Hugging Face's logo

egerber1
/
sap_predictions_model

Text Classification
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
 Community
egerber1 commited on
Commit
ad5ed72
·
verified ·
1 Parent(s): bf538f4

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -12
README.md CHANGED
@@ -1,11 +1,12 @@
1
  ---
2
  library_name: transformers
3
  license: mit
4
- base_model: xlm-roberta-large
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
 
9
  model-index:
10
  - name: sap_predictions_model
11
  results: []
@@ -16,10 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # sap_predictions_model
18
 
19
- This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 5.5535
22
- - Accuracy: 0.032
 
23
 
24
  ## Model description
25
 
@@ -38,21 +40,22 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-05
42
- - train_batch_size: 8
43
- - eval_batch_size: 8
44
  - seed: 42
 
 
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
 
47
  - num_epochs: 3
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 5.6447 | 1.0 | 1000 | 5.5726 | 0.032 |
54
- | 5.6596 | 2.0 | 2000 | 5.5561 | 0.032 |
55
- | 5.5823 | 3.0 | 3000 | 5.5535 | 0.032 |
56
 
57
 
58
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: mit
4
+ base_model: xlm-roberta-base
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
9
+ - f1
10
  model-index:
11
  - name: sap_predictions_model
12
  results: []
 
17
 
18
  # sap_predictions_model
19
 
20
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 4.6399
23
+ - Accuracy: 0.2433
24
+ - F1: 0.1390
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
  - seed: 42
47
+ - gradient_accumulation_steps: 2
48
+ - total_train_batch_size: 32
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
  - num_epochs: 3
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
57
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|
58
+ | 4.8717 | 2.1464 | 10000 | 4.9318 | 0.2161 | 0.1169 |
 
 
59
 
60
 
61
  ### Framework versions