augustocsc commited on
Commit
ea5a7f8
·
verified ·
1 Parent(s): 3a6bed1

Model save

Browse files
Files changed (4) hide show
  1. README.md +55 -55
  2. adapter_model.safetensors +1 -1
  3. all_results.json +5 -5
  4. train_results.json +5 -5
README.md CHANGED
@@ -5,18 +5,18 @@ base_model: gpt2
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: Se124M100KInfPrompt_endtoken
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
- # Se124M100KInfPrompt_endtoken
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6695
20
 
21
  ## Model description
22
 
@@ -47,58 +47,58 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-----:|:------:|:---------------:|
52
- | 0.7209 | 1.0 | 5717 | 0.7060 |
53
- | 0.7027 | 2.0 | 11434 | 0.6916 |
54
- | 0.7005 | 3.0 | 17151 | 0.6865 |
55
- | 0.7009 | 4.0 | 22868 | 0.6858 |
56
- | 0.6933 | 5.0 | 28585 | 0.6854 |
57
- | 0.6922 | 6.0 | 34302 | 0.6825 |
58
- | 0.6859 | 7.0 | 40019 | 0.6810 |
59
- | 0.6923 | 8.0 | 45736 | 0.6812 |
60
- | 0.6919 | 9.0 | 51453 | 0.6809 |
61
- | 0.6871 | 10.0 | 57170 | 0.6795 |
62
- | 0.6844 | 11.0 | 62887 | 0.6776 |
63
- | 0.6923 | 12.0 | 68604 | 0.6780 |
64
- | 0.6878 | 13.0 | 74321 | 0.6785 |
65
- | 0.6765 | 14.0 | 80038 | 0.6775 |
66
- | 0.6864 | 15.0 | 85755 | 0.6769 |
67
- | 0.6776 | 16.0 | 91472 | 0.6761 |
68
- | 0.6823 | 17.0 | 97189 | 0.6768 |
69
- | 0.6743 | 18.0 | 102906 | 0.6751 |
70
- | 0.682 | 19.0 | 108623 | 0.6776 |
71
- | 0.6902 | 20.0 | 114340 | 0.6762 |
72
- | 0.6774 | 21.0 | 120057 | 0.6751 |
73
- | 0.6748 | 22.0 | 125774 | 0.6747 |
74
- | 0.6864 | 23.0 | 131491 | 0.6745 |
75
- | 0.6819 | 24.0 | 137208 | 0.6756 |
76
- | 0.6818 | 25.0 | 142925 | 0.6745 |
77
- | 0.6757 | 26.0 | 148642 | 0.6737 |
78
- | 0.6801 | 27.0 | 154359 | 0.6734 |
79
- | 0.6717 | 28.0 | 160076 | 0.6724 |
80
- | 0.6717 | 29.0 | 165793 | 0.6722 |
81
- | 0.6802 | 30.0 | 171510 | 0.6723 |
82
- | 0.677 | 31.0 | 177227 | 0.6725 |
83
- | 0.6764 | 32.0 | 182944 | 0.6712 |
84
- | 0.6767 | 33.0 | 188661 | 0.6712 |
85
- | 0.6758 | 34.0 | 194378 | 0.6716 |
86
- | 0.6772 | 35.0 | 200095 | 0.6715 |
87
- | 0.679 | 36.0 | 205812 | 0.6717 |
88
- | 0.6744 | 37.0 | 211529 | 0.6702 |
89
- | 0.6654 | 38.0 | 217246 | 0.6707 |
90
- | 0.6723 | 39.0 | 222963 | 0.6704 |
91
- | 0.6758 | 40.0 | 228680 | 0.6701 |
92
- | 0.6795 | 41.0 | 234397 | 0.6701 |
93
- | 0.6681 | 42.0 | 240114 | 0.6698 |
94
- | 0.6761 | 43.0 | 245831 | 0.6700 |
95
- | 0.673 | 44.0 | 251548 | 0.6697 |
96
- | 0.6736 | 45.0 | 257265 | 0.6698 |
97
- | 0.673 | 46.0 | 262982 | 0.6695 |
98
- | 0.6686 | 47.0 | 268699 | 0.6695 |
99
- | 0.666 | 48.0 | 274416 | 0.6696 |
100
- | 0.663 | 49.0 | 280133 | 0.6695 |
101
- | 0.6667 | 50.0 | 285850 | 0.6695 |
102
 
103
 
104
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M100KInfPrompt_endtoken2
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
+ # Se124M100KInfPrompt_endtoken2
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6704
20
 
