Hugging Face's logo

juancopi81
/
js-fake-bach-epochs50

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
juancopi81 commited on
Commit
e3eb0ae
•
1 Parent(s): 034577e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: js-fake-bach-epochs50
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # js-fake-bach-epochs50
16
+
17
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.9888
20
+ - Accuracy: 0.0005
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: 0.0006058454513356471
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 32
42
+ - seed: 1
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_ratio: 0.01
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 1.3512 | 1.25 | 315 | 0.8371 | 0.0003 |
53
+ | 0.8149 | 2.51 | 630 | 0.7684 | 0.0006 |
54
+ | 0.7601 | 3.76 | 945 | 0.7187 | 0.0004 |
55
+ | 0.7186 | 5.02 | 1260 | 0.6903 | 0.0002 |
56
+ | 0.679 | 6.27 | 1575 | 0.6563 | 0.0005 |
57
+ | 0.6419 | 7.53 | 1890 | 0.6292 | 0.0001 |
58
+ | 0.6073 | 8.78 | 2205 | 0.5949 | 0.0006 |
59
+ | 0.575 | 10.04 | 2520 | 0.5828 | 0.0001 |
60
+ | 0.5425 | 11.29 | 2835 | 0.5696 | 0.0003 |
61
+ | 0.5174 | 12.55 | 3150 | 0.5609 | 0.0007 |
62
+ | 0.4933 | 13.8 | 3465 | 0.5576 | 0.0004 |
63
+ | 0.4696 | 15.06 | 3780 | 0.5661 | 0.0002 |
64
+ | 0.4423 | 16.31 | 4095 | 0.5708 | 0.0007 |
65
+ | 0.4196 | 17.57 | 4410 | 0.5780 | 0.0006 |
66
+ | 0.398 | 18.82 | 4725 | 0.5820 | 0.0009 |
67
+ | 0.374 | 20.08 | 5040 | 0.6099 | 0.0003 |
68
+ | 0.3452 | 21.33 | 5355 | 0.6230 | 0.0006 |
69
+ | 0.3256 | 22.59 | 5670 | 0.6386 | 0.0005 |
70
+ | 0.3047 | 23.84 | 5985 | 0.6462 | 0.0003 |
71
+ | 0.2812 | 25.1 | 6300 | 0.6789 | 0.0003 |
72
+ | 0.2582 | 26.35 | 6615 | 0.7053 | 0.0007 |
73
+ | 0.2406 | 27.61 | 6930 | 0.7199 | 0.0006 |
74
+ | 0.2237 | 28.86 | 7245 | 0.7399 | 0.0006 |
75
+ | 0.204 | 30.12 | 7560 | 0.7729 | 0.0006 |
76
+ | 0.1873 | 31.37 | 7875 | 0.7960 | 0.0004 |
77
+ | 0.1725 | 32.63 | 8190 | 0.8231 | 0.0005 |
78
+ | 0.1609 | 33.88 | 8505 | 0.8493 | 0.0004 |
79
+ | 0.1479 | 35.14 | 8820 | 0.8707 | 0.0003 |
80
+ | 0.1361 | 36.39 | 9135 | 0.8931 | 0.0003 |
81
+ | 0.1273 | 37.65 | 9450 | 0.9095 | 0.0003 |
82
+ | 0.12 | 38.9 | 9765 | 0.9339 | 0.0005 |
83
+ | 0.1129 | 40.16 | 10080 | 0.9444 | 0.0004 |
84
+ | 0.1062 | 41.41 | 10395 | 0.9626 | 0.0006 |
85
+ | 0.1027 | 42.67 | 10710 | 0.9669 | 0.0006 |
86
+ | 0.0994 | 43.92 | 11025 | 0.9713 | 0.0005 |
87
+ | 0.0955 | 45.18 | 11340 | 0.9830 | 0.0005 |
88
+ | 0.0939 | 46.43 | 11655 | 0.9855 | 0.0005 |
89
+ | 0.0924 | 47.69 | 11970 | 0.9884 | 0.0005 |
90
+ | 0.0916 | 48.94 | 12285 | 0.9888 | 0.0005 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.29.1
96
+ - Pytorch 2.0.0+cu118
97
+ - Datasets 2.12.0
98
+ - Tokenizers 0.13.3