lynhan commited on
Commit
fa20c6e
1 Parent(s): 5a05f65
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: beomi/kcbert-base
4
+ tags:
5
+ - HSJ
6
+ - 10_class
7
+ - multi_labels
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: model_output
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # model_output
18
+
19
+ This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on the unsmile_data dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1417
22
+ - Irap: 0.8781
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 2e-05
42
+ - train_batch_size: 64
43
+ - eval_batch_size: 64
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 5
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Irap |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | No log | 1.0 | 235 | 0.1262 | 0.8733 |
54
+ | No log | 2.0 | 470 | 0.1261 | 0.8757 |
55
+ | 0.0981 | 3.0 | 705 | 0.1313 | 0.8802 |
56
+ | 0.0981 | 4.0 | 940 | 0.1409 | 0.8751 |
57
+ | 0.0507 | 5.0 | 1175 | 0.1417 | 0.8781 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.42.4
63
+ - Pytorch 2.4.0+cu121
64
+ - Datasets 2.21.0
65
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/kcbert-base",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "LABEL_0": 0,
28
+ "LABEL_1": 1,
29
+ "LABEL_2": 2,
30
+ "LABEL_3": 3,
31
+ "LABEL_4": 4,
32
+ "LABEL_5": 5,
33
+ "LABEL_6": 6,
34
+ "LABEL_7": 7,
35
+ "LABEL_8": 8,
36
+ "LABEL_9": 9
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "max_position_embeddings": 300,
40
+ "model_type": "bert",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "pad_token_id": 0,
44
+ "pooler_fc_size": 768,
45
+ "pooler_num_attention_heads": 12,
46
+ "pooler_num_fc_layers": 3,
47
+ "pooler_size_per_head": 128,
48
+ "pooler_type": "first_token_transform",
49
+ "position_embedding_type": "absolute",
50
+ "problem_type": "multi_label_classification",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.42.4",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 30000
56
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a553b1b1a87f9ee0b98d601025a6f130490f3061169eeae62d174000efa2f91b
3
+ size 435728400
runs/Sep02_00-55-23_755aac27af4a/events.out.tfevents.1725238529.755aac27af4a.582.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add163943ec3fa383dd6c1b850e69ea207c0ed0fe74fc37f738b6cb6053e38ad
3
+ size 5765
runs/Sep02_01-07-37_755aac27af4a/events.out.tfevents.1725239280.755aac27af4a.582.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f4f9b734c4a8465afb2cfe411f0945e0ad21b4874e67454ac601b644925151
3
+ size 7859
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": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 300,
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 sha256:6f72702a726b768c1804e9b2ffdd7548f3705a04430961b58ed54c1f823c1610
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff