Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Hartunka/tiny_bert_rand_20_v2
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: tiny_bert_rand_20_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_20_v2_stsb
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_20_v2](https://huggingface.co/Hartunka/tiny_bert_rand_20_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.6271
+- Pearson: 0.2217
+- Spearmanr: 0.2267
+- Combined Score: 0.2242
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
+| 3.3593        | 1.0   | 23   | 2.3324          | 0.0965  | 0.0831    | 0.0898         |
+| 2.0103        | 2.0   | 46   | 2.6266          | 0.1156  | 0.0993    | 0.1075         |
+| 1.8753        | 3.0   | 69   | 2.4261          | 0.1551  | 0.1384    | 0.1468         |
+| 1.6951        | 4.0   | 92   | 2.4686          | 0.2094  | 0.2023    | 0.2059         |
+| 1.431         | 5.0   | 115  | 2.4817          | 0.2171  | 0.2103    | 0.2137         |
+| 1.3014        | 6.0   | 138  | 2.6271          | 0.2217  | 0.2267    | 0.2242         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745314143.s_005_m.2850172.30

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540002e8f8114df6e649ac29c28caac34b99c1a670943d80fa56998a9bfc4698
-size 7536
+oid sha256:94bd9eb41e44ff2ee4da4b4e8a265b8d48c280b176e51c1707acc0790890be1f
+size 9166

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d759e2158befcb05b97afea561e1c082e55675be9953b0717ae62e03e70a0a3
+oid sha256:5fdf92d126e503933f396e1b7b1944cd3cf94fcb0e1cf526bc8a18490bde86f8
 size 131854692