Hugging Face's logo

apatidar0
/
t5-base-dutch-finetuned-mt5_base_keyword_extraction_dutch

Text2Text Generation
Transformers
TensorBoard
Safetensors
t5
summarization dutch for keyword extraction from new
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
apatidar0 commited on
Commit
1eee82b
•
1 Parent(s): 35694f4

Training complete

Browse files
Files changed (4) hide show
  1. README.md +29 -29
  2. generation_config.json +1 -0
  3. model.safetensors +1 -1
  4. runs/Feb28_08-20-42_cd630655d525/events.out.tfevents.1709108449.cd630655d525.15303.0 +2 -2
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: apache-2.0
3
  base_model: yhavinga/t5-base-dutch
4
  tags:
5
- - summarization dutch for keyword extraction from the prompt for bm25 search
6
  - generated_from_trainer
7
  metrics:
8
  - rouge
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [yhavinga/t5-base-dutch](https://huggingface.co/yhavinga/t5-base-dutch) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6190
22
- - Rouge1: 0.5259
23
- - Rouge2: 0.3913
24
- - Rougel: 0.5107
25
- - Rougelsum: 0.5104
26
 
27
  ## Model description
28
 
@@ -42,11 +42,11 @@ More information needed
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 5.6e-05
45
- - train_batch_size: 15
46
- - eval_batch_size: 15
47
  - seed: 42
48
  - gradient_accumulation_steps: 2
49
- - total_train_batch_size: 30
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - num_epochs: 20
@@ -55,26 +55,26 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
- | No log | 0.99 | 87 | 1.2611 | 0.4697 | 0.3224 | 0.4518 | 0.4517 |
59
- | 1.3975 | 2.0 | 175 | 0.9301 | 0.5024 | 0.3619 | 0.4881 | 0.4878 |
60
- | 1.3975 | 2.99 | 262 | 0.7385 | 0.4958 | 0.3481 | 0.4781 | 0.4782 |
61
- | 0.7599 | 4.0 | 350 | 0.6660 | 0.4998 | 0.3532 | 0.4834 | 0.4831 |
62
- | 0.7599 | 4.99 | 437 | 0.6513 | 0.4925 | 0.3475 | 0.4763 | 0.4760 |
63
- | 0.5967 | 6.0 | 525 | 0.6456 | 0.5015 | 0.3545 | 0.4834 | 0.4826 |
64
- | 0.5967 | 6.99 | 612 | 0.6412 | 0.5031 | 0.3550 | 0.4838 | 0.4838 |
65
- | 0.5147 | 8.0 | 700 | 0.6355 | 0.5027 | 0.3563 | 0.4849 | 0.4840 |
66
- | 0.5147 | 8.99 | 787 | 0.6342 | 0.5083 | 0.3653 | 0.4912 | 0.4910 |
67
- | 0.456 | 10.0 | 875 | 0.6354 | 0.5070 | 0.3672 | 0.4912 | 0.4906 |
68
- | 0.456 | 10.99 | 962 | 0.6408 | 0.5046 | 0.3638 | 0.4889 | 0.4884 |
69
- | 0.4097 | 12.0 | 1050 | 0.6292 | 0.5080 | 0.3689 | 0.4925 | 0.4926 |
70
- | 0.4097 | 12.99 | 1137 | 0.6283 | 0.5104 | 0.3681 | 0.4952 | 0.4953 |
71
- | 0.3704 | 14.0 | 1225 | 0.6327 | 0.5116 | 0.3711 | 0.4942 | 0.4943 |
72
- | 0.3704 | 14.99 | 1312 | 0.6287 | 0.5127 | 0.3732 | 0.4961 | 0.4965 |
73
- | 0.3394 | 16.0 | 1400 | 0.6272 | 0.5179 | 0.3804 | 0.5015 | 0.5012 |
74
- | 0.3394 | 16.99 | 1487 | 0.6235 | 0.5232 | 0.3851 | 0.5070 | 0.5070 |
75
- | 0.3189 | 18.0 | 1575 | 0.6174 | 0.5245 | 0.3869 | 0.5093 | 0.5089 |
76
- | 0.3189 | 18.99 | 1662 | 0.6174 | 0.5261 | 0.3916 | 0.5118 | 0.5117 |
77
- | 0.3049 | 19.89 | 1740 | 0.6190 | 0.5259 | 0.3913 | 0.5107 | 0.5104 |
78
 
79
 
80
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: yhavinga/t5-base-dutch
4
  tags:
5
+ - summarization dutch for keyword extraction from new
6
  - generated_from_trainer
7
  metrics:
8
  - rouge
 
