Hugging Face's logo

ernstliang
/
my_awesome_billsum_model

Text2Text Generation
Transformers
PyTorch
t5
generated_from_trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
ernstliang commited on
Commit
e9e563a
•
1 Parent(s): a8e872e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -13
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Rouge1
23
  type: rouge
24
- value: 0.1804
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,11 +31,11 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 2.4418
35
- - Rouge1: 0.1804
36
- - Rouge2: 0.0804
37
- - Rougel: 0.1501
38
- - Rougelsum: 0.1505
39
  - Gen Len: 19.0
40
 
41
  ## Model description
@@ -62,20 +62,21 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - num_epochs: 4
 
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
70
- | No log | 1.0 | 124 | 2.6399 | 0.1372 | 0.0469 | 0.1153 | 0.1154 | 19.0 |
71
- | No log | 2.0 | 248 | 2.5002 | 0.1543 | 0.0599 | 0.1288 | 0.129 | 19.0 |
72
- | No log | 3.0 | 372 | 2.4550 | 0.1725 | 0.0747 | 0.1442 | 0.1442 | 19.0 |
73
- | No log | 4.0 | 496 | 2.4418 | 0.1804 | 0.0804 | 0.1501 | 0.1505 | 19.0 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.30.2
79
  - Pytorch 2.0.1
80
- - Datasets 2.13.1
81
- - Tokenizers 0.13.3
 
21
  metrics:
22
  - name: Rouge1
23
  type: rouge
24
+ value: 0.1818
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the billsum dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 2.4938
35
+ - Rouge1: 0.1818
36
+ - Rouge2: 0.0856
37
+ - Rougel: 0.1532
38
+ - Rougelsum: 0.1532
39
  - Gen Len: 19.0
40
 
41
  ## Model description
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - num_epochs: 4
65
+ - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
70
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
71
+ | No log | 1.0 | 124 | 2.6861 | 0.131 | 0.0448 | 0.1097 | 0.1098 | 19.0 |
72
+ | No log | 2.0 | 248 | 2.5567 | 0.1498 | 0.0578 | 0.124 | 0.1239 | 19.0 |
73
+ | No log | 3.0 | 372 | 2.5080 | 0.1728 | 0.0771 | 0.1466 | 0.1465 | 19.0 |
74
+ | No log | 4.0 | 496 | 2.4938 | 0.1818 | 0.0856 | 0.1532 | 0.1532 | 19.0 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.29.2
80
  - Pytorch 2.0.1
81
+ - Datasets 2.12.0
82
+ - Tokenizers 0.13.2