Hugging Face's logo

mrm8488
/
T5-base-finetuned-cuad

Text2Text Generation
Transformers
PyTorch
Safetensors
English
t5
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Community
2
mrm8488 commited on
Commit
d86a279
•
1 Parent(s): 1a2bb84

Update model

Browse files
Files changed (4) hide show
  1. README.md +15 -17
  2. pytorch_model.bin +1 -1
  3. tokenizer.json +0 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -4,23 +4,21 @@ language:
4
  license: mit
5
  tags:
6
  - generated_from_trainer
7
- - legal
8
- - qa
9
  datasets:
10
  - cuad
11
  model-index:
12
- - name: T5-base-cuad
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # T5-base fine-tuned on CUAD for legal QA
20
 
21
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the cuad dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4275
24
 
25
  ## Model description
26
 
@@ -40,8 +38,8 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
- - train_batch_size: 8
44
- - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
@@ -51,16 +49,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:-----:|:---------------:|
54
- | 0.5632 | 1.0 | 1398 | 0.4593 |
55
- | 0.5098 | 2.0 | 2796 | 0.4428 |
56
- | 0.4718 | 3.0 | 4194 | 0.4349 |
57
- | 0.4459 | 4.0 | 5592 | 0.4313 |
58
- | 0.4363 | 5.0 | 6990 | 0.4304 |
59
- | 0.4077 | 6.0 | 8388 | 0.4275 |
60
- | 0.4159 | 7.0 | 9786 | 0.4282 |
61
- | 0.4024 | 8.0 | 11184 | 0.4276 |
62
- | 0.4002 | 9.0 | 12582 | 0.4279 |
63
- | 0.3962 | 10.0 | 13980 | 0.4283 |
64
 
65
 
66
  ### Framework versions
4
  license: mit
5
  tags:
6
  - generated_from_trainer
 
 
7
  datasets:
8
  - cuad
9
  model-index:
10
+ - name: T5-base-cuad-512
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # T5-base-cuad-512
18
 
19
  This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the cuad dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.2209
22
 
23
  ## Model description
24
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 0.2809 | 1.0 | 2795 | 0.2331 |
53
+ | 0.2459 | 2.0 | 5590 | 0.2253 |
54
+ | 0.2355 | 3.0 | 8385 | 0.2220 |
55
+ | 0.2212 | 4.0 | 11180 | 0.2203 |
56
+ | 0.2068 | 5.0 | 13975 | 0.2197 |
57
+ | 0.2085 | 6.0 | 16770 | 0.2194 |
58
+ | 0.1968 | 7.0 | 19565 | 0.2199 |
59
+ | 0.1906 | 8.0 | 22360 | 0.2200 |
60
+ | 0.1909 | 9.0 | 25155 | 0.2208 |
61
+ | 0.1788 | 10.0 | 27950 | 0.2209 |
62
 
63
 
64
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c1b20a4bcc3450c0a6d5aae870e5f85f1e39727038c7f2ab1bec620c6b89ab6
3
  size 891730879
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e65d4359bcff70226ee97eb631b5f3355f471992434a0b6e96652e29c47a84e
3
  size 891730879
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbe211ddec5a2811b88b0942bdc83dff1a53449a061438e24ee06dba47ed3943
3
  size 3119
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a87dd286b8a42fb2a79575c9eb2dc02591f97e403760f49d3aceef0cba79e397
3
  size 3119