Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_km_10_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: tiny_bert_km_10_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_10_v2_mrpc
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_10_v2](https://huggingface.co/Hartunka/tiny_bert_km_10_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8221
+- Accuracy: 0.6569
+- F1: 0.7651
+- Combined Score: 0.7110
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.6326        | 1.0   | 15   | 0.6155          | 0.6863   | 0.8078 | 0.7470         |
+| 0.5959        | 2.0   | 30   | 0.6039          | 0.7059   | 0.8182 | 0.7620         |
+| 0.5662        | 3.0   | 45   | 0.6089          | 0.6936   | 0.8120 | 0.7528         |
+| 0.5395        | 4.0   | 60   | 0.6144          | 0.7010   | 0.8082 | 0.7546         |
+| 0.4794        | 5.0   | 75   | 0.6359          | 0.6838   | 0.7839 | 0.7339         |
+| 0.3903        | 6.0   | 90   | 0.7128          | 0.6593   | 0.7583 | 0.7088         |
+| 0.2926        | 7.0   | 105  | 0.8221          | 0.6569   | 0.7651 | 0.7110         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745273462.s_005_m.2836625.20

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3d0a9e17f5d92fe7dab19e03002ec41744fa6b1976cfbfc27c88a7dd4d1f88
-size 8118
+oid sha256:15e0673d48e404926e50947ecdb55b53a3853fbcddcdb1d1332b797668a75c3d
+size 9718

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca946d09c74d8b6d39d60a00bc7c6b4b57b5a8bcd7a89f39301a591ea6c940a7
+oid sha256:3616e5885b5c31803c6c8144af3cbb4df904c8985dd1047749005a7e178820b8
 size 131856744