wgcv commited on
Commit
c7beab0
1 Parent(s): 8a34c7c

Model save

Browse files
README.md CHANGED
@@ -2,13 +2,7 @@
2
  license: apache-2.0
3
  base_model: distilroberta-base
4
  tags:
5
- - text-classification
6
  - generated_from_trainer
7
- widget:
8
- - text: "Yucaipa owned Dominick 's before selling the chain to Safeway in 1998 for $ 2.5 billion., Yucaipa bought Dominick's in 1995 for $ 693 million and sold it to Safeway for $ 1.8 billion in 1998."
9
- example_title: Not Equivalent
10
- - text: "Revenue in the first quarter of the year dropped 15 percent from the same period a year earlier., With the scandal hanging over Stewart's company revenue the first quarter of the year dropped 15 percent from the same period a year earlier."
11
- example_title: Equivalent
12
  metrics:
13
  - accuracy
14
  - f1
@@ -22,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  # platzi-distilroberta-base-mrpc-wgcv
24
 
25
- This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue and the mrpc datasets.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 0.3977
28
- - Accuracy: 0.8358
29
- - F1: 0.8855
30
 
31
  ## Model description
32
 
@@ -46,8 +40,8 @@ More information needed
46
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 5e-05
49
- - train_batch_size: 128
50
- - eval_batch_size: 128
51
  - seed: 42
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
@@ -55,6 +49,9 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
 
 
 
58
 
59
 
60
  ### Framework versions
@@ -62,4 +59,4 @@ The following hyperparameters were used during training:
62
  - Transformers 4.41.2
63
  - Pytorch 2.3.0+cu121
64
  - Datasets 2.20.0
65
- - Tokenizers 0.19.1
 
2
  license: apache-2.0
3
  base_model: distilroberta-base
4
  tags:
 
5
  - generated_from_trainer
 
 
 
 
 
6
  metrics:
7
  - accuracy
8
  - f1
 
16
 
17
  # platzi-distilroberta-base-mrpc-wgcv
18
 
19
+ This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4002
22
+ - Accuracy: 0.8456
23
+ - F1: 0.8835
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 5e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 16
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
53
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
54
+ | 0.409 | 2.1739 | 500 | 0.4002 | 0.8456 | 0.8835 |
55
 
56
 
57
  ### Framework versions
 
59
  - Transformers 4.41.2
60
  - Pytorch 2.3.0+cu121
61
  - Datasets 2.20.0
62
+ - Tokenizers 0.19.1
runs/Jun23_22-38-15_c261aaf0d6a8/events.out.tfevents.1719182301.c261aaf0d6a8.177.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17dcb8b4710a565532875f43a08197321729d32794d98c3c671ffe4787cf361f
3
- size 5695
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05ea7b78efce42c7b64549e9dff70758ac6361c7f9f3a077df34dfd4a3828bb
3
+ size 6049