Rodrigo1771
commited on
Commit
•
8e76363
1
Parent(s):
75df356
Model save
Browse files- README.md +51 -13
- model.safetensors +1 -1
- train.log +10 -0
README.md
CHANGED
@@ -2,13 +2,39 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
|
4 |
tags:
|
5 |
-
- token-classification
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
-
-
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: output
|
11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,17 +42,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# output
|
18 |
|
19 |
-
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
-
|
22 |
-
-
|
23 |
-
-
|
24 |
-
-
|
25 |
-
-
|
26 |
-
- eval_runtime: 16.7962
|
27 |
-
- eval_samples_per_second: 405.27
|
28 |
-
- eval_steps_per_second: 50.666
|
29 |
-
- step: 0
|
30 |
|
31 |
## Model description
|
32 |
|
@@ -55,6 +77,22 @@ The following hyperparameters were used during training:
|
|
55 |
- lr_scheduler_type: linear
|
56 |
- num_epochs: 10.0
|
57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
### Framework versions
|
59 |
|
60 |
- Transformers 4.40.2
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- multi-train-drugtemist-dev-ner
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
model-index:
|
14 |
- name: output
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: multi-train-drugtemist-dev-ner
|
21 |
+
type: multi-train-drugtemist-dev-ner
|
22 |
+
config: MultiTrainDrugTEMISTDevNER
|
23 |
+
split: validation
|
24 |
+
args: MultiTrainDrugTEMISTDevNER
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.09270693512304251
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.9522058823529411
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.16896354888689555
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.7845534874460183
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
42 |
|
43 |
# output
|
44 |
|
45 |
+
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the multi-train-drugtemist-dev-ner dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 1.7861
|
48 |
+
- Precision: 0.0927
|
49 |
+
- Recall: 0.9522
|
50 |
+
- F1: 0.1690
|
51 |
+
- Accuracy: 0.7846
|
|
|
|
|
|
|
|
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
77 |
- lr_scheduler_type: linear
|
78 |
- num_epochs: 10.0
|
79 |
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
83 |
+
|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
84 |
+
| 0.2596 | 0.9997 | 1701 | 0.7913 | 0.0793 | 0.9366 | 0.1462 | 0.7672 |
|
85 |
+
| 0.1853 | 2.0 | 3403 | 0.6631 | 0.0969 | 0.9485 | 0.1759 | 0.8100 |
|
86 |
+
| 0.1254 | 2.9997 | 5104 | 1.0729 | 0.0906 | 0.9421 | 0.1653 | 0.7755 |
|
87 |
+
| 0.0823 | 4.0 | 6806 | 1.2568 | 0.0888 | 0.9504 | 0.1624 | 0.7719 |
|
88 |
+
| 0.0597 | 4.9997 | 8507 | 1.1908 | 0.0941 | 0.9375 | 0.1710 | 0.7837 |
|
89 |
+
| 0.0446 | 6.0 | 10209 | 1.3844 | 0.0944 | 0.9504 | 0.1718 | 0.7812 |
|
90 |
+
| 0.0325 | 6.9997 | 11910 | 1.5515 | 0.0937 | 0.9476 | 0.1705 | 0.7866 |
|
91 |
+
| 0.022 | 8.0 | 13612 | 1.6300 | 0.0926 | 0.9559 | 0.1689 | 0.7843 |
|
92 |
+
| 0.017 | 8.9997 | 15313 | 1.7459 | 0.0929 | 0.9531 | 0.1693 | 0.7845 |
|
93 |
+
| 0.0135 | 9.9971 | 17010 | 1.7861 | 0.0927 | 0.9522 | 0.1690 | 0.7846 |
|
94 |
+
|
95 |
+
|
96 |
### Framework versions
|
97 |
|
98 |
- Transformers 4.40.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 496262556
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a92e9473c4569e5b9f9c2355692ca54a9ea2c391a97e47dae7d504f0230253df
|
3 |
size 496262556
|
train.log
CHANGED
@@ -1603,3 +1603,13 @@ Training completed. Do not forget to share your model on huggingface.co/models =
|
|
1603 |
[INFO|trainer.py:2521] 2024-05-13 14:58:14,696 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-3403 (score: 0.17586912065439672).
|
1604 |
|
1605 |
|
1606 |
[INFO|trainer.py:4035] 2024-05-13 14:58:14,891 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1603 |
[INFO|trainer.py:2521] 2024-05-13 14:58:14,696 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-3403 (score: 0.17586912065439672).
|
1604 |
|
1605 |
|
1606 |
[INFO|trainer.py:4035] 2024-05-13 14:58:14,891 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
|
1607 |
+
[INFO|trainer.py:3305] 2024-05-13 14:58:37,779 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
|
1608 |
+
[INFO|configuration_utils.py:471] 2024-05-13 14:58:37,781 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
|
1609 |
+
[INFO|modeling_utils.py:2590] 2024-05-13 14:58:39,085 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
|
1610 |
+
[INFO|tokenization_utils_base.py:2488] 2024-05-13 14:58:39,087 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
|
1611 |
+
[INFO|tokenization_utils_base.py:2497] 2024-05-13 14:58:39,087 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
|
1612 |
+
[INFO|trainer.py:3305] 2024-05-13 14:58:39,136 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
|
1613 |
+
[INFO|configuration_utils.py:471] 2024-05-13 14:58:39,137 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
|
1614 |
+
[INFO|modeling_utils.py:2590] 2024-05-13 14:58:40,302 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
|
1615 |
+
[INFO|tokenization_utils_base.py:2488] 2024-05-13 14:58:40,303 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
|
1616 |
+
[INFO|tokenization_utils_base.py:2497] 2024-05-13 14:58:40,303 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
|