Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_100_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: tiny_bert_rand_100_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_rand_100_v2_mrpc
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v2](https://huggingface.co/Hartunka/tiny_bert_rand_100_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0011
+- Accuracy: 0.625
+- F1: 0.7193
+- Combined Score: 0.6721
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.627         | 1.0   | 15   | 0.6093          | 0.6985   | 0.8105 | 0.7545         |
+| 0.5922        | 2.0   | 30   | 0.5936          | 0.6838   | 0.7969 | 0.7403         |
+| 0.5576        | 3.0   | 45   | 0.6135          | 0.6863   | 0.8019 | 0.7441         |
+| 0.5114        | 4.0   | 60   | 0.6669          | 0.6348   | 0.7107 | 0.6727         |
+| 0.425         | 5.0   | 75   | 0.7027          | 0.6569   | 0.7473 | 0.7021         |
+| 0.3145        | 6.0   | 90   | 0.8699          | 0.6373   | 0.7259 | 0.6816         |
+| 0.2174        | 7.0   | 105  | 1.0011          | 0.625    | 0.7193 | 0.6721         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745321008.s_005_m.2850172.56

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126a21849a782867014e97e2dfa6fd30e3123272facad6a920357d333368d4c9
-size 8131
+oid sha256:c7c3495e970fcc21b20a7758db522a2963c79270ec3df3780812c35d73f41630
+size 9731

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c07e63c08e8e7bc580da895600e7241cd3ceb00f7ba2ffb0197bd1d78d2e61
+oid sha256:c331eda149130f43011d03efc7d533ffeeb226fd286caf8af460d6dcf8b57f61
 size 131856744