Hugging Face's logo

NasimB
/
gpt2_left_out_gutenberg

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
1
NasimB commited on
Commit
ef62ee8
·
1 Parent(s): c6f3b6e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - generator
7
+ model-index:
8
+ - name: gpt2_left_out_gutenberg
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
+ # gpt2_left_out_gutenberg
16
+
17
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.9287
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0005
39
+ - train_batch_size: 64
40
+ - eval_batch_size: 64
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - lr_scheduler_warmup_steps: 1000
45
+ - num_epochs: 10
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 5.8917 | 0.26 | 500 | 5.0150 |
53
+ | 4.6559 | 0.53 | 1000 | 4.6338 |
54
+ | 4.3512 | 0.79 | 1500 | 4.4091 |
55
+ | 4.1461 | 1.06 | 2000 | 4.2691 |
56
+ | 3.9654 | 1.32 | 2500 | 4.1719 |
57
+ | 3.8972 | 1.59 | 3000 | 4.0869 |
58
+ | 3.8271 | 1.85 | 3500 | 4.0113 |
59
+ | 3.6889 | 2.12 | 4000 | 3.9762 |
60
+ | 3.586 | 2.38 | 4500 | 3.9376 |
61
+ | 3.5724 | 2.65 | 5000 | 3.8870 |
62
+ | 3.5435 | 2.91 | 5500 | 3.8480 |
63
+ | 3.3888 | 3.17 | 6000 | 3.8520 |
64
+ | 3.3327 | 3.44 | 6500 | 3.8282 |
65
+ | 3.3538 | 3.7 | 7000 | 3.8039 |
66
+ | 3.3427 | 3.97 | 7500 | 3.7743 |
67
+ | 3.1287 | 4.23 | 8000 | 3.8093 |
68
+ | 3.1293 | 4.5 | 8500 | 3.7959 |
69
+ | 3.1508 | 4.76 | 9000 | 3.7735 |
70
+ | 3.1169 | 5.03 | 9500 | 3.7815 |
71
+ | 2.8937 | 5.29 | 10000 | 3.8078 |
72
+ | 2.9281 | 5.56 | 10500 | 3.7999 |
73
+ | 2.9357 | 5.82 | 11000 | 3.7869 |
74
+ | 2.8489 | 6.08 | 11500 | 3.8165 |
75
+ | 2.6858 | 6.35 | 12000 | 3.8367 |
76
+ | 2.7074 | 6.61 | 12500 | 3.8300 |
77
+ | 2.7252 | 6.88 | 13000 | 3.8234 |
78
+ | 2.5862 | 7.14 | 13500 | 3.8661 |
79
+ | 2.4957 | 7.41 | 14000 | 3.8772 |
80
+ | 2.5091 | 7.67 | 14500 | 3.8791 |
81
+ | 2.5155 | 7.94 | 15000 | 3.8773 |
82
+ | 2.3794 | 8.2 | 15500 | 3.9064 |
83
+ | 2.349 | 8.47 | 16000 | 3.9130 |
84
+ | 2.3595 | 8.73 | 16500 | 3.9154 |
85
+ | 2.3579 | 8.99 | 17000 | 3.9160 |
86
+ | 2.2743 | 9.26 | 17500 | 3.9268 |
87
+ | 2.2753 | 9.52 | 18000 | 3.9287 |
88
+ | 2.2734 | 9.79 | 18500 | 3.9287 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.26.1
94
+ - Pytorch 1.11.0+cu113
95
+ - Datasets 2.13.0
96
+ - Tokenizers 0.13.3