Hugging Face's logo

owanr
/
SChem5Labels-google-t5-v1_1-large-inter_model-frequency-model_annots_str

Generated from Trainer
Model card Files Community
owanr commited on
Commit
abb0bcf
·
1 Parent(s): b4289f5

End of training

Browse files
Files changed (3) hide show
  1. README.md +39 -71
  2. adapter_model.bin +1 -1
  3. training_args.bin +2 -2
README.md CHANGED
@@ -4,18 +4,18 @@ base_model: google/t5-v1_1-large
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
- - name: SChem5Labels-google-t5-v1_1-large-inter_model-frequency
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # SChem5Labels-google-t5-v1_1-large-inter_model-frequency
15
 
16
  This model is a fine-tuned version of [google/t5-v1_1-large](https://huggingface.co/google/t5-v1_1-large) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.6758
19
 
20
  ## Model description
21
 
@@ -46,78 +46,46 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 33.8422 | 1.0 | 25 | 36.5540 |
50
- | 32.9017 | 2.0 | 50 | 36.1137 |
51
- | 33.4329 | 3.0 | 75 | 34.8129 |
52
- | 31.8192 | 4.0 | 100 | 32.7578 |
53
- | 30.8395 | 5.0 | 125 | 28.4763 |
54
- | 29.5074 | 6.0 | 150 | 25.6394 |
55
- | 28.2813 | 7.0 | 175 | 24.6626 |
56
- | 26.0888 | 8.0 | 200 | 24.0502 |
57
- | 25.1282 | 9.0 | 225 | 23.2380 |
58
- | 23.4008 | 10.0 | 250 | 21.5011 |
59
- | 21.7893 | 11.0 | 275 | 19.6737 |
60
- | 18.3054 | 12.0 | 300 | 16.3135 |
61
- | 16.4864 | 13.0 | 325 | 15.0146 |
62
- | 15.5922 | 14.0 | 350 | 14.6707 |
63
- | 15.3752 | 15.0 | 375 | 14.3914 |
64
- | 15.1162 | 16.0 | 400 | 14.3017 |
65
- | 14.7205 | 17.0 | 425 | 13.8910 |
66
- | 14.469 | 18.0 | 450 | 13.6895 |
67
- | 14.1378 | 19.0 | 475 | 13.5207 |
68
- | 13.9013 | 20.0 | 500 | 13.3563 |
69
- | 13.7628 | 21.0 | 525 | 13.2093 |
70
- | 13.6721 | 22.0 | 550 | 13.1637 |
71
- | 13.674 | 23.0 | 575 | 13.0127 |
72
- | 13.4026 | 24.0 | 600 | 12.9253 |
73
- | 13.4045 | 25.0 | 625 | 12.8247 |
74
- | 13.1347 | 26.0 | 650 | 12.7143 |
75
- | 13.0661 | 27.0 | 675 | 12.6350 |
76
- | 12.8977 | 28.0 | 700 | 12.5850 |
77
- | 12.7914 | 29.0 | 725 | 12.4953 |
78
- | 12.5481 | 30.0 | 750 | 12.3920 |
79
- | 12.6336 | 31.0 | 775 | 12.3333 |
80
- | 12.4878 | 32.0 | 800 | 12.2702 |
81
- | 12.3079 | 33.0 | 825 | 12.2011 |
82
- | 12.3748 | 34.0 | 850 | 12.1754 |
83
- | 12.2519 | 35.0 | 875 | 12.1343 |
84
- | 12.3396 | 36.0 | 900 | 12.0725 |
85
- | 12.2185 | 37.0 | 925 | 11.9753 |
86
- | 11.8875 | 38.0 | 950 | 11.7175 |
87
- | 8.4831 | 39.0 | 975 | 7.6954 |
88
- | 3.4899 | 40.0 | 1000 | 2.1305 |
89
- | 1.7819 | 41.0 | 1025 | 1.0914 |
90
- | 1.1576 | 42.0 | 1050 | 0.7496 |
91
- | 0.9296 | 43.0 | 1075 | 0.5864 |
92
- | 0.7757 | 44.0 | 1100 | 0.5599 |
93
- | 0.7125 | 45.0 | 1125 | 0.5563 |
94
- | 0.6789 | 46.0 | 1150 | 0.5237 |
95
- | 0.6463 | 47.0 | 1175 | 0.5231 |
96
- | 0.6578 | 48.0 | 1200 | 0.5119 |
97
- | 0.6256 | 49.0 | 1225 | 0.5264 |
98
- | 0.6114 | 50.0 | 1250 | 0.5047 |
99
- | 0.6136 | 51.0 | 1275 | 0.5105 |
100
- | 0.6259 | 52.0 | 1300 | 0.5020 |
101
- | 0.578 | 53.0 | 1325 | 0.5053 |
102
- | 0.5717 | 54.0 | 1350 | 0.5021 |
103
- | 0.5804 | 55.0 | 1375 | 0.4999 |
104
- | 0.5851 | 56.0 | 1400 | 0.4934 |
105
- | 0.5879 | 57.0 | 1425 | 0.4905 |
106
- | 0.5812 | 58.0 | 1450 | 0.4958 |
107
- | 0.5448 | 59.0 | 1475 | 0.4923 |
108
- | 0.5523 | 60.0 | 1500 | 0.4962 |
109
- | 0.5733 | 61.0 | 1525 | 0.4925 |
110
- | 0.5586 | 62.0 | 1550 | 0.4878 |
111
- | 0.5675 | 63.0 | 1575 | 0.4921 |
112
- | 0.5484 | 64.0 | 1600 | 0.4940 |
113
- | 0.5522 | 65.0 | 1625 | 0.4896 |
114
- | 0.5428 | 66.0 | 1650 | 0.4902 |
115
- | 0.5656 | 67.0 | 1675 | 0.4945 |
116
 
