Model save

README.md

@@ -2,10 +2,9 @@
 library_name: transformers
 base_model: IVN-RIN/bioBIT
 tags:
-- token-classification
 - generated_from_trainer
 datasets:
-- Rodrigo1771/drugtemist-it-fasttext-8-ner
+- drugtemist-it-fasttext-85-ner
 metrics:
 - precision
 - recall
@@ -18,24 +17,24 @@ model-index:
       name: Token Classification
       type: token-classification
     dataset:
-      name: Rodrigo1771/drugtemist-it-fasttext-8-ner
-      type: Rodrigo1771/drugtemist-it-fasttext-8-ner
+      name: drugtemist-it-fasttext-85-ner
+      type: drugtemist-it-fasttext-85-ner
       config: DrugTEMIST Italian NER
       split: validation
       args: DrugTEMIST Italian NER
     metrics:
     - name: Precision
       type: precision
-      value: 0.9162702188392008
+      value: 0.9211538461538461
     - name: Recall
       type: recall
-      value: 0.9322362052274927
+      value: 0.9273959341723137
     - name: F1
       type: f1
-      value: 0.9241842610364683
+      value: 0.9242643511818619
     - name: Accuracy
       type: accuracy
-      value: 0.9987276032199429
+      value: 0.9986302259153467
 ---
 
 <!-- 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 [IVN-RIN/bioBIT](https://huggingface.co/IVN-RIN/bioBIT) on the Rodrigo1771/drugtemist-it-fasttext-8-ner dataset.
+This model is a fine-tuned version of [IVN-RIN/bioBIT](https://huggingface.co/IVN-RIN/bioBIT) on the drugtemist-it-fasttext-85-ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0064
-- Precision: 0.9163
-- Recall: 0.9322
-- F1: 0.9242
-- Accuracy: 0.9987
+- Loss: 0.0080
+- Precision: 0.9212
+- Recall: 0.9274
+- F1: 0.9243
+- Accuracy: 0.9986
 
 ## Model description
 
@@ -80,18 +79,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 470  | 0.0044          | 0.9108    | 0.8993 | 0.9050 | 0.9985   |
-| 0.0122        | 2.0   | 940  | 0.0051          | 0.9050    | 0.8848 | 0.8948 | 0.9984   |
-| 0.0032        | 3.0   | 1410 | 0.0049          | 0.9144    | 0.8993 | 0.9068 | 0.9985   |
-| 0.0017        | 4.0   | 1880 | 0.0060          | 0.9213    | 0.9177 | 0.9195 | 0.9986   |
-| 0.0011        | 5.0   | 2350 | 0.0071          | 0.9280    | 0.8858 | 0.9064 | 0.9985   |
-| 0.0007        | 6.0   | 2820 | 0.0060          | 0.9078    | 0.9245 | 0.9161 | 0.9986   |
-| 0.0005        | 7.0   | 3290 | 0.0059          | 0.9260    | 0.9206 | 0.9233 | 0.9988   |
-| 0.0004        | 8.0   | 3760 | 0.0064          | 0.9163    | 0.9322 | 0.9242 | 0.9987   |
-| 0.0002        | 9.0   | 4230 | 0.0067          | 0.9177    | 0.9284 | 0.9230 | 0.9986   |
-| 0.0001        | 10.0  | 4700 | 0.0069          | 0.9152    | 0.9303 | 0.9227 | 0.9987   |
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.9989 | 451  | 0.0051          | 0.9326    | 0.8703 | 0.9004 | 0.9984   |
+| 0.0116        | 2.0    | 903  | 0.0049          | 0.9066    | 0.9206 | 0.9135 | 0.9985   |
+| 0.0034        | 2.9989 | 1354 | 0.0056          | 0.8990    | 0.9216 | 0.9101 | 0.9984   |
+| 0.0018        | 4.0    | 1806 | 0.0066          | 0.9094    | 0.9235 | 0.9164 | 0.9985   |
+| 0.0011        | 4.9989 | 2257 | 0.0056          | 0.9082    | 0.9293 | 0.9187 | 0.9986   |
+| 0.0007        | 6.0    | 2709 | 0.0068          | 0.9145    | 0.9109 | 0.9127 | 0.9985   |
+| 0.0005        | 6.9989 | 3160 | 0.0076          | 0.8880    | 0.9284 | 0.9077 | 0.9984   |
+| 0.0003        | 8.0    | 3612 | 0.0080          | 0.9094    | 0.9235 | 0.9164 | 0.9986   |
+| 0.0002        | 8.9989 | 4063 | 0.0078          | 0.9162    | 0.9206 | 0.9184 | 0.9986   |
+| 0.0001        | 9.9889 | 4510 | 0.0080          | 0.9212    | 0.9274 | 0.9243 | 0.9986   |
 
 
 ### Framework versions

tb/events.out.tfevents.1725901915.0a1c9bec2a53.90165.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d822af7a4fd6d6b414212c3f333d6a722c187a65d96bf923fa31bab34ab59be8
-size 11251
+oid sha256:2d63946caf4f9ca0b3280d0fc5eccabd9aef94a286d7d6ea1cc1928df93ec63c
+size 12077

train.log

@@ -1566,3 +1566,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2632] 2024-09-09 17:53:06,832 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-4510 (score: 0.9242643511818619).
 
                                                   
 [INFO|trainer.py:4283] 2024-09-09 17:53:07,002 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3503] 2024-09-09 17:53:10,989 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 17:53:10,991 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 17:53:12,201 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 17:53:12,202 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 17:53:12,203 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3503] 2024-09-09 17:53:12,216 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 17:53:12,218 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 17:53:13,356 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 17:53:13,357 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 17:53:13,357 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.007998762652277946, 'eval_precision': 0.9211538461538461, 'eval_recall': 0.9273959341723137, 'eval_f1': 0.9242643511818619, 'eval_accuracy': 0.9986302259153467, 'eval_runtime': 17.8292, 'eval_samples_per_second': 381.284, 'eval_steps_per_second': 47.675, 'epoch': 9.99}
+{'train_runtime': 2471.8222, 'train_samples_per_second': 116.817, 'train_steps_per_second': 1.825, 'train_loss': 0.002201940788383577, 'epoch': 9.99}
+