Hugging Face's logo

Theoreticallyhugo
/
bert-ner-essays-classify_span

Text Classification
Transformers
PyTorch
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
Theoreticallyhugo commited on
Commit
50298c5
·
1 Parent(s): 2e3cdb1

trainer: training complete at 2023-11-14 13:31:47.312072.

Browse files
Files changed (1) hide show
  1. README.md +12 -11
README.md CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
3
  base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: bert-ner-essays-classify_span
8
  results: []
@@ -16,13 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
16
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
  - Loss: 0.6951
19
- - Ajorclaim: {'precision': 0.5098039215686274, 'recall': 0.4, 'f1': 0.4482758620689655, 'number': 65}
20
- - Laim: {'precision': 0.29545454545454547, 'recall': 0.23008849557522124, 'f1': 0.2587064676616916, 'number': 113}
21
- - Remise: {'precision': 0.23140495867768596, 'recall': 0.20588235294117646, 'f1': 0.2178988326848249, 'number': 136}
22
- - Overall Precision: 0.3077
23
- - Overall Recall: 0.2548
24
- - Overall F1: 0.2787
25
- - Overall Accuracy: 0.7077
26
 
27
  ## Model description
28
 
@@ -51,10 +52,10 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Ajorclaim | Laim | Remise | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
55
- |:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
56
- | No log | 1.0 | 267 | 0.7245 | {'precision': 0.5, 'recall': 0.2153846153846154, 'f1': 0.3010752688172043, 'number': 65} | {'precision': 0.1794871794871795, 'recall': 0.061946902654867256, 'f1': 0.09210526315789473, 'number': 113} | {'precision': 0.15625, 'recall': 0.07352941176470588, 'f1': 0.1, 'number': 136} | 0.2366 | 0.0987 | 0.1393 | 0.6650 |
57
- | 0.7275 | 2.0 | 534 | 0.6951 | {'precision': 0.5098039215686274, 'recall': 0.4, 'f1': 0.4482758620689655, 'number': 65} | {'precision': 0.29545454545454547, 'recall': 0.23008849557522124, 'f1': 0.2587064676616916, 'number': 113} | {'precision': 0.23140495867768596, 'recall': 0.20588235294117646, 'f1': 0.2178988326848249, 'number': 136} | 0.3077 | 0.2548 | 0.2787 | 0.7077 |
58
 
59
 
60
  ### Framework versions
 
3
  base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
  model-index:
9
  - name: bert-ner-essays-classify_span
10
  results: []
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.6951
21
+ - Claim: {'precision': 0.4811320754716981, 'recall': 0.3541666666666667, 'f1-score': 0.408, 'support': 144.0}
22
+ - Majorclaim: {'precision': 0.625, 'recall': 0.4861111111111111, 'f1-score': 0.5468749999999999, 'support': 72.0}
23
+ - Premise: {'precision': 0.7718120805369127, 'recall': 0.8778625954198473, 'f1-score': 0.8214285714285714, 'support': 393.0}
24
+ - Accuracy: 0.7077
25
+ - Macro avg: {'precision': 0.6259813853362036, 'recall': 0.5727134577325418, 'f1-score': 0.5921011904761905, 'support': 609.0}
26
+ - Weighted avg: {'precision': 0.6857227693250102, 'recall': 0.7077175697865353, 'f1-score': 0.6912125263898662, 'support': 609.0}
 
27
 
28
  ## Model description
29
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Claim | Majorclaim | Premise | Accuracy | Macro avg | Weighted avg |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------:|:--------:|:-----------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------:|
57
+ | No log | 1.0 | 267 | 0.7245 | {'precision': 0.35714285714285715, 'recall': 0.10416666666666667, 'f1-score': 0.16129032258064516, 'support': 144.0} | {'precision': 0.5806451612903226, 'recall': 0.25, 'f1-score': 0.34951456310679613, 'support': 72.0} | {'precision': 0.6940298507462687, 'recall': 0.9465648854961832, 'f1-score': 0.8008611410118407, 'support': 393.0} | 0.6650 | {'precision': 0.5439392897264828, 'recall': 0.4335771840542833, 'f1-score': 0.4372220088997607, 'support': 609.0} | {'precision': 0.6009667559684043, 'recall': 0.6650246305418719, 'f1-score': 0.5962714013349024, 'support': 609.0} |
58
+ | 0.7275 | 2.0 | 534 | 0.6951 | {'precision': 0.4811320754716981, 'recall': 0.3541666666666667, 'f1-score': 0.408, 'support': 144.0} | {'precision': 0.625, 'recall': 0.4861111111111111, 'f1-score': 0.5468749999999999, 'support': 72.0} | {'precision': 0.7718120805369127, 'recall': 0.8778625954198473, 'f1-score': 0.8214285714285714, 'support': 393.0} | 0.7077 | {'precision': 0.6259813853362036, 'recall': 0.5727134577325418, 'f1-score': 0.5921011904761905, 'support': 609.0} | {'precision': 0.6857227693250102, 'recall': 0.7077175697865353, 'f1-score': 0.6912125263898662, 'support': 609.0} |
59
 
60
 
61
  ### Framework versions