Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_20_v1
+tags:
+- generated_from_trainer
+metrics:
+- matthews_correlation
+- accuracy
+model-index:
+- name: tiny_bert_rand_20_v1_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_20_v1_cola
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_20_v1](https://huggingface.co/Hartunka/tiny_bert_rand_20_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7408
+- Matthews Correlation: 0.0593
+- Accuracy: 0.6405
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
+| 0.6196        | 1.0   | 34   | 0.6181          | 0.0                  | 0.6913   |
+| 0.5915        | 2.0   | 68   | 0.6220          | 0.0438               | 0.6922   |
+| 0.5622        | 3.0   | 102  | 0.6283          | 0.0719               | 0.6894   |
+| 0.5173        | 4.0   | 136  | 0.6516          | 0.1082               | 0.6740   |
+| 0.461         | 5.0   | 170  | 0.7096          | 0.0573               | 0.6443   |
+| 0.4116        | 6.0   | 204  | 0.7408          | 0.0593               | 0.6405   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1744652161.s_005_m.2701049.90

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d456cca0678a6eba18ebdc1516d5669531dd31b2fd1bb83b09b25d1ce3c37a
-size 7951
+oid sha256:a52077b17bd0682b1110b195a1e258361214b822b99b8871ad466b0573d12715
+size 8903

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3121d7238a937a6a80e99470ebdc5e8160754301169b3872124abe59be46a439
+oid sha256:8e6be35cb16522673708e1fbbc2caa4e52477ad249d044fc6a0e4206cb13148f
 size 131856744