Commit
·
998f6a7
1
Parent(s):
06e4300
Training in progress, step 2
Browse files- HW3_Data_ocr/dataset_dict.json +1 -0
- HW3_Data_ocr/test/data-00000-of-00001.arrow +3 -0
- HW3_Data_ocr/test/dataset_info.json +50 -0
- HW3_Data_ocr/test/state.json +13 -0
- HW3_Data_ocr/train/data-00000-of-00001.arrow +3 -0
- HW3_Data_ocr/train/dataset_info.json +50 -0
- HW3_Data_ocr/train/state.json +13 -0
- HW3_Encoded_te/data-00000-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00001-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00002-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00003-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00004-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00005-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00006-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00007-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00008-of-00010.arrow +3 -0
- HW3_Encoded_te/data-00009-of-00010.arrow +3 -0
- HW3_Encoded_te/dataset_info.json +60 -0
- HW3_Encoded_te/state.json +40 -0
- HW3_Encoded_tr/data-00000-of-00001.arrow +3 -0
- HW3_Encoded_tr/data-00000-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00001-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00002-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00003-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00004-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00005-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00006-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00007-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00008-of-00010.arrow +3 -0
- HW3_Encoded_tr/data-00009-of-00010.arrow +3 -0
- HW3_Encoded_tr/dataset_info.json +60 -0
- HW3_Encoded_tr/state.json +40 -0
- config.json +132 -0
- model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/Nov08_17-11-57_c3571ebff4b6/events.out.tfevents.1699463599.c3571ebff4b6.131.0 +3 -0
- runs/Nov08_17-15-33_c3571ebff4b6/events.out.tfevents.1699463762.c3571ebff4b6.131.1 +3 -0
- runs/Nov08_17-20-47_c3571ebff4b6/events.out.tfevents.1699464083.c3571ebff4b6.30091.0 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +79 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
HW3_Data_ocr/dataset_dict.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"splits": ["train", "test"]}
|
HW3_Data_ocr/test/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3117af89f2d6c9e9e97da01956422fa8db283d3db7e46ff94194677d214cc05d
|
| 3 |
+
size 30523912
|
HW3_Data_ocr/test/dataset_info.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"id": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"image": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"feature": {
|
| 12 |
+
"feature": {
|
| 13 |
+
"dtype": "uint8",
|
| 14 |
+
"_type": "Value"
|
| 15 |
+
},
|
| 16 |
+
"_type": "Sequence"
|
| 17 |
+
},
|
| 18 |
+
"_type": "Sequence"
|
| 19 |
+
},
|
| 20 |
+
"_type": "Sequence"
|
| 21 |
+
},
|
| 22 |
+
"answer": {
|
| 23 |
+
"dtype": "string",
|
| 24 |
+
"_type": "Value"
|
| 25 |
+
},
|
| 26 |
+
"question": {
|
| 27 |
+
"dtype": "string",
|
| 28 |
+
"_type": "Value"
|
| 29 |
+
},
|
| 30 |
+
"words": {
|
| 31 |
+
"feature": {
|
| 32 |
+
"dtype": "string",
|
| 33 |
+
"_type": "Value"
|
| 34 |
+
},
|
| 35 |
+
"_type": "Sequence"
|
| 36 |
+
},
|
| 37 |
+
"boxes": {
|
| 38 |
+
"feature": {
|
| 39 |
+
"feature": {
|
| 40 |
+
"dtype": "int64",
|
| 41 |
+
"_type": "Value"
|
| 42 |
+
},
