Hugging Face's logo

augustocsc
/
Se124M500KInfPrompt_endtoken

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
augustocsc commited on
Commit
f459e28
·
verified ·
1 Parent(s): a44bc18

Model save

Browse files
Files changed (4) hide show
  1. README.md +36 -55
  2. adapter_model.safetensors +1 -1
  3. all_results.json +6 -6
  4. train_results.json +6 -6
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: 0.6957
20
 
21
  ## Model description
22
 
@@ -46,58 +46,39 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:-----:|:---------------:|
51
- | 0.2129 | 1.0 | 1430 | 0.8043 |
52
- | 0.2018 | 2.0 | 2860 | 0.7705 |
53
- | 0.1949 | 3.0 | 4290 | 0.7588 |
54
- | 0.1913 | 4.0 | 5720 | 0.7498 |
55
- | 0.1921 | 5.0 | 7150 | 0.7435 |
56
- | 0.1903 | 6.0 | 8580 | 0.7371 |
57
- | 0.1888 | 7.0 | 10010 | 0.7339 |
58
- | 0.1881 | 8.0 | 11440 | 0.7299 |
59
- | 0.1872 | 9.0 | 12870 | 0.7267 |
60
- | 0.187 | 10.0 | 14300 | 0.7251 |
61
- | 0.184 | 11.0 | 15730 | 0.7229 |
62
- | 0.1846 | 12.0 | 17160 | 0.7212 |
63
- | 0.1851 | 13.0 | 18590 | 0.7182 |
64
- | 0.1804 | 14.0 | 20020 | 0.7153 |
65
- | 0.1848 | 15.0 | 21450 | 0.7141 |
66
- | 0.1824 | 16.0 | 22880 | 0.7144 |
67
- | 0.1796 | 17.0 | 24310 | 0.7116 |
68
- | 0.18 | 18.0 | 25740 | 0.7108 |
69
- | 0.1825 | 19.0 | 27170 | 0.7082 |
70
- | 0.1852 | 20.0 | 28600 | 0.7082 |
71
- | 0.1785 | 21.0 | 30030 | 0.7072 |
72
- | 0.1811 | 22.0 | 31460 | 0.7057 |
73
- | 0.178 | 23.0 | 32890 | 0.7059 |
74
- | 0.1827 | 24.0 | 34320 | 0.7046 |
75
- | 0.1813 | 25.0 | 35750 | 0.7033 |
76
- | 0.1825 | 26.0 | 37180 | 0.7039 |
77
- | 0.1795 | 27.0 | 38610 | 0.7032 |
78
- | 0.1801 | 28.0 | 40040 | 0.7017 |
79
- | 0.1781 | 29.0 | 41470 | 0.7013 |
80
- | 0.1823 | 30.0 | 42900 | 0.7010 |
81
- | 0.1781 | 31.0 | 44330 | 0.7012 |
82
- | 0.1809 | 32.0 | 45760 | 0.6999 |
83
- | 0.1764 | 33.0 | 47190 | 0.6996 |
84
- | 0.1791 | 34.0 | 48620 | 0.6983 |
85
- | 0.1793 | 35.0 | 50050 | 0.6988 |
86
- | 0.1785 | 36.0 | 51480 | 0.6980 |
87
- | 0.1777 | 37.0 | 52910 | 0.6980 |
88
- | 0.1774 | 38.0 | 54340 | 0.6980 |
89
- | 0.1795 | 39.0 | 55770 | 0.6976 |
90
- | 0.1772 | 40.0 | 57200 | 0.6974 |
91
- | 0.1793 | 41.0 | 58630 | 0.6974 |
92
- | 0.1777 | 42.0 | 60060 | 0.6968 |
93
- | 0.1777 | 43.0 | 61490 | 0.6965 |
94
- | 0.1779 | 44.0 | 62920 | 0.6965 |
95
- | 0.1782 | 45.0 | 64350 | 0.6964 |
96
- | 0.1765 | 46.0 | 65780 | 0.6961 |
97
- | 0.1758 | 47.0 | 67210 | 0.6962 |
98
- | 0.1763 | 48.0 | 68640 | 0.6960 |
99
- | 0.1788 | 49.0 | 70070 | 0.6958 |
100
- | 0.1776 | 50.0 | 71500 | 0.6957 |
101
 
102
 
103
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M500KInfPrompt_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
+ # Se124M500KInfPrompt_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: 0.6719
20
 
