Model save

README.md

@@ -3,10 +3,9 @@ library_name: transformers
 license: apache-2.0
 base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
 tags:
-- token-classification
 - generated_from_trainer
 datasets:
-- Rodrigo1771/symptemist-fasttext-8-ner
+- symptemist-fasttext-85-ner
 metrics:
 - precision
 - recall
@@ -19,24 +18,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: Rodrigo1771/symptemist-fasttext-8-ner
-      type: Rodrigo1771/symptemist-fasttext-8-ner
+      name: symptemist-fasttext-85-ner
+      type: symptemist-fasttext-85-ner
       config: SympTEMIST NER
       split: validation
       args: SympTEMIST NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.6764102564102564
+      value: 0.6548403446528129
     - name: Recall
       type: recall
-      value: 0.7219485495347564
+      value: 0.7071702244116037
     - name: F1
       type: f1
-      value: 0.6984379136881121
+      value: 0.6799999999999999
     - name: Accuracy
       type: accuracy
-      value: 0.9500465205813469
+      value: 0.9481215310083737
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,13 +43,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-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 Rodrigo1771/symptemist-fasttext-8-ner dataset.
+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 symptemist-fasttext-85-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3073
-- Precision: 0.6764
-- Recall: 0.7219
-- F1: 0.6984
-- Accuracy: 0.9500
+- Loss: 0.2930
+- Precision: 0.6548
+- Recall: 0.7072
+- F1: 0.6800
+- Accuracy: 0.9481
 
 ## Model description
 
@@ -81,18 +80,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 0.9975 | 203  | 0.1501          | 0.5960    | 0.6338 | 0.6143 | 0.9468   |
-| No log        | 2.0    | 407  | 0.1761          | 0.6529    | 0.6940 | 0.6729 | 0.9492   |
-| 0.1312        | 2.9975 | 610  | 0.1995          | 0.6322    | 0.7170 | 0.6720 | 0.9470   |
-| 0.1312        | 4.0    | 814  | 0.2182          | 0.6446    | 0.7137 | 0.6774 | 0.9483   |
-| 0.0248        | 4.9975 | 1017 | 0.2461          | 0.6251    | 0.7219 | 0.6701 | 0.9449   |
-| 0.0248        | 6.0    | 1221 | 0.2695          | 0.6410    | 0.7302 | 0.6827 | 0.9469   |
-| 0.0248        | 6.9975 | 1424 | 0.2829          | 0.6529    | 0.7340 | 0.6911 | 0.9470   |
-| 0.0081        | 8.0    | 1628 | 0.2982          | 0.6711    | 0.7181 | 0.6938 | 0.9494   |
-| 0.0081        | 8.9975 | 1831 | 0.3073          | 0.6764    | 0.7219 | 0.6984 | 0.9500   |
-| 0.0038        | 9.9754 | 2030 | 0.3079          | 0.6713    | 0.7165 | 0.6931 | 0.9500   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 171  | 0.1502          | 0.5421    | 0.6765 | 0.6019 | 0.9458   |
+| No log        | 2.0   | 342  | 0.1539          | 0.5958    | 0.6793 | 0.6348 | 0.9468   |
+| 0.1273        | 3.0   | 513  | 0.1838          | 0.6326    | 0.7077 | 0.6680 | 0.9468   |
+| 0.1273        | 4.0   | 684  | 0.2018          | 0.6322    | 0.7121 | 0.6698 | 0.9466   |
+| 0.1273        | 5.0   | 855  | 0.2153          | 0.6441    | 0.7192 | 0.6796 | 0.9465   |
+| 0.0234        | 6.0   | 1026 | 0.2498          | 0.6461    | 0.7006 | 0.6723 | 0.9470   |
+| 0.0234        | 7.0   | 1197 | 0.2653          | 0.6362    | 0.7209 | 0.6759 | 0.9462   |
+| 0.0234        | 8.0   | 1368 | 0.2808          | 0.6529    | 0.7115 | 0.6810 | 0.9473   |
+| 0.0082        | 9.0   | 1539 | 0.2917          | 0.6458    | 0.7115 | 0.6771 | 0.9467   |
+| 0.0082        | 10.0  | 1710 | 0.2930          | 0.6548    | 0.7072 | 0.6800 | 0.9481   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876f723be6ca469f211c557a65fa6be11b0b60eed47f4bdae5973bb6330c146c
+oid sha256:aa435b5d5128cb42a840438c5750299de3b5d75b06e70f57f6d654e4cc806af7
 size 496244100

tb/events.out.tfevents.1725884095.0a1c9bec2a53.15221.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d448c7000393aa4739bd3e8685df3e41ddb26d68381c46149f020f68e8f6eb
-size 10054
+oid sha256:8a5eb73def06ef281d6c5abe9cbb6a47c633f2d7191b334dbe5cbead1c284e80
+size 10880

train.log

@@ -877,3 +877,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2632] 2024-09-09 12:29:57,247 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-1368 (score: 0.680984808800419).
 
                                                   
 [INFO|trainer.py:4283] 2024-09-09 12:29:57,436 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3503] 2024-09-09 12:30:42,660 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 12:30:42,661 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 12:30:44,034 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 12:30:44,035 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 12:30:44,035 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3503] 2024-09-09 12:30:44,082 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 12:30:44,083 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 12:30:47,113 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 12:30:47,114 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 12:30:47,114 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.2930145561695099, 'eval_precision': 0.6548403446528129, 'eval_recall': 0.7071702244116037, 'eval_f1': 0.6799999999999999, 'eval_accuracy': 0.9481215310083737, 'eval_runtime': 5.9346, 'eval_samples_per_second': 424.463, 'eval_steps_per_second': 53.079, 'epoch': 10.0}
+{'train_runtime': 901.7971, 'train_samples_per_second': 121.269, 'train_steps_per_second': 1.896, 'train_loss': 0.047100042948248794, 'epoch': 10.0}
+