Model save

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+base_model: Hartunka/distilbert_km_20_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: distilbert_km_20_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_20_v2_qqp
+
+This model is a fine-tuned version of [Hartunka/distilbert_km_20_v2](https://huggingface.co/Hartunka/distilbert_km_20_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6166
+- Accuracy: 0.8329
+- F1: 0.7733
+- Combined Score: 0.8031
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.4873        | 1.0   | 1422  | 0.4439          | 0.7871   | 0.6789 | 0.7330         |
+| 0.3842        | 2.0   | 2844  | 0.4049          | 0.8114   | 0.7354 | 0.7734         |
+| 0.3094        | 3.0   | 4266  | 0.3997          | 0.8217   | 0.7599 | 0.7908         |
+| 0.2464        | 4.0   | 5688  | 0.4326          | 0.8267   | 0.7592 | 0.7929         |
+| 0.1952        | 5.0   | 7110  | 0.4403          | 0.8321   | 0.7708 | 0.8015         |
+| 0.1541        | 6.0   | 8532  | 0.5289          | 0.8303   | 0.7650 | 0.7976         |
+| 0.1242        | 7.0   | 9954  | 0.6010          | 0.8328   | 0.7704 | 0.8016         |
+| 0.1003        | 8.0   | 11376 | 0.6166          | 0.8329   | 0.7733 | 0.8031         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745323256.s_005_m.2850345.42

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b10397d83d64f7d96ea2dc27224d7844dc40e824a2c6e68a2ba7ee4c3b54525
-size 9452
+oid sha256:8cde0d289a7d316e0b7a289dd022539bf3db2162f64aa324000120d589466691
+size 10444

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5387b1be0ffe78a2632326585a5b0178728dc93a40762f8a6aa171115996986
+oid sha256:972a273db21fd949b393a6ff941dbfa1838d0bd5ed6efebac2162842846a8266
 size 267832560