Model save

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+base_model: Hartunka/distilbert_km_100_v2
+tags:
+- generated_from_trainer
+metrics:
+- spearmanr
+model-index:
+- name: distilbert_km_100_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. -->
+
+# distilbert_km_100_v2_stsb
+
+This model is a fine-tuned version of [Hartunka/distilbert_km_100_v2](https://huggingface.co/Hartunka/distilbert_km_100_v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5757
+- Pearson: 0.3414
+- Spearmanr: 0.3382
+- Combined Score: 0.3398
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
+| 2.9541        | 1.0   | 23   | 2.3048          | 0.1100  | 0.0962    | 0.1031         |
+| 1.9575        | 2.0   | 46   | 2.3279          | 0.2262  | 0.2085    | 0.2173         |
+| 1.7269        | 3.0   | 69   | 2.4054          | 0.2387  | 0.2248    | 0.2318         |
+| 1.4551        | 4.0   | 92   | 2.4810          | 0.2706  | 0.2568    | 0.2637         |
+| 1.1316        | 5.0   | 115  | 2.2465          | 0.3342  | 0.3295    | 0.3318         |
+| 0.8642        | 6.0   | 138  | 2.5217          | 0.3353  | 0.3416    | 0.3385         |
+| 0.6447        | 7.0   | 161  | 2.4307          | 0.3412  | 0.3420    | 0.3416         |
+| 0.5298        | 8.0   | 184  | 2.4239          | 0.3389  | 0.3371    | 0.3380         |
+| 0.429         | 9.0   | 207  | 2.6856          | 0.3281  | 0.3233    | 0.3257         |
+| 0.3557        | 10.0  | 230  | 2.5757          | 0.3414  | 0.3382    | 0.3398         |
+
+
+### Framework versions
+
+- Transformers 4.50.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.21.1

logs/events.out.tfevents.1745342504.s_005_m.2850345.84

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46384b2eb62fbfaa5285605ad8b36fee59dd84d79b91f62461b95d7e7f10204a
-size 9458
+oid sha256:e8bf2e0a7fe117eec52bbe2816579706b4257be90afb8a64c6739181bb8c3894
+size 11744

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d59f191842f1f889d35cec5dc650745697f219949ff3e650d1445189eafe8c
+oid sha256:6ec7422bbc44a9c1e2dea1a3b963cb7ae0f43be9389bdea8c4ac02d89c76d0e3
 size 267829484