Hugging Face's logo

izaitova
/
herbert-large-cased_nli

Safetensors
bert
Generated from Trainer
Model card Files Community
izaitova commited on
Commit
d66658a
·
verified ·
1 Parent(s): b6ff684

End of training

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ base_model: allegro/herbert-large-cased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: herbert-large-cased_nli
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # herbert-large-cased_nli
17
+
18
+ This model is a fine-tuned version of [allegro/herbert-large-cased](https://huggingface.co/allegro/herbert-large-cased) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.0905
21
+ - Accuracy: 0.77
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 40
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | No log | 1.0 | 625 | 0.6466 | 0.751 |
55
+ | No log | 2.0 | 1250 | 0.5856 | 0.79 |
56
+ | 0.5915 | 3.0 | 1875 | 0.6142 | 0.761 |
57
+ | 0.5915 | 4.0 | 2500 | 0.6803 | 0.78 |
58
+ | 0.4204 | 5.0 | 3125 | 0.7207 | 0.786 |
59
+ | 0.4204 | 6.0 | 3750 | 0.7956 | 0.777 |
60
+ | 0.4204 | 7.0 | 4375 | 0.7964 | 0.787 |
61
+ | 0.306 | 8.0 | 5000 | 0.7869 | 0.766 |
62
+ | 0.306 | 9.0 | 5625 | 0.8671 | 0.766 |
63
+ | 0.2192 | 10.0 | 6250 | 0.8832 | 0.778 |
64
+ | 0.2192 | 11.0 | 6875 | 0.9147 | 0.768 |
65
+ | 0.1595 | 12.0 | 7500 | 1.1113 | 0.756 |
66
+ | 0.1595 | 13.0 | 8125 | 1.0984 | 0.761 |
67
+ | 0.1595 | 14.0 | 8750 | 1.3107 | 0.758 |
68
+ | 0.1288 | 15.0 | 9375 | 1.2892 | 0.764 |
69
+ | 0.1288 | 16.0 | 10000 | 1.5291 | 0.741 |
70
+ | 0.1037 | 17.0 | 10625 | 1.2105 | 0.786 |
71
+ | 0.1037 | 18.0 | 11250 | 1.3468 | 0.78 |
72
+ | 0.1037 | 19.0 | 11875 | 1.5642 | 0.758 |
73
+ | 0.0864 | 20.0 | 12500 | 1.5304 | 0.768 |
74
+ | 0.0864 | 21.0 | 13125 | 1.4310 | 0.776 |
75
+ | 0.0728 | 22.0 | 13750 | 1.5636 | 0.762 |
76
+ | 0.0728 | 23.0 | 14375 | 1.5032 | 0.766 |
77
+ | 0.0583 | 24.0 | 15000 | 1.7275 | 0.763 |
78
+ | 0.0583 | 25.0 | 15625 | 1.6669 | 0.758 |
79
+ | 0.0583 | 26.0 | 16250 | 1.6029 | 0.767 |
80
+ | 0.0453 | 27.0 | 16875 | 1.6239 | 0.771 |
81
+ | 0.0453 | 28.0 | 17500 | 1.6007 | 0.781 |
82
+ | 0.0335 | 29.0 | 18125 | 1.7028 | 0.766 |
83
+ | 0.0335 | 30.0 | 18750 | 1.8058 | 0.776 |
84
+ | 0.0335 | 31.0 | 19375 | 1.7894 | 0.766 |
85
+ | 0.0267 | 32.0 | 20000 | 1.8930 | 0.765 |
86
+ | 0.0267 | 33.0 | 20625 | 1.8582 | 0.775 |
87
+ | 0.022 | 34.0 | 21250 | 1.9610 | 0.764 |
88
+ | 0.022 | 35.0 | 21875 | 2.0128 | 0.775 |
89
+ | 0.0163 | 36.0 | 22500 | 2.0248 | 0.773 |
90
+ | 0.0163 | 37.0 | 23125 | 2.0203 | 0.77 |
91
+ | 0.0163 | 38.0 | 23750 | 2.0615 | 0.77 |
92
+ | 0.0115 | 39.0 | 24375 | 2.0787 | 0.769 |
93
+ | 0.0115 | 40.0 | 25000 | 2.0905 | 0.77 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.39.3
99
+ - Pytorch 1.11.0a0+17540c5
100
+ - Datasets 2.20.0
101
+ - Tokenizers 0.15.2