Hugging Face's logo

NasimB
/
distilgpt2-dp

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
1
NasimB commited on
Commit
bf528e0
·
1 Parent(s): 097c046

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: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - generator
7
+ model-index:
8
+ - name: distilgpt2-dp
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
+ # distilgpt2-dp
16
+
17
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the generator dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 4.3310
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
+ | 6.7548 | 0.27 | 500 | 5.6494 |
53
+ | 5.3558 | 0.53 | 1000 | 5.1949 |
54
+ | 4.9963 | 0.8 | 1500 | 4.9488 |
55
+ | 4.7463 | 1.07 | 2000 | 4.7983 |
56
+ | 4.5597 | 1.34 | 2500 | 4.6942 |
57
+ | 4.4758 | 1.6 | 3000 | 4.5956 |
58
+ | 4.3994 | 1.87 | 3500 | 4.5174 |
59
+ | 4.2405 | 2.14 | 4000 | 4.4796 |
60
+ | 4.1533 | 2.4 | 4500 | 4.4339 |
61
+ | 4.1326 | 2.67 | 5000 | 4.3886 |
62
+ | 4.1027 | 2.94 | 5500 | 4.3479 |
63
+ | 3.9207 | 3.21 | 6000 | 4.3582 |
64
+ | 3.9044 | 3.47 | 6500 | 4.3315 |
65
+ | 3.9109 | 3.74 | 7000 | 4.3016 |
66
+ | 3.8938 | 4.01 | 7500 | 4.2895 |
67
+ | 3.6736 | 4.27 | 8000 | 4.3069 |
68
+ | 3.7072 | 4.54 | 8500 | 4.2876 |
69
+ | 3.7151 | 4.81 | 9000 | 4.2656 |
70
+ | 3.6379 | 5.07 | 9500 | 4.2858 |
71
+ | 3.4849 | 5.34 | 10000 | 4.2893 |
72
+ | 3.5254 | 5.61 | 10500 | 4.2735 |
73
+ | 3.5283 | 5.88 | 11000 | 4.2570 |
74
+ | 3.3946 | 6.14 | 11500 | 4.2931 |
75
+ | 3.3098 | 6.41 | 12000 | 4.2970 |
76
+ | 3.3318 | 6.68 | 12500 | 4.2866 |
77
+ | 3.3499 | 6.94 | 13000 | 4.2735 |
78
+ | 3.1802 | 7.21 | 13500 | 4.3088 |
79
+ | 3.1565 | 7.48 | 14000 | 4.3098 |
80
+ | 3.1709 | 7.75 | 14500 | 4.3050 |
81
+ | 3.1565 | 8.01 | 15000 | 4.3090 |
82
+ | 3.021 | 8.28 | 15500 | 4.3237 |
83
+ | 3.0356 | 8.55 | 16000 | 4.3252 |
84
+ | 3.0404 | 8.81 | 16500 | 4.3249 |
85
+ | 3.0277 | 9.08 | 17000 | 4.3288 |
86
+ | 2.9656 | 9.35 | 17500 | 4.3307 |
87
+ | 2.977 | 9.62 | 18000 | 4.3312 |
88
+ | 2.9747 | 9.88 | 18500 | 4.3310 |
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