Hugging Face's logo

ncantalupa
/
debiased_gpt_2

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
ncantalupa commited on
Commit
c56e6fa
·
verified ·
1 Parent(s): 4b2b916

End of training

Browse files
Files changed (2) hide show
  1. README.md +22 -52
  2. runs/Dec10_23-24-14_3bb107cd5bed/events.out.tfevents.1733873158.3bb107cd5bed.3915.1 +3 -0
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 [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5492
20
 
21
  ## Model description
22
 
@@ -41,62 +41,32 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 50
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | No log | 1.0 | 4 | 1.8397 |
51
- | No log | 2.0 | 8 | 1.7641 |
52
- | No log | 3.0 | 12 | 1.5924 |
53
- | No log | 4.0 | 16 | 1.4858 |
54
- | No log | 5.0 | 20 | 1.4142 |
55
- | No log | 6.0 | 24 | 1.3215 |
56
- | No log | 7.0 | 28 | 1.2303 |
57
- | No log | 8.0 | 32 | 1.1587 |
58
- | No log | 9.0 | 36 | 1.1007 |
59
- | No log | 10.0 | 40 | 1.0435 |
60
- | No log | 11.0 | 44 | 0.9819 |
61
- | No log | 12.0 | 48 | 0.9346 |
62
- | No log | 13.0 | 52 | 0.8925 |
63
- | No log | 14.0 | 56 | 0.8457 |
64
- | No log | 15.0 | 60 | 0.8009 |
65
- | No log | 16.0 | 64 | 0.7653 |
66
- | No log | 17.0 | 68 | 0.7394 |
67
- | No log | 18.0 | 72 | 0.7197 |
68
- | No log | 19.0 | 76 | 0.6985 |
69
- | No log | 20.0 | 80 | 0.6767 |
70
- | No log | 21.0 | 84 | 0.6623 |
71
- | No log | 22.0 | 88 | 0.6489 |
72
- | No log | 23.0 | 92 | 0.6306 |
73
- | No log | 24.0 | 96 | 0.6136 |
74
- | No log | 25.0 | 100 | 0.6019 |
75
- | No log | 26.0 | 104 | 0.5947 |
76
- | No log | 27.0 | 108 | 0.5925 |
77
- | No log | 28.0 | 112 | 0.5917 |
78
- | No log | 29.0 | 116 | 0.5887 |
79
- | No log | 30.0 | 120 | 0.5837 |
80
- | No log | 31.0 | 124 | 0.5771 |
81
- | No log | 32.0 | 128 | 0.5718 |
82
- | No log | 33.0 | 132 | 0.5679 |
83
- | No log | 34.0 | 136 | 0.5652 |
84
- | No log | 35.0 | 140 | 0.5611 |
85
- | No log | 36.0 | 144 | 0.5581 |
86
- | No log | 37.0 | 148 | 0.5562 |
87
- | No log | 38.0 | 152 | 0.5568 |
88
- | No log | 39.0 | 156 | 0.5556 |
89
- | No log | 40.0 | 160 | 0.5559 |
90
- | No log | 41.0 | 164 | 0.5555 |
91
- | No log | 42.0 | 168 | 0.5534 |
92
- | No log | 43.0 | 172 | 0.5516 |
93
- | No log | 44.0 | 176 | 0.5506 |
94
- | No log | 45.0 | 180 | 0.5503 |
95
- | No log | 46.0 | 184 | 0.5499 |
96
- | No log | 47.0 | 188 | 0.5496 |
97
- | No log | 48.0 | 192 | 0.5492 |
98
- | No log | 49.0 | 196 | 0.5492 |
99
- | No log | 50.0 | 200 | 0.5492 |
100
 
101
 
102
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.0493
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 1.0 | 8 | 1.4588 |
51
+ | No log | 2.0 | 16 | 1.0679 |
52
+ | No log | 3.0 | 24 | 0.7838 |
53
+ | No log | 4.0 | 32 | 0.4977 |
54
+ | No log | 5.0 | 40 | 0.3103 |
55
+ | No log | 6.0 | 48 | 0.1972 |
56
+ | No log | 7.0 | 56 | 0.1357 |
57
+ | No log | 8.0 | 64 | 0.0964 |
58
+ | No log | 9.0 | 72 | 0.0786 |
59
+ | No log | 10.0 | 80 | 0.0730 |
60
+ | No log | 11.0 | 88 | 0.0613 |
61
+ | No log | 12.0 | 96 | 0.0585 |
62
+ | No log | 13.0 | 104 | 0.0556 |
63
+ | No log | 14.0 | 112 | 0.0531 |
64
+ | No log | 15.0 | 120 | 0.0524 |
65
+ | No log | 16.0 | 128 | 0.0508 |
66
+ | No log | 17.0 | 136 | 0.0501 |
67
+ | No log | 18.0 | 144 | 0.0499 |
68
+ | No log | 19.0 | 152 | 0.0495 |
69
+ | No log | 20.0 | 160 | 0.0493 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
runs/Dec10_23-24-14_3bb107cd5bed/events.out.tfevents.1733873158.3bb107cd5bed.3915.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7ea91c83dce87fb5098ba581aa8476ce74b9761c81e8e0344e650e1b43caf
3
+ size 359