DrishtiSharma
commited on
Commit
•
760900f
1
Parent(s):
77e20e3
End of training
Browse files- .gitignore +1 -0
- amazon_polarity/adapter_config.json +41 -0
- amazon_polarity/head_config.json +20 -0
- amazon_polarity/pytorch_adapter.bin +3 -0
- amazon_polarity/pytorch_model_head.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
amazon_polarity/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": "RobertaModelWithHeads",
|
37 |
+
"model_name": "roberta-base",
|
38 |
+
"model_type": "roberta",
|
39 |
+
"name": "amazon_polarity",
|
40 |
+
"version": "3.2.0"
|
41 |
+
}
|
amazon_polarity/head_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"activation_function": "tanh",
|
4 |
+
"bias": true,
|
5 |
+
"head_type": "classification",
|
6 |
+
"label2id": {
|
7 |
+
"negative": 0,
|
8 |
+
"positive": 1
|
9 |
+
},
|
10 |
+
"layers": 2,
|
11 |
+
"num_labels": 2,
|
12 |
+
"use_pooler": false
|
13 |
+
},
|
14 |
+
"hidden_size": 768,
|
15 |
+
"model_class": "RobertaModelWithHeads",
|
16 |
+
"model_name": "roberta-base",
|
17 |
+
"model_type": "roberta",
|
18 |
+
"name": "amazon_polarity",
|
19 |
+
"version": "3.2.0"
|
20 |
+
}
|
amazon_polarity/pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15dbde0a8f90bbab7cf2b9b61a85960ce41f2a7edbe4132a4fabf0c8ac0ed266
|
3 |
+
size 3595621
|
amazon_polarity/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8a35335a34d0f775a437bc72049b2d6772306b299125efb02887f808f58378c
|
3 |
+
size 2370209
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:132474404420ba35535d7e8f6d1e95b24602d3d352bdff89a29c851efcc42ab8
|
3 |
+
size 3515
|