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-fasttext-9-ner
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: drugtemist-en-fasttext-9-ner
+      type: drugtemist-en-fasttext-9-ner
+      config: DrugTEMIST English NER
+      split: validation
+      args: DrugTEMIST English NER
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9311627906976744
+    - name: Recall
+      type: recall
+      value: 0.9328984156570364
+    - name: F1
+      type: f1
+      value: 0.9320297951582869
+    - name: Accuracy
+      type: accuracy
+      value: 0.998772081600759
+---
+
+<!-- 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-fasttext-9-ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0071
+- Precision: 0.9312
+- Recall: 0.9329
+- F1: 0.9320
+- Accuracy: 0.9988
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.9989 | 435  | 0.0060          | 0.8714    | 0.9217 | 0.8958 | 0.9981   |
+| 0.0156        | 2.0    | 871  | 0.0044          | 0.9183    | 0.9217 | 0.92   | 0.9987   |
+| 0.0038        | 2.9989 | 1306 | 0.0040          | 0.8969    | 0.9404 | 0.9181 | 0.9987   |
+| 0.0025        | 4.0    | 1742 | 0.0045          | 0.9078    | 0.9357 | 0.9215 | 0.9986   |
+| 0.0016        | 4.9989 | 2177 | 0.0054          | 0.9182    | 0.9096 | 0.9139 | 0.9986   |
+| 0.0011        | 6.0    | 2613 | 0.0053          | 0.9152    | 0.9254 | 0.9203 | 0.9986   |
+| 0.0009        | 6.9989 | 3048 | 0.0060          | 0.9263    | 0.9366 | 0.9314 | 0.9987   |
+| 0.0009        | 8.0    | 3484 | 0.0059          | 0.9181    | 0.9404 | 0.9291 | 0.9988   |
+| 0.0005        | 8.9989 | 3919 | 0.0067          | 0.9258    | 0.9301 | 0.9279 | 0.9988   |
+| 0.0003        | 9.9885 | 4350 | 0.0071          | 0.9312    | 0.9329 | 0.9320 | 0.9988   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

tb/events.out.tfevents.1725907965.3d77e24b7860.2139.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c6d45e4dd1301f179795387e2c7176810031e03dd91668cdfe33f7c66c3a40
-size 11057
+oid sha256:14b07a62348548449de69186f75d068b534a5f40b745fb2aaff56f5511f88a8b
+size 11883

train.log

@@ -1413,3 +1413,16 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|trainer.py:2632] 2024-09-09 19:22:55,109 >> Loading best model from /content/dissertation/scripts/ner/output/checkpoint-4350 (score: 0.9320297951582869).
 
                                                   
 [INFO|trainer.py:4283] 2024-09-09 19:22:55,259 >> Waiting for the current checkpoint push to be finished, this might take a couple of minutes.
+[INFO|trainer.py:3503] 2024-09-09 19:23:03,508 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 19:23:03,510 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 19:23:04,785 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 19:23:04,786 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 19:23:04,786 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+[INFO|trainer.py:3503] 2024-09-09 19:23:04,799 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
+[INFO|configuration_utils.py:472] 2024-09-09 19:23:04,800 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
+[INFO|modeling_utils.py:2799] 2024-09-09 19:23:05,818 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
+[INFO|tokenization_utils_base.py:2684] 2024-09-09 19:23:05,819 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2693] 2024-09-09 19:23:05,819 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
+{'eval_loss': 0.007080046460032463, 'eval_precision': 0.9311627906976744, 'eval_recall': 0.9328984156570364, 'eval_f1': 0.9320297951582869, 'eval_accuracy': 0.998772081600759, 'eval_runtime': 15.2679, 'eval_samples_per_second': 454.941, 'eval_steps_per_second': 56.917, 'epoch': 9.99}
+{'train_runtime': 1809.5975, 'train_samples_per_second': 153.852, 'train_steps_per_second': 2.404, 'train_loss': 0.003044272955806776, 'epoch': 9.99}
+