Buseak commited on
Commit
0325739
1 Parent(s): 5a86d8b

End of training

Browse files
Files changed (2) hide show
  1. README.md +73 -0
  2. generation_config.json +6 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - bleu
6
+ model-index:
7
+ - name: spell_corrector_bert2bert_1809_v3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # spell_corrector_bert2bert_1809_v3
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0003
19
+ - Bleu: 65.6869
20
+ - Gen Len: 16.0563
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 15
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
50
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
51
+ | No log | 1.0 | 488 | 0.3069 | 51.7893 | 16.1497 |
52
+ | 0.9648 | 2.0 | 976 | 0.1273 | 60.1518 | 16.0477 |
53
+ | 0.4398 | 3.0 | 1464 | 0.0652 | 63.3763 | 16.0624 |
54
+ | 0.2445 | 4.0 | 1952 | 0.0458 | 64.0081 | 16.0741 |
55
+ | 0.1417 | 5.0 | 2440 | 0.0270 | 64.8793 | 16.057 |
56
+ | 0.0958 | 6.0 | 2928 | 0.0230 | 65.1021 | 16.0524 |
57
+ | 0.0667 | 7.0 | 3416 | 0.0152 | 65.3175 | 16.0559 |
58
+ | 0.051 | 8.0 | 3904 | 0.0123 | 65.4032 | 16.0619 |
59
+ | 0.0382 | 9.0 | 4392 | 0.0079 | 65.4965 | 16.0555 |
60
+ | 0.028 | 10.0 | 4880 | 0.0058 | 65.5698 | 16.0577 |
61
+ | 0.0192 | 11.0 | 5368 | 0.0036 | 65.6254 | 16.0565 |
62
+ | 0.0143 | 12.0 | 5856 | 0.0020 | 65.6452 | 16.0581 |
63
+ | 0.0109 | 13.0 | 6344 | 0.0009 | 65.679 | 16.0563 |
64
+ | 0.0075 | 14.0 | 6832 | 0.0004 | 65.6856 | 16.0563 |
65
+ | 0.0052 | 15.0 | 7320 | 0.0003 | 65.6869 | 16.0563 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.33.2
71
+ - Pytorch 2.0.1+cu118
72
+ - Datasets 2.14.5
73
+ - Tokenizers 0.13.3
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 2,
3
+ "eos_token_id": 3,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.33.2"
6
+ }