|
| 43 |
+
"_type": "Sequence"
|
| 44 |
+
},
|
| 45 |
+
"_type": "Sequence"
|
| 46 |
+
}
|
| 47 |
+
},
|
| 48 |
+
"homepage": "",
|
| 49 |
+
"license": ""
|
| 50 |
+
}
|
HW3_Data_ocr/test/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "1d507536506aae4c",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
HW3_Data_ocr/train/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af961ca326fcb4043dc1ca58e0cb26a477ab8e6a4765fa1d127994e1eca9f98d
|
| 3 |
+
size 147849288
|
HW3_Data_ocr/train/dataset_info.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"id": {
|
| 6 |
+
"dtype": "string",
|
| 7 |
+
"_type": "Value"
|
| 8 |
+
},
|
| 9 |
+
"image": {
|
| 10 |
+
"feature": {
|
| 11 |
+
"feature": {
|
| 12 |
+
"feature": {
|
| 13 |
+
"dtype": "uint8",
|
| 14 |
+
"_type": "Value"
|
| 15 |
+
},
|
| 16 |
+
"_type": "Sequence"
|
| 17 |
+
},
|
| 18 |
+
"_type": "Sequence"
|
| 19 |
+
},
|
| 20 |
+
"_type": "Sequence"
|
| 21 |
+
},
|
| 22 |
+
"answer": {
|
| 23 |
+
"dtype": "string",
|
| 24 |
+
"_type": "Value"
|
| 25 |
+
},
|
| 26 |
+
"question": {
|
| 27 |
+
"dtype": "string",
|
| 28 |
+
"_type": "Value"
|
| 29 |
+
},
|
| 30 |
+
"words": {
|
| 31 |
+
"feature": {
|
| 32 |
+
"dtype": "string",
|
| 33 |
+
"_type": "Value"
|
| 34 |
+
},
|
| 35 |
+
"_type": "Sequence"
|
| 36 |
+
},
|
| 37 |
+
"boxes": {
|
| 38 |
+
"feature": {
|
| 39 |
+
"feature": {
|
| 40 |
+
"dtype": "int64",
|
| 41 |
+
"_type": "Value"
|
| 42 |
+
},
|
| 43 |
+
"_type": "Sequence"
|
| 44 |
+
},
|
| 45 |
+
"_type": "Sequence"
|
| 46 |
+
}
|
| 47 |
+
},
|
| 48 |
+
"homepage": "",
|
| 49 |
+
"license": ""
|
| 50 |
+
}
|
HW3_Data_ocr/train/state.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00001.arrow"
|
| 5 |
+
}
|
| 6 |
+
],
|
| 7 |
+
"_fingerprint": "f3c0ef9e1d56ad66",
|
| 8 |
+
"_format_columns": null,
|
| 9 |
+
"_format_kwargs": {},
|
| 10 |
+
"_format_type": null,
|
| 11 |
+
"_output_all_columns": false,
|
| 12 |
+
"_split": null
|
| 13 |
+
}
|
HW3_Encoded_te/data-00000-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af881cb86718deffe6643eab58e7c3850dff2d242add6a6b6364af3e8c65bf84
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00001-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf75fa5420c178a961fa524f5e4a97b33d8a0f460dbfbcfb0b8e6de39653d9e6
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00002-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:516f1983d209e6fb9b2c50b274fae7a8f97e8442e6bc52c9b314bcd04151fb90
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00003-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87c9f0510b1da3610aae4d4c5c71595467dc2cd1d422ec249197d22842c6eb2d
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00004-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84ff6acc8adef9c70330fe4cef7c70f1a9fa00d7f2c41c131f679648ac9099b9
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00005-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ad1cf48bd0cdcb1c813a39c9601bc0eb607d3fe642f3f920186d9f725657ed
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00006-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d925cfb52bfd87af150510f9ef3022dcdafc561c86d18a89c4c27c963e79ea40
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00007-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:607ee1170524c20056a71c0d9ac8539860f099c5af8498ae19416344b0677c14
