owanr commited on
Commit
992e413
·
1 Parent(s): 91b1b54

End of training

Browse files
Files changed (3) hide show
  1. README.md +43 -76
  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: Sentiment-google-t5-v1_1-large-intra_model
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
- # Sentiment-google-t5-v1_1-large-intra_model
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: 0.7339
19
 
20
  ## Model description
21
 
@@ -46,83 +46,50 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 26.7302 | 1.0 | 44 | 32.0492 |
50
- | 25.113 | 2.0 | 88 | 22.7557 |
51
- | 21.4851 | 3.0 | 132 | 18.4480 |
52
- | 18.4481 | 4.0 | 176 | 17.5011 |
53
- | 15.5054 | 5.0 | 220 | 15.3850 |
54
- | 13.9707 | 6.0 | 264 | 14.0484 |
55
- | 12.761 | 7.0 | 308 | 13.0622 |
56
- | 11.4704 | 8.0 | 352 | 11.7809 |
57
- | 10.9338 | 9.0 | 396 | 11.1087 |
58
- | 10.6337 | 10.0 | 440 | 10.8794 |
59
- | 10.6582 | 11.0 | 484 | 10.7107 |
60
- | 10.1968 | 12.0 | 528 | 10.5772 |
61
- | 10.2664 | 13.0 | 572 | 10.4157 |
62
- | 9.9849 | 14.0 | 616 | 10.0942 |
63
- | 9.793 | 15.0 | 660 | 9.7870 |
64
- | 9.5156 | 16.0 | 704 | 9.6306 |
65
- | 9.2593 | 17.0 | 748 | 9.3983 |
66
- | 9.0143 | 18.0 | 792 | 9.2612 |
67
- | 8.9484 | 19.0 | 836 | 9.1514 |
68
- | 8.6726 | 20.0 | 880 | 9.0762 |
69
- | 8.5408 | 21.0 | 924 | 8.9965 |
70
- | 8.5944 | 22.0 | 968 | 8.9159 |
71
- | 8.6721 | 23.0 | 1012 | 8.8716 |
72
- | 8.3201 | 24.0 | 1056 | 8.8215 |
73
- | 8.3462 | 25.0 | 1100 | 8.7718 |
74
- | 8.4289 | 26.0 | 1144 | 8.7137 |
75
- | 8.2034 | 27.0 | 1188 | 8.6723 |
76
- | 8.3529 | 28.0 | 1232 | 8.6228 |
77
- | 8.0051 | 29.0 | 1276 | 8.5437 |
78
- | 4.5951 | 30.0 | 1320 | 3.9884 |
79
- | 3.7689 | 31.0 | 1364 | 3.9752 |
80
- | 3.8886 | 32.0 | 1408 | 3.9401 |
81
- | 3.7918 | 33.0 | 1452 | 3.9255 |
82
- | 3.7159 | 34.0 | 1496 | 3.9135 |
83
- | 3.7364 | 35.0 | 1540 | 3.9024 |
84
- | 3.6379 | 36.0 | 1584 | 3.8933 |
85
- | 3.6834 | 37.0 | 1628 | 3.8782 |
86
- | 3.5196 | 38.0 | 1672 | 3.8675 |
87
- | 3.5423 | 39.0 | 1716 | 3.8485 |
88
- | 3.635 | 40.0 | 1760 | 3.8308 |
89
- | 3.5791 | 41.0 | 1804 | 3.7949 |
90
- | 3.5878 | 42.0 | 1848 | 3.6340 |
91
- | 1.9533 | 43.0 | 1892 | 1.6975 |
92
- | 1.3746 | 44.0 | 1936 | 0.9731 |
93
- | 1.1216 | 45.0 | 1980 | 0.8581 |
94
- | 1.0273 | 46.0 | 2024 | 0.7932 |
95
- | 0.9245 | 47.0 | 2068 | 0.6956 |
96
- | 0.8437 | 48.0 | 2112 | 0.6750 |
97
- | 0.8431 | 49.0 | 2156 | 0.6681 |
98
- | 0.8127 | 50.0 | 2200 | 0.6492 |
99
- | 0.7827 | 51.0 | 2244 | 0.6452 |
100
- | 0.7643 | 52.0 | 2288 | 0.6512 |
101
- | 0.7748 | 53.0 | 2332 | 0.6544 |
102
- | 0.7677 | 54.0 | 2376 | 0.6353 |
103
- | 0.7714 | 55.0 | 2420 | 0.6341 |
104
- | 0.7433 | 56.0 | 2464 | 0.6338 |
105
- | 0.7511 | 57.0 | 2508 | 0.6347 |
106
- | 0.7492 | 58.0 | 2552 | 0.6594 |
107
- | 0.7479 | 59.0 | 2596 | 0.6441 |
108
- | 0.7434 | 60.0 | 2640 | 0.6307 |
109
- | 0.7184 | 61.0 | 2684 | 0.6313 |
110
- | 0.7339 | 62.0 | 2728 | 0.6293 |
111
- | 0.7617 | 63.0 | 2772 | 0.6282 |
112
- | 0.7382 | 64.0 | 2816 | 0.6304 |
113
- | 0.7236 | 65.0 | 2860 | 0.6272 |
114
- | 0.7333 | 66.0 | 2904 | 0.6281 |
115
- | 0.7155 | 67.0 | 2948 | 0.6269 |
116
- | 0.726 | 68.0 | 2992 | 0.6299 |
117
- | 0.7463 | 69.0 | 3036 | 0.6287 |
118
- | 0.7202 | 70.0 | 3080 | 0.6278 |
119
- | 0.7402 | 71.0 | 3124 | 0.6293 |
120
- | 0.7418 | 72.0 | 3168 | 0.6325 |
121
 
