Model save

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_km_50_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: tiny_bert_km_50_v2_mrpc
+  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. -->
+
+# tiny_bert_km_50_v2_mrpc
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_50_v2](https://huggingface.co/Hartunka/tiny_bert_km_50_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8555
+- Accuracy: 0.7034
+- F1: 0.8
+- Combined Score: 0.7517
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.632         | 1.0   | 15   | 0.5975          | 0.7034   | 0.8169 | 0.7602         |
+| 0.5917        | 2.0   | 30   | 0.5832          | 0.7132   | 0.8251 | 0.7692         |
+| 0.5638        | 3.0   | 45   | 0.5895          | 0.7034   | 0.8180 | 0.7607         |
+| 0.5417        | 4.0   | 60   | 0.5812          | 0.7181   | 0.8212 | 0.7696         |
+| 0.5019        | 5.0   | 75   | 0.5993          | 0.7010   | 0.8039 | 0.7524         |
+| 0.4343        | 6.0   | 90   | 0.6206          | 0.6789   | 0.7813 | 0.7301         |
+| 0.3592        | 7.0   | 105  | 0.6731          | 0.7083   | 0.8007 | 0.7545         |
+| 0.2533        | 8.0   | 120  | 0.7867          | 0.7010   | 0.8007 | 0.7508         |
+| 0.1831        | 9.0   | 135  | 0.8555          | 0.7034   | 0.8    | 0.7517         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745283312.s_005_m.2836625.56

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a7688e113258ecae0e7180e510aeb944438397fa6a265ca4af10560cec5523
-size 9996
+oid sha256:86cca08f77f101aa79f5c2a671902adc58cdb7fe5009c68aaeafac4b6e290eae
+size 10988

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0be12e1b8cd48fb1116e5f598778e2e1844848aaf994672d6b977733327446f
+oid sha256:ca652db5927f148180cd83a64f2165bad78791bbfec254ff35f617fb40260e72
 size 131856744