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00008-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c87318fbe84ae5d153dc3c262885ba5262cf52588ac82d18a1bde80505ad0875
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/data-00009-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0d88c1d7f0523b93a2de1398e07c9a0a23006e3bdad73a7c050aef9f63fe1fd
|
| 3 |
+
size 3323016
|
HW3_Encoded_te/dataset_info.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"image": {
|
| 6 |
+
"feature": {
|
| 7 |
+
"feature": {
|
| 8 |
+
"feature": {
|
| 9 |
+
"dtype": "uint8",
|
| 10 |
+
"_type": "Value"
|
| 11 |
+
},
|
| 12 |
+
"_type": "Sequence"
|
| 13 |
+
},
|
| 14 |
+
"_type": "Sequence"
|
| 15 |
+
},
|
| 16 |
+
"_type": "Sequence"
|
| 17 |
+
},
|
| 18 |
+
"input_ids": {
|
| 19 |
+
"feature": {
|
| 20 |
+
"dtype": "int32",
|
| 21 |
+
"_type": "Value"
|
| 22 |
+
},
|
| 23 |
+
"_type": "Sequence"
|
| 24 |
+
},
|
| 25 |
+
"token_type_ids": {
|
| 26 |
+
"feature": {
|
| 27 |
+
"dtype": "int8",
|
| 28 |
+
"_type": "Value"
|
| 29 |
+
},
|
| 30 |
+
"_type": "Sequence"
|
| 31 |
+
},
|
| 32 |
+
"attention_mask": {
|
| 33 |
+
"feature": {
|
| 34 |
+
"dtype": "int8",
|
| 35 |
+
"_type": "Value"
|
| 36 |
+
},
|
| 37 |
+
"_type": "Sequence"
|
| 38 |
+
},
|
| 39 |
+
"bbox": {
|
| 40 |
+
"feature": {
|
| 41 |
+
"feature": {
|
| 42 |
+
"dtype": "int64",
|
| 43 |
+
"_type": "Value"
|
| 44 |
+
},
|
| 45 |
+
"_type": "Sequence"
|
| 46 |
+
},
|
| 47 |
+
"_type": "Sequence"
|
| 48 |
+
},
|
| 49 |
+
"start_positions": {
|
| 50 |
+
"dtype": "int64",
|
| 51 |
+
"_type": "Value"
|
| 52 |
+
},
|
| 53 |
+
"end_positions": {
|
| 54 |
+
"dtype": "int64",
|
| 55 |
+
"_type": "Value"
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"homepage": "",
|
| 59 |
+
"license": ""
|
| 60 |
+
}
|
HW3_Encoded_te/state.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00010.arrow"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"filename": "data-00001-of-00010.arrow"
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"filename": "data-00002-of-00010.arrow"
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"filename": "data-00003-of-00010.arrow"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"filename": "data-00004-of-00010.arrow"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"filename": "data-00005-of-00010.arrow"
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"filename": "data-00006-of-00010.arrow"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"filename": "data-00007-of-00010.arrow"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"filename": "data-00008-of-00010.arrow"
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"filename": "data-00009-of-00010.arrow"
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"_fingerprint": "c8ef0892137ccf76",
|
| 35 |
+
"_format_columns": null,
|
| 36 |
+
"_format_kwargs": {},
|
| 37 |
+
"_format_type": null,
|
| 38 |
+
"_output_all_columns": false,
|
| 39 |
+
"_split": null
|
| 40 |
+
}
|
HW3_Encoded_tr/data-00000-of-00001.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbb896695747eaa30d35fc097b7e508b4a6064e1dba51cad8872c8ef57ba75d4
|
| 3 |
+
size 157992720
|
HW3_Encoded_tr/data-00000-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e70f5c89fec743ea8d14d4b4fb2cf763044c3d3d0326e4ff47a5549318d3987
|
| 3 |
+
size 15906312
|
HW3_Encoded_tr/data-00001-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aa80fb2ae9ba0d43446e1027b42ef13583b166476953627145a269107a653ec
|
