Hugging Face's logo

stulcrad
/
CNEC2_0_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
4849ff3
•
1 Parent(s): c0afc96

Model save

Browse files
Files changed (3) hide show
  1. README.md +20 -25
  2. model.safetensors +1 -1
  3. runs/Mar06_16-56-24_n32/events.out.tfevents.1709740585.n32.1455937.2 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8299725022914757
29
  - name: Recall
30
  type: recall
31
- value: 0.874034749034749
32
  - name: F1
33
  type: f1
34
- value: 0.8514339445228021
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9687092568448501
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: 0.1727
48
- - Precision: 0.8300
49
- - Recall: 0.8740
50
- - F1: 0.8514
51
- - Accuracy: 0.9687
52
 
53
  ## Model description
54
 
@@ -68,31 +68,26 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-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: 8
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.3664 | 0.56 | 500 | 0.1708 | 0.6886 | 0.8132 | 0.7457 | 0.9536 |
83
- | 0.1841 | 1.11 | 1000 | 0.1512 | 0.7474 | 0.8470 | 0.7941 | 0.9631 |
84
- | 0.1528 | 1.67 | 1500 | 0.1650 | 0.7530 | 0.8181 | 0.7842 | 0.9612 |
85
- | 0.1313 | 2.22 | 2000 | 0.1598 | 0.7809 | 0.8687 | 0.8225 | 0.9656 |
86
- | 0.1094 | 2.78 | 2500 | 0.1421 | 0.7791 | 0.8475 | 0.8118 | 0.9636 |
87
- | 0.0897 | 3.33 | 3000 | 0.1395 | 0.7958 | 0.8634 | 0.8282 | 0.9669 |
88
- | 0.0864 | 3.89 | 3500 | 0.1454 | 0.7897 | 0.8789 | 0.8319 | 0.9664 |
89
- | 0.0674 | 4.44 | 4000 | 0.1524 | 0.8174 | 0.8663 | 0.8411 | 0.9675 |
90
- | 0.0689 | 5.0 | 4500 | 0.1475 | 0.8178 | 0.8687 | 0.8425 | 0.9674 |
91
- | 0.05 | 5.56 | 5000 | 0.1628 | 0.8257 | 0.8731 | 0.8487 | 0.9676 |
92
- | 0.0521 | 6.11 | 5500 | 0.1614 | 0.8257 | 0.8644 | 0.8446 | 0.9668 |
93
- | 0.0409 | 6.67 | 6000 | 0.1648 | 0.8258 | 0.8740 | 0.8492 | 0.9681 |
94
- | 0.0345 | 7.22 | 6500 | 0.1684 | 0.8295 | 0.8711 | 0.8498 | 0.9682 |
95
- | 0.0302 | 7.78 | 7000 | 0.1727 | 0.8300 | 0.8740 | 0.8514 | 0.9687 |
96
 
97
 
98
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.82387923147301
29
  - name: Recall
30
  type: recall
31
+ value: 0.8692084942084942
32
  - name: F1
33
  type: f1
34
+ value: 0.8459370596524189
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9673185571490657
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: 0.1697
48
+ - Precision: 0.8239
49
+ - Recall: 0.8692
50
+ - F1: 0.8459
51
+ - Accuracy: 0.9673
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
+ - lr_scheduler_warmup_ratio: 0.1
77
+ - lr_scheduler_warmup_steps: 500
78
  - num_epochs: 8
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
83
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
84
+ | 0.7425 | 1.11 | 500 | 0.1666 | 0.6549 | 0.7814 | 0.7126 | 0.9549 |
85
+ | 0.1416 | 2.22 | 1000 | 0.1419 | 0.7585 | 0.8567 | 0.8046 | 0.9628 |
86
+ | 0.0883 | 3.33 | 1500 | 0.1513 | 0.8017 | 0.8644 | 0.8319 | 0.9657 |
87
+ | 0.06 | 4.44 | 2000 | 0.1414 | 0.8151 | 0.8552 | 0.8347 | 0.9669 |
88
+ | 0.0433 | 5.56 | 2500 | 0.1518 | 0.8121 | 0.8533 | 0.8322 | 0.9667 |
89
+ | 0.0262 | 6.67 | 3000 | 0.1580 | 0.8236 | 0.8697 | 0.8460 | 0.9684 |
90
+ | 0.0175 | 7.78 | 3500 | 0.1697 | 0.8239 | 0.8692 | 0.8459 | 0.9673 |
 
 
 
 
 
 
 
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cd7c1c4f0fd632bd1d2c646bf2a80de85405737972aacb7a2f318ce8fffab72
3
  size 2235481556
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4c06c783fdec2a49582224faa00d7500c6af54c347f1f272d8a52aa6fea0f4
3
  size 2235481556
runs/Mar06_16-56-24_n32/events.out.tfevents.1709740585.n32.1455937.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b153036b7804890f76b20d62170cdbe5c345b9ffe56e4e10959c7df1a71daab3
3
- size 9386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb72e48d1bb128a8d03b8641f4b9124c7346cf0c8cfea7b4eccb2ee387cb1dc9
3
+ size 9740