Hugging Face's logo

NasimB
/
gpt2-dp-3

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
NasimB commited on
Commit
deaf19b
·
1 Parent(s): 28fddcc

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-dp-3
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-dp-3
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: 4.4076
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
+ | 6.7156 | 0.27 | 500 | 5.6535 |
53
+ | 5.3578 | 0.53 | 1000 | 5.2045 |
54
+ | 5.0077 | 0.8 | 1500 | 4.9659 |
55
+ | 4.7593 | 1.07 | 2000 | 4.8126 |
56
+ | 4.5687 | 1.34 | 2500 | 4.7029 |
57
+ | 4.4766 | 1.6 | 3000 | 4.5953 |
58
+ | 4.3917 | 1.87 | 3500 | 4.5056 |
59
+ | 4.2228 | 2.14 | 4000 | 4.4626 |
60
+ | 4.1279 | 2.4 | 4500 | 4.4147 |
61
+ | 4.1019 | 2.67 | 5000 | 4.3627 |
62
+ | 4.0683 | 2.94 | 5500 | 4.3206 |
63
+ | 3.869 | 3.21 | 6000 | 4.3295 |
64
+ | 3.8494 | 3.47 | 6500 | 4.3034 |
65
+ | 3.8533 | 3.74 | 7000 | 4.2734 |
66
+ | 3.8342 | 4.01 | 7500 | 4.2661 |
67
+ | 3.5799 | 4.27 | 8000 | 4.2817 |
68
+ | 3.6163 | 4.54 | 8500 | 4.2654 |
69
+ | 3.6245 | 4.81 | 9000 | 4.2402 |
70
+ | 3.5328 | 5.07 | 9500 | 4.2692 |
71
+ | 3.3455 | 5.34 | 10000 | 4.2804 |
72
+ | 3.3898 | 5.61 | 10500 | 4.2662 |
73
+ | 3.3933 | 5.88 | 11000 | 4.2519 |
74
+ | 3.2239 | 6.14 | 11500 | 4.3025 |
75
+ | 3.1152 | 6.41 | 12000 | 4.3098 |
76
+ | 3.14 | 6.68 | 12500 | 4.3060 |
77
+ | 3.1585 | 6.94 | 13000 | 4.2908 |
78
+ | 2.9392 | 7.21 | 13500 | 4.3478 |
79
+ | 2.9031 | 7.48 | 14000 | 4.3549 |
80
+ | 2.9201 | 7.75 | 14500 | 4.3523 |
81
+ | 2.9044 | 8.01 | 15000 | 4.3650 |
82
+ | 2.7244 | 8.28 | 15500 | 4.3877 |
83
+ | 2.7371 | 8.55 | 16000 | 4.3929 |
84
+ | 2.745 | 8.81 | 16500 | 4.3943 |
85
+ | 2.7233 | 9.08 | 17000 | 4.4028 |
86
+ | 2.6481 | 9.35 | 17500 | 4.4060 |
87
+ | 2.6578 | 9.62 | 18000 | 4.4077 |
88
+ | 2.6554 | 9.88 | 18500 | 4.4076 |
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