18
 
19
  This model is a fine-tuned version of [yhavinga/t5-base-dutch](https://huggingface.co/yhavinga/t5-base-dutch) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6065
22
+ - Rouge1: 0.7675
23
+ - Rouge2: 0.5965
24
+ - Rougel: 0.7531
25
+ - Rougelsum: 0.7534
26
 
27
  ## Model description
28
 
 
42
 
43
  The following hyperparameters were used during training:
44
  - learning_rate: 5.6e-05
45
+ - train_batch_size: 14
46
+ - eval_batch_size: 14
47
  - seed: 42
48
  - gradient_accumulation_steps: 2
49
+ - total_train_batch_size: 28
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
  - num_epochs: 20
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
+ | No log | 1.0 | 94 | 1.2820 | 0.4332 | 0.3007 | 0.4175 | 0.4174 |
59
+ | 1.4828 | 2.0 | 188 | 0.9360 | 0.6075 | 0.4541 | 0.5916 | 0.5912 |
60
+ | 1.4828 | 3.0 | 282 | 0.7435 | 0.6542 | 0.4825 | 0.6358 | 0.6366 |
61
+ | 0.7633 | 4.0 | 376 | 0.6623 | 0.6867 | 0.5071 | 0.6692 | 0.6697 |
62
+ | 0.7633 | 5.0 | 470 | 0.6481 | 0.7061 | 0.5254 | 0.6909 | 0.6913 |
63
+ | 0.5935 | 6.0 | 564 | 0.6456 | 0.7155 | 0.5367 | 0.6984 | 0.6995 |
64
+ | 0.5935 | 7.0 | 658 | 0.6387 | 0.7162 | 0.5388 | 0.6993 | 0.7001 |
65
+ | 0.5101 | 8.0 | 752 | 0.6341 | 0.7247 | 0.5495 | 0.7086 | 0.7102 |
66
+ | 0.5101 | 9.0 | 846 | 0.6306 | 0.7335 | 0.5527 | 0.7166 | 0.7176 |
67
+ | 0.4449 | 10.0 | 940 | 0.6412 | 0.7324 | 0.5559 | 0.7160 | 0.7166 |
68
+ | 0.4449 | 11.0 | 1034 | 0.6439 | 0.7273 | 0.5513 | 0.7126 | 0.7136 |
69
+ | 0.4001 | 12.0 | 1128 | 0.6294 | 0.7415 | 0.5644 | 0.7266 | 0.7268 |
70
+ | 0.4001 | 13.0 | 1222 | 0.6252 | 0.7447 | 0.5658 | 0.7294 | 0.7296 |
71
+ | 0.3589 | 14.0 | 1316 | 0.6257 | 0.7490 | 0.5743 | 0.7341 | 0.7347 |
72
+ | 0.3589 | 15.0 | 1410 | 0.6132 | 0.7474 | 0.5751 | 0.7339 | 0.7346 |
73
+ | 0.3263 | 16.0 | 1504 | 0.6119 | 0.7616 | 0.5858 | 0.7469 | 0.7470 |
74
+ | 0.3263 | 17.0 | 1598 | 0.6088 | 0.7674 | 0.5945 | 0.7527 | 0.7530 |
75
+ | 0.2989 | 18.0 | 1692 | 0.6108 | 0.7655 | 0.5917 | 0.7510 | 0.7514 |
76
+ | 0.2989 | 19.0 | 1786 | 0.6020 | 0.7681 | 0.5961 | 0.7539 | 0.7545 |
77
+ | 0.2846 | 20.0 | 1880 | 0.6065 | 0.7675 | 0.5965 | 0.7531 | 0.7534 |
78
 
79
 
80
  ### Framework versions
generation_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
 
4
  "pad_token_id": 0,
5
  "transformers_version": "4.37.2"
6
  }
 
1
  {
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
+ "max_new_tokens": 512,
5
  "pad_token_id": 0,
6
  "transformers_version": "4.37.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c26e2dda6c82ce585e79b1be4dbafda1598f7280f47a96a4011ffe0e3b06a63e
3
  size 891567912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3155e0d5e1b33cc724ca0bc294fa837dcabb84e24192752c773acbc149a6d908
3
  size 891567912
runs/Feb28_08-20-42_cd630655d525/events.out.tfevents.1709108449.cd630655d525.15303.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad4db04896681c311033d6b6bf538f2621ce0471af317e9a86e7db9e404bc090
3
- size 8212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5264483b0561dbd97b6fbc35a1cdc0d7a19dd00f3ce7ac2abe7a8fd849fce554
3
+ size 16932