| 3 |
+
size 15906312
|
HW3_Encoded_tr/data-00002-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:227a0a0258ca59599c186448354245336d2aed341453e36da96f9082c6cb6c88
|
| 3 |
+
size 15906312
|
HW3_Encoded_tr/data-00003-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23ecbda78acf3edcb8e732e8b2f4d01e923c51bea2646c59b99d6e290a489322
|
| 3 |
+
size 15906312
|
HW3_Encoded_tr/data-00004-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57aa551d085119d4e0f88fd78b03ac3d49b41d722f150022c83b10666cb45e41
|
| 3 |
+
size 15731568
|
HW3_Encoded_tr/data-00005-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ac89dc3ce17866225ed3d04059a86e3c1f01452ced73a93789332de99748218
|
| 3 |
+
size 15731568
|
HW3_Encoded_tr/data-00006-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d6e0810433ba242cc3822bb2384607aaff66f6bfaaa10474a1e080413c0432
|
| 3 |
+
size 15731568
|
HW3_Encoded_tr/data-00007-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8c8a13bcd3a0c91e6e52781ddad8c67b2510d32913818431970e5bd2d38d249
|
| 3 |
+
size 15731568
|
HW3_Encoded_tr/data-00008-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a3cc4a22a74e9b697ede75a0525987627dd04a3b9eefc89d196e726d2dd3b6a
|
| 3 |
+
size 15731568
|
HW3_Encoded_tr/data-00009-of-00010.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57f454865343904f346406866476cbd1dab775f9f6e0d497eab9482fc586c5a3
|
| 3 |
+
size 15731568
|
HW3_Encoded_tr/dataset_info.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"citation": "",
|
| 3 |
+
"description": "",
|
| 4 |
+
"features": {
|
| 5 |
+
"image": {
|
| 6 |
+
"feature": {
|
| 7 |
+
"feature": {
|
| 8 |
+
"feature": {
|
| 9 |
+
"dtype": "uint8",
|
| 10 |
+
"_type": "Value"
|
| 11 |
+
},
|
| 12 |
+
"_type": "Sequence"
|
| 13 |
+
},
|
| 14 |
+
"_type": "Sequence"
|
| 15 |
+
},
|
| 16 |
+
"_type": "Sequence"
|
| 17 |
+
},
|
| 18 |
+
"input_ids": {
|
| 19 |
+
"feature": {
|
| 20 |
+
"dtype": "int32",
|
| 21 |
+
"_type": "Value"
|
| 22 |
+
},
|
| 23 |
+
"_type": "Sequence"
|
| 24 |
+
},
|
| 25 |
+
"token_type_ids": {
|
| 26 |
+
"feature": {
|
| 27 |
+
"dtype": "int8",
|
| 28 |
+
"_type": "Value"
|
| 29 |
+
},
|
| 30 |
+
"_type": "Sequence"
|
| 31 |
+
},
|
| 32 |
+
"attention_mask": {
|
| 33 |
+
"feature": {
|
| 34 |
+
"dtype": "int8",
|
| 35 |
+
"_type": "Value"
|
| 36 |
+
},
|
| 37 |
+
"_type": "Sequence"
|
| 38 |
+
},
|
| 39 |
+
"bbox": {
|
| 40 |
+
"feature": {
|
| 41 |
+
"feature": {
|
| 42 |
+
"dtype": "int64",
|
| 43 |
+
"_type": "Value"
|
| 44 |
+
},
|
| 45 |
+
"_type": "Sequence"
|
| 46 |
+
},
|
| 47 |
+
"_type": "Sequence"
|
| 48 |
+
},
|
| 49 |
+
"start_positions": {
|
| 50 |
+
"dtype": "int64",
|
| 51 |
+
"_type": "Value"
|
| 52 |
+
},
|
| 53 |
+
"end_positions": {
|
| 54 |
+
"dtype": "int64",
|
| 55 |
+
"_type": "Value"
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"homepage": "",
|
| 59 |
+
"license": ""
|
| 60 |
+
}
|
HW3_Encoded_tr/state.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00010.arrow"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"filename": "data-00001-of-00010.arrow"
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"filename": "data-00002-of-00010.arrow"
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"filename": "data-00003-of-00010.arrow"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"filename": "data-00004-of-00010.arrow"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"filename": "data-00005-of-00010.arrow"
