Model save

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+base_model: Hartunka/distilbert_rand_20_v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: distilbert_rand_20_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. -->
+
+# distilbert_rand_20_v2_mnli
+
+This model is a fine-tuned version of [Hartunka/distilbert_rand_20_v2](https://huggingface.co/Hartunka/distilbert_rand_20_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1486
+- Accuracy: 0.6417
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.9775        | 1.0   | 1534  | 0.9092          | 0.5704   |
+| 0.8776        | 2.0   | 3068  | 0.8706          | 0.6022   |
+| 0.7966        | 3.0   | 4602  | 0.8162          | 0.6407   |
+| 0.7182        | 4.0   | 6136  | 0.8156          | 0.6444   |
+| 0.6474        | 5.0   | 7670  | 0.8175          | 0.6536   |
+| 0.5759        | 6.0   | 9204  | 0.8543          | 0.6559   |
+| 0.5059        | 7.0   | 10738 | 0.9203          | 0.6520   |
+| 0.4401        | 8.0   | 12272 | 1.0364          | 0.6452   |
+| 0.3795        | 9.0   | 13806 | 1.1486          | 0.6417   |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745365276.s_005_m.2850345.142

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb34230a02f0dfefaacef8b997056ae91d140309950eade166df969b9e9d3e09
-size 9370
+oid sha256:e95f8e5d570ea42b197051eebb23658f3d9dcc5185b97e3fc179dd275c22b8a6
+size 10258

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecb07027ffd25ee26e3f20dd23db5fbf5cbb9683645ecd01160848f8b948f54
+oid sha256:f588db68623d80ab7df1db66cfadefa7752ed550526ac7fda1eb3f69317067b6
 size 267835644