Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_5_v2
+tags:
+- generated_from_trainer
+metrics:
+- matthews_correlation
+- accuracy
+model-index:
+- name: tiny_bert_rand_5_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_5_v2_cola
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7743
+- Matthews Correlation: 0.0624
+- Accuracy: 0.6232
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
+| 0.6181        | 1.0   | 34   | 0.6160          | 0.0                  | 0.6913   |
+| 0.603         | 2.0   | 68   | 0.6146          | 0.0                  | 0.6913   |
+| 0.5863        | 3.0   | 102  | 0.6145          | 0.0071               | 0.6855   |
+| 0.5473        | 4.0   | 136  | 0.6423          | 0.1090               | 0.6874   |
+| 0.5062        | 5.0   | 170  | 0.6451          | 0.1031               | 0.6663   |
+| 0.4682        | 6.0   | 204  | 0.7057          | 0.0943               | 0.6596   |
+| 0.4321        | 7.0   | 238  | 0.7519          | 0.0915               | 0.6357   |
+| 0.4043        | 8.0   | 272  | 0.7743          | 0.0624               | 0.6232   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745292880.s_005_m.2836625.90

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d353a084c8f876530347b6cf133753580c3472c63b3995c3bd6c695881e46def
-size 9142
+oid sha256:116d324a08324c8d3a8fba96b2243ce269121c80f145833b82d88f5323a526d0
+size 10094

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b828563ad170006adba31ba7c74496ab243dd276c8bf7c3a7a3b3c0bd84d0971
+oid sha256:39223d084c9f77c94c0e8224237bce6ea347c4e32464b66cf45ca72909be9cd9
 size 131856744