Model save

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+base_model: Hartunka/distilbert_km_100_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: distilbert_km_100_v2_qqp
+  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. -->
+
+# distilbert_km_100_v2_qqp
+
+This model is a fine-tuned version of [Hartunka/distilbert_km_100_v2](https://huggingface.co/Hartunka/distilbert_km_100_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6220
+- Accuracy: 0.8306
+- F1: 0.7703
+- Combined Score: 0.8005
+
+## 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: 256
+- eval_batch_size: 256
+- seed: 10
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Combined Score |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.4895        | 1.0   | 1422  | 0.4377          | 0.7879   | 0.6969 | 0.7424         |
+| 0.3864        | 2.0   | 2844  | 0.4062          | 0.8125   | 0.7412 | 0.7768         |
+| 0.3094        | 3.0   | 4266  | 0.4029          | 0.8218   | 0.7585 | 0.7901         |
+| 0.2466        | 4.0   | 5688  | 0.4315          | 0.8274   | 0.7543 | 0.7909         |
+| 0.1952        | 5.0   | 7110  | 0.4506          | 0.8262   | 0.7676 | 0.7969         |
+| 0.1554        | 6.0   | 8532  | 0.5192          | 0.8311   | 0.7715 | 0.8013         |
+| 0.1248        | 7.0   | 9954  | 0.5749          | 0.8286   | 0.7695 | 0.7991         |
+| 0.1022        | 8.0   | 11376 | 0.6220          | 0.8306   | 0.7703 | 0.8005         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745339205.s_005_m.2850345.78

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275f07071839d36754e42671054c4f5a202bcad55bafba9236b2811cab058259
-size 9457
+oid sha256:21277b5e9917fbac4172d4b09542b1ad836198b25f7dd8e44606aff5063d83cd
+size 10449

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccefc311b4c54834e4de50bb583afc751e86d6ef00a92a0698144fae26a3964
+oid sha256:9ba73a908c47298ffad7dc01c887857e8e9f2337c7396004a3ed50a8518c8a49
 size 267832560