Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_10_v2
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: tiny_bert_rand_10_v2_stsb
+  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_rand_10_v2_stsb
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_10_v2](https://huggingface.co/Hartunka/tiny_bert_rand_10_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4510
+- Pearson: 0.2983
+- Spearmanr: 0.3000
+- Combined Score: 0.2992
+
+## 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 | Pearson | Spearmanr | Combined Score |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
+| 3.1623        | 1.0   | 23   | 2.2278          | 0.1029  | 0.1103    | 0.1066         |
+| 2.0283        | 2.0   | 46   | 2.6435          | 0.0808  | 0.0590    | 0.0699         |
+| 1.8414        | 3.0   | 69   | 2.4582          | 0.1896  | 0.1824    | 0.1860         |
+| 1.6228        | 4.0   | 92   | 2.4701          | 0.2441  | 0.2441    | 0.2441         |
+| 1.3269        | 5.0   | 115  | 2.4297          | 0.2678  | 0.2654    | 0.2666         |
+| 1.0809        | 6.0   | 138  | 2.4510          | 0.2983  | 0.3000    | 0.2992         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745309622.s_005_m.2850172.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f978196c1c23bce535d7a308aa8807253ffbcda40eb26669657423df9e8c92
-size 7536
+oid sha256:5672dd2fd3a0d1c5de774100f6c63050674c0dc94f651cdcfb011e3e8c1342af
+size 9166

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4942970e73ebda337535aef6893ae84d596c3bdf4a8368f75f83659c011ade1
+oid sha256:47c023224fda02bf2112ff4f055b1b5cac4c18e6762fceab9ebe6e0bc0660c16
 size 131854692