Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/bert_base_rand_5_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_base_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. -->
+
+# bert_base_rand_5_v2_mnli
+
+This model is a fine-tuned version of [Hartunka/bert_base_rand_5_v2](https://huggingface.co/Hartunka/bert_base_rand_5_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1639
+- Accuracy: 0.6609
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.9841        | 1.0   | 1534  | 0.9164          | 0.5656   |
+| 0.8816        | 2.0   | 3068  | 0.8639          | 0.6032   |
+| 0.802         | 3.0   | 4602  | 0.8340          | 0.6224   |
+| 0.7236        | 4.0   | 6136  | 0.8123          | 0.6467   |
+| 0.6505        | 5.0   | 7670  | 0.8058          | 0.6626   |
+| 0.5786        | 6.0   | 9204  | 0.8321          | 0.6625   |
+| 0.5046        | 7.0   | 10738 | 0.8853          | 0.6595   |
+| 0.4363        | 8.0   | 12272 | 0.9630          | 0.6584   |
+| 0.3721        | 9.0   | 13806 | 1.0416          | 0.6501   |
+| 0.3164        | 10.0  | 15340 | 1.1639          | 0.6609   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745462753.s_005_m.2892304.34

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb8f28b5bbbb13b614ce1f6c8672bfb542307d672b16148cd029b7e1bdd86f6
-size 9896
+oid sha256:ab5f97a60f3acdaacf8a825a0035b7f691439149fcc50ac535fb7bf31d203dee
+size 10784

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e4b4e2f69771093834c5b8199d8373400907cae4d208d80633ada1d9a979ab
+oid sha256:ad4ba30277da0f6006969aa63036fe3cdd8e729d6ee8969074c346de986ce437
 size 437956332