Hugging Face's logo

DanielNRU
/
pollen-ner2-1950

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
 Community
DanielNRU commited on
Commit
2bfff38
·
verified ·
1 Parent(s): f41552a

Model save

Browse files
Files changed (1) hide show
  1. README.md +12 -14
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: DeepPavlov/rubert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -8,21 +8,21 @@ metrics:
8
  - recall
9
  - f1
10
  model-index:
11
- - name: pollen-ner-1950
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # pollen-ner-1950
19
 
20
- This model is a fine-tuned version of [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.1418
23
- - Precision: 0.8904
24
- - Recall: 0.9297
25
- - F1: 0.9096
26
 
27
  ## Model description
28
 
@@ -53,12 +53,10 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
55
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
56
- | No log | 1.0 | 244 | 0.1403 | 0.8831 | 0.9257 | 0.9039 |
57
- | No log | 2.0 | 488 | 0.1444 | 0.8838 | 0.9317 | 0.9071 |
58
- | 0.1561 | 3.0 | 732 | 0.1403 | 0.8834 | 0.9277 | 0.9050 |
59
- | 0.1561 | 4.0 | 976 | 0.1418 | 0.8904 | 0.9297 | 0.9096 |
60
- | 0.1523 | 5.0 | 1220 | 0.1430 | 0.88 | 0.9277 | 0.9032 |
61
- | 0.1523 | 6.0 | 1464 | 0.1391 | 0.8868 | 0.9277 | 0.9068 |
62
 
63
 
64
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
+ base_model: DeepPavlov/bert-base-bg-cs-pl-ru-cased
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
8
  - recall
9
  - f1
10
  model-index:
11
+ - name: pollen-ner2-1950
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ # pollen-ner2-1950
19
 
20
+ This model is a fine-tuned version of [DeepPavlov/bert-base-bg-cs-pl-ru-cased](https://huggingface.co/DeepPavlov/bert-base-bg-cs-pl-ru-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.1604
23
+ - Precision: 0.8460
24
+ - Recall: 0.8936
25
+ - F1: 0.8691
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
55
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
56
+ | No log | 1.0 | 244 | 0.1742 | 0.8165 | 0.8936 | 0.8533 |
57
+ | No log | 2.0 | 488 | 0.1641 | 0.8405 | 0.8996 | 0.8691 |
58
+ | 0.2384 | 3.0 | 732 | 0.1700 | 0.8259 | 0.8956 | 0.8593 |
59
+ | 0.2384 | 4.0 | 976 | 0.1604 | 0.8460 | 0.8936 | 0.8691 |
 
 
60
 
61
 
62
  ### Framework versions