Hugging Face's logo

pabRomero
/
BioBERT-full-finetuned-ner-pablo

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
pabRomero commited on
Commit
48d18a3
·
verified ·
1 Parent(s): 332cba0

Training complete

Browse files
Files changed (2) hide show
  1. README.md +15 -20
  2. runs/Sep05_11-34-51_24b5dd7b9e65/events.out.tfevents.1725536092.24b5dd7b9e65.183.1 +2 -2
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 [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1081
24
- - Precision: 0.8057
25
- - Recall: 0.8003
26
- - F1: 0.8030
27
- - Accuracy: 0.9743
28
 
29
  ## Model description
30
 
@@ -43,32 +43,27 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 0.0002
47
- - train_batch_size: 16
48
- - eval_batch_size: 16
49
  - seed: 42
50
- - gradient_accumulation_steps: 4
51
- - total_train_batch_size: 64
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - lr_scheduler_warmup_ratio: 0.05
55
- - num_epochs: 5
56
  - mixed_precision_training: Native AMP
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
- |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
- | No log | 0.9970 | 252 | 0.0943 | 0.7586 | 0.7859 | 0.7720 | 0.9732 |
63
- | 0.1716 | 1.9980 | 505 | 0.0917 | 0.7950 | 0.7738 | 0.7843 | 0.9745 |
64
- | 0.1716 | 2.9990 | 758 | 0.0886 | 0.7956 | 0.7925 | 0.7940 | 0.9742 |
65
- | 0.0465 | 4.0 | 1011 | 0.0956 | 0.8055 | 0.7971 | 0.8013 | 0.9743 |
66
- | 0.0465 | 4.9852 | 1260 | 0.1081 | 0.8057 | 0.8003 | 0.8030 | 0.9743 |
67
 
68
 
69
  ### Framework versions
70
 
71
  - Transformers 4.44.2
72
- - Pytorch 2.4.0+cu121
73
  - Datasets 2.21.0
74
  - Tokenizers 0.19.1
 
20
 
21
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0618
24
+ - Precision: 0.8313
25
+ - Recall: 0.8344
26
+ - F1: 0.8329
27
+ - Accuracy: 0.9809
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 32
48
+ - eval_batch_size: 32
49
  - seed: 42
 
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - num_epochs: 2
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
59
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
60
+ | No log | 1.0 | 231 | 0.0879 | 0.7575 | 0.8070 | 0.7815 | 0.9737 |
61
+ | No log | 2.0 | 462 | 0.0618 | 0.8313 | 0.8344 | 0.8329 | 0.9809 |
 
 
 
62
 
63
 
64
  ### Framework versions
65
 
66
  - Transformers 4.44.2
67
+ - Pytorch 2.4.1+cu121
68
  - Datasets 2.21.0
69
  - Tokenizers 0.19.1
runs/Sep05_11-34-51_24b5dd7b9e65/events.out.tfevents.1725536092.24b5dd7b9e65.183.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:249e965e52a9c309cf082b39fd04d0dfb5a4c0023f60702cb03e94bf8add9e70
3
- size 6195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2249461ee029028abb2c87af1220a09403646a7e4c2eb012829c2ef27f1acdd5
3
+ size 7021