nadahlberg commited on
Commit
ee66605
1 Parent(s): 99f261c

Update from nathandahlberg

Browse files
config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForMultiLabelSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Affidavit",
15
+ "1": "Answer",
16
+ "2": "Application",
17
+ "3": "Arrest",
18
+ "4": "Attorney Appearance",
19
+ "5": "Case Management Order",
20
+ "6": "Certificate",
21
+ "7": "Clerk Entry",
22
+ "8": "Complaint",
23
+ "9": "Consent Judgment",
24
+ "10": "Cover Sheet",
25
+ "11": "Declaration",
26
+ "12": "Dismiss with Prejudice",
27
+ "13": "Dismiss without Prejudice",
28
+ "14": "Entry of Dismissal",
29
+ "15": "Filed in Error",
30
+ "16": "Indicator of Case Closed / Terminated",
31
+ "17": "Indictment",
32
+ "18": "Judgment",
33
+ "19": "Mandate",
34
+ "20": "Mediation",
35
+ "21": "Memorandum / Brief",
36
+ "22": "Minute Entry",
37
+ "23": "Mod Amended",
38
+ "24": "Mod Consent",
39
+ "25": "Mod Joint",
40
+ "26": "Mod Sealed",
41
+ "27": "Mod Voluntary",
42
+ "28": "Motion",
43
+ "29": "Motion for Default Judgment",
44
+ "30": "Motion for Leave",
45
+ "31": "Motion for Summary Judgment",
46
+ "32": "Motion for Time Extension",
47
+ "33": "Motion in Limine",
48
+ "34": "Motion to Compel",
49
+ "35": "Motion to Continue",
50
+ "36": "Motion to Detain",
51
+ "37": "Motion to Dismiss",
52
+ "38": "Motion to Stay",
53
+ "39": "Motion to Withdraw",
54
+ "40": "Notice",
55
+ "41": "Notice of Appearance",
56
+ "42": "Notice of Dismissal",
57
+ "43": "Notice of Hearing",
58
+ "44": "Notice of Motion",
59
+ "45": "Notice of Settlement",
60
+ "46": "Opinion",
61
+ "47": "Order",
62
+ "48": "Order Deny",
63
+ "49": "Order Grant",
64
+ "50": "Order Partial",
65
+ "51": "Petition",
66
+ "52": "Protective Order",
67
+ "53": "Report",
68
+ "54": "Report and Recommendation",
69
+ "55": "Response / Reply",
70
+ "56": "Return of Service",
71
+ "57": "Scheduling Order",
72
+ "58": "Stipulation",
73
+ "59": "Stipulation of Dismissal",
74
+ "60": "Stipulation of Settlement",
75
+ "61": "Submission",
76
+ "62": "Summons",
77
+ "63": "Transcript",
78
+ "64": "Trial",
79
+ "65": "Voluntary Dismissal",
80
+ "66": "Waiver"
81
+ },
82
+ "initializer_range": 0.02,
83
+ "intermediate_size": 3072,
84
+ "label2id": {
85
+ "Affidavit": 0,
86
+ "Answer": 1,
87
+ "Application": 2,
88
+ "Arrest": 3,
89
+ "Attorney Appearance": 4,
90
+ "Case Management Order": 5,
91
+ "Certificate": 6,
92
+ "Clerk Entry": 7,
93
+ "Complaint": 8,
94
+ "Consent Judgment": 9,
95
+ "Cover Sheet": 10,
96
+ "Declaration": 11,
97
+ "Dismiss with Prejudice": 12,
98
+ "Dismiss without Prejudice": 13,
99
+ "Entry of Dismissal": 14,
100
+ "Filed in Error": 15,
101
+ "Indicator of Case Closed / Terminated": 16,
102
+ "Indictment": 17,
103
+ "Judgment": 18,
104
+ "Mandate": 19,
105
+ "Mediation": 20,
106
+ "Memorandum / Brief": 21,
107
+ "Minute Entry": 22,
108
+ "Mod Amended": 23,
109
+ "Mod Consent": 24,
110
+ "Mod Joint": 25,
111
+ "Mod Sealed": 26,
112
+ "Mod Voluntary": 27,
113
+ "Motion": 28,
114
+ "Motion for Default Judgment": 29,
115
+ "Motion for Leave": 30,
116
+ "Motion for Summary Judgment": 31,
117
+ "Motion for Time Extension": 32,
118
+ "Motion in Limine": 33,
119
+ "Motion to Compel": 34,
120
+ "Motion to Continue": 35,
121
+ "Motion to Detain": 36,
122
+ "Motion to Dismiss": 37,
123
+ "Motion to Stay": 38,
124
+ "Motion to Withdraw": 39,
125
+ "Notice": 40,
126
+ "Notice of Appearance": 41,
127
+ "Notice of Dismissal": 42,
128
+ "Notice of Hearing": 43,
129
+ "Notice of Motion": 44,
130
+ "Notice of Settlement": 45,
131
+ "Opinion": 46,
132
+ "Order": 47,
133
+ "Order Deny": 48,
134
+ "Order Grant": 49,
135
+ "Order Partial": 50,
136
+ "Petition": 51,
137
+ "Protective Order": 52,
138
+ "Report": 53,
139
+ "Report and Recommendation": 54,
140
+ "Response / Reply": 55,
141
+ "Return of Service": 56,
142
+ "Scheduling Order": 57,
143
+ "Stipulation": 58,
144
+ "Stipulation of Dismissal": 59,
145
+ "Stipulation of Settlement": 60,
146
+ "Submission": 61,
147
+ "Summons": 62,
148
+ "Transcript": 63,
149
+ "Trial": 64,
150
+ "Voluntary Dismissal": 65,
151
+ "Waiver": 66
152
+ },
153
+ "layer_norm_eps": 1e-05,
154
+ "max_position_embeddings": 514,
155
+ "model_type": "roberta",
156
+ "num_attention_heads": 12,
157
+ "num_hidden_layers": 6,
158
+ "pad_token_id": 1,
159
+ "position_embedding_type": "absolute",
160
+ "transformers_version": "4.3.2",
161
+ "type_vocab_size": 1,
162
+ "use_cache": true,
163
+ "vocab_size": 50265
164
+ }
eval_results.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ LRAP = 0.9944991902182245
2
+ eval_loss = 0.004638983611384319
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model_args.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"adam_epsilon": 1e-08, "best_model_dir": "/home/nathan/Desktop/models/final_model", "cache_dir": "data/temp/cache/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 1, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "adafactor_eps": [1e-30, 0.001], "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_beta1": null, "adafactor_scale_parameter": true, "adafactor_relative_step": true, "adafactor_warmup_init": true, "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "/home/nathan/Desktop/models/triplet/0_Transformer", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 100, "optimizer": "AdamW", "output_dir": "/home/nathan/Desktop/models/finetuned", "overwrite_output_dir": true, "process_count": 30, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 5000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": "data/temp/logs/", "thread_count": null, "tokenizer_type": null, "tokenizer_name": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": false, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 1686, "weight_decay": 0.0, "model_class": "MultiLabelClassificationModel", "sliding_window": false, "stride": 0.8, "threshold": 0.5, "tie_value": 1, "labels_list": [], "labels_map": {}, "lazy_loading": false, "special_tokens_list": []}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25a4d1b0d82e24a9bf4b81debf5aec73ae4d31e9ce84535886aa4e63b329602
3
+ size 331092155
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1387c5d406f827546435a170828ac7006bec8a1f1f6857de18f87fbeb4f36836
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "/home/nathan/Desktop/models/triplet/0_Transformer", "special_tokens_map_file": "checkpoints/checkpoint-1265929-epoch-7/special_tokens_map.json", "do_lower_case": false, "tokenizer_file": null}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4aad121c9a47180006c9eaa3789c1c4835a63e36d80e49f4c01b2134cf9951
3
+ size 3055
vocab.json ADDED
The diff for this file is too large to render. See raw diff