varun-v-rao commited on
Commit
5f98141
1 Parent(s): c080376

End of training

Browse files
README.md CHANGED
@@ -1,42 +1,74 @@
1
  ---
 
 
2
  tags:
3
- - adapter-transformers
4
- - gpt2
5
  datasets:
6
- - snli
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  ---
8
 
9
- # Adapter `varun-v-rao/gpt2-bn-adapter-895K-snli-model2` for openai-community/gpt2
 
10
 
11
- An [adapter](https://adapterhub.ml) for the `openai-community/gpt2` model that was trained on the [snli](https://huggingface.co/datasets/snli/) dataset.
12
 
13
- This adapter was created for usage with the **[Adapters](https://github.com/Adapter-Hub/adapters)** library.
 
 
 
14
 
15
- ## Usage
16
 
17
- First, install `adapters`:
18
 
19
- ```
20
- pip install -U adapters
21
- ```
22
 
23
- Now, the adapter can be loaded and activated like this:
24
 
25
- ```python
26
- from adapters import AutoAdapterModel
27
 
28
- model = AutoAdapterModel.from_pretrained("openai-community/gpt2")
29
- adapter_name = model.load_adapter("varun-v-rao/gpt2-bn-adapter-895K-snli-model2", source="hf", set_active=True)
30
- ```
31
 
32
- ## Architecture & Training
33
 
34
- <!-- Add some description here -->
35
 
36
- ## Evaluation results
 
 
 
 
 
 
 
37
 
38
- <!-- Add some description here -->
39
 
40
- ## Citation
 
 
 
 
41
 
42
- <!-- Add some description here -->
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
+ base_model: openai-community/gpt2
4
  tags:
5
+ - generated_from_trainer
 
6
  datasets:
7
+ - stanfordnlp/snli
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: gpt2-bn-adapter-895K-snli-model2
12
+ results:
13
+ - task:
14
+ name: Text Classification
15
+ type: text-classification
16
+ dataset:
17
+ name: snli
18
+ type: stanfordnlp/snli
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.8307254623044097
23
  ---
24
 
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
 
28
+ # gpt2-bn-adapter-895K-snli-model2
29
 
30
+ This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the snli dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.4359
33
+ - Accuracy: 0.8307
34
 
35
+ ## Model description
36
 
37
+ More information needed
38
 
39
+ ## Intended uses & limitations
 
 
40
 
41
+ More information needed
42
 
43
+ ## Training and evaluation data
 
44
 
45
+ More information needed
 
 
46
 
47
+ ## Training procedure
48
 
49
+ ### Training hyperparameters
50
 
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 2e-05
53
+ - train_batch_size: 64
54
+ - eval_batch_size: 32
55
+ - seed: 74
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 3
59
 
60
+ ### Training results
61
 
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
64
+ | 0.5679 | 1.0 | 8584 | 0.4726 | 0.8140 |
65
+ | 0.5194 | 2.0 | 17168 | 0.4418 | 0.8279 |
66
+ | 0.5206 | 3.0 | 25752 | 0.4359 | 0.8307 |
67
 
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.35.2
72
+ - Pytorch 2.1.1+cu121
73
+ - Datasets 2.15.0
74
+ - Tokenizers 0.15.0
runs/Jun19_17-51-23_gl1517.arc-ts.umich.edu/events.out.tfevents.1718833888.gl1517.arc-ts.umich.edu.685140.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebd84bca93ffb50558ad3bf62f9f46b6ba54dc7f81c519ad338b4d8f3e99ae29
3
- size 11089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8f6936c79013a756361ee27bc756937dd9390f0db8f3bdc10d00695da46dc5
3
+ size 14498
snli/adapter_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": null,
10
+ "inv_adapter_reduction_factor": null,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": false,
17
+ "non_linearity": "relu",
18
+ "original_ln_after": true,
19
+ "original_ln_before": true,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 16,
28
+ "residual_before_ln": true,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "config_id": "9076f36a74755ac4",
35
+ "hidden_size": 768,
36
+ "model_class": "GPT2ForSequenceClassification",
37
+ "model_name": "openai-community/gpt2",
38
+ "model_type": "gpt2",
39
+ "name": "snli",
40
+ "version": "0.1.1"
41
+ }
snli/head_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 768,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1,
7
+ "LABEL_2": 2
8
+ },
9
+ "model_class": "GPT2ForSequenceClassification",
10
+ "model_name": "openai-community/gpt2",
11
+ "model_type": "gpt2",
12
+ "name": null,
13
+ "num_labels": 3,
14
+ "version": "0.1.1"
15
+ }
snli/pytorch_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40035afb5ba2879b861f65e3a86b00c3be5c7372f8df1f28f97aff36db589141
3
+ size 3595558
snli/pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da1062aa5c0469d088b080293d6397eb2ba00a86d9a13eea1b0cf1fe364dfc6
3
+ size 10515