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"filename": "data-00006-of-00010.arrow"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"filename": "data-00007-of-00010.arrow"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"filename": "data-00008-of-00010.arrow"
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"filename": "data-00009-of-00010.arrow"
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"_fingerprint": "cb3a769983d499c2",
|
| 35 |
+
"_format_columns": null,
|
| 36 |
+
"_format_kwargs": {},
|
| 37 |
+
"_format_type": null,
|
| 38 |
+
"_output_all_columns": false,
|
| 39 |
+
"_split": null
|
| 40 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv2-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv2ForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"convert_sync_batchnorm": true,
|
| 8 |
+
"coordinate_size": 128,
|
| 9 |
+
"detectron2_config_args": {
|
| 10 |
+
"MODEL.ANCHOR_GENERATOR.SIZES": [
|
| 11 |
+
[
|
| 12 |
+
32
|
| 13 |
+
],
|
| 14 |
+
[
|
| 15 |
+
64
|
| 16 |
+
],
|
| 17 |
+
[
|
| 18 |
+
128
|
| 19 |
+
],
|
| 20 |
+
[
|
| 21 |
+
256
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
512
|
| 25 |
+
]
|
| 26 |
+
],
|
| 27 |
+
"MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
|
| 28 |
+
"MODEL.FPN.IN_FEATURES": [
|
| 29 |
+
"res2",
|
| 30 |
+
"res3",
|
| 31 |
+
"res4",
|
| 32 |
+
"res5"
|
| 33 |
+
],
|
| 34 |
+
"MODEL.MASK_ON": true,
|
| 35 |
+
"MODEL.PIXEL_STD": [
|
| 36 |
+
57.375,
|
| 37 |
+
57.12,
|
| 38 |
+
58.395
|
| 39 |
+
],
|
| 40 |
+
"MODEL.POST_NMS_TOPK_TEST": 1000,
|
| 41 |
+
"MODEL.RESNETS.ASPECT_RATIOS": [
|
| 42 |
+
[
|
| 43 |
+
0.5,
|
| 44 |
+
1.0,
|
| 45 |
+
2.0
|
| 46 |
+
]
|
| 47 |
+
],
|
| 48 |
+
"MODEL.RESNETS.DEPTH": 101,
|
| 49 |
+
"MODEL.RESNETS.NUM_GROUPS": 32,
|
| 50 |
+
"MODEL.RESNETS.OUT_FEATURES": [
|
| 51 |
+
"res2",
|
| 52 |
+
"res3",
|
| 53 |
+
"res4",
|
| 54 |
+
"res5"
|
| 55 |
+
],
|
| 56 |
+
"MODEL.RESNETS.SIZES": [
|
| 57 |
+
[
|
| 58 |
+
32
|
| 59 |
+
],
|
| 60 |
+
[
|
| 61 |
+
64
|
| 62 |
+
],
|
| 63 |
+
[
|
| 64 |
+
128
|
| 65 |
+
],
|
| 66 |
+
[
|
| 67 |
+
256
|
| 68 |
+
],
|
| 69 |
+
[
|
| 70 |
+
512
|
| 71 |
+
]
|
| 72 |
+
],
|
| 73 |
+
"MODEL.RESNETS.STRIDE_IN_1X1": false,
|
| 74 |
+
"MODEL.RESNETS.WIDTH_PER_GROUP": 8,
|
| 75 |
+
"MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
|
| 76 |
+
"MODEL.ROI_BOX_HEAD.NUM_FC": 2,
|
| 77 |
+
"MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
|
| 78 |
+
"MODEL.ROI_HEADS.IN_FEATURES": [
|
| 79 |
+
"p2",
|
| 80 |
+
"p3",
|
| 81 |
+
"p4",
|
| 82 |
+
"p5"
|
| 83 |
+
],
|
| 84 |
+
"MODEL.ROI_HEADS.NAME": "StandardROIHeads",
|
| 85 |
+
"MODEL.ROI_HEADS.NUM_CLASSES": 5,
|
| 86 |
+
"MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
|
| 87 |
+
"MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
|
| 88 |
+
"MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
|
| 89 |
+
"MODEL.RPN.IN_FEATURES": [
|
| 90 |
+
"p2",
|
| 91 |
+
"p3",
|
| 92 |
+
"p4",
|
| 93 |
+
"p5",
|
| 94 |
+
"p6"
|
| 95 |
+
],
|
| 96 |
+
"MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
|
| 97 |
+
"MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
|
| 98 |
+
"MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
|
| 99 |
+
},
|
| 100 |
+
"fast_qkv": true,
|
| 101 |
+
"gradient_checkpointing": false,
|
| 102 |
+
"has_relative_attention_bias": true,
|
| 103 |
+
"has_spatial_attention_bias": true,
|
