Model save

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_5_v1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tiny_bert_rand_5_v1_sst2
+  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_v1_sst2
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6272
+- Accuracy: 0.8016
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4063        | 1.0   | 264  | 0.4534          | 0.8142   |
+| 0.2372        | 2.0   | 528  | 0.4991          | 0.8085   |
+| 0.1798        | 3.0   | 792  | 0.5130          | 0.8085   |
+| 0.1434        | 4.0   | 1056 | 0.5430          | 0.8119   |
+| 0.1149        | 5.0   | 1320 | 0.6099          | 0.8062   |
+| 0.0949        | 6.0   | 1584 | 0.6272          | 0.8016   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1744645214.s_005_m.2701049.64

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33444786ce435c4623eab82c290ebd14897cf8af27bce6f043c64021be353615
-size 7653
+oid sha256:50991e25ac2670e16746df18fb373e98131692774534551b22300d6694a01e6d
+size 8541

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f97ade27449a38141c2dd53ffef1a1ba79e2b06382399b16cd121b3c2f2271
+oid sha256:91008afe315592994cc48aa0d1ca3fc1f7085a05431f0a37186f7244097911a6
 size 131856744