NasimB commited on
Commit
a2a55e2
·
1 Parent(s): 52550d6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - generator
7
+ model-index:
8
+ - name: gpt2-dp-cl-length
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-cl-length
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: 4.7161
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: 7
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 6.6691 | 0.26 | 500 | 5.8270 |
53
+ | 5.2775 | 0.53 | 1000 | 5.4588 |
54
+ | 4.9444 | 0.79 | 1500 | 5.2410 |
55
+ | 4.7094 | 1.05 | 2000 | 5.1417 |
56
+ | 4.5245 | 1.31 | 2500 | 4.9932 |
57
+ | 4.4306 | 1.58 | 3000 | 4.9406 |
58
+ | 4.3594 | 1.84 | 3500 | 4.9073 |
59
+ | 4.2194 | 2.1 | 4000 | 4.8631 |
60
+ | 4.0996 | 2.36 | 4500 | 4.8316 |
61
+ | 4.0865 | 2.63 | 5000 | 4.7686 |
62
+ | 4.05 | 2.89 | 5500 | 4.7494 |
63
+ | 3.8858 | 3.15 | 6000 | 4.7704 |
64
+ | 3.814 | 3.42 | 6500 | 4.6998 |
65
+ | 3.8032 | 3.68 | 7000 | 4.6793 |
66
+ | 3.7885 | 3.94 | 7500 | 4.6676 |
67
+ | 3.5761 | 4.2 | 8000 | 4.6765 |
68
+ | 3.5336 | 4.47 | 8500 | 4.6792 |
69
+ | 3.535 | 4.73 | 9000 | 4.6749 |
70
+ | 3.5307 | 4.99 | 9500 | 4.6553 |
71
+ | 3.2929 | 5.25 | 10000 | 4.7027 |
72
+ | 3.2874 | 5.52 | 10500 | 4.6926 |
73
+ | 3.2883 | 5.78 | 11000 | 4.6927 |
74
+ | 3.2606 | 6.04 | 11500 | 4.7025 |
75
+ | 3.1356 | 6.31 | 12000 | 4.7098 |
76
+ | 3.1392 | 6.57 | 12500 | 4.7123 |
77
+ | 3.1374 | 6.83 | 13000 | 4.7161 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.26.1
83
+ - Pytorch 1.11.0+cu113
84
+ - Datasets 2.13.0
85
+ - Tokenizers 0.13.3