Hugging Face's logo

ar5entum
/
bart_rom_dev_tl

Text2Text Generation
Transformers
TensorBoard
Safetensors
English
Hindi
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ar5entum commited on
Commit
b9cf533
·
verified ·
1 Parent(s): 3dba795

Model save

Browse files
Files changed (2) hide show
  1. README.md +165 -0
  2. generation_config.json +8 -0
README.md ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: ar5entum/bart_hin_eng_mt
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - bleu
8
+ model-index:
9
+ - name: bart_rom_dev_tl
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bart_rom_dev_tl
17
+
18
+ This model is a fine-tuned version of [ar5entum/bart_hin_eng_mt](https://huggingface.co/ar5entum/bart_hin_eng_mt) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0998
21
+ - Bleu: 63.9396
22
+ - Gen Len: 114.6678
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 100
43
+ - eval_batch_size: 40
44
+ - seed: 42
45
+ - distributed_type: multi-GPU
46
+ - num_devices: 2
47
+ - total_train_batch_size: 200
48
+ - total_eval_batch_size: 80
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 80
52
+ - num_epochs: 100.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
57
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:--------:|
58
+ | 1.1468 | 1.0 | 71 | 1.0356 | 0.1783 | 127.8914 |
59
+ | 0.9193 | 2.0 | 142 | 0.7876 | 0.7522 | 120.098 |
60
+ | 0.714 | 3.0 | 213 | 0.5704 | 2.2388 | 116.7362 |
61
+ | 0.5751 | 4.0 | 284 | 0.4415 | 5.169 | 115.8671 |
62
+ | 0.4807 | 5.0 | 355 | 0.3694 | 9.2386 | 114.9026 |
63
+ | 0.4178 | 6.0 | 426 | 0.3220 | 13.4352 | 114.9967 |
64
+ | 0.3717 | 7.0 | 497 | 0.2920 | 16.5527 | 114.3776 |
65
+ | 0.3355 | 8.0 | 568 | 0.2728 | 18.8968 | 113.7553 |
66
+ | 0.3103 | 9.0 | 639 | 0.2502 | 22.688 | 114.4191 |
67
+ | 0.2916 | 10.0 | 710 | 0.2346 | 24.9505 | 114.3487 |
68
+ | 0.2696 | 11.0 | 781 | 0.2237 | 26.5227 | 114.2283 |
69
+ | 0.2583 | 12.0 | 852 | 0.2129 | 28.6141 | 114.0349 |
70
+ | 0.2438 | 13.0 | 923 | 0.2019 | 30.3471 | 114.3934 |
71
+ | 0.23 | 14.0 | 994 | 0.1972 | 31.3042 | 114.2145 |
72
+ | 0.2158 | 15.0 | 1065 | 0.1871 | 33.5445 | 114.5664 |
73
+ | 0.2108 | 16.0 | 1136 | 0.1811 | 34.5349 | 114.2928 |
74
+ | 0.2033 | 17.0 | 1207 | 0.1749 | 35.8154 | 114.4217 |
75
+ | 0.1901 | 18.0 | 1278 | 0.1706 | 36.853 | 114.55 |
76
+ | 0.1879 | 19.0 | 1349 | 0.1665 | 37.8791 | 114.4046 |
77
+ | 0.1772 | 20.0 | 1420 | 0.1605 | 39.197 | 114.6211 |
78
+ | 0.167 | 21.0 | 1491 | 0.1582 | 40.4274 | 114.5737 |
