Model save

README.md

@@ -2,10 +2,9 @@
 license: apache-2.0
 base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
 tags:
-- token-classification
 - generated_from_trainer
 datasets:
-- Rodrigo1771/combined-train-drugtemist-dev-ner
+- distemist-ner
 metrics:
 - precision
 - recall
@@ -18,24 +17,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: Rodrigo1771/combined-train-drugtemist-dev-ner
-      type: Rodrigo1771/combined-train-drugtemist-dev-ner
-      config: CombinedTrainDrugTEMISTDevNER
+      name: distemist-ner
+      type: distemist-ner
+      config: DisTEMIST NER
       split: validation
-      args: CombinedTrainDrugTEMISTDevNER
+      args: DisTEMIST NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.09532555790247038
+      value: 0.7882031427920747
     - name: Recall
       type: recall
-      value: 0.9540441176470589
+      value: 0.8097800655124006
     - name: F1
       type: f1
-      value: 0.17333222008850296
+      value: 0.7988459319099828
     - name: Accuracy
       type: accuracy
-      value: 0.7932840841995413
+      value: 0.9766776058330014
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,13 +42,13 @@ 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/combined-train-drugtemist-dev-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 distemist-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0503
-- Precision: 0.0953
-- Recall: 0.9540
-- F1: 0.1733
-- Accuracy: 0.7933
+- Loss: 0.1367
+- Precision: 0.7882
+- Recall: 0.8098
+- F1: 0.7988
+- Accuracy: 0.9767
 
 ## Model description
 
@@ -82,16 +81,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 0.9988 | 425  | 0.6611          | 0.0883    | 0.9292 | 0.1613 | 0.7850   |
-| 0.3349        | 2.0    | 851  | 0.9204          | 0.0787    | 0.9301 | 0.1451 | 0.7551   |
-| 0.1788        | 2.9988 | 1276 | 0.9545          | 0.0844    | 0.9329 | 0.1549 | 0.7645   |
-| 0.1227        | 4.0    | 1702 | 1.0924          | 0.0885    | 0.9412 | 0.1618 | 0.7692   |
-| 0.0856        | 4.9988 | 2127 | 1.0503          | 0.0953    | 0.9540 | 0.1733 | 0.7933   |
-| 0.0597        | 6.0    | 2553 | 1.2642          | 0.0912    | 0.9449 | 0.1663 | 0.7788   |
-| 0.0597        | 6.9988 | 2978 | 1.3262          | 0.0928    | 0.9485 | 0.1690 | 0.7829   |
-| 0.0458        | 8.0    | 3404 | 1.3698          | 0.0926    | 0.9522 | 0.1688 | 0.7849   |
-| 0.0343        | 8.9988 | 3829 | 1.4433          | 0.0907    | 0.9449 | 0.1655 | 0.7822   |
-| 0.0292        | 9.9882 | 4250 | 1.4862          | 0.0914    | 0.9458 | 0.1667 | 0.7821   |
+| No log        | 0.9988 | 425  | 0.0738          | 0.7233    | 0.7866 | 0.7536 | 0.9733   |
+| 0.0996        | 2.0    | 851  | 0.0787          | 0.7364    | 0.8065 | 0.7698 | 0.9743   |
+| 0.0458        | 2.9988 | 1276 | 0.0788          | 0.7715    | 0.8154 | 0.7929 | 0.9759   |
+| 0.0279        | 4.0    | 1702 | 0.0922          | 0.7754    | 0.8112 | 0.7929 | 0.9757   |
+| 0.0169        | 4.9988 | 2127 | 0.0994          | 0.7585    | 0.8163 | 0.7863 | 0.9744   |
+| 0.0114        | 6.0    | 2553 | 0.1080          | 0.7766    | 0.8058 | 0.7909 | 0.9765   |
+| 0.0114        | 6.9988 | 2978 | 0.1166          | 0.7792    | 0.8100 | 0.7943 | 0.9760   |
+| 0.0079        | 8.0    | 3404 | 0.1294          | 0.7939    | 0.8093 | 0.8015 | 0.9768   |
+| 0.0053        | 8.9988 | 3829 | 0.1340          | 0.7876    | 0.8105 | 0.7989 | 0.9766   |
+| 0.0038        | 9.9882 | 4250 | 0.1367          | 0.7882    | 0.8098 | 0.7988 | 0.9767   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:330e96edeac6225449c5591541d607c0e092e4936d47f3ad60c87e78453fc12e
+oid sha256:6026be240f87a4fc70253ff6e37cf795b93399098bcc5e7dbc2d3ff76e7dcea3
 size 496244100

tb/events.out.tfevents.1725049548.6b97e535edda.20735.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1342923497305415fbad0344b56c8f0bde91efd2f3828fdedebab38b1b40be32
-size 11051
+oid sha256:288393d27fba4eca473a2f23089dcbee70efa764ffa6c2e99b2653da55d02bfe
+size 11877

train.log

@@ -1496,3 +1496,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2621] 2024-08-30 20:45:52,646 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-3404 (score: 0.8015293708724366).
 
                                                   
 [INFO|trainer.py:4239] 2024-08-30 20:45:52,840 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3478] 2024-08-30 20:45:55,484 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 20:45:55,486 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 20:45:56,829 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:56,830 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:56,830 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3478] 2024-08-30 20:45:56,879 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-08-30 20:45:56,881 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2690] 2024-08-30 20:45:58,218 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2574] 2024-08-30 20:45:58,219 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2583] 2024-08-30 20:45:58,219 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.13674204051494598, 'eval_precision': 0.7882031427920747, 'eval_recall': 0.8097800655124006, 'eval_f1': 0.7988459319099828, 'eval_accuracy': 0.9766776058330014, 'eval_runtime': 14.8828, 'eval_samples_per_second': 457.575, 'eval_steps_per_second': 57.247, 'epoch': 9.99}
+{'train_runtime': 1203.9865, 'train_samples_per_second': 226.157, 'train_steps_per_second': 3.53, 'train_loss': 0.02590363489880281, 'epoch': 9.99}
+