Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: Hartunka/bert_base_km_20_v1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: bert_base_km_20_v1_mrpc
+  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_km_20_v1_mrpc
+
+This model is a fine-tuned version of [Hartunka/bert_base_km_20_v1](https://huggingface.co/Hartunka/bert_base_km_20_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4105
+- Accuracy: 0.6471
+- F1: 0.7447
+- Combined Score: 0.6959
+
+## 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 | F1     | Combined Score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.6264        | 1.0   | 15   | 0.6000          | 0.7108   | 0.8109 | 0.7608         |
+| 0.5604        | 2.0   | 30   | 0.5820          | 0.7132   | 0.8186 | 0.7659         |
+| 0.4642        | 3.0   | 45   | 0.6451          | 0.6863   | 0.7785 | 0.7324         |
+| 0.3411        | 4.0   | 60   | 0.7176          | 0.6838   | 0.7741 | 0.7290         |
+| 0.1998        | 5.0   | 75   | 0.9085          | 0.6912   | 0.7864 | 0.7388         |
+| 0.1089        | 6.0   | 90   | 1.1335          | 0.6005   | 0.6895 | 0.6450         |
+| 0.0526        | 7.0   | 105  | 1.4105          | 0.6471   | 0.7447 | 0.6959         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745028407.s_005_m.2780655.20

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71234722114dd7990e1d5dc1b633a7a5324c3aaf3372dcc156dcf1d984aeb967
-size 7494
+oid sha256:2cb613408c4bd2148bdffb6ebce8e9e307b589e24c61229ed3d9471cfc09beac
+size 9720

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48eb5bdc54de027ae54fd0ff5bff62ae2fda50456e194f79337998e834b9f5d0
+oid sha256:c76a5fb50105f6bf547038b88d726c640c5cf6e06495c937d50127cf189b067c
 size 437953248