21
  ## Model description
22
 
 
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 0.7736 | 1.0 | 1066 | 0.7302 |
53
+ | 0.7318 | 2.0 | 2132 | 0.7070 |
54
+ | 0.7189 | 3.0 | 3198 | 0.7002 |
55
+ | 0.7128 | 4.0 | 4264 | 0.6952 |
56
+ | 0.7031 | 5.0 | 5330 | 0.6878 |
57
+ | 0.6944 | 6.0 | 6396 | 0.6873 |
58
+ | 0.6935 | 7.0 | 7462 | 0.6879 |
59
+ | 0.6987 | 8.0 | 8528 | 0.6837 |
60
+ | 0.7011 | 9.0 | 9594 | 0.6830 |
61
+ | 0.6799 | 10.0 | 10660 | 0.6819 |
62
+ | 0.6754 | 11.0 | 11726 | 0.6793 |
63
+ | 0.6769 | 12.0 | 12792 | 0.6800 |
64
+ | 0.6827 | 13.0 | 13858 | 0.6766 |
65
+ | 0.6905 | 14.0 | 14924 | 0.6808 |
66
+ | 0.6769 | 15.0 | 15990 | 0.6769 |
67
+ | 0.6751 | 16.0 | 17056 | 0.6776 |
68
+ | 0.688 | 17.0 | 18122 | 0.6739 |
69
+ | 0.6922 | 18.0 | 19188 | 0.6772 |
70
+ | 0.6804 | 19.0 | 20254 | 0.6743 |
71
+ | 0.6718 | 20.0 | 21320 | 0.6738 |
72
+ | 0.681 | 21.0 | 22386 | 0.6749 |
73
+ | 0.6757 | 22.0 | 23452 | 0.6729 |
74
+ | 0.6777 | 23.0 | 24518 | 0.6756 |
75
+ | 0.6667 | 24.0 | 25584 | 0.6730 |
76
+ | 0.6758 | 25.0 | 26650 | 0.6719 |
77
+ | 0.6602 | 26.0 | 27716 | 0.6715 |
78
+ | 0.6746 | 27.0 | 28782 | 0.6723 |
79
+ | 0.6647 | 28.0 | 29848 | 0.6721 |
80
+ | 0.6673 | 29.0 | 30914 | 0.6732 |
81
+ | 0.6745 | 30.0 | 31980 | 0.6728 |
82
+ | 0.6659 | 31.0 | 33046 | 0.6710 |
83
+ | 0.6578 | 32.0 | 34112 | 0.6710 |
84
+ | 0.6649 | 33.0 | 35178 | 0.6711 |
85
+ | 0.6665 | 34.0 | 36244 | 0.6710 |
86
+ | 0.6608 | 35.0 | 37310 | 0.6714 |
87
+ | 0.6623 | 36.0 | 38376 | 0.6708 |
88
+ | 0.6789 | 37.0 | 39442 | 0.6704 |
89
+ | 0.6536 | 38.0 | 40508 | 0.6708 |
90
+ | 0.6746 | 39.0 | 41574 | 0.6710 |
91
+ | 0.6634 | 40.0 | 42640 | 0.6704 |
92
+ | 0.65 | 41.0 | 43706 | 0.6710 |
93
+ | 0.6638 | 42.0 | 44772 | 0.6702 |
94
+ | 0.6586 | 43.0 | 45838 | 0.6705 |
95
+ | 0.6546 | 44.0 | 46904 | 0.6706 |
96
+ | 0.651 | 45.0 | 47970 | 0.6701 |
97
+ | 0.6604 | 46.0 | 49036 | 0.6705 |
98
+ | 0.6756 | 47.0 | 50102 | 0.6706 |
99
+ | 0.6612 | 48.0 | 51168 | 0.6705 |
100
+ | 0.6553 | 49.0 | 52234 | 0.6705 |
101
+ | 0.6561 | 50.0 | 53300 | 0.6704 |
102
 
103
 
104
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70fca0a71e66cf9a0d4139c4189e0eee25ba6249aa02c731201e0cc323595050
3
  size 309980480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dbedf96eccfbf562fc49ec87ec06f9f4334af5516644a67c35d1b3d6953a060
3
  size 309980480
all_results.json CHANGED
@@ -5,9 +5,9 @@
5
  "eval_samples_per_second": 577.411,
6
  "eval_steps_per_second": 72.176,
7
  "perplexity": 1.953220034675124,
8
- "total_flos": 1.49878932701184e+17,
9
- "train_loss": 0.6821009000064568,
10
- "train_runtime": 10227.5107,
11
- "train_samples_per_second": 223.564,
12
- "train_steps_per_second": 27.949
13
  }
 
5
  "eval_samples_per_second": 577.411,
6
  "eval_steps_per_second": 72.176,
7
  "perplexity": 1.953220034675124,
8
+ "total_flos": 2.3883058800820224e+16,
9
+ "train_loss": 0.6825056470402187,
10
+ "train_runtime": 1762.4542,
11
+ "train_samples_per_second": 241.935,
12
+ "train_steps_per_second": 30.242
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 50.0,
3
- "total_flos": 1.49878932701184e+17,
4
- "train_loss": 0.6821009000064568,
5
- "train_runtime": 10227.5107,
6
- "train_samples_per_second": 223.564,
7
- "train_steps_per_second": 27.949
8
  }
 
1
  {
2
  "epoch": 50.0,
3
+ "total_flos": 2.3883058800820224e+16,
4
+ "train_loss": 0.6825056470402187,
5
+ "train_runtime": 1762.4542,
6
+ "train_samples_per_second": 241.935,
7
+ "train_steps_per_second": 30.242
8
  }