| 104 |
+
"has_visual_segment_embedding": true,
|
| 105 |
+
"hidden_act": "gelu",
|
| 106 |
+
"hidden_dropout_prob": 0.1,
|
| 107 |
+
"hidden_size": 768,
|
| 108 |
+
"image_feature_pool_shape": [
|
| 109 |
+
7,
|
| 110 |
+
7,
|
| 111 |
+
256
|
| 112 |
+
],
|
| 113 |
+
"initializer_range": 0.02,
|
| 114 |
+
"intermediate_size": 3072,
|
| 115 |
+
"layer_norm_eps": 1e-12,
|
| 116 |
+
"max_2d_position_embeddings": 1024,
|
| 117 |
+
"max_position_embeddings": 512,
|
| 118 |
+
"max_rel_2d_pos": 256,
|
| 119 |
+
"max_rel_pos": 128,
|
| 120 |
+
"model_type": "layoutlmv2",
|
| 121 |
+
"num_attention_heads": 12,
|
| 122 |
+
"num_hidden_layers": 12,
|
| 123 |
+
"output_past": true,
|
| 124 |
+
"pad_token_id": 0,
|
| 125 |
+
"rel_2d_pos_bins": 64,
|
| 126 |
+
"rel_pos_bins": 32,
|
| 127 |
+
"shape_size": 128,
|
| 128 |
+
"torch_dtype": "float32",
|
| 129 |
+
"transformers_version": "4.35.0",
|
| 130 |
+
"type_vocab_size": 2,
|
| 131 |
+
"vocab_size": 30522
|
| 132 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74fbba9ad6309d40399d40a303a1f30356f70d0e63b88b0115392547273c1c35
|
| 3 |
+
size 802053752
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_ocr": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "LayoutLMv2FeatureExtractor",
|
| 5 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
| 6 |
+
"ocr_lang": null,
|
| 7 |
+
"processor_class": "LayoutLMv2Processor",
|
| 8 |
+
"resample": 2,
|
| 9 |
+
"size": {
|
| 10 |
+
"height": 224,
|
| 11 |
+
"width": 224
|
| 12 |
+
},
|
| 13 |
+
"tesseract_config": ""
|
| 14 |
+
}
|
runs/Nov08_17-11-57_c3571ebff4b6/events.out.tfevents.1699463599.c3571ebff4b6.131.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c428a425235dc67e9a89ebae2fb1b507f308e614edfa31e8b2bb50b74998fd9
|
| 3 |
+
size 6269
|
runs/Nov08_17-15-33_c3571ebff4b6/events.out.tfevents.1699463762.c3571ebff4b6.131.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38d1ec12c42f6dda74fe5da396944e9f3073b9749f37ce26711614d98e918994
|
| 3 |
+
size 88
|
runs/Nov08_17-20-47_c3571ebff4b6/events.out.tfevents.1699464083.c3571ebff4b6.30091.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b963c61d7cd631ee9cffda63ff2d72528c245286b9c2abdf42dbfa7c46ca4ce
|
| 3 |
+
size 6683
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"additional_special_tokens": [],
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "[CLS]",
|
| 47 |
+
"cls_token_box": [
|
| 48 |
+
0,
|
| 49 |
+
0,
|
| 50 |
+
0,
|
| 51 |
+
0
|
| 52 |
+
],
|
| 53 |
+
"do_basic_tokenize": true,
|
| 54 |
+
"do_lower_case": true,
|
| 55 |
+
"mask_token": "[MASK]",
|
| 56 |
+
"model_max_length": 512,
|
| 57 |
+
"never_split": null,
|
| 58 |
+
"only_label_first_subword": true,
|
| 59 |
+
"pad_token": "[PAD]",
|
| 60 |
+
"pad_token_box": [
|
| 61 |
+
0,
|
| 62 |
+
0,
|
| 63 |
+
0,
|
| 64 |
+
0
|
| 65 |
+
],
|
| 66 |
+
"pad_token_label": -100,
|
| 67 |
+
"processor_class": "LayoutLMv2Processor",
|
| 68 |
+
"sep_token": "[SEP]",
|
| 69 |
+
"sep_token_box": [
|
| 70 |
+
1000,
|
| 71 |
+
1000,
|
| 72 |
+
1000,
|
| 73 |
+
1000
|
| 74 |
+
],
|
| 75 |
+
"strip_accents": null,
|
| 76 |
+
"tokenize_chinese_chars": true,
|
| 77 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
| 78 |
+
"unk_token": "[UNK]"
|
| 79 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4d5be9136ffa846888699ee1fdeb2386b5ea792d4184943ed799d4a737afc42
|
| 3 |
+
size 4600
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|