Model save

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+base_model: Hartunka/distilbert_km_100_v1
+tags:
+- generated_from_trainer
+metrics:
+- matthews_correlation
+- accuracy
+model-index:
+- name: distilbert_km_100_v1_cola
+  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. -->
+
+# distilbert_km_100_v1_cola
+
+This model is a fine-tuned version of [Hartunka/distilbert_km_100_v1](https://huggingface.co/Hartunka/distilbert_km_100_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8330
+- Matthews Correlation: 0.0623
+- Accuracy: 0.6242
+
+## 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 | Matthews Correlation | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
+| 0.6195        | 1.0   | 34   | 0.6249          | 0.0                  | 0.6913   |
+| 0.601         | 2.0   | 68   | 0.6169          | 0.0416               | 0.6922   |
+| 0.5701        | 3.0   | 102  | 0.6249          | 0.0117               | 0.6759   |
+| 0.5237        | 4.0   | 136  | 0.6790          | 0.0385               | 0.6683   |
+| 0.4548        | 5.0   | 170  | 0.6883          | 0.0972               | 0.6481   |
+| 0.3985        | 6.0   | 204  | 0.7564          | 0.0769               | 0.6453   |
+| 0.3411        | 7.0   | 238  | 0.8330          | 0.0623               | 0.6242   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1744693689.s_005_m.602156.72

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3f18474c92444ad698a6cedf91112e6c743db6410ec7eaf6c3d4fa2387a27e
-size 7953
+oid sha256:709e89db232cea00a40aeec24eddbd6e83d7a2a2f5fa2ad4cc8a142f99254ee0
+size 9503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276a7c29f0a121a35a8bee3920fa49b7d29db3d9a66ec7c6b7837525513a498d
+oid sha256:0f4d7f953f37e249365a2506251902be8f308d15fb93c95d83482d0c57c21287
 size 267832560