muhtasham commited on
Commit
41ffd0e
·
1 Parent(s): 24f2c6b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - precision
6
+ - recall
7
+ - f1
8
+ - accuracy
9
+ model-index:
10
+ - name: tiny-mlm-wikitext-from-scratch-custom-tokenizer-target-conll2003
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
+ # tiny-mlm-wikitext-from-scratch-custom-tokenizer-target-conll2003
18
+
19
+ This model is a fine-tuned version of [muhtasham/tiny-mlm-wikitext-from-scratch-custom-tokenizer](https://huggingface.co/muhtasham/tiny-mlm-wikitext-from-scratch-custom-tokenizer) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.3451
22
+ - Precision: 0.3914
23
+ - Recall: 0.5631
24
+ - F1: 0.4618
25
+ - Accuracy: 0.8978
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 3e-05
45
+ - train_batch_size: 32
46
+ - eval_batch_size: 32
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: constant
50
+ - training_steps: 5000
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
56
+ | 1.0009 | 1.14 | 500 | 0.6888 | 0.1156 | 0.1160 | 0.1158 | 0.8144 |
57
+ | 0.6084 | 2.28 | 1000 | 0.5797 | 0.2110 | 0.2735 | 0.2382 | 0.8417 |
58
+ | 0.5231 | 3.42 | 1500 | 0.5113 | 0.2567 | 0.3295 | 0.2886 | 0.8560 |
59
+ | 0.4552 | 4.56 | 2000 | 0.4575 | 0.2947 | 0.4061 | 0.3415 | 0.8701 |
60
+ | 0.4 | 5.69 | 2500 | 0.4172 | 0.3182 | 0.4615 | 0.3767 | 0.8802 |
61
+ | 0.3587 | 6.83 | 3000 | 0.3915 | 0.3378 | 0.4921 | 0.4006 | 0.8871 |
62
+ | 0.3263 | 7.97 | 3500 | 0.3719 | 0.3638 | 0.5296 | 0.4313 | 0.8918 |
63
+ | 0.2975 | 9.11 | 4000 | 0.3605 | 0.3687 | 0.5411 | 0.4385 | 0.8939 |
64
+ | 0.2748 | 10.25 | 4500 | 0.3509 | 0.3868 | 0.5471 | 0.4532 | 0.8969 |
65
+ | 0.2602 | 11.39 | 5000 | 0.3451 | 0.3914 | 0.5631 | 0.4618 | 0.8978 |
66
+
67
+
68
+ ### Framework versions
69
+
70
+ - Transformers 4.26.0.dev0
71
+ - Pytorch 1.13.1+cu116
72
+ - Datasets 2.8.1.dev0
73
+ - Tokenizers 0.13.2