Hugging Face's logo

satyanshu404
/
long-t5-local-base-finetuned-justification-v03

Text2Text Generation
Transformers
Safetensors
longt5
Generated from Trainer
Inference Endpoints
Model card Files Community
satyanshu404 commited on
Commit
4886f61
·
verified ·
1 Parent(s): b2946d9

End of training

Browse files
Files changed (3) hide show
  1. README.md +156 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/long-t5-local-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: long-t5-local-base-finetuned-justification-v03
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
+ # long-t5-local-base-finetuned-justification-v03
15
+
16
+ This model is a fine-tuned version of [google/long-t5-local-base](https://huggingface.co/google/long-t5-local-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.0759
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-07
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 100
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 37.3451 | 1.0 | 676 | 30.7532 |
50
+ | 35.6146 | 2.0 | 1352 | 28.8261 |
51
+ | 32.3915 | 3.0 | 2028 | 26.9524 |
52
+ | 30.6984 | 4.0 | 2704 | 25.0794 |
53
+ | 29.1119 | 5.0 | 3380 | 23.2287 |
54
+ | 25.8833 | 6.0 | 4056 | 21.3800 |
55
+ | 24.6464 | 7.0 | 4732 | 19.5382 |
56
+ | 23.0238 | 8.0 | 5408 | 17.7077 |
57
+ | 20.1628 | 9.0 | 6084 | 15.7830 |
58
+ | 18.3835 | 10.0 | 6760 | 13.7916 |
59
+ | 17.0307 | 11.0 | 7436 | 11.7701 |
60
+ | 13.9093 | 12.0 | 8112 | 9.7176 |
61
+ | 12.3394 | 13.0 | 8788 | 7.7920 |
62
+ | 10.888 | 14.0 | 9464 | 6.6093 |
63
+ | 8.1438 | 15.0 | 10140 | 6.1657 |
64
+ | 7.1948 | 16.0 | 10816 | 5.9876 |
65
+ | 6.4311 | 17.0 | 11492 | 5.8574 |
66
+ | 5.2684 | 18.0 | 12168 | 5.7303 |
67
+ | 5.2309 | 19.0 | 12844 | 5.6090 |
68
+ | 4.6475 | 20.0 | 13520 | 5.4782 |
69
+ | 4.583 | 21.0 | 14196 | 5.3425 |
70
+ | 4.3645 | 22.0 | 14872 | 5.2021 |
71
+ | 4.1721 | 23.0 | 15548 | 5.0568 |
72
+ | 4.1423 | 24.0 | 16224 | 4.9156 |
73
+ | 3.983 | 25.0 | 16900 | 4.7832 |
74
+ | 3.9396 | 26.0 | 17576 | 4.6574 |
75
+ | 3.8342 | 27.0 | 18252 | 4.5455 |
76
+ | 3.651 | 28.0 | 18928 | 4.4371 |
77
+ | 3.663 | 29.0 | 19604 | 4.3453 |
78
+ | 3.5847 | 30.0 | 20280 | 4.2648 |
79
+ | 3.5013 | 31.0 | 20956 | 4.1942 |
80
+ | 3.5122 | 32.0 | 21632 | 4.1298 |
81
+ | 3.3473 | 33.0 | 22308 | 4.0700 |
82
+ | 3.3417 | 34.0 | 22984 | 4.0167 |
83
+ | 3.3881 | 35.0 | 23660 | 3.9700 |
84
+ | 3.2404 | 36.0 | 24336 | 3.9258 |
85
+ | 3.2232 | 37.0 | 25012 | 3.8830 |
86
+ | 3.2287 | 38.0 | 25688 | 3.8438 |
87
+ | 3.0759 | 39.0 | 26364 | 3.8066 |
88
+ | 3.053 | 40.0 | 27040 | 3.7711 |
89
+ | 3.0726 | 41.0 | 27716 | 3.7386 |
90
+ | 3.0198 | 42.0 | 28392 | 3.7072 |
91
+ | 3.0923 | 43.0 | 29068 | 3.6768 |
92
