Model save

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_100_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tiny_bert_rand_100_v2_rte
+  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_rte
+
+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: 1.1385
+- Accuracy: 0.5271
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.7006        | 1.0   | 10   | 0.6890          | 0.5523   |
+| 0.6901        | 2.0   | 20   | 0.6870          | 0.5523   |
+| 0.6767        | 3.0   | 30   | 0.6920          | 0.5632   |
+| 0.6364        | 4.0   | 40   | 0.7453          | 0.5451   |
+| 0.5824        | 5.0   | 50   | 0.8142          | 0.5271   |
+| 0.4991        | 6.0   | 60   | 0.9068          | 0.5199   |
+| 0.3752        | 7.0   | 70   | 1.1385          | 0.5271   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745322965.s_005_m.2850172.62

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54bbf770c00ababca61333eaccd3ad24ab904bc9099323515aa5a33e4ab3b5e
-size 7616
+oid sha256:99b38f1a79e5e21fbf9f79654fb0fba469b380a3adca481ef6c61a41ebd9af8f
+size 9012

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4312b889abc8176632aa2b9deb256265cf01743afbe4741597ff262b614f959c
+oid sha256:56ad59b83ec1c4048fdddb118bc282151a5a1712ae50cfdfac0e45b4320e13c8
 size 131856744