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
7d328f6
·
verified ·
1 Parent(s): 9e3cd62

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. runs/Mar07_18-16-05_g05/events.out.tfevents.1709831765.g05.3355634.2 +2 -2
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.831814415907208
29
  - name: Recall
30
  type: recall
31
- value: 0.887709991158267
32
  - name: F1
33
  type: f1
34
- value: 0.8588537211291701
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9631523478668176
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: 0.1988
48
- - Precision: 0.8318
49
- - Recall: 0.8877
50
- - F1: 0.8589
51
- - Accuracy: 0.9632
52
 
53
  ## Model description
54
 
@@ -68,30 +68,30 @@ 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
  - lr_scheduler_warmup_ratio: 0.1
77
- - lr_scheduler_warmup_steps: 1000
78
- - num_epochs: 10
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
83
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
84
- | 1.0776 | 0.85 | 500 | 0.3123 | 0.5698 | 0.6799 | 0.6200 | 0.9204 |
85
- | 0.3031 | 1.7 | 1000 | 0.2037 | 0.7176 | 0.8143 | 0.7629 | 0.9474 |
86
- | 0.2204 | 2.56 | 1500 | 0.1951 | 0.7407 | 0.8400 | 0.7872 | 0.9496 |
87
- | 0.18 | 3.41 | 2000 | 0.1868 | 0.7400 | 0.8546 | 0.7932 | 0.9544 |
88
- | 0.1501 | 4.26 | 2500 | 0.1725 | 0.7852 | 0.8660 | 0.8236 | 0.9590 |
89
- | 0.1209 | 5.11 | 3000 | 0.1842 | 0.8026 | 0.8859 | 0.8422 | 0.9609 |
90
- | 0.1061 | 5.96 | 3500 | 0.1814 | 0.7875 | 0.8749 | 0.8289 | 0.9616 |
91
- | 0.0833 | 6.81 | 4000 | 0.1893 | 0.8163 | 0.8899 | 0.8515 | 0.9626 |
92
- | 0.0771 | 7.67 | 4500 | 0.1847 | 0.8244 | 0.8859 | 0.8540 | 0.9623 |
93
- | 0.0603 | 8.52 | 5000 | 0.1875 | 0.8297 | 0.8917 | 0.8596 | 0.9637 |
94
- | 0.0569 | 9.37 | 5500 | 0.1988 | 0.8318 | 0.8877 | 0.8589 | 0.9632 |
95
 
96
 
97
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.7681443703413103
29
  - name: Recall
30
  type: recall
31
+ value: 0.865605658709107
32
  - name: F1
33
  type: f1
34
+ value: 0.8139679900228644
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.959834497833639
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: 0.1868
48
+ - Precision: 0.7681
49
+ - Recall: 0.8656
50
+ - F1: 0.8140
51
+ - Accuracy: 0.9598
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 4
72
+ - eval_batch_size: 4
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: 5
79
 
80
  ### Training results
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
83
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
84
+ | 1.0063 | 0.43 | 500 | 0.2980 | 0.6364 | 0.7476 | 0.6875 | 0.9276 |
85
+ | 0.347 | 0.85 | 1000 | 0.2429 | 0.6877 | 0.8108 | 0.7442 | 0.9445 |
86
+ | 0.2611 | 1.28 | 1500 | 0.2480 | 0.6955 | 0.8280 | 0.7560 | 0.9466 |
87
+ | 0.2294 | 1.7 | 2000 | 0.2350 | 0.7126 | 0.8342 | 0.7686 | 0.9496 |
88
+ | 0.2058 | 2.13 | 2500 | 0.2064 | 0.6924 | 0.8139 | 0.7482 | 0.9507 |
89
+ | 0.1843 | 2.56 | 3000 | 0.1968 | 0.7509 | 0.8568 | 0.8003 | 0.9542 |
90
+ | 0.1693 | 2.98 | 3500 | 0.1890 | 0.7538 | 0.8364 | 0.7930 | 0.9573 |
91
+ | 0.1408 | 3.41 | 4000 | 0.2034 | 0.7270 | 0.8333 | 0.7765 | 0.9542 |
92
+ | 0.1441 | 3.83 | 4500 | 0.2004 | 0.7398 | 0.8599 | 0.7953 | 0.9569 |
93
+ | 0.1164 | 4.26 | 5000 | 0.1974 | 0.7588 | 0.8652 | 0.8085 | 0.9586 |
94
+ | 0.1131 | 4.68 | 5500 | 0.1868 | 0.7681 | 0.8656 | 0.8140 | 0.9598 |
95
 
96
 
97
  ### Framework versions
runs/Mar07_18-16-05_g05/events.out.tfevents.1709831765.g05.3355634.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb638fd279697f16c5dfbdf50bacb409bf4fc54b32fff8525f77fef2809d45ea
3
- size 12030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d16bc2036ac0c1c824689932ebc95a0f681730ac48eaf8b0dd060dcd0283d1
3
+ size 12384