Hugging Face's logo

tiagoblima
/
t5_base-qg-ap-oficial

Text2Text Generation
Transformers
Safetensors
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
tiagoblima commited on
Commit
e3d4861
•
1 Parent(s): d162079

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -15
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ license: mit
3
  base_model: unicamp-dl/ptt5-base-portuguese-vocab
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - tiagoblima/du-qg-squadv1_pt
8
  model-index:
9
  - name: t5_base-qg-ap-oficial
10
  results: []
@@ -15,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # t5_base-qg-ap-oficial
17
 
18
- This model is a fine-tuned version of [unicamp-dl/ptt5-base-portuguese-vocab](https://huggingface.co/unicamp-dl/ptt5-base-portuguese-vocab) on the tiagoblima/du-qg-squadv1_pt dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.9945
21
 
22
  ## Model description
23
 
@@ -37,11 +35,9 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
40
- - train_batch_size: 8
41
- - eval_batch_size: 4
42
  - seed: 42
43
- - gradient_accumulation_steps: 4
44
- - total_train_batch_size: 32
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
46
  - lr_scheduler_type: linear
47
  - num_epochs: 5.0
@@ -50,16 +46,16 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:-----:|:---------------:|
53
- | 2.1593 | 1.0 | 2366 | 2.0509 |
54
- | 1.9907 | 2.0 | 4733 | 2.0158 |
55
- | 1.9408 | 3.0 | 7099 | 2.0011 |
56
- | 1.8321 | 4.0 | 9466 | 1.9945 |
57
- | 1.7928 | 5.0 | 11830 | 1.9992 |
58
 
59
 
60
  ### Framework versions
61
 
62
  - Transformers 4.35.2
63
- - Pytorch 2.0.0
64
  - Datasets 2.15.0
65
- - Tokenizers 0.15.0
 
3
  base_model: unicamp-dl/ptt5-base-portuguese-vocab
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: t5_base-qg-ap-oficial
8
  results: []
 
13
 
14
  # t5_base-qg-ap-oficial
15
 
16
+ This model is a fine-tuned version of [unicamp-dl/ptt5-base-portuguese-vocab](https://huggingface.co/unicamp-dl/ptt5-base-portuguese-vocab) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.7673
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0001
38
+ - train_batch_size: 32
39
+ - eval_batch_size: 64
40
  - seed: 42
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
42
  - lr_scheduler_type: linear
43
  - num_epochs: 5.0
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 1.928 | 1.0 | 2367 | 1.8312 |
50
+ | 1.7467 | 2.0 | 4734 | 1.7875 |
51
+ | 1.6658 | 3.0 | 7101 | 1.7681 |
52
+ | 1.5892 | 4.0 | 9468 | 1.7632 |
53
+ | 1.5483 | 5.0 | 11835 | 1.7673 |
54
 
55
 
56
  ### Framework versions
57
 
58
  - Transformers 4.35.2
59
+ - Pytorch 2.1.0+cu121
60
  - Datasets 2.15.0
61
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd14265aac0435771eae311887b5e52c81da1f11b0d5510b208a55e950ec469e
3
  size 891644712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54dc671bbc7016070224e672cbd10a575b40c747646ff60d23615c79a4d1d41f
3
  size 891644712