Model save

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_km_100_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: tiny_bert_km_100_v2_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. -->
+
+# tiny_bert_km_100_v2_mrpc
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_km_100_v2](https://huggingface.co/Hartunka/tiny_bert_km_100_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9051
+- Accuracy: 0.6495
+- F1: 0.7478
+- Combined Score: 0.6987
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
+| 0.6358        | 1.0   | 15   | 0.6057          | 0.7059   | 0.8204 | 0.7631         |
+| 0.5975        | 2.0   | 30   | 0.5954          | 0.7083   | 0.8232 | 0.7658         |
+| 0.5692        | 3.0   | 45   | 0.5977          | 0.7083   | 0.8216 | 0.7650         |
+| 0.5442        | 4.0   | 60   | 0.5924          | 0.6985   | 0.8057 | 0.7521         |
+| 0.4983        | 5.0   | 75   | 0.6211          | 0.6985   | 0.8013 | 0.7499         |
+| 0.4324        | 6.0   | 90   | 0.6470          | 0.6863   | 0.7823 | 0.7343         |
+| 0.3495        | 7.0   | 105  | 0.7373          | 0.6789   | 0.7783 | 0.7286         |
+| 0.2481        | 8.0   | 120  | 0.8264          | 0.6789   | 0.7828 | 0.7308         |
+| 0.1813        | 9.0   | 135  | 0.9051          | 0.6495   | 0.7478 | 0.6987         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745288179.s_005_m.2836625.74

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a19197ddb28d9b059b275ea4b4edde0ad1fd522586f2b20e1ec79e3dc537e1b
-size 5619
+oid sha256:94f96ed170232308c08a8e31c415eb09b2ba8ebaa2e213c1a4dd2982a5862488
+size 10993

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbc481a02266a92d392671c0b81466a156ffd999c9c846f4dd90c1b7032d424
+oid sha256:f77cea89a2cf64c4e259877dfa325cf6361f765ef8f4acb0db55fc186785a2d1
 size 131856744