Training in progress, epoch 1
Browse files- README.md +50 -0
- config.json +74 -0
- model.safetensors +3 -0
- runs/May22_16-45-48_indolem-petl-vm/events.out.tfevents.1716396355.indolem-petl-vm.141728.0 +3 -0
- runs/May22_16-49-19_indolem-petl-vm/events.out.tfevents.1716396564.indolem-petl-vm.142486.0 +3 -0
- runs/May22_16-54-23_indolem-petl-vm/events.out.tfevents.1716396868.indolem-petl-vm.143236.0 +3 -0
- runs/May22_16-59-17_indolem-petl-vm/events.out.tfevents.1716397162.indolem-petl-vm.145268.0 +3 -0
- runs/May22_17-02-24_indolem-petl-vm/events.out.tfevents.1716397350.indolem-petl-vm.146763.0 +3 -0
- runs/May22_17-08-23_indolem-petl-vm/events.out.tfevents.1716397711.indolem-petl-vm.159747.0 +3 -0
- runs/May22_17-13-46_indolem-petl-vm/events.out.tfevents.1716398033.indolem-petl-vm.162315.0 +3 -0
- runs/May22_17-16-41_indolem-petl-vm/events.out.tfevents.1716398207.indolem-petl-vm.163762.0 +3 -0
- runs/May22_17-17-22_indolem-petl-vm/events.out.tfevents.1716398248.indolem-petl-vm.164229.0 +3 -0
- runs/May22_17-19-56_indolem-petl-vm/events.out.tfevents.1716398402.indolem-petl-vm.165023.0 +3 -0
- runs/May22_17-21-14_indolem-petl-vm/events.out.tfevents.1716398479.indolem-petl-vm.165490.0 +3 -0
- runs/May22_17-29-13_indolem-petl-vm/events.out.tfevents.1716398963.indolem-petl-vm.167700.0 +3 -0
- runs/May22_17-31-21_indolem-petl-vm/events.out.tfevents.1716399087.indolem-petl-vm.168394.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- id
|
4 |
+
license: mit
|
5 |
+
base_model: indolem/indobert-base-uncased
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: nerugm-base-0
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# nerugm-base-0
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 4
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 20.0
|
44 |
+
|
45 |
+
### Framework versions
|
46 |
+
|
47 |
+
- Transformers 4.39.3
|
48 |
+
- Pytorch 2.3.0+cu121
|
49 |
+
- Datasets 2.19.1
|
50 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "indolem/indobert-base-uncased",
|
3 |
+
"adapters": {
|
4 |
+
"adapters": {},
|
5 |
+
"config_map": {},
|
6 |
+
"fusion_config_map": {},
|
7 |
+
"fusions": {}
|
8 |
+
},
|
9 |
+
"architectures": [
|
10 |
+
"BertAdapterModel"
|
11 |
+
],
|
12 |
+
"attention_probs_dropout_prob": 0.1,
|
13 |
+
"bos_token_id": 0,
|
14 |
+
"classifier_dropout": null,
|
15 |
+
"custom_heads": {},
|
16 |
+
"eos_token_ids": 0,
|
17 |
+
"hidden_act": "gelu",
|
18 |
+
"hidden_dropout_prob": 0.1,
|
19 |
+
"hidden_size": 768,
|
20 |
+
"id2label": {
|
21 |
+
"0": "B-LOCATION",
|
22 |
+
"1": "B-ORGANIZATION",
|
23 |
+
"2": "B-PERSON",
|
24 |
+
"3": "B-QUANTITY",
|
25 |
+
"4": "B-TIME",
|
26 |
+
"5": "I-LOCATION",
|
27 |
+
"6": "I-ORGANIZATION",
|
28 |
+
"7": "I-PERSON",
|
29 |
+
"8": "I-QUANTITY",
|
30 |
+
"9": "I-TIME",
|
31 |
+
"10": "O"
|
32 |
+
},
|
33 |
+
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
+
"label2id": {
|
36 |
+
"B-LOCATION": 0,
|
37 |
+
"B-ORGANIZATION": 1,
|
38 |
+
"B-PERSON": 2,
|
39 |
+
"B-QUANTITY": 3,
|
40 |
+
"B-TIME": 4,
|
41 |
+
"I-LOCATION": 5,
|
42 |
+
"I-ORGANIZATION": 6,
|
43 |
+
"I-PERSON": 7,
|
44 |
+
"I-QUANTITY": 8,
|
45 |
+
"I-TIME": 9,
|
46 |
+
"O": 10
|
47 |
+
},
|
48 |
+
"layer_norm_eps": 1e-12,
|
49 |
+
"max_position_embeddings": 512,
|
50 |
+
"model_type": "bert",
|
51 |
+
"num_attention_heads": 12,
|
52 |
+
"num_hidden_layers": 12,
|
53 |
+
"output_past": true,
|
54 |
+
"pad_token_id": 0,
|
55 |
+
"position_embedding_type": "absolute",
|
56 |
+
"prediction_heads": {
|
57 |
+
"default": {
|
58 |
+
"activation_function": "gelu",
|
59 |
+
"bias": true,
|
60 |
+
"embedding_size": 768,
|
61 |
+
"head_type": "masked_lm",
|
62 |
+
"label2id": null,
|
63 |
+
