ynuozhang
commited on
Commit
·
ec353cd
1
Parent(s):
b3c5f36
update
Browse files- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/dataset_dict.json +1 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/train/dataset_info.json +23 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/train/state.json +13 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/val/dataset_info.json +23 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/val/state.json +13 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/dataset_dict.json +1 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/train/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/train/dataset_info.json +59 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/train/state.json +13 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/val/data-00000-of-00001.arrow +3 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/val/dataset_info.json +59 -0
- training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/val/state.json +13 -0
- training_data_cleaned/permeability_penetrance/permeability_meta_with_split.csv +3 -0
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfd98aa97bb66d135eda67e5bb282b3d6e922bf17daf14ff8932afb9b47d1028
|
| 3 |
+
size 9583616
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/train/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "68b5bbea4df1c6ba",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c137cb1fd1a75f53c5532f4c1dde6f7a50376998c6f57661c80f54c804160d
|
| 3 |
+
size 2397704
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/val/dataset_info.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"sequence": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"embedding": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"_type": "Value"
|
| 13 |
+
},
|
| 14 |
+
"_type": "List"
|
| 15 |
+
},
|
| 16 |
+
"label": {
|
| 17 |
+
"dtype": "int64",
|
| 18 |
+
"_type": "Value"
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"homepage": "",
|
| 22 |
+
"license": ""
|
| 23 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_pooled/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "07e6819c90f3bf76",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "val"]}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaf4c4a94135b6eb05ba47eb281b4147987166ecaf3b9da0ee6f1073080d4e7d
|
| 3 |
+
size 88694064
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/train/dataset_info.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "generator",
|
| 3 |
+
"citation": "",
|
| 4 |
+
"config_name": "default",
|
| 5 |
+
"dataset_name": "generator",
|
| 6 |
+
"dataset_size": 88692128,
|
| 7 |
+
"description": "",
|
| 8 |
+
"download_checksums": {},
|
| 9 |
+
"download_size": 0,
|
| 10 |
+
"features": {
|
| 11 |
+
"sequence": {
|
| 12 |
+
"dtype": "string",
|
| 13 |
+
"_type": "Value"
|
| 14 |
+
},
|
| 15 |
+
"label": {
|
| 16 |
+
"dtype": "int64",
|
| 17 |
+
"_type": "Value"
|
| 18 |
+
},
|
| 19 |
+
"embedding": {
|
| 20 |
+
"feature": {
|
| 21 |
+
"feature": {
|
| 22 |
+
"dtype": "float16",
|
| 23 |
+
"_type": "Value"
|
| 24 |
+
},
|
| 25 |
+
"length": 1280,
|
| 26 |
+
"_type": "List"
|
| 27 |
+
},
|
| 28 |
+
"_type": "List"
|
| 29 |
+
},
|
| 30 |
+
"attention_mask": {
|
| 31 |
+
"feature": {
|
| 32 |
+
"dtype": "int8",
|
| 33 |
+
"_type": "Value"
|
| 34 |
+
},
|
| 35 |
+
"_type": "List"
|
| 36 |
+
},
|
| 37 |
+
"length": {
|
| 38 |
+
"dtype": "int64",
|
| 39 |
+
"_type": "Value"
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"homepage": "",
|
| 43 |
+
"license": "",
|
| 44 |
+
"size_in_bytes": 88692128,
|
| 45 |
+
"splits": {
|
| 46 |
+
"train": {
|
| 47 |
+
"name": "train",
|
| 48 |
+
"num_bytes": 88692128,
|
| 49 |
+
"num_examples": 1859,
|
| 50 |
+
"dataset_name": "generator"
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
+
"version": {
|
| 54 |
+
"version_str": "0.0.0",
|
| 55 |
+
"major": 0,
|
| 56 |
+
"minor": 0,
|
| 57 |
+
"patch": 0
|
| 58 |
+
}
|
| 59 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "a5bcd22fd3db0f14",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": "train"
|
| 13 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/val/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04600597c40e081ec90a164471a17d86b132e10c51913eb01c9279173c9d1eb5
|
| 3 |
+
size 22009232
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/val/dataset_info.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "generator",
|
| 3 |
+
"citation": "",
|
| 4 |
+
"config_name": "default",
|
| 5 |
+
"dataset_name": "generator",
|
| 6 |
+
"dataset_size": 22007790,
|
| 7 |
+
"description": "",
|
| 8 |
+
"download_checksums": {},
|
| 9 |
+
"download_size": 0,
|
| 10 |
+
"features": {
|
| 11 |
+
"sequence": {
|
| 12 |
+
"dtype": "string",
|
| 13 |
+
"_type": "Value"
|
| 14 |
+
},
|
| 15 |
+
"label": {
|
| 16 |
+
"dtype": "int64",
|
| 17 |
+
"_type": "Value"
|
| 18 |
+
},
|
| 19 |
+
"embedding": {
|
| 20 |
+
"feature": {
|
| 21 |
+
"feature": {
|
| 22 |
+
"dtype": "float16",
|
| 23 |
+
"_type": "Value"
|
| 24 |
+
},
|
| 25 |
+
"length": 1280,
|
| 26 |
+
"_type": "List"
|
| 27 |
+
},
|
| 28 |
+
"_type": "List"
|
| 29 |
+
},
|
| 30 |
+
"attention_mask": {
|
| 31 |
+
"feature": {
|
| 32 |
+
"dtype": "int8",
|
| 33 |
+
"_type": "Value"
|
| 34 |
+
},
|
| 35 |
+
"_type": "List"
|
| 36 |
+
},
|
| 37 |
+
"length": {
|
| 38 |
+
"dtype": "int64",
|
| 39 |
+
"_type": "Value"
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"homepage": "",
|
| 43 |
+
"license": "",
|
| 44 |
+
"size_in_bytes": 22007790,
|
| 45 |
+
"splits": {
|
| 46 |
+
"train": {
|
| 47 |
+
"name": "train",
|
| 48 |
+
"num_bytes": 22007790,
|
| 49 |
+
"num_examples": 465,
|
| 50 |
+
"dataset_name": "generator"
|
| 51 |
+
}
|
| 52 |
+
},
|
| 53 |
+
"version": {
|
| 54 |
+
"version_str": "0.0.0",
|
| 55 |
+
"major": 0,
|
| 56 |
+
"minor": 0,
|
| 57 |
+
"patch": 0
|
| 58 |
+
}
|
| 59 |
+
}
|
training_data_cleaned/permeability_penetrance/perm_wt_with_embeddings_unpooled/val/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "a0279a68c4421c5c",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": "train"
|
| 13 |
+
}
|
training_data_cleaned/permeability_penetrance/permeability_meta_with_split.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c924f1b92fac14f2007afb1b4b3641047896219a17a5780beb865ee0f4b35ec8
|
| 3 |
+
size 82999
|