122
 
123
  ### Framework versions
124
 
125
  - Transformers 4.34.0
126
  - Pytorch 2.1.0+cu121
127
- - Datasets 2.14.5
128
  - Tokenizers 0.14.1
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: Sentiment-google-t5-v1_1-large-intra_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
+ # Sentiment-google-t5-v1_1-large-intra_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: 1.6025
19
 
20
  ## Model description
21
 
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 20.2785 | 1.0 | 44 | 24.1630 |
50
+ | 16.5089 | 2.0 | 88 | 12.6240 |
51
+ | 12.1856 | 3.0 | 132 | 9.5483 |
52
+ | 9.6054 | 4.0 | 176 | 9.1792 |
53
+ | 8.6106 | 5.0 | 220 | 8.9367 |
54
+ | 8.4152 | 6.0 | 264 | 8.7252 |
55
+ | 8.3046 | 7.0 | 308 | 8.5101 |
56
+ | 7.8895 | 8.0 | 352 | 8.1848 |
57
+ | 7.7099 | 9.0 | 396 | 7.7711 |
58
+ | 7.3027 | 10.0 | 440 | 7.4309 |
59
+ | 7.1553 | 11.0 | 484 | 7.2568 |
60
+ | 6.9202 | 12.0 | 528 | 7.1566 |
61
+ | 6.8527 | 13.0 | 572 | 7.0624 |
62
+ | 6.5631 | 14.0 | 616 | 6.8983 |
63
+ | 1.0138 | 15.0 | 660 | 0.7973 |
64
+ | 0.8985 | 16.0 | 704 | 0.7822 |
65
+ | 0.8793 | 17.0 | 748 | 0.7791 |
66
+ | 0.8737 | 18.0 | 792 | 0.7799 |
67
+ | 0.8562 | 19.0 | 836 | 0.7812 |
68
+ | 0.8563 | 20.0 | 880 | 0.7742 |
69
+ | 0.8498 | 21.0 | 924 | 0.7738 |
70
+ | 0.8316 | 22.0 | 968 | 0.7683 |
71
+ | 0.8281 | 23.0 | 1012 | 0.7688 |
72
+ | 0.8314 | 24.0 | 1056 | 0.7732 |
73
+ | 0.8161 | 25.0 | 1100 | 0.7660 |
74
+ | 0.8273 | 26.0 | 1144 | 0.7634 |
75
+ | 0.8314 | 27.0 | 1188 | 0.7622 |
76
+ | 0.828 | 28.0 | 1232 | 0.7625 |
77
+ | 0.8161 | 29.0 | 1276 | 0.7605 |
78
+ | 0.812 | 30.0 | 1320 | 0.7602 |
79
+ | 0.8126 | 31.0 | 1364 | 0.7580 |
80
+ | 0.8021 | 32.0 | 1408 | 0.7649 |
81
+ | 0.7973 | 33.0 | 1452 | 0.7588 |
82
+ | 0.8076 | 34.0 | 1496 | 0.7569 |
83
+ | 0.819 | 35.0 | 1540 | 0.7559 |
84
+ | 0.8069 | 36.0 | 1584 | 0.7540 |
85
+ | 0.8042 | 37.0 | 1628 | 0.7546 |
86
+ | 0.8054 | 38.0 | 1672 | 0.7579 |
87
+ | 0.8049 | 39.0 | 1716 | 0.7584 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
 
90
  ### Framework versions
91
 
92
  - Transformers 4.34.0
93
  - Pytorch 2.1.0+cu121
94
+ - Datasets 2.6.1
95
  - Tokenizers 0.14.1
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dfa2728d8e50b09fa9045270adddc11886e0a4458567a6b4d82bd2c23e382ea
3
  size 4825098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed82b97f080fd59aaba0ec1d729e838a13659979eeb68e6336f5a1568b996d8f
3
  size 4825098
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:627db213e40b8aaa6b8bc0b1c3763d813a8ee3c37b0e182da37984b5f7500d76
3
- size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d2a934089e4d98ae45b2530a5603eacd94e465221cdddd249b52863e0aac4f
3
+ size 6136