Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_5_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tiny_bert_rand_5_v2_mnli
+  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_mnli
+
+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: 0.9851
+- Accuracy: 0.6293
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.9894        | 1.0   | 1534  | 0.9260          | 0.5553   |
+| 0.9044        | 2.0   | 3068  | 0.8912          | 0.5842   |
+| 0.8553        | 3.0   | 4602  | 0.8659          | 0.5969   |
+| 0.8096        | 4.0   | 6136  | 0.8656          | 0.6083   |
+| 0.765         | 5.0   | 7670  | 0.8499          | 0.6164   |
+| 0.7195        | 6.0   | 9204  | 0.8635          | 0.6300   |
+| 0.6754        | 7.0   | 10738 | 0.8770          | 0.6363   |
+| 0.6336        | 8.0   | 12272 | 0.9145          | 0.6287   |
+| 0.5919        | 9.0   | 13806 | 0.9488          | 0.6296   |
+| 0.5523        | 10.0  | 15340 | 0.9851          | 0.6293   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745295570.s_005_m.2836625.106

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205e4c07ed9f91dae7ea5f1878278521ded7ab2c9ab77dd1fe4ca78a2f502f24
-size 9894
+oid sha256:f1f72e6dde9b772a50395c3d36893cf8fbd967923c6e4580fa89be5ead39e2fb
+size 10782

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7a3ebfddb2b0190b6a15c1b74ecd943fce002debee7a60c7b6b36955f61297
+oid sha256:244fe7c2df9f8ee0e8ce7c62f12b76864181d0cfc13eaea19a106fb248c0ad7f
 size 131858796