Hugging Face's logo

luisgasco
/
biomedical-roberta-finetuned-iomed_task

Token Classification
Transformers
PyTorch
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
luisgasco commited on
Commit
9b13431
•
1 Parent(s): 3117cc6

luisgasco/biomedical-roberta-finetuned-iomed_task_b4_ep13

Browse files
Files changed (3) hide show
  1. README.md +21 -21
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
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 [PlanTL-GOB-ES/roberta-base-biomedical-es](https://huggingface.co/PlanTL-GOB-ES/roberta-base-biomedical-es) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.0367
24
- - Precision: 0.2541
25
- - Recall: 0.4551
26
- - F1: 0.3261
27
- - Accuracy: 0.7718
28
 
29
  ## Model description
30
 
@@ -43,28 +43,28 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 3.5e-06
47
- - train_batch_size: 2
48
- - eval_batch_size: 2
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 7
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 1.2727 | 0.7 | 1064 | 1.1739 | 0.1144 | 0.2850 | 0.1632 | 0.7461 |
59
- | 0.9857 | 1.4 | 2128 | 1.0956 | 0.1626 | 0.3425 | 0.2205 | 0.7620 |
60
- | 0.9233 | 2.1 | 3192 | 1.0081 | 0.1457 | 0.3181 | 0.1999 | 0.7646 |
61
- | 0.8635 | 2.8 | 4256 | 1.0164 | 0.2019 | 0.3945 | 0.2671 | 0.7705 |
62
- | 0.821 | 3.5 | 5320 | 0.9852 | 0.1896 | 0.3827 | 0.2536 | 0.7709 |
63
- | 0.7574 | 4.2 | 6384 | 1.0179 | 0.2230 | 0.4157 | 0.2903 | 0.7714 |
64
- | 0.7725 | 4.9 | 7448 | 1.0378 | 0.2276 | 0.4299 | 0.2976 | 0.7695 |
65
- | 0.7365 | 5.6 | 8512 | 1.0315 | 0.2290 | 0.4354 | 0.3001 | 0.7722 |
66
- | 0.6596 | 6.3 | 9576 | 1.0406 | 0.2475 | 0.4496 | 0.3193 | 0.7723 |
67
- | 0.7028 | 7.0 | 10640 | 1.0367 | 0.2541 | 0.4551 | 0.3261 | 0.7718 |
68
 
69
 
70
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-biomedical-es](https://huggingface.co/PlanTL-GOB-ES/roberta-base-biomedical-es) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.0160
24
+ - Precision: 0.1934
25
+ - Recall: 0.3953
26
+ - F1: 0.2597
27
+ - Accuracy: 0.7681
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 2.2e-06
47
+ - train_batch_size: 4
48
+ - eval_batch_size: 4
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 13
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 2.1178 | 1.3 | 988 | 1.3039 | 0.0802 | 0.2102 | 0.1161 | 0.7321 |
59
+ | 1.2448 | 2.6 | 1976 | 1.1444 | 0.1161 | 0.2811 | 0.1643 | 0.7568 |
60
+ | 1.0297 | 3.9 | 2964 | 1.0724 | 0.1484 | 0.3299 | 0.2047 | 0.7658 |
61
+ | 0.9496 | 5.2 | 3952 | 1.0342 | 0.1676 | 0.3583 | 0.2284 | 0.7685 |
62
+ | 0.88 | 6.5 | 4940 | 1.0465 | 0.1805 | 0.3795 | 0.2446 | 0.7660 |
63
+ | 0.8168 | 7.8 | 5928 | 1.0253 | 0.1713 | 0.3638 | 0.2329 | 0.7624 |
64
+ | 0.7863 | 9.1 | 6916 | 1.0293 | 0.1754 | 0.3622 | 0.2364 | 0.7641 |
65
+ | 0.784 | 10.4 | 7904 | 1.0159 | 0.1920 | 0.3890 | 0.2571 | 0.7648 |
66
+ | 0.7161 | 11.7 | 8892 | 1.0121 | 0.1853 | 0.3819 | 0.2495 | 0.7654 |
67
+ | 0.7629 | 13.0 | 9880 | 1.0160 | 0.1934 | 0.3953 | 0.2597 | 0.7681 |
68
 
69
 
70
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3336f5acce2df48d4d076c0c31960b640e88f41df9cafe8497a494986c6ccb4b
3
  size 501676841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b53d4bb2530f6d567d9403670543fe6dd55b7a07c19969f95c8eb7de9997e40
3
  size 501676841
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b82526b27a6dc267a55ec693230527a40540df7b8e615851d154ac5a3c4b551
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185547245231b7005ff1ff9d78c9bfb91d32fe3ad9a0f57599a98198931df0c5
3
  size 4091