vinh120203 commited on
Commit
b7d38aa
·
verified ·
1 Parent(s): 2757009

railwayBK-sentiment-analysis

Browse files
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ProsusAI/finbert
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ - f1
8
+ - precision
9
+ - recall
10
+ model-index:
11
+ - name: finBert
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # finBert
19
+
20
+ This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3623
23
+ - Accuracy: 0.868
24
+ - F1: 0.8666
25
+ - Precision: 0.8671
26
+ - Recall: 0.8685
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
+ - train_batch_size: 32
47
+ - eval_batch_size: 32
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 100
52
+ - num_epochs: 3
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 1.2152 | 0.0820 | 50 | 0.6140 | 0.7004 | 0.6545 | 0.7339 | 0.7020 |
60
+ | 0.5357 | 0.1639 | 100 | 0.4736 | 0.8265 | 0.8216 | 0.8270 | 0.8268 |
61
+ | 0.4421 | 0.2459 | 150 | 0.4189 | 0.8501 | 0.8466 | 0.8494 | 0.8505 |
62
+ | 0.4591 | 0.3279 | 200 | 0.4177 | 0.8390 | 0.8336 | 0.8417 | 0.8395 |
63
+ | 0.4382 | 0.4098 | 250 | 0.3876 | 0.8549 | 0.8537 | 0.8538 | 0.8550 |
64
+ | 0.4002 | 0.4918 | 300 | 0.4063 | 0.8434 | 0.8454 | 0.8503 | 0.8433 |
65
+ | 0.4085 | 0.5738 | 350 | 0.3818 | 0.8576 | 0.8574 | 0.8572 | 0.8579 |
66
+ | 0.3692 | 0.6557 | 400 | 0.3700 | 0.8608 | 0.8592 | 0.8598 | 0.8611 |
67
+ | 0.3686 | 0.7377 | 450 | 0.3730 | 0.8610 | 0.8604 | 0.8600 | 0.8613 |
68
+ | 0.3966 | 0.8197 | 500 | 0.3760 | 0.8566 | 0.8573 | 0.8584 | 0.8569 |
69
+ | 0.3729 | 0.9016 | 550 | 0.3533 | 0.8673 | 0.8667 | 0.8664 | 0.8675 |
70
+ | 0.3605 | 0.9836 | 600 | 0.3582 | 0.8632 | 0.8637 | 0.8645 | 0.8632 |
71
+ | 0.3471 | 1.0656 | 650 | 0.3671 | 0.8644 | 0.8643 | 0.8646 | 0.8645 |
72
+ | 0.3397 | 1.1475 | 700 | 0.3632 | 0.8658 | 0.8658 | 0.8656 | 0.8660 |
73
+ | 0.2977 | 1.2295 | 750 | 0.3737 | 0.8631 | 0.8619 | 0.8620 | 0.8634 |
74
+ | 0.3047 | 1.3115 | 800 | 0.3609 | 0.8656 | 0.8664 | 0.8673 | 0.8657 |
75
+ | 0.2817 | 1.3934 | 850 | 0.3816 | 0.8682 | 0.8661 | 0.8675 | 0.8685 |
76
+ | 0.2667 | 1.4754 | 900 | 0.3734 | 0.8690 | 0.8680 | 0.8686 | 0.8692 |
77
+ | 0.2809 | 1.5574 | 950 | 0.3523 | 0.8702 | 0.8706 | 0.8710 | 0.8703 |
78
+ | 0.2964 | 1.6393 | 1000 | 0.3621 | 0.8709 | 0.8693 | 0.8705 | 0.8711 |
79
+ | 0.2993 | 1.7213 | 1050 | 0.3502 | 0.8731 | 0.8728 | 0.8729 | 0.8732 |
80
+ | 0.3153 | 1.8033 | 1100 | 0.3532 | 0.8723 | 0.8703 | 0.8718 | 0.8726 |
81
+ | 0.3089 | 1.8852 | 1150 | 0.3581 | 0.8721 | 0.8710 | 0.8711 | 0.8724 |
82
+ | 0.3027 | 1.9672 | 1200 | 0.3513 | 0.8725 | 0.8712 | 0.8719 | 0.8727 |
83
+ | 0.2294 | 2.0492 | 1250 | 0.3673 | 0.8714 | 0.8715 | 0.8715 | 0.8715 |
84
+ | 0.2321 | 2.1311 | 1300 | 0.3630 | 0.8716 | 0.8718 | 0.8727 | 0.8716 |
85
+ | 0.2003 | 2.2131 | 1350 | 0.3951 | 0.872 | 0.8714 | 0.8711 | 0.8722 |
86
+ | 0.1948 | 2.2951 | 1400 | 0.3912 | 0.8724 | 0.8721 | 0.8719 | 0.8726 |
87
+ | 0.1939 | 2.3770 | 1450 | 0.3871 | 0.8733 | 0.8734 | 0.8734 | 0.8735 |
88
+ | 0.1897 | 2.4590 | 1500 | 0.3937 | 0.8738 | 0.8732 | 0.8730 | 0.8741 |
89
+ | 0.1951 | 2.5410 | 1550 | 0.3915 | 0.8711 | 0.8702 | 0.8704 | 0.8713 |
90
+ | 0.193 | 2.6230 | 1600 | 0.3902 | 0.8732 | 0.8729 | 0.8727 | 0.8734 |
91
+ | 0.1982 | 2.7049 | 1650 | 0.3903 | 0.8734 | 0.8734 | 0.8733 | 0.8736 |
92
+ | 0.1836 | 2.7869 | 1700 | 0.3929 | 0.8734 | 0.8732 | 0.8731 | 0.8736 |
93
+ | 0.2112 | 2.8689 | 1750 | 0.3927 | 0.8742 | 0.8738 | 0.8738 | 0.8743 |
94
+ | 0.1937 | 2.9508 | 1800 | 0.3899 | 0.8738 | 0.8739 | 0.8741 | 0.8740 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.42.4
100
+ - Pytorch 2.3.1+cu121
101
+ - Tokenizers 0.19.1
Untitled0.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ProsusAI/finbert",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "Positive",
14
+ "1": "Neutral",
15
+ "2": "Negative"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Negative": 2,
21
+ "Neutral": 1,
22
+ "Positive": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.42.4",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38680c0a8ea1fb6d962d52faaae32bfa1ee5cb80fa4cbe42fdf0e885d755baf3
3
+ size 437961724
multi-class-logs/events.out.tfevents.1721280146.4867d8d32b72.4228.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37af7f3e26eaf7217ce2f2c9a7f94f29a7e80aa8ffde8261595eb88d784920a
3
+ size 30015
multi-class-logs/events.out.tfevents.1721284078.4867d8d32b72.4228.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55cb682c05184ec91f0c512c2875abe1f70811969b2e38d5d1c8a438b63df02f
3
+ size 1504
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96fc7d766cdf02412a5d1b261185556de7cc08c52e37956b0f2e385760c094c2
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff