Training in progress, step 500
Browse files- config.json +30 -30
- model.safetensors +1 -1
- preprocessor_config.json +2 -20
- runs/Mar14_05-51-55_1bc8b9c17103/events.out.tfevents.1710395517.1bc8b9c17103.709.0 +3 -0
- special_tokens_map.json +35 -5
- tokenizer.json +10 -1
- tokenizer_config.json +24 -1
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -8,42 +8,42 @@
|
|
| 8 |
"hidden_dropout_prob": 0.1,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
-
"0": "
|
| 12 |
-
"1": "
|
| 13 |
-
"2": "
|
| 14 |
-
"3": "
|
| 15 |
-
"4": "
|
| 16 |
"5": "attorneys for co-counsel",
|
| 17 |
-
"6": "
|
| 18 |
-
"7": "
|
| 19 |
-
"8": "
|
| 20 |
-
"9": "
|
| 21 |
-
"10": "
|
| 22 |
-
"11": "
|
| 23 |
-
"12": "
|
| 24 |
-
"13": "
|
| 25 |
-
"14": "
|
| 26 |
-
"15": "
|
| 27 |
},
|
| 28 |
"initializer_range": 0.02,
|
| 29 |
"intermediate_size": 3072,
|
| 30 |
"label2id": {
|
| 31 |
-
"SBN":
|
| 32 |
-
"address":
|
| 33 |
-
"attorney for defendant/cross-complainant/cross-defendant":
|
| 34 |
-
"attorney_name":
|
| 35 |
"attorneys for co-counsel": 5,
|
| 36 |
-
"attorneys for co-defendant":
|
| 37 |
-
"attorneys for defendant":
|
| 38 |
-
"attorneys for plaintiff":
|
| 39 |
-
"co-counsel for plaintiff":
|
| 40 |
-
"counsel for plaintiff":
|
| 41 |
-
"email":
|
| 42 |
-
"fax":
|
| 43 |
-
"lawfirm":
|
| 44 |
-
"other":
|
| 45 |
-
"parties":
|
| 46 |
-
"telephone":
|
| 47 |
},
|
| 48 |
"layer_norm_eps": 1e-12,
|
| 49 |
"max_2d_position_embeddings": 1024,
|
|
|
|
| 8 |
"hidden_dropout_prob": 0.1,
|
| 9 |
"hidden_size": 768,
|
| 10 |
"id2label": {
|
| 11 |
+
"0": "attorneys for plaintiff",
|
| 12 |
+
"1": "attorney for defendant/cross-complainant/cross-defendant",
|
| 13 |
+
"2": "address",
|
| 14 |
+
"3": "lawfirm",
|
| 15 |
+
"4": "other",
|
| 16 |
"5": "attorneys for co-counsel",
|
| 17 |
+
"6": "email",
|
| 18 |
+
"7": "co-counsel for plaintiff",
|
| 19 |
+
"8": "attorney_name",
|
| 20 |
+
"9": "attorneys for defendant",
|
| 21 |
+
"10": "parties",
|
| 22 |
+
"11": "SBN",
|
| 23 |
+
"12": "attorneys for co-defendant",
|
| 24 |
+
"13": "fax",
|
| 25 |
+
"14": "telephone",
|
| 26 |
+
"15": "counsel for plaintiff"
|
| 27 |
},
|
| 28 |
"initializer_range": 0.02,
|
| 29 |
"intermediate_size": 3072,
|
| 30 |
"label2id": {
|
| 31 |
+
"SBN": 11,
|
| 32 |
+
"address": 2,
|
| 33 |
+
"attorney for defendant/cross-complainant/cross-defendant": 1,
|
| 34 |
+
"attorney_name": 8,
|
| 35 |
"attorneys for co-counsel": 5,
|
| 36 |
+
"attorneys for co-defendant": 12,
|
| 37 |
+
"attorneys for defendant": 9,
|
| 38 |
+
"attorneys for plaintiff": 0,
|
| 39 |
+
"co-counsel for plaintiff": 7,
|
| 40 |
+
"counsel for plaintiff": 15,
|
| 41 |
+
"email": 6,
|
| 42 |
+
"fax": 13,
|
| 43 |
+
"lawfirm": 3,
|
| 44 |
+
"other": 4,
|
| 45 |
+
"parties": 10,
|
| 46 |
+
"telephone": 14
|
| 47 |
},
|
| 48 |
"layer_norm_eps": 1e-12,
|
| 49 |
"max_2d_position_embeddings": 1024,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 450585896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48408ca2aaa52846d41ea09c9b4189b1ddcae6012f773e03fac23eea82ec0402
|
| 3 |
size 450585896
|
preprocessor_config.json
CHANGED
|
@@ -4,11 +4,6 @@
|
|
| 4 |
"do_resize",
|
| 5 |
"size",
|
| 6 |
"resample",
|
| 7 |
-
"do_rescale",
|
| 8 |
-
"rescale_factor",
|
| 9 |
-
"do_normalize",
