ana-grassmann commited on
Commit
3480a8f
·
verified ·
1 Parent(s): db9a92e

End of training

Browse files
README.md CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
3
  library_name: peft
4
  tags:
5
  - generated_from_trainer
6
- base_model: google-bert/bert-base-uncased
7
  metrics:
8
  - accuracy
9
  - f1
@@ -19,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # bert-finetuned-spam
21
 
22
- This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: nan
25
- - Accuracy: 0.4740
26
- - F1: 0.0
27
- - Precision: 0.0
28
- - Recall: 0.0
29
 
30
  ## Model description
31
 
@@ -44,20 +44,21 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 2.984949946835231e-05
48
  - train_batch_size: 64
49
- - eval_batch_size: 8
50
- - seed: 16
 
 
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 2
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|:---------:|:------:|
59
- | 0.0 | 1.0 | 1044 | nan | 0.4740 | 0.0 | 0.0 | 0.0 |
60
- | 0.0 | 2.0 | 2088 | nan | 0.4740 | 0.0 | 0.0 | 0.0 |
61
 
62
 
63
  ### Framework versions
 
3
  library_name: peft
4
  tags:
5
  - generated_from_trainer
6
+ base_model: bert-base-uncased
7
  metrics:
8
  - accuracy
9
  - f1
 
19
 
20
  # bert-finetuned-spam
21
 
22
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1469
25
+ - Accuracy: 0.9455
26
+ - F1: 0.9466
27
+ - Precision: 0.9782
28
+ - Recall: 0.9168
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 6.432402847051035e-05
48
  - train_batch_size: 64
49
+ - eval_batch_size: 64
50
+ - seed: 34
51
+ - gradient_accumulation_steps: 4
52
+ - total_train_batch_size: 256
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: linear
55
+ - num_epochs: 1
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
60
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
61
+ | No log | 1.0 | 261 | 0.1469 | 0.9455 | 0.9466 | 0.9782 | 0.9168 |
 
62
 
63
 
64
  ### Framework versions
runs/May08_02-03-26_12393a500f3c/events.out.tfevents.1715137298.12393a500f3c.651.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f44a66494114cf54a5b25ddfe7cda2f855627e67c8662cb824ac0933f27f705e
3
+ size 560