+ | 2.986 | 44.0 | 29744 | 3.6489 |
93
+ | 2.9184 | 45.0 | 30420 | 3.6221 |
94
+ | 2.9114 | 46.0 | 31096 | 3.5972 |
95
+ | 2.9585 | 47.0 | 31772 | 3.5736 |
96
+ | 2.91 | 48.0 | 32448 | 3.5477 |
97
+ | 2.8974 | 49.0 | 33124 | 3.5252 |
98
+ | 2.9211 | 50.0 | 33800 | 3.5020 |
99
+ | 2.785 | 51.0 | 34476 | 3.4795 |
100
+ | 2.8177 | 52.0 | 35152 | 3.4581 |
101
+ | 2.9204 | 53.0 | 35828 | 3.4392 |
102
+ | 2.7911 | 54.0 | 36504 | 3.4199 |
103
+ | 2.8178 | 55.0 | 37180 | 3.4013 |
104
+ | 2.8029 | 56.0 | 37856 | 3.3830 |
105
+ | 2.7654 | 57.0 | 38532 | 3.3655 |
106
+ | 2.7854 | 58.0 | 39208 | 3.3486 |
107
+ | 2.7322 | 59.0 | 39884 | 3.3314 |
108
+ | 2.722 | 60.0 | 40560 | 3.3161 |
109
+ | 2.6665 | 61.0 | 41236 | 3.3016 |
110
+ | 2.719 | 62.0 | 41912 | 3.2865 |
111
+ | 2.6758 | 63.0 | 42588 | 3.2720 |
112
+ | 2.6586 | 64.0 | 43264 | 3.2582 |
113
+ | 2.6443 | 65.0 | 43940 | 3.2451 |
114
+ | 2.6656 | 66.0 | 44616 | 3.2322 |
115
+ | 2.6183 | 67.0 | 45292 | 3.2206 |
116
+ | 2.6143 | 68.0 | 45968 | 3.2087 |
117
+ | 2.6117 | 69.0 | 46644 | 3.1989 |
118
+ | 2.6567 | 70.0 | 47320 | 3.1890 |
119
+ | 2.5946 | 71.0 | 47996 | 3.1797 |
120
+ | 2.5836 | 72.0 | 48672 | 3.1703 |
121
+ | 2.5928 | 73.0 | 49348 | 3.1627 |
122
+ | 2.6024 | 74.0 | 50024 | 3.1552 |
123
+ | 2.6117 | 75.0 | 50700 | 3.1469 |
124
+ | 2.5681 | 76.0 | 51376 | 3.1392 |
125
+ | 2.5731 | 77.0 | 52052 | 3.1329 |
126
+ | 2.5749 | 78.0 | 52728 | 3.1267 |
127
+ | 2.5788 | 79.0 | 53404 | 3.1208 |
128
+ | 2.5478 | 80.0 | 54080 | 3.1156 |
129
+ | 2.6048 | 81.0 | 54756 | 3.1104 |
130
+ | 2.5514 | 82.0 | 55432 | 3.1062 |
131
+ | 2.5705 | 83.0 | 56108 | 3.1027 |
132
+ | 2.5733 | 84.0 | 56784 | 3.0994 |
133
+ | 2.4704 | 85.0 | 57460 | 3.0965 |
134
+ | 2.558 | 86.0 | 58136 | 3.0928 |
135
+ | 2.5566 | 87.0 | 58812 | 3.0895 |
136
+ | 2.4822 | 88.0 | 59488 | 3.0869 |
137
+ | 2.5377 | 89.0 | 60164 | 3.0844 |
138
+ | 2.5173 | 90.0 | 60840 | 3.0826 |
139
+ | 2.5312 | 91.0 | 61516 | 3.0809 |
140
+ | 2.5038 | 92.0 | 62192 | 3.0799 |
141
+ | 2.5645 | 93.0 | 62868 | 3.0788 |
142
+ | 2.5612 | 94.0 | 63544 | 3.0778 |
143
+ | 2.4948 | 95.0 | 64220 | 3.0770 |
144
+ | 2.538 | 96.0 | 64896 | 3.0765 |
145
+ | 2.4701 | 97.0 | 65572 | 3.0762 |
146
+ | 2.5269 | 98.0 | 66248 | 3.0759 |
147
+ | 2.5265 | 99.0 | 66924 | 3.0759 |
148
+ | 2.4955 | 100.0 | 67600 | 3.0759 |
149
+
150
+
151
+ ### Framework versions
152
+
153
+ - Transformers 4.38.2
154
+ - Pytorch 2.2.2+cu121
155
+ - Datasets 2.18.0
156
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe583c8ed5c658ce6094f54683ff208d8be497d39be7b4908732b70dd13ca425
3
  size 990345312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8098aa74bfe23681ccf63adc7d6c7d6d11452f8f6fd9d979164e4ec78a7ea6c
3
  size 990345312