Hugging Face's logo

NasimB
/
gpt2-2_left_out_cbt

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
1
NasimB commited on
Commit
33f60dc
·
1 Parent(s): 310f843

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - generator
7
+ model-index:
8
+ - name: gpt2-2_left_out_cbt
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
+ # gpt2-2_left_out_cbt
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: 3.9359
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
+ | 5.9415 | 0.25 | 500 | 5.0484 |
53
+ | 4.7309 | 0.5 | 1000 | 4.6647 |
54
+ | 4.4299 | 0.75 | 1500 | 4.4406 |
55
+ | 4.2176 | 1.0 | 2000 | 4.3150 |
56
+ | 4.0185 | 1.25 | 2500 | 4.2114 |
57
+ | 3.9488 | 1.5 | 3000 | 4.1259 |
58
+ | 3.8765 | 1.75 | 3500 | 4.0526 |
59
+ | 3.8178 | 2.0 | 4000 | 4.0013 |
60
+ | 3.6252 | 2.25 | 4500 | 3.9677 |
61
+ | 3.6126 | 2.5 | 5000 | 3.9257 |
62
+ | 3.5877 | 2.75 | 5500 | 3.8858 |
63
+ | 3.5664 | 3.0 | 6000 | 3.8677 |
64
+ | 3.3588 | 3.25 | 6500 | 3.8655 |
65
+ | 3.3839 | 3.5 | 7000 | 3.8408 |
66
+ | 3.375 | 3.75 | 7500 | 3.8131 |
67
+ | 3.3702 | 4.0 | 8000 | 3.8096 |
68
+ | 3.1311 | 4.25 | 8500 | 3.8272 |
69
+ | 3.1718 | 4.5 | 9000 | 3.8071 |
70
+ | 3.1835 | 4.75 | 9500 | 3.7894 |
71
+ | 3.1802 | 5.01 | 10000 | 3.7920 |
72
+ | 2.9241 | 5.26 | 10500 | 3.8233 |
73
+ | 2.9597 | 5.51 | 11000 | 3.8156 |
74
+ | 2.9773 | 5.76 | 11500 | 3.8019 |
75
+ | 2.9708 | 6.01 | 12000 | 3.8077 |
76
+ | 2.7159 | 6.26 | 12500 | 3.8440 |
77
+ | 2.7495 | 6.51 | 13000 | 3.8459 |
78
+ | 2.761 | 6.76 | 13500 | 3.8406 |
79
+ | 2.7542 | 7.01 | 14000 | 3.8461 |
80
+ | 2.5238 | 7.26 | 14500 | 3.8832 |
81
+ | 2.5459 | 7.51 | 15000 | 3.8868 |
82
+ | 2.5638 | 7.76 | 15500 | 3.8872 |
83
+ | 2.555 | 8.01 | 16000 | 3.8932 |
84
+ | 2.388 | 8.26 | 16500 | 3.9161 |
85
+ | 2.4017 | 8.51 | 17000 | 3.9215 |
86
+ | 2.4056 | 8.76 | 17500 | 3.9236 |
87
+ | 2.3998 | 9.01 | 18000 | 3.9254 |
88
+ | 2.3199 | 9.26 | 18500 | 3.9339 |
89
+ | 2.3241 | 9.51 | 19000 | 3.9359 |
90
+ | 2.3205 | 9.76 | 19500 | 3.9359 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.26.1
96
+ - Pytorch 1.11.0+cu113
97
+ - Datasets 2.13.0
98
+ - Tokenizers 0.13.3