Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_10_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tiny_bert_rand_10_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_10_v2_mnli
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v2](https://huggingface.co/Hartunka/tiny_bert_rand_10_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9256
+- Accuracy: 0.6564
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.9938        | 1.0   | 1534  | 0.9397          | 0.5474   |
+| 0.9048        | 2.0   | 3068  | 0.8723          | 0.5955   |
+| 0.8336        | 3.0   | 4602  | 0.8226          | 0.6361   |
+| 0.7696        | 4.0   | 6136  | 0.8077          | 0.6479   |
+| 0.7202        | 5.0   | 7670  | 0.7942          | 0.6551   |
+| 0.6775        | 6.0   | 9204  | 0.8227          | 0.6631   |
+| 0.6399        | 7.0   | 10738 | 0.8303          | 0.6600   |
+| 0.6018        | 8.0   | 12272 | 0.8506          | 0.6582   |
+| 0.5655        | 9.0   | 13806 | 0.9015          | 0.6542   |
+| 0.5303        | 10.0  | 15340 | 0.9256          | 0.6564   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745309742.s_005_m.2850172.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85f00147fcc4581ce88c0d71a3822b9b9ef60ec9ea2a1bbceabc5a5a04b98bea
-size 9899
+oid sha256:7feaca31b87ccc94bc692d563944d0b9db5172ecced4db49387a514655a5e734
+size 10787

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b734004b22fd8303209aa576757325cee42ea540b7db13ff14c793c45037f92c
+oid sha256:3e1727be20b426091832aba4a9b90f612446f8e50be183e91cd626dbca3b29db
 size 131858796