End of training

README.md

@@ -1,42 +1,74 @@
 ---
+license: mit
+base_model: openai-community/gpt2-large
 tags:
-- adapter-transformers
-- gpt2
+- generated_from_trainer
 datasets:
-- snli
+- stanfordnlp/snli
+metrics:
+- accuracy
+model-index:
+- name: gpt2-large-bn-adapter-7.42M-snli-model1
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: snli
+      type: stanfordnlp/snli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8999187157081894
 ---
 
-# Adapter `varun-v-rao/gpt2-large-bn-adapter-7.42M-snli-model1` for openai-community/gpt2-large
+<!-- 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. -->
 
-An [adapter](https://adapterhub.ml) for the `openai-community/gpt2-large` model that was trained on the [snli](https://huggingface.co/datasets/snli/) dataset.
+# gpt2-large-bn-adapter-7.42M-snli-model1
 
-This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
+This model is a fine-tuned version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the snli dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2789
+- Accuracy: 0.8999
 
-## Usage
+## Model description
 
-First, install `adapters`:
+More information needed
 
-```
-pip install -U adapters
-```
+## Intended uses & limitations
 
-Now, the adapter can be loaded and activated like this:
+More information needed
 
-```python
-from adapters import AutoAdapterModel
+## Training and evaluation data
 
-model = AutoAdapterModel.from_pretrained("openai-community/gpt2-large")
-adapter_name = model.load_adapter("varun-v-rao/gpt2-large-bn-adapter-7.42M-snli-model1", source="hf", set_active=True)
-```
+More information needed
 
-## Architecture & Training
+## Training procedure
 
-<!-- Add some description here -->
+### Training hyperparameters
 
-## Evaluation results
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 23
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
 
-<!-- Add some description here -->
+### Training results
 
-## Citation
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3594        | 1.0   | 17168 | 0.3009          | 0.8894   |
+| 0.3278        | 2.0   | 34336 | 0.2831          | 0.8967   |
+| 0.3089        | 3.0   | 51504 | 0.2789          | 0.8999   |
 
-<!-- Add some description here -->
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

runs/Jun24_03-00-35_gl1500.arc-ts.umich.edu/events.out.tfevents.1719212466.gl1500.arc-ts.umich.edu.199701.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac4a7453b7c596e6efcbc6f1347adfcbd2465a5b96ca80eb3ef03c9d39a74ca
-size 16591
+oid sha256:2050ed5109a7ea5efcddfebec936a5e7f4b1ea96956c21c693778e2559ecdf6e
+size 22880

snli/pytorch_adapter.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207afe89af3015147aaa29ff00fa8ae3543d4d5745a2bc2f898b204419d27552
+oid sha256:c6e6574ab8d2b146d1cf515c3cfb9cff2deece941d7fbdee69caf47154925fef
 size 29739378

snli/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7041212c0430d1f3a1ab5c0560ade9d9d6c95d9d324cb16cd25304c680540cb4
+oid sha256:e8cd8018d957c26c21f8e5cf1ed2270d73c4f415085f7917f56bff84f08d3de6
 size 16659