Hugging Face's logo

stulcrad
/
CNEC2_0_extended_xlm-roberta-large

Token Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
cf612ee
·
verified ·
1 Parent(s): 8fc7bbe

Model save

Browse files
Files changed (1) hide show
  1. README.md +29 -22
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8721153846153846
29
  - name: Recall
30
  type: recall
31
- value: 0.9002481389578164
32
  - name: F1
33
  type: f1
34
- value: 0.8859584859584859
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9766100702576113
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: 0.1464
48
- - Precision: 0.8721
49
- - Recall: 0.9002
50
- - F1: 0.8860
51
- - Accuracy: 0.9766
52
 
53
  ## Model description
54
 
@@ -73,22 +73,29 @@ 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: 12
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.2193 | 1.12 | 1000 | 0.1389 | 0.7636 | 0.8194 | 0.7905 | 0.9628 |
83
- | 0.1528 | 2.24 | 2000 | 0.1285 | 0.8106 | 0.8600 | 0.8346 | 0.9678 |
84
- | 0.119 | 3.36 | 3000 | 0.1278 | 0.8234 | 0.8491 | 0.8361 | 0.9679 |
85
- | 0.0904 | 4.48 | 4000 | 0.1104 | 0.8466 | 0.8680 | 0.8571 | 0.9747 |
86
- | 0.0768 | 5.6 | 5000 | 0.1269 | 0.8486 | 0.8819 | 0.8649 | 0.9734 |
87
- | 0.0709 | 6.72 | 6000 | 0.1293 | 0.8601 | 0.8878 | 0.8737 | 0.9759 |
88
- | 0.0586 | 7.84 | 7000 | 0.1404 | 0.8624 | 0.8928 | 0.8773 | 0.9753 |
89
- | 0.0486 | 8.96 | 8000 | 0.1445 | 0.8675 | 0.9002 | 0.8836 | 0.9766 |
90
- | 0.0488 | 10.08 | 9000 | 0.1467 | 0.8608 | 0.8963 | 0.8782 | 0.9753 |
91
- | 0.035 | 11.2 | 10000 | 0.1464 | 0.8721 | 0.9002 | 0.8860 | 0.9766 |
 
 
 
 
 
 
 
92
 
93
 
94
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8543457497612226
29
  - name: Recall
30
  type: recall
31
+ value: 0.8878411910669975
32
  - name: F1
33
  type: f1
34
+ value: 0.8707714772450719
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9749707259953162
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: 0.1492
48
+ - Precision: 0.8543
49
+ - Recall: 0.8878
50
+ - F1: 0.8708
51
+ - Accuracy: 0.9750
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
+ | 0.4615 | 0.56 | 500 | 0.1970 | 0.6988 | 0.7057 | 0.7022 | 0.9497 |
83
+ | 0.2127 | 1.12 | 1000 | 0.1455 | 0.7812 | 0.8238 | 0.8019 | 0.9626 |
84
+ | 0.1765 | 1.68 | 1500 | 0.1284 | 0.8042 | 0.8357 | 0.8197 | 0.9674 |
85
+ | 0.149 | 2.24 | 2000 | 0.1307 | 0.8250 | 0.8541 | 0.8393 | 0.9698 |
86
+ | 0.1286 | 2.8 | 2500 | 0.1214 | 0.8178 | 0.8600 | 0.8384 | 0.9717 |
87
+ | 0.1172 | 3.36 | 3000 | 0.1271 | 0.8285 | 0.8536 | 0.8409 | 0.9716 |
88
+ | 0.1115 | 3.92 | 3500 | 0.1290 | 0.8305 | 0.8586 | 0.8443 | 0.9726 |
89
+ | 0.0978 | 4.48 | 4000 | 0.1251 | 0.8321 | 0.8630 | 0.8473 | 0.9736 |
90
+ | 0.0907 | 5.04 | 4500 | 0.1301 | 0.8417 | 0.8710 | 0.8561 | 0.9742 |
91
+ | 0.0812 | 5.6 | 5000 | 0.1235 | 0.8365 | 0.8630 | 0.8495 | 0.9721 |
92
+ | 0.0755 | 6.16 | 5500 | 0.1269 | 0.8201 | 0.8685 | 0.8436 | 0.9727 |
93
+ | 0.0647 | 6.72 | 6000 | 0.1325 | 0.8490 | 0.8789 | 0.8637 | 0.9742 |
94
+ | 0.0589 | 7.28 | 6500 | 0.1373 | 0.8529 | 0.8774 | 0.8650 | 0.9746 |
95
+ | 0.0559 | 7.84 | 7000 | 0.1419 | 0.8463 | 0.8824 | 0.8639 | 0.9747 |
96
+ | 0.0549 | 8.4 | 7500 | 0.1400 | 0.8444 | 0.8834 | 0.8634 | 0.9745 |
97
+ | 0.0479 | 8.96 | 8000 | 0.1462 | 0.8530 | 0.8844 | 0.8684 | 0.9752 |
98
+ | 0.0462 | 9.52 | 8500 | 0.1492 | 0.8543 | 0.8878 | 0.8708 | 0.9750 |
99
 
100
 
101
  ### Framework versions