Hugging Face's logo

stulcrad
/
CNEC_2_0_robeczech-base

Token Classification
Transformers
Safetensors
Czech
roberta
Generated from Trainer
Eval Results
Model card Files
xet
Community
stulcrad commited on
Commit
a688651
·
verified ·
1 Parent(s): 6739de5

Model save

Browse files
Files changed (2) hide show
  1. README.md +25 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8365384615384616
29
  - name: Recall
30
  type: recall
31
- value: 0.871244635193133
32
  - name: F1
33
  type: f1
34
- value: 0.8535388927820603
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9514473176379776
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 [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.2519
48
- - Precision: 0.8365
49
- - Recall: 0.8712
50
- - F1: 0.8535
51
- - Accuracy: 0.9514
52
 
53
  ## Model description
54
 
@@ -68,28 +68,30 @@ More information needed
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: 25
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.8466 | 2.22 | 1000 | 0.6707 | 0.2808 | 0.2192 | 0.2462 | 0.8543 |
83
- | 0.4773 | 4.44 | 2000 | 0.4052 | 0.6754 | 0.6423 | 0.6585 | 0.9160 |
84
- | 0.3036 | 6.67 | 3000 | 0.3057 | 0.7601 | 0.7672 | 0.7636 | 0.9364 |
85
- | 0.2299 | 8.89 | 4000 | 0.2633 | 0.7982 | 0.8190 | 0.8085 | 0.9430 |
86
- | 0.1791 | 11.11 | 5000 | 0.2386 | 0.8195 | 0.8380 | 0.8286 | 0.9485 |
87
- | 0.1418 | 13.33 | 6000 | 0.2398 | 0.8268 | 0.8484 | 0.8374 | 0.9487 |
88
- | 0.1181 | 15.56 | 7000 | 0.2467 | 0.8259 | 0.8566 | 0.8409 | 0.9474 |
89
- | 0.1018 | 17.78 | 8000 | 0.2454 | 0.8359 | 0.8670 | 0.8511 | 0.9507 |
90
- | 0.09 | 20.0 | 9000 | 0.2507 | 0.8355 | 0.8702 | 0.8525 | 0.9514 |
91
- | 0.0821 | 22.22 | 10000 | 0.2511 | 0.8361 | 0.8702 | 0.8528 | 0.9518 |
92
- | 0.0753 | 24.44 | 11000 | 0.2519 | 0.8365 | 0.8712 | 0.8535 | 0.9514 |
 
 
93
 
94
 
95
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.853103448275862
29
  - name: Recall
30
  type: recall
31
+ value: 0.8848354792560801
32
  - name: F1
33
  type: f1
34
+ value: 0.8686797752808989
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.954457738324971
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 [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.3306
48
+ - Precision: 0.8531
49
+ - Recall: 0.8848
50
+ - F1: 0.8687
51
+ - Accuracy: 0.9545
52
 
53
  ## Model description
54
 
 
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: 30
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.4499 | 2.22 | 2000 | 0.3871 | 0.7163 | 0.7099 | 0.7131 | 0.9222 |
83
+ | 0.2342 | 4.44 | 4000 | 0.2576 | 0.8149 | 0.8251 | 0.8200 | 0.9451 |
84
+ | 0.1449 | 6.67 | 6000 | 0.2407 | 0.8231 | 0.8523 | 0.8375 | 0.9492 |
85
+ | 0.1027 | 8.89 | 8000 | 0.2267 | 0.8362 | 0.8748 | 0.8551 | 0.9527 |
86
+ | 0.0751 | 11.11 | 10000 | 0.2429 | 0.8394 | 0.8712 | 0.8550 | 0.9522 |
87
+ | 0.0473 | 13.33 | 12000 | 0.2633 | 0.8439 | 0.8720 | 0.8577 | 0.9535 |
88
+ | 0.0369 | 15.56 | 14000 | 0.2821 | 0.8468 | 0.8755 | 0.8609 | 0.9541 |
89
+ | 0.0286 | 17.78 | 16000 | 0.2797 | 0.8534 | 0.8827 | 0.8678 | 0.9558 |
90
+ | 0.0234 | 20.0 | 18000 | 0.2860 | 0.8550 | 0.8834 | 0.8690 | 0.9558 |
91
+ | 0.0168 | 22.22 | 20000 | 0.3146 | 0.8471 | 0.8795 | 0.8630 | 0.9531 |
92
+ | 0.0142 | 24.44 | 22000 | 0.3165 | 0.8488 | 0.8816 | 0.8649 | 0.9530 |
93
+ | 0.011 | 26.67 | 24000 | 0.3291 | 0.8518 | 0.8816 | 0.8664 | 0.9537 |
94
+ | 0.0092 | 28.89 | 26000 | 0.3306 | 0.8531 | 0.8848 | 0.8687 | 0.9545 |
95
 
96
 
97
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d929b230551f136eed99a4b2e3a10c137c707af9e596418e8333fb6a54d45440
3
  size 501850868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaee998440ba7d7c2e33cdeef3176ef85945913d1944744319b86d4be11b6503
3
  size 501850868