117
 
118
  ### Framework versions
119
 
120
  - Transformers 4.34.0
121
  - Pytorch 2.1.0+cu121
122
- - Datasets 2.14.5
123
  - Tokenizers 0.14.1
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: SChem5Labels-google-t5-v1_1-large-inter_model-frequency-model_annots_str
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ # SChem5Labels-google-t5-v1_1-large-inter_model-frequency-model_annots_str
15
 
16
  This model is a fine-tuned version of [google/t5-v1_1-large](https://huggingface.co/google/t5-v1_1-large) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.9844
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 20.3817 | 1.0 | 25 | 23.8120 |
50
+ | 19.4374 | 2.0 | 50 | 21.8918 |
51
+ | 18.745 | 3.0 | 75 | 19.3959 |
52
+ | 16.896 | 4.0 | 100 | 15.4970 |
53
+ | 15.3045 | 5.0 | 125 | 11.5374 |
54
+ | 12.9955 | 6.0 | 150 | 9.6467 |
55
+ | 11.2112 | 7.0 | 175 | 8.9925 |
56
+ | 9.4851 | 8.0 | 200 | 8.7994 |
57
+ | 8.7487 | 9.0 | 225 | 8.5320 |
58
+ | 8.1197 | 10.0 | 250 | 8.3570 |
59
+ | 7.9164 | 11.0 | 275 | 8.2662 |
60
+ | 7.7789 | 12.0 | 300 | 8.1800 |
61
+ | 7.6671 | 13.0 | 325 | 8.0987 |
62
+ | 7.5107 | 14.0 | 350 | 7.9659 |
63
+ | 7.457 | 15.0 | 375 | 7.6850 |
64
+ | 7.1712 | 16.0 | 400 | 7.3914 |
65
+ | 6.9462 | 17.0 | 425 | 7.2019 |
66
+ | 6.8109 | 18.0 | 450 | 7.0657 |
67
+ | 6.7403 | 19.0 | 475 | 6.9778 |
68
+ | 6.5766 | 20.0 | 500 | 6.9288 |
69
+ | 6.505 | 21.0 | 525 | 6.8702 |
70
+ | 6.5148 | 22.0 | 550 | 6.8175 |
71
+ | 6.541 | 23.0 | 575 | 6.7619 |
72
+ | 4.3898 | 24.0 | 600 | 1.0917 |
73
+ | 1.0874 | 25.0 | 625 | 0.7681 |
74
+ | 0.8058 | 26.0 | 650 | 0.7295 |
75
+ | 0.7847 | 27.0 | 675 | 0.7244 |
76
+ | 0.7779 | 28.0 | 700 | 0.7195 |
77
+ | 0.7741 | 29.0 | 725 | 0.7205 |
78
+ | 0.7606 | 30.0 | 750 | 0.7222 |
79
+ | 0.7613 | 31.0 | 775 | 0.7189 |
80
+ | 0.7676 | 32.0 | 800 | 0.7119 |
81
+ | 0.7547 | 33.0 | 825 | 0.7138 |
82
+ | 0.7433 | 34.0 | 850 | 0.7148 |
83
+ | 0.7729 | 35.0 | 875 | 0.7202 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
 
85
 
86
  ### Framework versions
87
 
88
  - Transformers 4.34.0
89
  - Pytorch 2.1.0+cu121
90
+ - Datasets 2.6.1
91
  - Tokenizers 0.14.1
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15e56d0e371a2e92d463e9844a15034da1a88cece6104074805dab170d366ec5
3
  size 4825098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c694b16648b6eccad2a8826933faa4ec44323f901ddcc9b63e9088ab45ab55
3
  size 4825098
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94ee14bc2aa984d93f868f31f75c57d52ea51af578430f7b2cf0110953c86413
3
- size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2b969121e4121393c63637b71e1d7d67a428db04445efb93b4741719464ebf
3
+ size 6136