Commit
•
e63645f
1
Parent(s):
fe05ae1
End of training
Browse files
README.md
CHANGED
@@ -1,42 +1,74 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
-
-
|
4 |
-
- bart
|
5 |
datasets:
|
6 |
-
- snli
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
-
|
|
|
10 |
|
11 |
-
|
12 |
|
13 |
-
This
|
|
|
|
|
|
|
14 |
|
15 |
-
##
|
16 |
|
17 |
-
|
18 |
|
19 |
-
|
20 |
-
pip install -U adapters
|
21 |
-
```
|
22 |
|
23 |
-
|
24 |
|
25 |
-
|
26 |
-
from adapters import AutoAdapterModel
|
27 |
|
28 |
-
|
29 |
-
adapter_name = model.load_adapter("varun-v-rao/bart-base-bn-adapter-895K-snli-model1", source="hf", set_active=True)
|
30 |
-
```
|
31 |
|
32 |
-
##
|
33 |
|
34 |
-
|
35 |
|
36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
|
38 |
-
|
39 |
|
40 |
-
|
|
|
|
|
|
|
|
|
41 |
|
42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/bart-base
|
4 |
tags:
|
5 |
+
- generated_from_trainer
|
|
|
6 |
datasets:
|
7 |
+
- stanfordnlp/snli
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: bart-base-bn-adapter-895K-snli-model1
|
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: 0.8574476732371469
|
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 |
+
# bart-base-bn-adapter-895K-snli-model1
|
29 |
|
30 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the snli dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.3775
|
33 |
+
- Accuracy: 0.8574
|
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: 65
|
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 |
+
| 0.5241 | 1.0 | 8584 | 0.4209 | 0.8340 |
|
65 |
+
| 0.4838 | 2.0 | 17168 | 0.3869 | 0.8509 |
|
66 |
+
| 0.4716 | 3.0 | 25752 | 0.3775 | 0.8574 |
|
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_15-59-07_gl1523.arc-ts.umich.edu/events.out.tfevents.1718827154.gl1523.arc-ts.umich.edu.4088181.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f38f20a692c09f306cf7c2a47b6fcb8b201eb5c31999257651aba14e195485f
|
3 |
+
size 15178
|
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": "BartForSequenceClassification",
|
37 |
+
"model_name": "facebook/bart-base",
|
38 |
+
"model_type": "bart",
|
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": "BartForSequenceClassification",
|
10 |
+
"model_name": "facebook/bart-base",
|
11 |
+
"model_type": "bart",
|
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 sha256:98c186b47fe54c13d5228d5eb0632463cafb342238f71515f8dc133ef02c1325
|
3 |
+
size 3595942
|
snli/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5483ce86846ce3689c84e40384d0f3d79351449ee6ffee4e3aa8d2e4f2bdbe84
|
3 |
+
size 2373800
|