Training complete

README.md

@@ -0,0 +1,93 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- conll2003
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-finetuned-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: conll2003
+      type: conll2003
+      config: conll2003
+      split: validation
+      args: conll2003
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9385279946835022
+    - name: Recall
+      type: recall
+      value: 0.9506900033658701
+    - name: F1
+      type: f1
+      value: 0.9445698520190619
+    - name: Accuracy
+      type: accuracy
+      value: 0.9866662742096898
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/raspuntinov_ai/huggingface/runs/6o6422zh)
+# bert-finetuned-ner
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0584
+- Precision: 0.9385
+- Recall: 0.9507
+- F1: 0.9446
+- Accuracy: 0.9867
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.076         | 1.0   | 1756 | 0.0642          | 0.9049    | 0.9337 | 0.9191 | 0.9819   |
+| 0.0356        | 2.0   | 3512 | 0.0652          | 0.9386    | 0.9470 | 0.9428 | 0.9860   |
+| 0.0245        | 3.0   | 5268 | 0.0584          | 0.9385    | 0.9507 | 0.9446 | 0.9867   |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

runs/Aug07_12-11-40_3dd46047685a/events.out.tfevents.1723032716.3dd46047685a.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0edb8bdb613f780ecacfeda0160d3c5bd54c6858a380463517233d3cdcf4929d
-size 8238
+oid sha256:218421595c21e246c80b0b0e5cb734bdc1d128b2718390254c5525cbbdc90263
+size 9064