End of training

README.md

@@ -1,42 +1,62 @@
 ---
+license: apache-2.0
+base_model: bert-large-cased
 tags:
-- adapter-transformers
-- bert
-datasets:
-- snli
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: bert-large-cased-bn-adapter-3.17M-snli-model3
+  results: []
 ---
 
-# Adapter `varun-v-rao/bert-large-cased-bn-adapter-3.17M-snli-model3` for bert-large-cased
+<!-- 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 `bert-large-cased` model that was trained on the [snli](https://huggingface.co/datasets/snli/) dataset.
+# bert-large-cased-bn-adapter-3.17M-snli-model3
 
-This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
+This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7627
+- Accuracy: 0.7315
 
-## 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("bert-large-cased")
-adapter_name = model.load_adapter("varun-v-rao/bert-large-cased-bn-adapter-3.17M-snli-model3", 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: 64
+- eval_batch_size: 64
+- seed: 61
+- 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.4101        | 1.0   | 8584  | 0.3392          | 0.8718   |
+| 0.3707        | 2.0   | 17168 | 0.3116          | 0.8842   |
+| 0.3628        | 3.0   | 25752 | 0.3035          | 0.8879   |
 
-<!-- Add some description here -->
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

runs/Feb06_23-46-56_gl1509.arc-ts.umich.edu/events.out.tfevents.1707281229.gl1509.arc-ts.umich.edu.21360.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb359a29483a08f418bf4a7cb238585280014f274585f64832c4ab2d85b76e3b
-size 11074
+oid sha256:d60a20c42dab9097949e1321145f78c6b80933ec26df45bf82772db284f5ec6f
+size 14483

runs/Feb06_23-46-56_gl1509.arc-ts.umich.edu/events.out.tfevents.1707289823.gl1509.arc-ts.umich.edu.21360.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48aba707fac72a5b9e555848e4da361d34f272fb247339471ca02c30cd7d9e67
+size 1404

snli/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": "BertForSequenceClassification",
+  "model_name": "bert-large-cased",
+  "model_type": "bert",
+  "name": "snli",
+  "version": "0.1.1"
+}

snli/head_config.json

@@ -0,0 +1,15 @@
+{
+  "config": null,
+  "hidden_size": 1024,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "model_class": "BertForSequenceClassification",
+  "model_name": "bert-large-cased",
+  "model_type": "bert",
+  "name": null,
+  "num_labels": 3,
+  "version": "0.1.1"
+}

snli/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22766092cf5182dd20a6708c2c57c270c29c647ec3da2b6d6b3fdb0fa7ff6fd7
+size 12721878

snli/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e328ad7c773c3d7255bbb5245af9a3a68706bf55666e8ee8cdce12c57a8106
+size 13850