ckandemir commited on
Commit
eb82b04
1 Parent(s): 3c1b69a

End of training

Browse files
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - ckandemir/bitcoin_tweets_sentiment_kaggle
8
+ metrics:
9
+ - accuracy
10
+ - f1
11
+ model-index:
12
+ - name: bitcoin_tweet_sentiment_classification
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: ckandemir/bitcoin_tweets_sentiment_kaggle
19
+ type: ckandemir/bitcoin_tweets_sentiment_kaggle
20
+ metrics:
21
+ - name: Accuracy
22
+ type: accuracy
23
+ value: 0.7150837988826816
24
+ - name: F1
25
+ type: f1
26
+ value: 0.7212944928862212
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # bitcoin_tweet_sentiment_classification
33
+
34
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the ckandemir/bitcoin_tweets_sentiment_kaggle dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.4542
37
+ - Accuracy: 0.7151
38
+ - F1: 0.7213
39
+
40
+ ## Model description
41
+
42
+ More information needed
43
+
44
+ ## Intended uses & limitations
45
+
46
+ More information needed
47
+
48
+ ## Training and evaluation data
49
+
50
+ More information needed
51
+
52
+ ## Training procedure
53
+
54
+ ### Training hyperparameters
55
+
56
+ The following hyperparameters were used during training:
57
+ - learning_rate: 5e-06
58
+ - train_batch_size: 24
59
+ - eval_batch_size: 24
60
+ - seed: 42
61
+ - gradient_accumulation_steps: 3
62
+ - total_train_batch_size: 72
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: cosine_with_restarts
65
+ - lr_scheduler_warmup_steps: 1000
66
+ - training_steps: 1000
67
+ - mixed_precision_training: Native AMP
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
72
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
73
+ | 0.8941 | 0.65 | 50 | 0.8733 | 0.5698 | 0.5654 |
74
+ | 0.8565 | 1.3 | 100 | 0.8042 | 0.6690 | 0.6031 |
75
+ | 0.7896 | 1.96 | 150 | 0.7219 | 0.6802 | 0.5740 |
76
+ | 0.7174 | 2.61 | 200 | 0.6379 | 0.7514 | 0.6955 |
77
+ | 0.633 | 3.26 | 250 | 0.5745 | 0.7514 | 0.6930 |
78
+ | 0.5824 | 3.91 | 300 | 0.5303 | 0.75 | 0.6919 |
79
+ | 0.5365 | 4.57 | 350 | 0.4997 | 0.7514 | 0.7014 |
80
+ | 0.5089 | 5.22 | 400 | 0.4766 | 0.7458 | 0.6991 |
81
+ | 0.4893 | 5.87 | 450 | 0.4596 | 0.7486 | 0.7174 |
82
+ | 0.463 | 6.52 | 500 | 0.4446 | 0.7514 | 0.7127 |
83
+ | 0.4496 | 7.17 | 550 | 0.4407 | 0.7165 | 0.7048 |
84
+ | 0.4357 | 7.83 | 600 | 0.4364 | 0.7277 | 0.7246 |
85
+ | 0.4257 | 8.48 | 650 | 0.4324 | 0.7067 | 0.7115 |
86
+ | 0.4029 | 9.13 | 700 | 0.4314 | 0.7277 | 0.7180 |
87
+ | 0.3955 | 9.78 | 750 | 0.4354 | 0.7151 | 0.7164 |
88
+ | 0.3886 | 10.43 | 800 | 0.4396 | 0.7221 | 0.7244 |
89
+ | 0.3788 | 11.09 | 850 | 0.4363 | 0.7235 | 0.7194 |
90
+ | 0.366 | 11.74 | 900 | 0.4528 | 0.7179 | 0.7215 |
91
+ | 0.3298 | 12.39 | 950 | 0.4766 | 0.7053 | 0.7107 |
92
+ | 0.3423 | 13.04 | 1000 | 0.4542 | 0.7151 | 0.7213 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.35.0
98
+ - Pytorch 2.1.0+cu118
99
+ - Datasets 2.14.6
100
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
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": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
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": "4.35.0",
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:db1e8ebade6a08779564ad1b0c939a3ea55304d8d5c33de5a655606172c405d5
3
+ size 437961724
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:c87220bec2b5737acfd4ab66eb3c66b83a2ca68d4bb31691c965d487a62ed8f3
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff