sarasarasara commited on
Commit
ff556e9
1 Parent(s): 38ba8d4

sarasarasara/model-name

Browse files
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - sem_eval_2018_task_1
8
+ metrics:
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: bert-finetuned-sem_eval-english
13
+ results:
14
+ - task:
15
+ name: Text Classification
16
+ type: text-classification
17
+ dataset:
18
+ name: sem_eval_2018_task_1
19
+ type: sem_eval_2018_task_1
20
+ config: subtask5.english
21
+ split: validation
22
+ args: subtask5.english
23
+ metrics:
24
+ - name: F1
25
+ type: f1
26
+ value: 0.6611215454789374
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value: 0.24717832957110608
30
+ ---
31
+
32
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
+ should probably proofread and complete it, then remove this comment. -->
34
+
35
+ # bert-finetuned-sem_eval-english
36
+
37
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the sem_eval_2018_task_1 dataset.
38
+ It achieves the following results on the evaluation set:
39
+ - Loss: 0.3263
40
+ - F1: 0.6611
41
+ - Roc Auc: 0.7630
42
+ - Accuracy: 0.2472
43
+
44
+ ## Model description
45
+
46
+ More information needed
47
+
48
+ ## Intended uses & limitations
49
+
50
+ More information needed
51
+
52
+ ## Training and evaluation data
53
+
54
+ More information needed
55
+
56
+ ## Training procedure
57
+
58
+ ### Training hyperparameters
59
+
60
+ The following hyperparameters were used during training:
61
+ - learning_rate: 2e-05
62
+ - train_batch_size: 8
63
+ - eval_batch_size: 8
64
+ - seed: 42
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: linear
67
+ - num_epochs: 1
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
72
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
73
+ | 0.404 | 1.0 | 855 | 0.3263 | 0.6611 | 0.7630 | 0.2472 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.34.0
79
+ - Pytorch 2.0.1+cu118
80
+ - Datasets 2.14.5
81
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "anger",
14
+ "1": "anticipation",
15
+ "2": "disgust",
16
+ "3": "fear",
17
+ "4": "joy",
18
+ "5": "love",
19
+ "6": "optimism",
20
+ "7": "pessimism",
21
+ "8": "sadness",
22
+ "9": "surprise",
23
+ "10": "trust"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "anger": 0,
29
+ "anticipation": 1,
30
+ "disgust": 2,
31
+ "fear": 3,
32
+ "joy": 4,
33
+ "love": 5,
34
+ "optimism": 6,
35
+ "pessimism": 7,
36
+ "sadness": 8,
37
+ "surprise": 9,
38
+ "trust": 10
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "bert",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 0,
46
+ "position_embedding_type": "absolute",
47
+ "problem_type": "multi_label_classification",
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.34.0",
50
+ "type_vocab_size": 2,
51
+ "use_cache": true,
52
+ "vocab_size": 30522
53
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc15f3a37adf6b5fd30446eeed9a38062335cfed2536076fd675481ef571a41
3
+ size 438031153
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2b90faa8e0dc6d4161f59e300ac06034f6b617a9666e20fecdd6c1dbe8d010
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff