Hugging Face's logo

NasimB
/
gpt2-og-concat-modified-aochild

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
1
NasimB commited on
Commit
01e2412
·
1 Parent(s): c391831

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +42 -41
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 3.9794
20
 
21
  ## Model description
22
 
@@ -49,46 +49,47 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:-----:|:---------------:|
52
- | 6.0128 | 0.25 | 500 | 5.1030 |
53
- | 4.7835 | 0.5 | 1000 | 4.7239 |
54
- | 4.4818 | 0.75 | 1500 | 4.4931 |
55
- | 4.2968 | 0.99 | 2000 | 4.3427 |
56
- | 4.0729 | 1.24 | 2500 | 4.2546 |
57
- | 4.0104 | 1.49 | 3000 | 4.1723 |
58
- | 3.9301 | 1.74 | 3500 | 4.0984 |
59
- | 3.8714 | 1.99 | 4000 | 4.0260 |
60
- | 3.6651 | 2.24 | 4500 | 4.0073 |
61
- | 3.6615 | 2.49 | 5000 | 3.9649 |
62
- | 3.6536 | 2.73 | 5500 | 3.9218 |
63
- | 3.6176 | 2.98 | 6000 | 3.8865 |
64
- | 3.4173 | 3.23 | 6500 | 3.8994 |
65
- | 3.417 | 3.48 | 7000 | 3.8757 |
66
- | 3.4275 | 3.73 | 7500 | 3.8510 |
67
- | 3.4222 | 3.98 | 8000 | 3.8219 |
68
- | 3.1956 | 4.23 | 8500 | 3.8624 |
69
- | 3.2089 | 4.48 | 9000 | 3.8454 |
70
- | 3.2244 | 4.72 | 9500 | 3.8260 |
71
- | 3.2269 | 4.97 | 10000 | 3.8127 |
72
- | 2.9805 | 5.22 | 10500 | 3.8611 |
73
- | 3.0025 | 5.47 | 11000 | 3.8554 |
74
- | 3.0116 | 5.72 | 11500 | 3.8414 |
75
- | 3.0185 | 5.97 | 12000 | 3.8279 |
76
- | 2.7847 | 6.22 | 12500 | 3.8847 |
77
- | 2.7716 | 6.46 | 13000 | 3.8881 |
78
- | 2.7941 | 6.71 | 13500 | 3.8777 |
79
- | 2.8037 | 6.96 | 14000 | 3.8724 |
80
- | 2.5926 | 7.21 | 14500 | 3.9231 |
81
- | 2.5722 | 7.46 | 15000 | 3.9299 |
82
- | 2.5901 | 7.71 | 15500 | 3.9287 |
83
- | 2.5932 | 7.96 | 16000 | 3.9275 |
84
- | 2.4474 | 8.2 | 16500 | 3.9592 |
85
- | 2.4243 | 8.45 | 17000 | 3.9647 |
86
- | 2.4339 | 8.7 | 17500 | 3.9664 |
87
- | 2.4348 | 8.95 | 18000 | 3.9665 |
88
- | 2.3628 | 9.2 | 18500 | 3.9769 |
89
- | 2.3544 | 9.45 | 19000 | 3.9787 |
90
- | 2.354 | 9.7 | 19500 | 3.9795 |
91
- | 2.3533 | 9.95 | 20000 | 3.9794 |
 
92
 
93
 
94
  ### Framework versions
 
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: 3.9256
20
 
21
  ## Model description
22
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 5.9858 | 0.24 | 500 | 5.0593 |
53
+ | 4.752 | 0.48 | 1000 | 4.6760 |
54
+ | 4.4497 | 0.72 | 1500 | 4.4435 |
55
+ | 4.2543 | 0.96 | 2000 | 4.2976 |
56
+ | 4.0555 | 1.21 | 2500 | 4.2137 |
57
+ | 3.9693 | 1.45 | 3000 | 4.1335 |
58
+ | 3.906 | 1.69 | 3500 | 4.0568 |
59
+ | 3.8429 | 1.93 | 4000 | 3.9920 |
60
+ | 3.6732 | 2.17 | 4500 | 3.9691 |
61
+ | 3.6327 | 2.41 | 5000 | 3.9306 |
62
+ | 3.6116 | 2.65 | 5500 | 3.8914 |
63
+ | 3.5938 | 2.89 | 6000 | 3.8513 |
64
+ | 3.455 | 3.13 | 6500 | 3.8610 |
65
+ | 3.3859 | 3.38 | 7000 | 3.8405 |
66
+ | 3.3923 | 3.62 | 7500 | 3.8156 |
67
+ | 3.3951 | 3.86 | 8000 | 3.7887 |
68
+ | 3.2753 | 4.1 | 8500 | 3.8143 |
69
+ | 3.1704 | 4.34 | 9000 | 3.8108 |
70
+ | 3.1945 | 4.58 | 9500 | 3.7931 |
71
+ | 3.1957 | 4.82 | 10000 | 3.7730 |
72
+ | 3.1308 | 5.06 | 10500 | 3.7997 |
73
+ | 2.9454 | 5.3 | 11000 | 3.8140 |
74
+ | 2.981 | 5.54 | 11500 | 3.8037 |
75
+ | 2.9917 | 5.79 | 12000 | 3.7886 |
76
+ | 2.9661 | 6.03 | 12500 | 3.8061 |
77
+ | 2.7333 | 6.27 | 13000 | 3.8368 |
78
+ | 2.7658 | 6.51 | 13500 | 3.8365 |
79
+ | 2.7757 | 6.75 | 14000 | 3.8304 |
80
+ | 2.7771 | 6.99 | 14500 | 3.8187 |
81
+ | 2.5518 | 7.23 | 15000 | 3.8726 |
82
+ | 2.56 | 7.47 | 15500 | 3.8759 |
83
+ | 2.5737 | 7.71 | 16000 | 3.8764 |
84
+ | 2.5772 | 7.96 | 16500 | 3.8738 |
85
+ | 2.4267 | 8.2 | 17000 | 3.9046 |
86
+ | 2.4129 | 8.44 | 17500 | 3.9102 |
87
+ | 2.4256 | 8.68 | 18000 | 3.9135 |
88
+ | 2.4177 | 8.92 | 18500 | 3.9138 |
89
+ | 2.3675 | 9.16 | 19000 | 3.9222 |
90
+ | 2.3412 | 9.4 | 19500 | 3.9246 |
91
+ | 2.3399 | 9.64 | 20000 | 3.9256 |
92
+ | 2.3381 | 9.88 | 20500 | 3.9256 |
93
 
94
 
95
  ### Framework versions