Upload 10 files
Browse files- config.json +105 -0
- eval_results.txt +4 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- model_args.json +1 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "B-CARDINAL",
|
15 |
+
"1": "I-CARDINAL",
|
16 |
+
"2": "B-DATE",
|
17 |
+
"3": "I-DATE",
|
18 |
+
"4": "B-EVENT",
|
19 |
+
"5": "I-EVENT",
|
20 |
+
"6": "B-FAC",
|
21 |
+
"7": "I-FAC",
|
22 |
+
"8": "B-GPE",
|
23 |
+
"9": "I-GPE",
|
24 |
+
"10": "B-LANGUAGE",
|
25 |
+
"11": "I-LANGUAGE",
|
26 |
+
"12": "B-LAW",
|
27 |
+
"13": "I-LAW",
|
28 |
+
"14": "B-LOC",
|
29 |
+
"15": "I-LOC",
|
30 |
+
"16": "B-MONEY",
|
31 |
+
"17": "I-MONEY",
|
32 |
+
"18": "B-NORP",
|
33 |
+
"19": "I-NORP",
|
34 |
+
"20": "B-ORDINAL",
|
35 |
+
"21": "I-ORDINAL",
|
36 |
+
"22": "B-ORG",
|
37 |
+
"23": "I-ORG",
|
38 |
+
"24": "B-PERCENT",
|
39 |
+
"25": "I-PERCENT",
|
40 |
+
"26": "B-PERSON",
|
41 |
+
"27": "I-PERSON",
|
42 |
+
"28": "B-PRODUCT",
|
43 |
+
"29": "I-PRODUCT",
|
44 |
+
"30": "B-QUANTITY",
|
45 |
+
"31": "I-QUANTITY",
|
46 |
+
"32": "B-TIME",
|
47 |
+
"33": "I-TIME",
|
48 |
+
"34": "B-WORK_OF_ART",
|
49 |
+
"35": "I-WORK_OF_ART",
|
50 |
+
"36": "O"
|
51 |
+
},
|
52 |
+
"initializer_range": 0.02,
|
53 |
+
"intermediate_size": 3072,
|
54 |
+
"label2id": {
|
55 |
+
"B-CARDINAL": 0,
|
56 |
+
"B-DATE": 2,
|
57 |
+
"B-EVENT": 4,
|
58 |
+
"B-FAC": 6,
|
59 |
+
"B-GPE": 8,
|
60 |
+
"B-LANGUAGE": 10,
|
61 |
+
"B-LAW": 12,
|
62 |
+
"B-LOC": 14,
|
63 |
+
"B-MONEY": 16,
|
64 |
+
"B-NORP": 18,
|
65 |
+
"B-ORDINAL": 20,
|
66 |
+
"B-ORG": 22,
|
67 |
+
"B-PERCENT": 24,
|
68 |
+
"B-PERSON": 26,
|
69 |
+
"B-PRODUCT": 28,
|
70 |
+
"B-QUANTITY": 30,
|
71 |
+
"B-TIME": 32,
|
72 |
+
"B-WORK_OF_ART": 34,
|
73 |
+
"I-CARDINAL": 1,
|
74 |
+
"I-DATE": 3,
|
75 |
+
"I-EVENT": 5,
|
76 |
+
"I-FAC": 7,
|
77 |
+
"I-GPE": 9,
|
78 |
+
"I-LANGUAGE": 11,
|
79 |
+
"I-LAW": 13,
|
80 |
+
"I-LOC": 15,
|
81 |
+
"I-MONEY": 17,
|
82 |
+
"I-NORP": 19,
|
83 |
+
"I-ORDINAL": 21,
|
84 |
+
"I-ORG": 23,
|
85 |
+
"I-PERCENT": 25,
|
86 |
+
"I-PERSON": 27,
|
87 |
+
"I-PRODUCT": 29,
|
88 |
+
"I-QUANTITY": 31,
|
89 |
+
"I-TIME": 33,
|
90 |
+
"I-WORK_OF_ART": 35,
|
91 |
+
"O": 36
|
92 |
+
},
|
93 |
+
"layer_norm_eps": 1e-05,
|
94 |
+
"max_position_embeddings": 514,
|
95 |
+
"model_type": "roberta",
|
96 |
+
"num_attention_heads": 12,
|
97 |
+
"num_hidden_layers": 12,
|
98 |
+
"pad_token_id": 1,
|
99 |
+
"position_embedding_type": "absolute",
|
100 |
+
"torch_dtype": "float32",
|
101 |
+
"transformers_version": "4.38.2",
|
102 |
+
"type_vocab_size": 1,
|
103 |
+
"use_cache": true,
|
104 |
+
"vocab_size": 50265
|
105 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.08307243298469602
|
2 |
+
f1_score = 0.8707822598618231
|
3 |
+
precision = 0.8569924548166346
|
4 |
+
recall = 0.8850231041043762
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:184b948ccd52b2fd4f1d9c687bbc183e009684c785ee5df73443a0fe7c5660a1
|
3 |
+
size 496357908
|
model_args.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0.01, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 2, "encoding": null, "eval_batch_size": 128, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 200, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 4, "learning_rate": 0.0001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "roberta-base", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 5, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": null, "tokenizer_type": null, "train_batch_size": 128, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {"name": "RoBERTa"}, "wandb_project": "ner-transformer-finetuning", "warmup_ratio": 0.06, "warmup_steps": 45, "weight_decay": 0.0, "model_class": "NERModel", "classification_report": true, "labels_list": ["B-CARDINAL", "I-CARDINAL", "B-DATE", "I-DATE", "B-EVENT", "I-EVENT", "B-FAC", "I-FAC", "B-GPE", "I-GPE", "B-LANGUAGE", "I-LANGUAGE", "B-LAW", "I-LAW", "B-LOC", "I-LOC", "B-MONEY", "I-MONEY", "B-NORP", "I-NORP", "B-ORDINAL", "I-ORDINAL", "B-ORG", "I-ORG", "B-PERCENT", "I-PERCENT", "B-PERSON", "I-PERSON", "B-PRODUCT", "I-PRODUCT", "B-QUANTITY", "I-QUANTITY", "B-TIME", "I-TIME", "B-WORK_OF_ART", "I-WORK_OF_ART", "O"], "lazy_loading": false, "lazy_loading_start_line": 0, "onnx": false, "special_tokens_list": []}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"do_lower_case": false,
|
49 |
+
"eos_token": "</s>",
|
50 |
+
"errors": "replace",
|
51 |
+
"mask_token": "<mask>",
|
52 |
+
"model_max_length": 512,
|
53 |
+
"pad_token": "<pad>",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cccd66a03d0113f1af9fc31c2a46f999d2176c02ba1789086132e7165b7e3ada
|
3 |
+
size 4024
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|