0.8762 | 0.8378 | 0.9603 |
87
+ | 0.057 | 10.2 | 3000 | 0.2066 | 0.8277 | 0.8878 | 0.8567 | 0.9630 |
88
+ | 0.0474 | 11.9 | 3500 | 0.2138 | 0.8169 | 0.8905 | 0.8521 | 0.9612 |
89
+ | 0.0365 | 13.61 | 4000 | 0.2118 | 0.8294 | 0.8923 | 0.8597 | 0.9630 |
 
 
 
90
 
91
 
92
  ### Framework versions
runs/Mar05_20-39-32_n21/events.out.tfevents.1709667575.n21.1799025.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b1be4a007c8b93da6fc63275578f06d4dc634e35640d9fe34f58a6075180916
3
- size 10142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5aa60279539ebcf4c3ce5dcc05fc346b83a26127e3b6d18ab2ef42fd22b2af
3
+ size 10496