Hugging Face's logo

Yeji-Seong
/
distilbert-base-uncased-tokenclassification_lora

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Yeji-Seong commited on
Commit
41743e6
•
1 Parent(s): 4555f08

End of training

Browse files
Files changed (2) hide show
  1. README.md +18 -18
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.3089
25
- - Precision: 0.25
26
- - Recall: 0.0251
27
- - F1: 0.0457
28
- - Accuracy: 0.9238
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 2e-05
48
  - train_batch_size: 16
49
  - eval_batch_size: 16
50
  - seed: 42
@@ -54,18 +54,18 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | No log | 1.0 | 213 | 0.4282 | 0.0 | 0.0 | 0.0 | 0.9205 |
60
- | No log | 2.0 | 426 | 0.3958 | 0.0 | 0.0 | 0.0 | 0.9205 |
61
- | 0.2774 | 3.0 | 639 | 0.3582 | 0.0 | 0.0 | 0.0 | 0.9205 |
62
- | 0.2774 | 4.0 | 852 | 0.3379 | 0.0 | 0.0 | 0.0 | 0.9207 |
63
- | 0.2222 | 5.0 | 1065 | 0.3254 | 0.0 | 0.0 | 0.0 | 0.9210 |
64
- | 0.2222 | 6.0 | 1278 | 0.3208 | 0.0 | 0.0 | 0.0 | 0.9215 |
65
- | 0.2222 | 7.0 | 1491 | 0.3145 | 0.2292 | 0.0132 | 0.0249 | 0.9224 |
66
- | 0.2028 | 8.0 | 1704 | 0.3115 | 0.2353 | 0.0191 | 0.0354 | 0.9231 |
67
- | 0.2028 | 9.0 | 1917 | 0.3091 | 0.2561 | 0.0251 | 0.0458 | 0.9238 |
68
- | 0.1935 | 10.0 | 2130 | 0.3089 | 0.25 | 0.0251 | 0.0457 | 0.9238 |
69
 
70
 
71
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.4813
25
+ - Precision: 0.0
26
+ - Recall: 0.0
27
+ - F1: 0.0
28
+ - Accuracy: 0.9205
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 0.0002
48
  - train_batch_size: 16
49
  - eval_batch_size: 16
50
  - seed: 42
 
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
59
+ | No log | 1.0 | 213 | 0.4828 | 0.0 | 0.0 | 0.0 | 0.9205 |
60
+ | No log | 2.0 | 426 | 0.4831 | 0.0 | 0.0 | 0.0 | 0.9205 |
61
+ | 0.3175 | 3.0 | 639 | 0.4825 | 0.0 | 0.0 | 0.0 | 0.9205 |
62
+ | 0.3175 | 4.0 | 852 | 0.4820 | 0.0 | 0.0 | 0.0 | 0.9205 |
63
+ | 0.3157 | 5.0 | 1065 | 0.4817 | 0.0 | 0.0 | 0.0 | 0.9205 |
64
+ | 0.3157 | 6.0 | 1278 | 0.4810 | 0.0 | 0.0 | 0.0 | 0.9205 |
65
+ | 0.3157 | 7.0 | 1491 | 0.4803 | 0.0 | 0.0 | 0.0 | 0.9205 |
66
+ | 0.3171 | 8.0 | 1704 | 0.4819 | 0.0 | 0.0 | 0.0 | 0.9205 |
67
+ | 0.3171 | 9.0 | 1917 | 0.4813 | 0.0 | 0.0 | 0.0 | 0.9205 |
68
+ | 0.3147 | 10.0 | 2130 | 0.4813 | 0.0 | 0.0 | 0.0 | 0.9205 |
69
 
70
 
71
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2ec2b1ca4e60ebaf527954db1f4c1d7815b13929b9d0ddd2dcb7a327bfe5060
3
  size 2402996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81323539090176102292a7502a4477dcabe1145f7394d0fb76c45ca2d8e66b5d
3
  size 2402996