Hugging Face's logo

daspartho
/
prompt-extend

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Community
1
daspartho commited on
Commit
68ce505
•
1 Parent(s): 1a1b581

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -18
README.md CHANGED
@@ -6,15 +6,29 @@ model-index:
6
  - name: prompt-extend
7
  results: []
8
  ---
9
- [![Generic badge](https://img.shields.io/badge/🤗-Open%20in%20Spaces-blue.svg)](https://huggingface.co/spaces/daspartho/prompt-extend)
10
 
11
- # Prompt Extend
 
12
 
13
- GPT-2 model trained on [dataset](https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts) of stable diffusion prompts.
14
 
15
- ## Intended uses
 
 
16
 
17
- Extend stable diffusion prompts with suitable style cues.
 
 
 
 
 
 
 
 
 
 
 
 
18
 
19
  ### Training hyperparameters
20
 
@@ -28,26 +42,33 @@ The following hyperparameters were used during training:
28
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
29
  - lr_scheduler_type: cosine
30
  - lr_scheduler_warmup_ratio: 0.1
31
- - num_epochs: 3
32
  - mixed_precision_training: Native AMP
33
 
34
  ### Training results
35
 
36
  | Training Loss | Epoch | Step | Validation Loss |
37
  |:-------------:|:-----:|:----:|:---------------:|
38
- | 6.3816 | 0.35 | 100 | 4.1823 |
39
- | 3.7123 | 0.69 | 200 | 3.3033 |
40
- | 3.118 | 1.04 | 300 | 2.8311 |
41
- | 2.7291 | 1.39 | 400 | 2.5503 |
42
- | 2.4918 | 1.74 | 500 | 2.3653 |
43
- | 2.3379 | 2.08 | 600 | 2.2375 |
44
- | 2.1952 | 2.43 | 700 | 2.1714 |
45
- | 2.1593 | 2.78 | 800 | 2.1453 |
 
 
 
 
 
 
 
46
 
47
 
48
  ### Framework versions
49
 
50
- - Transformers 4.23.1
51
- - Pytorch 1.12.1+cu113
52
- - Datasets 2.6.1
53
- - Tokenizers 0.13.1
 
6
  - name: prompt-extend
7
  results: []
8
  ---
 
9
 
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # prompt-extend
14
 
15
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 2.0437
18
 
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
 
33
  ### Training hyperparameters
34
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_ratio: 0.1
45
+ - num_epochs: 5
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 6.3538 | 0.32 | 500 | 4.7231 |
53
+ | 4.2863 | 0.64 | 1000 | 3.7473 |
54
+ | 3.5828 | 0.96 | 1500 | 3.2410 |
55
+ | 3.1699 | 1.28 | 2000 | 2.9410 |
56
+ | 2.9123 | 1.6 | 2500 | 2.7295 |
57
+ | 2.7413 | 1.92 | 3000 | 2.5568 |
58
+ | 2.5181 | 2.24 | 3500 | 2.4281 |
59
+ | 2.394 | 2.56 | 4000 | 2.3263 |
60
+ | 2.3157 | 2.88 | 4500 | 2.2393 |
61
+ | 2.1822 | 3.2 | 5000 | 2.1750 |
62
+ | 2.091 | 3.52 | 5500 | 2.1231 |
63
+ | 2.0489 | 3.84 | 6000 | 2.0844 |
64
+ | 1.9873 | 4.16 | 6500 | 2.0609 |
65
+ | 1.9335 | 4.48 | 7000 | 2.0487 |
66
+ | 1.9307 | 4.8 | 7500 | 2.0437 |
67
 
68
 
69
  ### Framework versions
70
 
71
+ - Transformers 4.24.0
72
+ - Pytorch 1.13.0+cu117
73
+ - Datasets 2.7.1
74
+ - Tokenizers 0.13.2