Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_km_20_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: tiny_bert_km_20_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_20_v2_mrpc
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_20_v2](https://huggingface.co/Hartunka/tiny_bert_km_20_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7322
+- Accuracy: 0.6691
+- F1: 0.7723
+- Combined Score: 0.7207
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.6363        | 1.0   | 15   | 0.6099          | 0.6936   | 0.8086 | 0.7511         |
+| 0.6012        | 2.0   | 30   | 0.6003          | 0.7059   | 0.8187 | 0.7623         |
+| 0.5689        | 3.0   | 45   | 0.6050          | 0.7083   | 0.8178 | 0.7630         |
+| 0.5499        | 4.0   | 60   | 0.6045          | 0.7059   | 0.8131 | 0.7595         |
+| 0.5072        | 5.0   | 75   | 0.6230          | 0.6912   | 0.7974 | 0.7443         |
+| 0.4501        | 6.0   | 90   | 0.6497          | 0.6716   | 0.7729 | 0.7222         |
+| 0.371         | 7.0   | 105  | 0.7322          | 0.6691   | 0.7723 | 0.7207         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745278287.s_005_m.2836625.38

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:412fb037a2483e06fb6f9defea3fdf31993f3f3107b86f082cacfddd377f3fe9
-size 8118
+oid sha256:98c52aea9e5dd5d28c159d6f8d67ee2051bea7038e6c7d56d593a15448ca60d1
+size 9718

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11871c693fb32ef01284bb13afc414c03723af3073c8fb0d195a70d57ae432ac
+oid sha256:0e6370d3a052f92f40d4633d71fe8516e3977fe646374ac7c0249cfb64366057
 size 131856744