End of training
Browse files- README.md +68 -0
- config.json +150 -0
- model.safetensors +3 -0
- runs/Mar28_14-38-14_arimo-ThinkBook-14-G5-IRH/events.out.tfevents.1711633096.arimo-ThinkBook-14-G5-IRH.35878.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: bert-base-uncased-finetuned-advanced-srl_arg
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# bert-base-uncased-finetuned-advanced-srl_arg
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0914
|
24 |
+
- Precision: 0.8664
|
25 |
+
- Recall: 0.8673
|
26 |
+
- F1: 0.8669
|
27 |
+
- Accuracy: 0.9812
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 3
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0457 | 1.0 | 2655 | 0.0849 | 0.8447 | 0.8644 | 0.8544 | 0.9792 |
|
59 |
+
| 0.0322 | 2.0 | 5310 | 0.0883 | 0.8586 | 0.8679 | 0.8632 | 0.9806 |
|
60 |
+
| 0.0234 | 3.0 | 7965 | 0.0914 | 0.8664 | 0.8673 | 0.8669 | 0.9812 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.37.0
|
66 |
+
- Pytorch 2.0.1+cu117
|
67 |
+
- Datasets 2.16.1
|
68 |
+
- Tokenizers 0.15.1
|
config.json
ADDED
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ARG0",
|
14 |
+
"1": "ARG1",
|
15 |
+
"2": "ARG1-DSP",
|
16 |
+
"3": "ARG2",
|
17 |
+
"4": "ARG3",
|
18 |
+
"5": "ARG4",
|
19 |
+
"6": "ARG5",
|
20 |
+
"7": "ARGA",
|
21 |
+
"8": "ARGM-ADJ",
|
22 |
+
"9": "ARGM-ADV",
|
23 |
+
"10": "ARGM-CAU",
|
24 |
+
"11": "ARGM-COM",
|
25 |
+
"12": "ARGM-CXN",
|
26 |
+
"13": "ARGM-DIR",
|
27 |
+
"14": "ARGM-DIS",
|
28 |
+
"15": "ARGM-EXT",
|
29 |
+
"16": "ARGM-GOL",
|
30 |
+
"17": "ARGM-LOC",
|
31 |
+
"18": "ARGM-LVB",
|
32 |
+
"19": "ARGM-MNR",
|
33 |
+
"20": "ARGM-MOD",
|
34 |
+
"21": "ARGM-NEG",
|
35 |
+
"22": "ARGM-PRD",
|
36 |
+
"23": "ARGM-PRP",
|
37 |
+
"24": "ARGM-PRR",
|
38 |
+
"25": "ARGM-REC",
|
39 |
+
"26": "ARGM-TMP",
|
40 |
+
"27": "C-ARG0",
|
41 |
+
"28": "C-ARG1",
|
42 |
+
"29": "C-ARG1-DSP",
|
43 |
+
"30": "C-ARG2",
|
44 |
+
"31": "C-ARG3",
|
45 |
+
"32": "C-ARG4",
|
46 |
+
"33": "C-ARGM-ADV",
|
47 |
+
"34": "C-ARGM-COM",
|
48 |
+
"35": "C-ARGM-CXN",
|
49 |
+
"36": "C-ARGM-DIR",
|
50 |
+
"37": "C-ARGM-EXT",
|
51 |
+
"38": "C-ARGM-GOL",
|
52 |
+
"39": "C-ARGM-LOC",
|
53 |
+
"40": "C-ARGM-MNR",
|
54 |
+
"41": "C-ARGM-PRP",
|
55 |
+
"42": "C-ARGM-PRR",
|
56 |
+
"43": "C-ARGM-TMP",
|
57 |
+
"44": "C-V",
|
58 |
+
"45": "R-ARG0",
|
59 |
+
"46": "R-ARG1",
|
60 |
+
"47": "R-ARG2",
|
61 |
+
"48": "R-ARG3",
|
62 |
+
"49": "R-ARG4",
|
63 |
+
"50": "R-ARGM-ADJ",
|
64 |
+
"51": "R-ARGM-ADV",
|
65 |
+
"52": "R-ARGM-CAU",
|
66 |
+
"53": "R-ARGM-COM",
|
67 |
+
"54": "R-ARGM-DIR",
|
68 |
+
"55": "R-ARGM-GOL",
|
69 |
+
"56": "R-ARGM-LOC",
|
70 |
+
"57": "R-ARGM-MNR",
|
71 |
+
"58": "R-ARGM-TMP",