79
+ | 0.1678 | 22.0 | 1562 | 0.1549 | 40.4937 | 114.377 |
80
+ | 0.1621 | 23.0 | 1633 | 0.1508 | 42.0233 | 114.5882 |
81
+ | 0.1585 | 24.0 | 1704 | 0.1477 | 42.7916 | 114.573 |
82
+ | 0.1494 | 25.0 | 1775 | 0.1449 | 43.8836 | 114.6026 |
83
+ | 0.1477 | 26.0 | 1846 | 0.1424 | 44.1819 | 114.5197 |
84
+ | 0.1441 | 27.0 | 1917 | 0.1399 | 44.9919 | 114.6526 |
85
+ | 0.1379 | 28.0 | 1988 | 0.1375 | 45.8493 | 114.5329 |
86
+ | 0.1354 | 29.0 | 2059 | 0.1358 | 45.7367 | 114.4757 |
87
+ | 0.1325 | 30.0 | 2130 | 0.1330 | 46.9613 | 114.698 |
88
+ | 0.1288 | 31.0 | 2201 | 0.1315 | 47.5834 | 114.6257 |
89
+ | 0.1262 | 32.0 | 2272 | 0.1300 | 47.9596 | 114.5145 |
90
+ | 0.1232 | 33.0 | 2343 | 0.1277 | 48.2481 | 114.6474 |
91
+ | 0.1173 | 34.0 | 2414 | 0.1264 | 48.8469 | 114.623 |
92
+ | 0.1138 | 35.0 | 2485 | 0.1248 | 49.5157 | 114.6112 |
93
+ | 0.1126 | 36.0 | 2556 | 0.1237 | 49.6457 | 114.5947 |
94
+ | 0.1125 | 37.0 | 2627 | 0.1225 | 50.4627 | 114.6875 |
95
+ | 0.1101 | 38.0 | 2698 | 0.1207 | 50.9736 | 114.6388 |
96
+ | 0.1069 | 39.0 | 2769 | 0.1198 | 51.5928 | 114.6579 |
97
+ | 0.1035 | 40.0 | 2840 | 0.1185 | 52.0712 | 114.6132 |
98
+ | 0.096 | 41.0 | 2911 | 0.1175 | 52.6016 | 114.6441 |
99
+ | 0.0958 | 42.0 | 2982 | 0.1172 | 52.9595 | 114.6066 |
100
+ | 0.0967 | 43.0 | 3053 | 0.1160 | 52.6965 | 114.6461 |
101
+ | 0.0948 | 44.0 | 3124 | 0.1151 | 53.5073 | 114.6737 |
102
+ | 0.0957 | 45.0 | 3195 | 0.1144 | 53.5772 | 114.6822 |
103
+ | 0.0922 | 46.0 | 3266 | 0.1135 | 54.2084 | 114.6612 |
104
+ | 0.0903 | 47.0 | 3337 | 0.1127 | 54.2512 | 114.6368 |
105
+ | 0.088 | 48.0 | 3408 | 0.1119 | 55.1423 | 114.6947 |
106
+ | 0.0869 | 49.0 | 3479 | 0.1109 | 55.4669 | 114.6467 |
107
+ | 0.0849 | 50.0 | 3550 | 0.1110 | 55.7087 | 114.5855 |
108
+ | 0.0825 | 51.0 | 3621 | 0.1105 | 55.5851 | 114.6349 |
109
+ | 0.0818 | 52.0 | 3692 | 0.1097 | 57.163 | 114.727 |
110
+ | 0.0811 | 53.0 | 3763 | 0.1089 | 57.233 | 114.5928 |
111
+ | 0.0767 | 54.0 | 3834 | 0.1083 | 57.0785 | 114.6822 |
112
+ | 0.0751 | 55.0 | 3905 | 0.1081 | 57.4657 | 114.6487 |
113
+ | 0.0737 | 56.0 | 3976 | 0.1078 | 57.6215 | 114.848 |
114
+ | 0.0766 | 57.0 | 4047 | 0.1071 | 57.8275 | 114.5743 |
115
+ | 0.0766 | 58.0 | 4118 | 0.1064 | 58.1423 | 114.6309 |
116
+ | 0.0716 | 59.0 | 4189 | 0.1056 | 58.5167 | 114.7026 |
117
+ | 0.071 | 60.0 | 4260 | 0.1053 | 59.226 | 114.627 |
118
+ | 0.0715 | 61.0 | 4331 | 0.1054 | 59.1511 | 114.6697 |
119
+ | 0.0709 | 62.0 | 4402 | 0.1046 | 59.3669 | 114.6816 |
120
