Model save

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+base_model: Hartunka/bert_base_rand_100_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert_base_rand_100_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_100_v2_mnli
+
+This model is a fine-tuned version of [Hartunka/bert_base_rand_100_v2](https://huggingface.co/Hartunka/bert_base_rand_100_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0930
+- Accuracy: 0.6595
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.9712        | 1.0   | 1534  | 0.8988          | 0.5824   |
+| 0.861         | 2.0   | 3068  | 0.8350          | 0.6276   |
+| 0.769         | 3.0   | 4602  | 0.7970          | 0.6504   |
+| 0.6896        | 4.0   | 6136  | 0.7633          | 0.6661   |
+| 0.6191        | 5.0   | 7670  | 0.7852          | 0.6735   |
+| 0.5467        | 6.0   | 9204  | 0.8340          | 0.6729   |
+| 0.4721        | 7.0   | 10738 | 0.8675          | 0.6770   |
+| 0.4013        | 8.0   | 12272 | 0.9629          | 0.6663   |
+| 0.3355        | 9.0   | 13806 | 1.0930          | 0.6595   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745517906.s_005_m.2892304.106

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7a1321fc68d6351d8deeb868b35b10b3dec1e4dcb388b94c8fe04ba6c5e5494
-size 9372
+oid sha256:86273b392b31c8290b690855f314de8db9b66c0fb9b3faf2e6eae8edd19a32fe
+size 10260

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d562794788e867032953313e3e6560306445abc4aa7092b8f1e4acaee3ad11a4
+oid sha256:849f34afbc1600c5ec8d199e787fa12df368cc37a863da8a44d0165ce39778f0
 size 437956332