Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_50_v2
+tags:
+- generated_from_trainer
+metrics:
+- matthews_correlation
+- accuracy
+model-index:
+- name: tiny_bert_rand_50_v2_cola
+  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_rand_50_v2_cola
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_50_v2](https://huggingface.co/Hartunka/tiny_bert_rand_50_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7221
+- Matthews Correlation: 0.0817
+- Accuracy: 0.6376
+
+## 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 | Matthews Correlation | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
+| 0.6135        | 1.0   | 34   | 0.6176          | 0.0                  | 0.6913   |
+| 0.6006        | 2.0   | 68   | 0.6197          | 0.0                  | 0.6913   |
+| 0.5776        | 3.0   | 102  | 0.6242          | 0.0372               | 0.6903   |
+| 0.5383        | 4.0   | 136  | 0.6582          | 0.0622               | 0.6721   |
+| 0.4936        | 5.0   | 170  | 0.6671          | 0.0857               | 0.6491   |
+| 0.4569        | 6.0   | 204  | 0.7221          | 0.0817               | 0.6376   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745316374.s_005_m.2850172.36

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4ffe243d7673afe7f39256f5f77570deb552781176714dad8b1e89bfaba56d
-size 7353
+oid sha256:48ddee3f60002751258b2ec2a54592bfff3cd348fb2901b6ab709f6de3ceab54
+size 8903

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb383a395cc36d673692bb7667543215db22a489f23a3167c85480a3bea6feb
+oid sha256:0de09e7f0bef4de71c6f7402739df74ea54e162b654282ad915cafdeaaffe422
 size 131856744