Model save

README.md

@@ -1,12 +1,11 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
+base_model: michiyasunaga/BioLinkBERT-base
 tags:
-- token-classification
 - generated_from_trainer
 datasets:
-- Rodrigo1771/symptemist-fasttext-9-ner
+- drugtemist-en-fasttext-75-ner
 metrics:
 - precision
 - recall
@@ -19,24 +18,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: Rodrigo1771/symptemist-fasttext-9-ner
-      type: Rodrigo1771/symptemist-fasttext-9-ner
-      config: SympTEMIST NER
+      name: drugtemist-en-fasttext-75-ner
+      type: drugtemist-en-fasttext-75-ner
+      config: DrugTEMIST English NER
       split: validation
-      args: SympTEMIST NER
+      args: DrugTEMIST English NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.6659969864389754
+      value: 0.9194876486733761
     - name: Recall
       type: recall
-      value: 0.7257799671592775
+      value: 0.9366262814538676
     - name: F1
       type: f1
-      value: 0.6946045049764275
+      value: 0.92797783933518
     - name: Accuracy
       type: accuracy
-      value: 0.9496615226667522
+      value: 0.9987511511734993
 ---
 
 <!-- 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-9-ner dataset.
+This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the drugtemist-en-fasttext-75-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2450
-- Precision: 0.6660
-- Recall: 0.7258
-- F1: 0.6946
-- Accuracy: 0.9497
+- Loss: 0.0077
+- Precision: 0.9195
+- Recall: 0.9366
+- F1: 0.9280
+- Accuracy: 0.9988
 
 ## 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        | 0.9968 | 155  | 0.1485          | 0.5669    | 0.6218 | 0.5931 | 0.9436   |
-| No log        | 2.0    | 311  | 0.1609          | 0.5623    | 0.7159 | 0.6299 | 0.9409   |
-| No log        | 2.9968 | 466  | 0.1635          | 0.6210    | 0.7219 | 0.6677 | 0.9487   |
-| 0.1246        | 4.0    | 622  | 0.2047          | 0.6659    | 0.6765 | 0.6712 | 0.9493   |
-| 0.1246        | 4.9968 | 777  | 0.2134          | 0.6562    | 0.7115 | 0.6828 | 0.9480   |
-| 0.1246        | 6.0    | 933  | 0.2259          | 0.6518    | 0.7099 | 0.6796 | 0.9494   |
-| 0.0242        | 6.9968 | 1088 | 0.2450          | 0.6660    | 0.7258 | 0.6946 | 0.9497   |
-| 0.0242        | 8.0    | 1244 | 0.2650          | 0.6491    | 0.7230 | 0.6841 | 0.9491   |
-| 0.0242        | 8.9968 | 1399 | 0.2745          | 0.6646    | 0.7126 | 0.6878 | 0.9498   |
-| 0.0083        | 9.9678 | 1550 | 0.2774          | 0.6628    | 0.7187 | 0.6896 | 0.9503   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0183        | 1.0   | 507  | 0.0055          | 0.8974    | 0.9376 | 0.9170 | 0.9985   |
+| 0.0043        | 2.0   | 1014 | 0.0059          | 0.9099    | 0.9320 | 0.9208 | 0.9986   |
+| 0.0022        | 3.0   | 1521 | 0.0057          | 0.9015    | 0.9301 | 0.9156 | 0.9985   |
+| 0.0018        | 4.0   | 2028 | 0.0072          | 0.9275    | 0.9180 | 0.9227 | 0.9986   |
+| 0.0009        | 5.0   | 2535 | 0.0064          | 0.9078    | 0.9357 | 0.9215 | 0.9987   |
+| 0.0007        | 6.0   | 3042 | 0.0064          | 0.9194    | 0.9357 | 0.9275 | 0.9987   |
+| 0.0004        | 7.0   | 3549 | 0.0072          | 0.9289    | 0.9376 | 0.9332 | 0.9988   |
+| 0.0004        | 8.0   | 4056 | 0.0076          | 0.9250    | 0.9422 | 0.9335 | 0.9988   |
+| 0.0003        | 9.0   | 4563 | 0.0077          | 0.9161    | 0.9366 | 0.9263 | 0.9987   |
+| 0.0002        | 10.0  | 5070 | 0.0077          | 0.9195    | 0.9366 | 0.9280 | 0.9988   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e48e5070a2e48a4126a57b8ab250a702091d9f63b94e626651db619192f99cd
+oid sha256:710b5b97380a4c9d2cf0065106cab4f3ec295524e9a6face82f289921e3f95ca
 size 430601004

tb/events.out.tfevents.1725886210.0a1c9bec2a53.24273.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6956b7438a04ebcdd54d7b8e8dbc8d1d73ef4c8218c0dbd353b0ce76c8773f
-size 11479
+oid sha256:a173893ab6ea4bae83ba8f7d43d877ca16a06c53d30cb7f414ae20737d881888
+size 12305

train.log

@@ -1416,3 +1416,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2632] 2024-09-09 13:26:47,099 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-4056 (score: 0.9335180055401663).
 
                                                   
 [INFO|trainer.py:4283] 2024-09-09 13:26:47,281 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3503] 2024-09-09 13:27:14,809 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 13:27:14,811 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 13:27:16,086 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 13:27:16,087 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 13:27:16,087 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3503] 2024-09-09 13:27:16,100 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 13:27:16,101 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 13:27:17,200 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 13:27:17,201 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 13:27:17,201 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.00769586768001318, 'eval_precision': 0.9194876486733761, 'eval_recall': 0.9366262814538676, 'eval_f1': 0.92797783933518, 'eval_accuracy': 0.9987511511734993, 'eval_runtime': 15.2047, 'eval_samples_per_second': 456.832, 'eval_steps_per_second': 57.153, 'epoch': 10.0}
+{'train_runtime': 2196.5741, 'train_samples_per_second': 147.716, 'train_steps_per_second': 2.308, 'train_loss': 0.0028968164414402532, 'epoch': 10.0}
+