|
72 |
+
"59": "_"
|
73 |
+
},
|
74 |
+
"initializer_range": 0.02,
|
75 |
+
"intermediate_size": 3072,
|
76 |
+
"label2id": {
|
77 |
+
"ARG0": 0,
|
78 |
+
"ARG1": 1,
|
79 |
+
"ARG1-DSP": 2,
|
80 |
+
"ARG2": 3,
|
81 |
+
"ARG3": 4,
|
82 |
+
"ARG4": 5,
|
83 |
+
"ARG5": 6,
|
84 |
+
"ARGA": 7,
|
85 |
+
"ARGM-ADJ": 8,
|
86 |
+
"ARGM-ADV": 9,
|
87 |
+
"ARGM-CAU": 10,
|
88 |
+
"ARGM-COM": 11,
|
89 |
+
"ARGM-CXN": 12,
|
90 |
+
"ARGM-DIR": 13,
|
91 |
+
"ARGM-DIS": 14,
|
92 |
+
"ARGM-EXT": 15,
|
93 |
+
"ARGM-GOL": 16,
|
94 |
+
"ARGM-LOC": 17,
|
95 |
+
"ARGM-LVB": 18,
|
96 |
+
"ARGM-MNR": 19,
|
97 |
+
"ARGM-MOD": 20,
|
98 |
+
"ARGM-NEG": 21,
|
99 |
+
"ARGM-PRD": 22,
|
100 |
+
"ARGM-PRP": 23,
|
101 |
+
"ARGM-PRR": 24,
|
102 |
+
"ARGM-REC": 25,
|
103 |
+
"ARGM-TMP": 26,
|
104 |
+
"C-ARG0": 27,
|
105 |
+
"C-ARG1": 28,
|
106 |
+
"C-ARG1-DSP": 29,
|
107 |
+
"C-ARG2": 30,
|
108 |
+
"C-ARG3": 31,
|
109 |
+
"C-ARG4": 32,
|
110 |
+
"C-ARGM-ADV": 33,
|
111 |
+
"C-ARGM-COM": 34,
|
112 |
+
"C-ARGM-CXN": 35,
|
113 |
+
"C-ARGM-DIR": 36,
|
114 |
+
"C-ARGM-EXT": 37,
|
115 |
+
"C-ARGM-GOL": 38,
|
116 |
+
"C-ARGM-LOC": 39,
|
117 |
+
"C-ARGM-MNR": 40,
|
118 |
+
"C-ARGM-PRP": 41,
|
119 |
+
"C-ARGM-PRR": 42,
|
120 |
+
"C-ARGM-TMP": 43,
|
121 |
+
"C-V": 44,
|
122 |
+
"R-ARG0": 45,
|
123 |
+
"R-ARG1": 46,
|
124 |
+
"R-ARG2": 47,
|
125 |
+
"R-ARG3": 48,
|
126 |
+
"R-ARG4": 49,
|
127 |
+
"R-ARGM-ADJ": 50,
|
128 |
+
"R-ARGM-ADV": 51,
|
129 |
+
"R-ARGM-CAU": 52,
|
130 |
+
"R-ARGM-COM": 53,
|
131 |
+
"R-ARGM-DIR": 54,
|
132 |
+
"R-ARGM-GOL": 55,
|
133 |
+
"R-ARGM-LOC": 56,
|
134 |
+
"R-ARGM-MNR": 57,
|
135 |
+
"R-ARGM-TMP": 58,
|
136 |
+
"_": 59
|
137 |
+
},
|
138 |
+
"layer_norm_eps": 1e-12,
|
139 |
+
"max_position_embeddings": 512,
|
140 |
+
"model_type": "bert",
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_hidden_layers": 12,
|
143 |
+
"pad_token_id": 0,
|
144 |
+
"position_embedding_type": "absolute",
|
145 |
+
"torch_dtype": "float32",
|
146 |
+
"transformers_version": "4.37.0",
|
147 |
+
"type_vocab_size": 2,
|
148 |
+
"use_cache": true,
|
149 |
+
"vocab_size": 30522
|
150 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c10ef017207aca43e0fe461a8e59c747ef6de25a71c5d7488374e04541673959
|
3 |
+
size 435774496
|
runs/Mar28_14-38-14_arimo-ThinkBook-14-G5-IRH/events.out.tfevents.1711633096.arimo-ThinkBook-14-G5-IRH.35878.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4074ccfb0b4f4d5b72900301f17291282ca929c209a4559d5d9a528ea086087
|
3 |
+
size 11067
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:387b7a48c50a8d0ae28469f492bb538d73e39ba4df76df873f43ae56ee9e9dd9
|
3 |
+
size 4347
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|