Hugging Face's logo

aiface
/
bart-large-mnli_nli

Text Classification
Transformers
Safetensors
bart
Generated from Trainer
Model card Files
xet
Community
aiface commited on
Commit
a117045
·
verified ·
1 Parent(s): e5d61d9

Model save

Browse files
Files changed (5) hide show
  1. README.md +88 -0
  2. classification_report_test.txt +14 -0
  3. confusion_matrix_test.csv +4 -0
  4. model.safetensors +1 -1
  5. model_predict.csv +0 -0
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: facebook/bart-large-mnli
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: bart-large-mnli_nli
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # bart-large-mnli_nli
18
+
19
+ This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 3.1748
22
+ - Accuracy: 0.6146
23
+ - Precision Macro: 0.6164
24
+ - Recall Macro: 0.6143
25
+ - F1 Macro: 0.6144
26
+ - F1 Weighted: 0.6145
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 64
47
+ - eval_batch_size: 64
48
+ - seed: 42
49
+ - gradient_accumulation_steps: 2
50
+ - total_train_batch_size: 128
51
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 20
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision Macro | Recall Macro | F1 Macro | F1 Weighted |
60
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:-----------:|
61
+ | 0.9341 | 1.0 | 143 | 0.9033 | 0.5916 | 0.6003 | 0.5914 | 0.5927 | 0.5926 |
62
+ | 0.858 | 2.0 | 286 | 0.9499 | 0.5477 | 0.6120 | 0.5459 | 0.5366 | 0.5368 |
63
+ | 0.8298 | 3.0 | 429 | 0.9050 | 0.5849 | 0.5995 | 0.5868 | 0.5782 | 0.5775 |
64
+ | 0.7423 | 4.0 | 572 | 0.9457 | 0.6027 | 0.6128 | 0.6037 | 0.5964 | 0.5959 |
65
+ | 0.6525 | 5.0 | 715 | 0.9301 | 0.6009 | 0.6127 | 0.6002 | 0.6008 | 0.6008 |
66
+ | 0.5548 | 6.0 | 858 | 1.0490 | 0.6200 | 0.6258 | 0.6209 | 0.6164 | 0.6159 |
67
+ | 0.4609 | 7.0 | 1001 | 1.0379 | 0.6137 | 0.6159 | 0.6144 | 0.6131 | 0.6129 |
68
+ | 0.3427 | 8.0 | 1144 | 1.1565 | 0.6018 | 0.6050 | 0.6013 | 0.6017 | 0.6017 |
69
+ | 0.2528 | 9.0 | 1287 | 1.3466 | 0.5809 | 0.5906 | 0.5801 | 0.5788 | 0.5790 |
70
+ | 0.1635 | 10.0 | 1430 | 1.5895 | 0.6111 | 0.6163 | 0.6121 | 0.6090 | 0.6087 |
71
+ | 0.1308 | 11.0 | 1573 | 1.7222 | 0.6106 | 0.6118 | 0.6111 | 0.6104 | 0.6103 |
72
+ | 0.0883 | 12.0 | 1716 | 2.1606 | 0.6027 | 0.6052 | 0.6022 | 0.6019 | 0.6020 |
73
+ | 0.057 | 13.0 | 1859 | 2.2558 | 0.6093 | 0.6101 | 0.6093 | 0.6088 | 0.6087 |
74
+ | 0.0431 | 14.0 | 2002 | 2.4892 | 0.6169 | 0.6173 | 0.6168 | 0.6168 | 0.6168 |
75
+ | 0.0246 | 15.0 | 2145 | 2.8257 | 0.6155 | 0.6178 | 0.6153 | 0.6147 | 0.6147 |
76
+ | 0.0144 | 16.0 | 2288 | 2.8977 | 0.6169 | 0.6172 | 0.6168 | 0.6168 | 0.6168 |
77
+ | 0.0116 | 17.0 | 2431 | 3.0826 | 0.6173 | 0.6202 | 0.6170 | 0.6175 | 0.6175 |
78
+ | 0.0071 | 18.0 | 2574 | 3.1267 | 0.6164 | 0.6186 | 0.6160 | 0.6163 | 0.6163 |
79
+ | 0.0019 | 19.0 | 2717 | 3.1718 | 0.6142 | 0.6161 | 0.6138 | 0.6139 | 0.6140 |
80
+ | 0.0033 | 20.0 | 2860 | 3.1748 | 0.6146 | 0.6164 | 0.6143 | 0.6144 | 0.6145 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.55.0
86
+ - Pytorch 2.7.0+cu126
87
+ - Datasets 4.0.0
88
+ - Tokenizers 0.21.4
classification_report_test.txt ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ entailment 0.64 0.60 0.62 750
4
+ contradiction 0.56 0.63 0.60 737
5
+ neutral 0.67 0.63 0.65 777
6
+
7
+ accuracy 0.62 2264
8
+ macro avg 0.62 0.62 0.62 2264
9
+ weighted avg 0.63 0.62 0.62 2264
10
+
11
+ Confusion matrix:
12
+ [[451 188 111]
13
+ [139 467 131]
14
+ [115 172 490]]
confusion_matrix_test.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ ,entailment,contradiction,neutral
2
+ entailment,451,188,111
3
+ contradiction,139,467,131
4
+ neutral,115,172,490
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3623c0a6ef699b9243655431599225b3ba6115ae2f6a49463205925fad02e57e
3
  size 1629436964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d61c807f3e9d4ea350d12487a6d7df59aef9787bdea9e0428912d54f2210ede
3
  size 1629436964
model_predict.csv ADDED
The diff for this file is too large to render. See raw diff