+ | 0.0703 | 63.0 | 4473 | 0.1046 | 59.418 | 114.6171 |
121
+ | 0.0686 | 64.0 | 4544 | 0.1039 | 60.1412 | 114.6961 |
122
+ | 0.066 | 65.0 | 4615 | 0.1037 | 60.4565 | 114.7559 |
123
+ | 0.0647 | 66.0 | 4686 | 0.1039 | 59.9588 | 114.6382 |
124
+ | 0.0668 | 67.0 | 4757 | 0.1030 | 60.5026 | 114.7447 |
125
+ | 0.0649 | 68.0 | 4828 | 0.1035 | 60.2735 | 114.6099 |
126
+ | 0.0637 | 69.0 | 4899 | 0.1032 | 60.6524 | 114.6171 |
127
+ | 0.0641 | 70.0 | 4970 | 0.1029 | 60.7721 | 114.7461 |
128
+ | 0.0639 | 71.0 | 5041 | 0.1025 | 61.1837 | 114.6901 |
129
+ | 0.062 | 72.0 | 5112 | 0.1024 | 61.3516 | 114.7447 |
130
+ | 0.0588 | 73.0 | 5183 | 0.1025 | 61.3766 | 114.6539 |
131
+ | 0.0609 | 74.0 | 5254 | 0.1019 | 61.8364 | 114.7467 |
132
+ | 0.0592 | 75.0 | 5325 | 0.1020 | 61.7948 | 114.7072 |
133
+ | 0.0604 | 76.0 | 5396 | 0.1019 | 61.8981 | 114.6921 |
134
+ | 0.0593 | 77.0 | 5467 | 0.1013 | 61.9623 | 114.6921 |
135
+ | 0.057 | 78.0 | 5538 | 0.1013 | 62.2082 | 114.6553 |
136
+ | 0.0595 | 79.0 | 5609 | 0.1011 | 62.3174 | 114.6684 |
137
+ | 0.0565 | 80.0 | 5680 | 0.1010 | 62.1364 | 114.6158 |
138
+ | 0.0592 | 81.0 | 5751 | 0.1009 | 62.6892 | 114.6671 |
139
+ | 0.0563 | 82.0 | 5822 | 0.1010 | 62.431 | 114.7099 |
140
+ | 0.0544 | 83.0 | 5893 | 0.1007 | 62.78 | 114.6579 |
141
+ | 0.0546 | 84.0 | 5964 | 0.1009 | 62.8921 | 114.6112 |
142
+ | 0.0558 | 85.0 | 6035 | 0.1007 | 62.7137 | 114.7289 |
143
+ | 0.0529 | 86.0 | 6106 | 0.1008 | 62.859 | 114.6401 |
144
+ | 0.0549 | 87.0 | 6177 | 0.1003 | 63.1903 | 114.6934 |
145
+ | 0.0544 | 88.0 | 6248 | 0.1003 | 63.2949 | 114.6888 |
146
+ | 0.0535 | 89.0 | 6319 | 0.1005 | 63.3252 | 114.6546 |
147
+ | 0.0547 | 90.0 | 6390 | 0.0999 | 63.3835 | 114.7 |
148
+ | 0.0533 | 91.0 | 6461 | 0.0999 | 63.5284 | 114.6875 |
149
+ | 0.0523 | 92.0 | 6532 | 0.1000 | 63.6207 | 114.7145 |
150
+ | 0.0533 | 93.0 | 6603 | 0.0999 | 63.5598 | 114.723 |
151
+ | 0.0545 | 94.0 | 6674 | 0.0999 | 63.6451 | 114.7303 |
152
+ | 0.052 | 95.0 | 6745 | 0.0999 | 63.6712 | 114.7283 |
153
+ | 0.0527 | 96.0 | 6816 | 0.1001 | 63.7187 | 114.6711 |
154
+ | 0.0511 | 97.0 | 6887 | 0.0999 | 63.9161 | 114.6671 |
155
+ | 0.0531 | 98.0 | 6958 | 0.0999 | 63.8758 | 114.6645 |
156
+ | 0.0539 | 99.0 | 7029 | 0.0999 | 63.9162 | 114.6566 |
157
+ | 0.0533 | 100.0 | 7100 | 0.0998 | 63.9396 | 114.6678 |
158
+
159
+
160
+ ### Framework versions
161
+
162
+ - Transformers 4.45.0.dev0
163
+ - Pytorch 2.4.0+cu121
164
+ - Datasets 2.21.0
165
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.45.0.dev0"
8
+ }