|
| 10 |
-
"image_mean",
|
| 11 |
-
"image_std",
|
| 12 |
"apply_ocr",
|
| 13 |
"ocr_lang",
|
| 14 |
"tesseract_config",
|
|
@@ -17,24 +12,11 @@
|
|
| 17 |
"input_data_format"
|
| 18 |
],
|
| 19 |
"apply_ocr": false,
|
| 20 |
-
"do_normalize": true,
|
| 21 |
-
"do_rescale": true,
|
| 22 |
"do_resize": true,
|
| 23 |
-
"
|
| 24 |
-
0.5,
|
| 25 |
-
0.5,
|
| 26 |
-
0.5
|
| 27 |
-
],
|
| 28 |
-
"image_processor_type": "LayoutLMv3ImageProcessor",
|
| 29 |
-
"image_std": [
|
| 30 |
-
0.5,
|
| 31 |
-
0.5,
|
| 32 |
-
0.5
|
| 33 |
-
],
|
| 34 |
"ocr_lang": null,
|
| 35 |
-
"processor_class": "
|
| 36 |
"resample": 2,
|
| 37 |
-
"rescale_factor": 0.00392156862745098,
|
| 38 |
"size": {
|
| 39 |
"height": 224,
|
| 40 |
"width": 224
|
|
|
|
| 4 |
"do_resize",
|
| 5 |
"size",
|
| 6 |
"resample",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"apply_ocr",
|
| 8 |
"ocr_lang",
|
| 9 |
"tesseract_config",
|
|
|
|
| 12 |
"input_data_format"
|
| 13 |
],
|
| 14 |
"apply_ocr": false,
|
|
|
|
|
|
|
| 15 |
"do_resize": true,
|
| 16 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"ocr_lang": null,
|
| 18 |
+
"processor_class": "LayoutLMv2Processor",
|
| 19 |
"resample": 2,
|
|
|
|
| 20 |
"size": {
|
| 21 |
"height": 224,
|
| 22 |
"width": 224
|
runs/Mar14_05-51-55_1bc8b9c17103/events.out.tfevents.1710395517.1bc8b9c17103.709.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb1f065ae61c2fa028600cbab058d43079ca1dceb8613c528da753af99a6a87c
|
| 3 |
+
size 10702
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,37 @@
|
|
| 1 |
{
|
| 2 |
-
"cls_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 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
CHANGED
|
@@ -6,7 +6,16 @@
|
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
| 12 |
"id": 0,
|
|
|
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -41,17 +41,40 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
|
|
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
"never_split": null,
|
|
|
|
| 51 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"sep_token": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
-
"tokenizer_class": "
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"additional_special_tokens": [],
|
| 45 |
+
"apply_ocr": false,
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "[CLS]",
|
| 48 |
+
"cls_token_box": [
|
| 49 |
+
0,
|
| 50 |
+
0,
|
| 51 |
+
0,
|
| 52 |
+
0
|
| 53 |
+
],
|
| 54 |
"do_basic_tokenize": true,
|
| 55 |
"do_lower_case": true,
|
| 56 |
"mask_token": "[MASK]",
|
| 57 |
"model_max_length": 512,
|
| 58 |
"never_split": null,
|
| 59 |
+
"only_label_first_subword": true,
|
| 60 |
"pad_token": "[PAD]",
|
| 61 |
+
"pad_token_box": [
|
| 62 |
+
0,
|
| 63 |
+
0,
|
| 64 |
+
0,
|
| 65 |
+
0
|
| 66 |
+
],
|
| 67 |
+
"pad_token_label": -100,
|
| 68 |
+
"processor_class": "LayoutLMv2Processor",
|
| 69 |
"sep_token": "[SEP]",
|
| 70 |
+
"sep_token_box": [
|
| 71 |
+
1000,
|
| 72 |
+
1000,
|
| 73 |
+
1000,
|
| 74 |
+
1000
|
| 75 |
+
],
|
| 76 |
"strip_accents": null,
|
| 77 |
"tokenize_chinese_chars": true,
|
| 78 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
| 79 |
"unk_token": "[UNK]"
|
| 80 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7066bcf11f4f969e1ee2cadda78e00d46157ec009c614bdcb604a54b96c6fd8d
|
| 3 |
size 4856
|