End of training

README.md

@@ -1,42 +1,54 @@
 ---
+license: mit
+base_model: roberta-large
 tags:
-- roberta
-- adapter-transformers
+- generated_from_trainer
 datasets:
-- squad
+- varun-v-rao/squad
+model-index:
+- name: roberta-large-bn-adapter-3.17M-squad-model1
+  results: []
 ---
 
-# Adapter `varun-v-rao/roberta-large-bn-adapter-3.17M-squad-model1` for roberta-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 `roberta-large` model that was trained on the [squad](https://huggingface.co/datasets/squad/) dataset.
+# roberta-large-bn-adapter-3.17M-squad-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 [roberta-large](https://huggingface.co/roberta-large) on the squad dataset.
 
-## 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("roberta-large")
-adapter_name = model.load_adapter("varun-v-rao/roberta-large-bn-adapter-3.17M-squad-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: 16
+- eval_batch_size: 4
+- seed: 95
+- 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
 
-<!-- Add some description here -->
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

runs/Feb08_19-14-25_gl1510.arc-ts.umich.edu/events.out.tfevents.1707437679.gl1510.arc-ts.umich.edu.2843306.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20eefc799b74a4c2ba0fc0640e123a961d7fb8263dace9d951c720cbb969fbe
-size 9741
+oid sha256:2c5e76b974ac03a7a8079b2426d032081370c76a7656f0baf9699ed12b7c27da
+size 10095

squad/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "9076f36a74755ac4",
+  "hidden_size": 1024,
+  "model_class": "RobertaForQuestionAnswering",
+  "model_name": "roberta-large",
+  "model_type": "roberta",
+  "name": "squad",
+  "version": "0.1.1"
+}

squad/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 1024,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "RobertaForQuestionAnswering",
+  "model_name": "roberta-large",
+  "model_type": "roberta",
+  "name": null,
+  "num_labels": 2,
+  "version": "0.1.1"
+}

squad/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efee8b008cd99b2f2b4238f77f3448ab4d5c75ed58a0adbfb1de3902a3191ef5
+size 12722262

squad/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c9ee56a28926da0895354c024984d69dfc6e2202700696a71188e91f966a50
+size 9754