21
  ## Model description
22
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:------:|:---------------:|
51
+ | 0.1898 | 1.0 | 5427 | 0.7433 |
52
+ | 0.1857 | 2.0 | 10854 | 0.7238 |
53
+ | 0.1843 | 3.0 | 16281 | 0.7118 |
54
+ | 0.1813 | 4.0 | 21708 | 0.7045 |
55
+ | 0.1802 | 5.0 | 27135 | 0.6990 |
56
+ | 0.1785 | 6.0 | 32562 | 0.6944 |
57
+ | 0.1769 | 7.0 | 37989 | 0.6918 |
58
+ | 0.1743 | 8.0 | 43416 | 0.6875 |
59
+ | 0.1752 | 9.0 | 48843 | 0.6854 |
60
+ | 0.1756 | 10.0 | 54270 | 0.6854 |
61
+ | 0.1736 | 11.0 | 59697 | 0.6837 |
62
+ | 0.1756 | 12.0 | 65124 | 0.6812 |
63
+ | 0.173 | 13.0 | 70551 | 0.6798 |
64
+ | 0.1737 | 14.0 | 75978 | 0.6791 |
65
+ | 0.1741 | 15.0 | 81405 | 0.6783 |
66
+ | 0.177 | 16.0 | 86832 | 0.6771 |
67
+ | 0.1734 | 17.0 | 92259 | 0.6765 |
68
+ | 0.1719 | 18.0 | 97686 | 0.6760 |
69
+ | 0.1737 | 19.0 | 103113 | 0.6763 |
70
+ | 0.1716 | 20.0 | 108540 | 0.6747 |
71
+ | 0.1713 | 21.0 | 113967 | 0.6741 |
72
+ | 0.1739 | 22.0 | 119394 | 0.6738 |
73
+ | 0.1694 | 23.0 | 124821 | 0.6737 |
74
+ | 0.1703 | 24.0 | 130248 | 0.6743 |
75
+ | 0.1697 | 25.0 | 135675 | 0.6730 |
76
+ | 0.172 | 26.0 | 141102 | 0.6731 |
77
+ | 0.1711 | 27.0 | 146529 | 0.6720 |
78
+ | 0.1726 | 28.0 | 151956 | 0.6720 |
79
+ | 0.1703 | 29.0 | 157383 | 0.6716 |
80
+ | 0.1732 | 30.0 | 162810 | 0.6716 |
81
+ | 0.171 | 31.0 | 168237 | 0.6719 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9181e691728283da052e440eb03c026ec4bd673683dbd9545d920d8b44e50a3a
3
  size 309974336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963ff76e5201583684dcef52121403c7aa5c0888a7400872b43677f42ec1461d
3
  size 309974336
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 50.0,
3
  "eval_loss": 0.6956692934036255,
4
  "eval_runtime": 59.8322,
5
  "eval_samples_per_second": 163.257,
6
  "eval_steps_per_second": 5.114,
7
  "perplexity": 2.005050592091695,
8
- "total_flos": 1.49878932701184e+17,
9
- "train_loss": 0.18437957987751993,
10
- "train_runtime": 7319.2549,
11
- "train_samples_per_second": 312.395,
12
- "train_steps_per_second": 9.769
13
  }
 
1
  {
2
+ "epoch": 31.0,
3
  "eval_loss": 0.6956692934036255,
4
  "eval_runtime": 59.8322,
5
  "eval_samples_per_second": 163.257,
6
  "eval_steps_per_second": 5.114,
7
  "perplexity": 2.005050592091695,
8
+ "total_flos": 3.528546650263388e+17,
9
+ "train_loss": 0.17647521918996942,
10
+ "train_runtime": 17128.7716,
11
+ "train_samples_per_second": 506.884,
12
+ "train_steps_per_second": 15.842
13
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 50.0,
3
- "total_flos": 1.49878932701184e+17,
4
- "train_loss": 0.18437957987751993,
5
- "train_runtime": 7319.2549,
6
- "train_samples_per_second": 312.395,
7
- "train_steps_per_second": 9.769
8
  }
 
1
  {
2
+ "epoch": 31.0,
3
+ "total_flos": 3.528546650263388e+17,
4
+ "train_loss": 0.17647521918996942,
5
+ "train_runtime": 17128.7716,
6
+ "train_samples_per_second": 506.884,
7
+ "train_steps_per_second": 15.842
8
  }