End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: mit
+base_model: roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- recall
+- precision
+model-index:
+- name: roberta-512-fbeta1.6-learning1
+  results: []
+---
+
+<!-- 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. -->
+
+# roberta-512-fbeta1.6-learning1
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0723
+- Accuracy: 0.9825
+- F1: 0.9768
+- Recall: 0.9828
+- Precision: 0.9708
+- False positive rate: 0.0177
+- False negative rate: 0.0172
+- Fbeta 0.5: 0.9732
+- Fbeta 1.6: 0.9794
+- Fbeta 5: 0.9824
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 600
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1     | Recall | Precision | False positive rate | False negative rate | Fbeta 0.5 | Fbeta 1.6 | Fbeta 5 |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:------:|:---------:|:-------------------:|:-------------------:|:---------:|:---------:|:-------:|
+| 0.1369        | 0.4999 | 2934  | 0.0811          | 0.9764   | 0.9690 | 0.9823 | 0.9561    | 0.0271              | 0.0177              | 0.9612    | 0.9748    | 0.9812  |
+| 0.077         | 0.9998 | 5868  | 0.0791          | 0.9802   | 0.9734 | 0.9659 | 0.9811    | 0.0112              | 0.0341              | 0.9780    | 0.9701    | 0.9665  |
+| 0.0556        | 1.4997 | 8802  | 0.0690          | 0.9809   | 0.9745 | 0.9732 | 0.9758    | 0.0145              | 0.0268              | 0.9753    | 0.9740    | 0.9733  |
+| 0.0531        | 1.9997 | 11736 | 0.0871          | 0.9801   | 0.9736 | 0.9793 | 0.9680    | 0.0195              | 0.0207              | 0.9702    | 0.9761    | 0.9788  |
+| 0.0373        | 2.4996 | 14670 | 0.0777          | 0.9822   | 0.9763 | 0.9797 | 0.9730    | 0.0163              | 0.0203              | 0.9744    | 0.9778    | 0.9794  |
+| 0.0383        | 2.9995 | 17604 | 0.0723          | 0.9825   | 0.9768 | 0.9828 | 0.9708    | 0.0177              | 0.0172              | 0.9732    | 0.9794    | 0.9824  |
+| 0.0243        | 3.4994 | 20538 | 0.0969          | 0.9825   | 0.9768 | 0.9810 | 0.9726    | 0.0166              | 0.0190              | 0.9742    | 0.9786    | 0.9807  |
+| 0.0251        | 3.9993 | 23472 | 0.0917          | 0.9834   | 0.9780 | 0.9805 | 0.9754    | 0.0148              | 0.0195              | 0.9764    | 0.9791    | 0.9803  |
+| 0.0171        | 4.4992 | 26406 | 0.0975          | 0.9832   | 0.9777 | 0.9806 | 0.9748    | 0.0152              | 0.0194              | 0.9759    | 0.9790    | 0.9804  |
+| 0.0161        | 4.9991 | 29340 | 0.1046          | 0.9835   | 0.9781 | 0.9790 | 0.9772    | 0.0137              | 0.0210              | 0.9776    | 0.9785    | 0.9789  |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c3ad6759d5906e4a7cca7a06860a3c9a972762b8016428e645e8020d9b7f0f
+oid sha256:b663c8f8f9e72fdf40a40289780d4ece5c74b4cf17876bed0aeca10bad345652
 size 498612824