"layer_norm": true,
|
64 |
+
"layers": 2,
|
65 |
+
"shift_labels": false,
|
66 |
+
"vocab_size": 31923
|
67 |
+
}
|
68 |
+
},
|
69 |
+
"torch_dtype": "float32",
|
70 |
+
"transformers_version": "4.39.3",
|
71 |
+
"type_vocab_size": 2,
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 31923
|
74 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2526f225abb29839f07fe66227822e80b340b353426b877e062ed0c26a53e80
|
3 |
+
size 444752860
|
runs/May22_16-45-48_indolem-petl-vm/events.out.tfevents.1716396355.indolem-petl-vm.141728.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06ba35de20b8b4a0486bcdd1d72f370cdf35a4b33dcbac3e43b14f4bd441bc39
|
3 |
+
size 5681
|
runs/May22_16-49-19_indolem-petl-vm/events.out.tfevents.1716396564.indolem-petl-vm.142486.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d02c805d21d9440102d23a4cd3c9b6b7620eb6f19aa3934514c07fda52a351c
|
3 |
+
size 5681
|
runs/May22_16-54-23_indolem-petl-vm/events.out.tfevents.1716396868.indolem-petl-vm.143236.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bc44dacceb9050c4421c85b1b47ea08207f57878135c0d9e68fd87cc905de21
|
3 |
+
size 5681
|
runs/May22_16-59-17_indolem-petl-vm/events.out.tfevents.1716397162.indolem-petl-vm.145268.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87667b3c2a5026915c1c82a4ab1bb85df2f9816340c28d4dc10ef045b83b38aa
|
3 |
+
size 5681
|
runs/May22_17-02-24_indolem-petl-vm/events.out.tfevents.1716397350.indolem-petl-vm.146763.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:040a7a63c5038bfc6a4b7beb9a49d0d21fd2a2058969f635916b02eef12b93b4
|
3 |
+
size 5680
|
runs/May22_17-08-23_indolem-petl-vm/events.out.tfevents.1716397711.indolem-petl-vm.159747.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027c06fb60857b4f65279dc33e8dce82046866826dda3c405b85e1808f9e73cd
|
3 |
+
size 5680
|
runs/May22_17-13-46_indolem-petl-vm/events.out.tfevents.1716398033.indolem-petl-vm.162315.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2051467104ea25051169375ecdef0571c89dd6589d512d5b7fc0186f16d75a44
|
3 |
+
size 5680
|
runs/May22_17-16-41_indolem-petl-vm/events.out.tfevents.1716398207.indolem-petl-vm.163762.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba306e5fa97e4004351066b18ed8e0d902e1962a2acff46a7b2e895a6bed0b7a
|
3 |
+
size 5468
|
runs/May22_17-17-22_indolem-petl-vm/events.out.tfevents.1716398248.indolem-petl-vm.164229.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b28b4e5a190606be62d7805b67ea8a8a6acc5b0a8d530bba28cf76514d6b94d
|
3 |
+
size 5468
|
runs/May22_17-19-56_indolem-petl-vm/events.out.tfevents.1716398402.indolem-petl-vm.165023.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c467061984e6ffcc398e4618a945ee7233caa31cbd005b8e8f7af0b61529292f
|
3 |
+
size 5467
|
runs/May22_17-21-14_indolem-petl-vm/events.out.tfevents.1716398479.indolem-petl-vm.165490.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b08a6c2c72c2d0ebf18c771ddd500fff92fcf8e209edca551c31591c113ba120
|
3 |
+
size 22241
|
runs/May22_17-29-13_indolem-petl-vm/events.out.tfevents.1716398963.indolem-petl-vm.167700.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b156731e3c00348afda62753a0a995ff96bd0c17eb9552d27af09de7299c87
|
3 |
+
size 11059
|
runs/May22_17-31-21_indolem-petl-vm/events.out.tfevents.1716399087.indolem-petl-vm.168394.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46f91c9e71e9e44d9391105bdf4a60390215743fc8cb453f7f4643f87ed89dd1
|
3 |
+
size 6151
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[MASK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[SEP]",
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecee0425c2136ee0bd447630801432ea6d478d280a31eacb203354fa4d79a67b
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|