Hugging Face's logo

vodailuong2510
/
saved_model_trial_3

Question Answering
Transformers
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
Community
vodailuong2510 commited on
Commit
e0b84f9
路
verified 路
1 Parent(s): 15f7699

Model save

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.9205
22
- - Exact Match: 48.3146
23
- - F1: 0.0
24
 
25
  ## Model description
26
 
@@ -39,20 +39,21 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 4.5803465942607646e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - num_epochs: 2
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
54
- | No log | 1.0 | 22 | 4.8278 | 41.5730 | 2.2007 |
55
- | No log | 2.0 | 44 | 3.9205 | 48.3146 | 0.0 |
 
56
 
57
 
58
  ### Framework versions
@@ -60,4 +61,4 @@ The following hyperparameters were used during training:
60
  - Transformers 4.51.2
61
  - Pytorch 2.6.0+cu124
62
  - Datasets 3.5.0
63
- - Tokenizers 0.21.1
 
18
 
19
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 4.9815
22
+ - Exact Match: 37.0787
23
+ - F1: 0.8810
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 1.1642094602798244e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 3
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
53
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:------:|
54
+ | No log | 1.0 | 22 | 5.6802 | 34.8315 | 0.6986 |
55
+ | No log | 2.0 | 44 | 5.1777 | 39.3258 | 0.8457 |
56
+ | No log | 3.0 | 66 | 4.9815 | 37.0787 | 0.8810 |
57
 
58
 
59
  ### Framework versions
 
61
  - Transformers 4.51.2
62
  - Pytorch 2.6.0+cu124
63
  - Datasets 3.5.0
64
+ - Tokenizers 0.21.2