Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Hartunka/tiny_bert_rand_100_v1
+tags:
+- generated_from_trainer
+metrics:
+- matthews_correlation
+- accuracy
+model-index:
+- name: tiny_bert_rand_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. -->
+
+# tiny_bert_rand_100_v1_cola
+
+This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v1](https://huggingface.co/Hartunka/tiny_bert_rand_100_v1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8240
+- Matthews Correlation: 0.0899
+- Accuracy: 0.6366
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
+| 0.6124        | 1.0   | 34   | 0.6175          | 0.0                  | 0.6913   |
+| 0.6026        | 2.0   | 68   | 0.6177          | 0.0                  | 0.6913   |
+| 0.5763        | 3.0   | 102  | 0.6167          | 0.0252               | 0.6894   |
+| 0.532         | 4.0   | 136  | 0.6645          | 0.1127               | 0.6759   |
+| 0.4889        | 5.0   | 170  | 0.6773          | 0.1094               | 0.6606   |
+| 0.4476        | 6.0   | 204  | 0.7167          | 0.0621               | 0.6261   |
+| 0.4192        | 7.0   | 238  | 0.7917          | 0.0922               | 0.6165   |
+| 0.3928        | 8.0   | 272  | 0.8240          | 0.0899               | 0.6366   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.19.1

logs/events.out.tfevents.1744830065.s_004_m

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bdd38ba16634a69b480fb1422ab288f5148a15ba80c42bb8b006234d8f4a70
-size 7831
+oid sha256:95417ecd37b0103db9c932abc8fd55a0f67fe281bbc0f73f8fb8d02ab2eb85f3
+size 9768

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:237730f6fbc04109179fbd1e2e514011485cafeaa7e9513d800801e2adc7f1b7
+oid sha256:b243f24423c15ebe61a4f2fb2ff67ae8dd7b9f6e1a5a6eaa86556d4ef8f63445
 size 131856744