Model save

README.md

@@ -0,0 +1,91 @@
+---
+base_model: gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- matthews_correlation
+- accuracy
+model-index:
+- name: hBERTv1_new_pretrain_w_init_48_ver2_cola
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: glue
+      type: glue
+      config: cola
+      split: validation
+      args: cola
+    metrics:
+    - name: Matthews Correlation
+      type: matthews_correlation
+      value: 0.0
+    - name: Accuracy
+      type: accuracy
+      value: 0.6912751793861389
+---
+
+<!-- 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. -->
+
+# hBERTv1_new_pretrain_w_init_48_ver2_cola
+
+This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6184
+- Matthews Correlation: 0.0
+- Accuracy: 0.6913
+
+## 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: 4e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 10
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|:--------:|
+| 0.6277        | 1.0   | 134  | 0.6457          | 0.0                  | 0.6913   |
+| 0.6178        | 2.0   | 268  | 0.6240          | 0.0                  | 0.6913   |
+| 0.6152        | 3.0   | 402  | 0.6201          | 0.0                  | 0.6913   |
+| 0.6138        | 4.0   | 536  | 0.6181          | 0.0                  | 0.6913   |
+| 0.6111        | 5.0   | 670  | 0.6181          | 0.0                  | 0.6913   |
+| 0.6122        | 6.0   | 804  | 0.6232          | 0.0                  | 0.6913   |
+| 0.611         | 7.0   | 938  | 0.6179          | 0.0                  | 0.6913   |
+| 0.6087        | 8.0   | 1072 | 0.6182          | 0.0                  | 0.6913   |
+| 0.6112        | 9.0   | 1206 | 0.6226          | 0.0                  | 0.6913   |
+| 0.6116        | 10.0  | 1340 | 0.6210          | 0.0                  | 0.6913   |
+| 0.6091        | 11.0  | 1474 | 0.6194          | 0.0                  | 0.6913   |
+| 0.6087        | 12.0  | 1608 | 0.6184          | 0.0                  | 0.6913   |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 1.14.0a0+410ce96
+- Datasets 2.14.5
+- Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d72b5807a3a94548318e684254ac6791acf4a83956a5dde1b65d5d6d0b9ba5
+oid sha256:df8771a51b6b0b7c090762bc673e57b793bc670874dcc8a3c84e86801bd240bc
 size 481099229