Model save

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- super_glue
+metrics:
+- accuracy
+model-index:
+- name: superglue_rte-bert-base-uncased
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: super_glue
+      type: super_glue
+      config: rte
+      split: validation
+      args: rte
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.631768953068592
+---
+
+<!-- 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. -->
+
+# superglue_rte-bert-base-uncased
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the super_glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.9334
+- Accuracy: 0.6318
+
+## 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: 4
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.6845        | 1.0   | 623   | 0.6880          | 0.5379   |
+| 0.6015        | 2.0   | 1246  | 0.8206          | 0.6426   |
+| 0.5012        | 3.0   | 1869  | 1.4769          | 0.6354   |
+| 0.4173        | 4.0   | 2492  | 1.7735          | 0.6570   |
+| 0.078         | 5.0   | 3115  | 2.2116          | 0.6354   |
+| 0.0732        | 6.0   | 3738  | 2.6033          | 0.6318   |
+| 0.0703        | 7.0   | 4361  | 2.7944          | 0.6390   |
+| 0.0543        | 8.0   | 4984  | 2.6007          | 0.6462   |
+| 0.0505        | 9.0   | 5607  | 2.4168          | 0.6462   |
+| 0.0412        | 10.0  | 6230  | 2.7503          | 0.6787   |
+| 0.0303        | 11.0  | 6853  | 3.2166          | 0.6643   |
+| 0.0214        | 12.0  | 7476  | 3.0135          | 0.6498   |
+| 0.0416        | 13.0  | 8099  | 2.9919          | 0.6534   |
+| 0.0252        | 14.0  | 8722  | 3.0985          | 0.6570   |
+| 0.0122        | 15.0  | 9345  | 3.5950          | 0.6209   |
+| 0.009         | 16.0  | 9968  | 3.5463          | 0.6354   |
+| 0.0034        | 17.0  | 10591 | 3.6333          | 0.6570   |
+| 0.0109        | 18.0  | 11214 | 3.6860          | 0.6426   |
+| 0.0041        | 19.0  | 11837 | 3.9160          | 0.6354   |
+| 0.0           | 20.0  | 12460 | 3.9334          | 0.6318   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 1.13.0+cu117
+- Datasets 2.15.0
+- Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368d663992f187e6ccaf07f7e7270f8aa8fbeed675823fdd83852375c28ac6f9
+oid sha256:1be1db2adfe3d5918bb2b0b1cdfda58b5bdf89a554746c0ea91488700701c3a4
 size 438003505