Model save

README.md

@@ -0,0 +1,102 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: michiyasunaga/BioLinkBERT-base
+tags:
+- generated_from_trainer
+datasets:
+- drugtemist-en-75-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: drugtemist-en-75-ner
+      type: drugtemist-en-75-ner
+      config: DrugTEMIST English NER
+      split: validation
+      args: DrugTEMIST English NER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.921028466483012
+    - name: Recall
+      type: recall
+      value: 0.934762348555452
+    - name: F1
+      type: f1
+      value: 0.9278445883441258
+    - name: Accuracy
+      type: accuracy
+      value: 0.9986883598917199
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# output
+
+This model is a fine-tuned version of [michiyasunaga/BioLinkBERT-base](https://huggingface.co/michiyasunaga/BioLinkBERT-base) on the drugtemist-en-75-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0083
+- Precision: 0.9210
+- Recall: 0.9348
+- F1: 0.9278
+- Accuracy: 0.9987
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0189        | 1.0   | 504  | 0.0052          | 0.8712    | 0.9394 | 0.9040 | 0.9984   |
+| 0.0047        | 2.0   | 1008 | 0.0048          | 0.9253    | 0.9236 | 0.9244 | 0.9987   |
+| 0.0027        | 3.0   | 1512 | 0.0059          | 0.9252    | 0.9226 | 0.9239 | 0.9986   |
+| 0.0015        | 4.0   | 2016 | 0.0065          | 0.9342    | 0.9264 | 0.9303 | 0.9987   |
+| 0.0011        | 5.0   | 2520 | 0.0073          | 0.9073    | 0.9394 | 0.9231 | 0.9986   |
+| 0.0005        | 6.0   | 3024 | 0.0090          | 0.9191    | 0.9217 | 0.9204 | 0.9984   |
+| 0.0007        | 7.0   | 3528 | 0.0084          | 0.9074    | 0.9310 | 0.9190 | 0.9986   |
+| 0.0004        | 8.0   | 4032 | 0.0085          | 0.9093    | 0.9338 | 0.9214 | 0.9986   |
+| 0.0003        | 9.0   | 4536 | 0.0080          | 0.9186    | 0.9357 | 0.9271 | 0.9987   |
+| 0.0002        | 10.0  | 5040 | 0.0083          | 0.9210    | 0.9348 | 0.9278 | 0.9987   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930cdd9f6291711dcb334098788802aeee4b3c6d1a8d98d1889a344d7444d764
+oid sha256:bac7367dde258c667978ad27522f15a1f2caeb2ed58166eec16673704a732e98
 size 430601004

tb/events.out.tfevents.1725526555.6cb9bed92fd1.4510.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884cbb8be15cd6d233094b68f0e245ec6164497d625655076ec354a404f9f9dd
-size 11479
+oid sha256:9b997e02cb357ba36d50ba20ca9d874b3df1576e5d678167da71f72577e0f45e
+size 12305

train.log

@@ -1276,3 +1276,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2632] 2024-09-05 09:16:45,046 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-2016 (score: 0.930276087973795).
 
                                                   
 [INFO|trainer.py:4283] 2024-09-05 09:16:45,216 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3503] 2024-09-05 09:16:57,035 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-05 09:16:57,037 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-05 09:16:58,300 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 09:16:58,301 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 09:16:58,301 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3503] 2024-09-05 09:16:58,314 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-05 09:16:58,315 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-05 09:16:59,583 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-05 09:16:59,584 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-05 09:16:59,585 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.008253143168985844, 'eval_precision': 0.921028466483012, 'eval_recall': 0.934762348555452, 'eval_f1': 0.9278445883441258, 'eval_accuracy': 0.9986883598917199, 'eval_runtime': 13.7257, 'eval_samples_per_second': 506.057, 'eval_steps_per_second': 63.312, 'epoch': 10.0}
+{'train_runtime': 1249.6681, 'train_samples_per_second': 257.924, 'train_steps_per_second': 4.033, 'train_loss': 0.0030765269683407886, 'epoch': 10.0}
+