GuCuChiara commited on
Commit
9e0f02f
1 Parent(s): a540252

Training complete

Browse files
Files changed (1) hide show
  1. README.md +19 -15
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4109
24
- - Precision: 0.5413
25
- - Recall: 0.5693
26
- - F1: 0.5550
27
- - Accuracy: 0.9254
28
 
29
  ## Model description
30
 
@@ -49,25 +49,29 @@ The following hyperparameters were used during training:
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 8
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | No log | 1.0 | 71 | 0.2386 | 0.5723 | 0.5449 | 0.5583 | 0.9273 |
59
- | No log | 2.0 | 142 | 0.3000 | 0.5767 | 0.5693 | 0.5730 | 0.9240 |
60
- | No log | 3.0 | 213 | 0.2973 | 0.5882 | 0.5830 | 0.5856 | 0.9279 |
61
- | No log | 4.0 | 284 | 0.3333 | 0.5222 | 0.5742 | 0.5470 | 0.9205 |
62
- | No log | 5.0 | 355 | 0.3613 | 0.5012 | 0.5957 | 0.5444 | 0.9184 |
63
- | No log | 6.0 | 426 | 0.3772 | 0.5516 | 0.5693 | 0.5603 | 0.9268 |
64
- | No log | 7.0 | 497 | 0.4006 | 0.5574 | 0.5596 | 0.5585 | 0.9257 |
65
- | 0.0539 | 8.0 | 568 | 0.4109 | 0.5413 | 0.5693 | 0.5550 | 0.9254 |
 
 
 
 
66
 
67
 
68
  ### Framework versions
69
 
70
- - Transformers 4.35.0
71
  - Pytorch 2.1.0+cu118
72
  - Datasets 2.14.6
73
  - Tokenizers 0.14.1
 
20
 
21
  This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2557
24
+ - Precision: 0.4943
25
+ - Recall: 0.5046
26
+ - F1: 0.4994
27
+ - Accuracy: 0.9407
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 12
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 71 | 0.2423 | 0.1951 | 0.1433 | 0.1653 | 0.9109 |
59
+ | No log | 2.0 | 142 | 0.2177 | 0.2905 | 0.3474 | 0.3164 | 0.9138 |
60
+ | No log | 3.0 | 213 | 0.1822 | 0.3912 | 0.3701 | 0.3804 | 0.9325 |
61
+ | No log | 4.0 | 284 | 0.1845 | 0.3839 | 0.4367 | 0.4086 | 0.9298 |
62
+ | No log | 5.0 | 355 | 0.2033 | 0.4533 | 0.4271 | 0.4398 | 0.9367 |
63
+ | No log | 6.0 | 426 | 0.2005 | 0.4535 | 0.4736 | 0.4633 | 0.9365 |
64
+ | No log | 7.0 | 497 | 0.2297 | 0.4352 | 0.5155 | 0.4720 | 0.9321 |
65
+ | 0.1436 | 8.0 | 568 | 0.2236 | 0.4854 | 0.4656 | 0.4753 | 0.9395 |
66
+ | 0.1436 | 9.0 | 639 | 0.2335 | 0.4935 | 0.5101 | 0.5016 | 0.9397 |
67
+ | 0.1436 | 10.0 | 710 | 0.2413 | 0.4829 | 0.5075 | 0.4949 | 0.9405 |
68
+ | 0.1436 | 11.0 | 781 | 0.2557 | 0.4849 | 0.5239 | 0.5036 | 0.9383 |
69
+ | 0.1436 | 12.0 | 852 | 0.2557 | 0.4943 | 0.5046 | 0.4994 | 0.9407 |
70
 
71
 
72
  ### Framework versions
73
 
74
+ - Transformers 4.35.1
75
  - Pytorch 2.1.0+cu118
76
  - Datasets 2.14.6
77
  - Tokenizers 0.14.1