Kritawat commited on
Commit
5c9e905
1 Parent(s): 5492830

Kritawat/vibe-roberta

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: SamLowe/roberta-base-go_emotions
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - f1
8
+ - accuracy
9
+ model-index:
10
+ - name: bert-finetuned-sem_eval-english
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
+ # bert-finetuned-sem_eval-english
18
+
19
+ This model is a fine-tuned version of [SamLowe/roberta-base-go_emotions](https://huggingface.co/SamLowe/roberta-base-go_emotions) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1189
22
+ - F1: 0.5833
23
+ - Roc Auc: 0.7555
24
+ - Accuracy: 0.3939
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 2e-05
44
+ - train_batch_size: 8
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 5
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
55
+ | No log | 1.0 | 29 | 0.1381 | 0.5217 | 0.7178 | 0.3030 |
56
+ | No log | 2.0 | 58 | 0.1193 | 0.5532 | 0.7367 | 0.3636 |
57
+ | No log | 3.0 | 87 | 0.1220 | 0.5417 | 0.7355 | 0.3636 |
58
+ | No log | 4.0 | 116 | 0.1189 | 0.5833 | 0.7555 | 0.3939 |
59
+ | No log | 5.0 | 145 | 0.1186 | 0.5833 | 0.7555 | 0.3939 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.39.2
65
+ - Pytorch 2.2.1+cu121
66
+ - Datasets 2.18.0
67
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SamLowe/roberta-base-go_emotions",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "admiration",
15
+ "1": "amusement",
16
+ "2": "anger",
17
+ "3": "annoyance",
18
+ "4": "approval",
19
+ "5": "caring",
20
+ "6": "confusion",
21
+ "7": "curiosity",
22
+ "8": "desire",
23
+ "9": "disappointment",
24
+ "10": "disapproval",
25
+ "11": "disgust",
26
+ "12": "embarrassment",
27
+ "13": "excitement",
28
+ "14": "fear",
29
+ "15": "gratitude",
30
+ "16": "grief",
31
+ "17": "joy",
32
+ "18": "love",
33
+ "19": "nervousness",
34
+ "20": "optimism",
35
+ "21": "pride",
36
+ "22": "realization",
37
+ "23": "relief",
38
+ "24": "remorse",
39
+ "25": "sadness",
40
+ "26": "surprise",
41
+ "27": "neutrality"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "label2id": {
46
+ "admiration": 0,
47
+ "amusement": 1,
48
+ "anger": 2,
49
+ "annoyance": 3,
50
+ "approval": 4,
51
+ "caring": 5,
52
+ "confusion": 6,
53
+ "curiosity": 7,
54
+ "desire": 8,
55
+ "disappointment": 9,
56
+ "disapproval": 10,
57
+ "disgust": 11,
58
+ "embarrassment": 12,
59
+ "excitement": 13,
60
+ "fear": 14,
61
+ "gratitude": 15,
62
+ "grief": 16,
63
+ "joy": 17,
64
+ "love": 18,
65
+ "nervousness": 19,
66
+ "neutrality": 27,
67
+ "optimism": 20,
68
+ "pride": 21,
69
+ "realization": 22,
70
+ "relief": 23,
71
+ "remorse": 24,
72
+ "sadness": 25,
73
+ "surprise": 26
74
+ },
75
+ "layer_norm_eps": 1e-05,
76
+ "max_position_embeddings": 514,
77
+ "model_type": "roberta",
78
+ "num_attention_heads": 12,
79
+ "num_hidden_layers": 12,
80
+ "pad_token_id": 1,
81
+ "position_embedding_type": "absolute",
82
+ "problem_type": "multi_label_classification",
83
+ "torch_dtype": "float32",
84
+ "transformers_version": "4.39.2",
85
+ "type_vocab_size": 1,
86
+ "use_cache": true,
87
+ "vocab_size": 50265
88
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c1997e39ad9fe0746d26738878fe63c8dd48a9879eafe5c7577d531df5c7ae
3
+ size 498692800
runs/Apr01_13-26-09_8aba0301d117/events.out.tfevents.1711977971.8aba0301d117.210.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c8944de55459ed9d69ce5ace4e05d93fdb0097d61ea753da987ccfaa5cae8c
3
+ size 8334
runs/Apr01_13-26-09_8aba0301d117/events.out.tfevents.1711979586.8aba0301d117.210.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de49121a627d8388a50324a831f3a3085d504e4d8f19a7282ba7a252cc228d2
3
+ size 928
runs/Apr01_14-48-07_8aba0301d117/events.out.tfevents.1711982890.8aba0301d117.20219.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb28632aab5f2b3b8301acca087eb43002ce65b264a28c19df0a13fbd6105250
3
+ size 8366
runs/Apr01_14-48-07_8aba0301d117/events.out.tfevents.1711984587.8aba0301d117.20219.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8017a4c437caeac9b6c58cab3a466575ec9dd79456be425277d0542ccadb960b
3
+ size 928
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_length": 128,
52
+ "model_max_length": 512,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "<pad>",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "</s>",
58
+ "stride": 0,
59
+ "tokenizer_class": "RobertaTokenizer",
60
+ "trim_offsets": true,
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0b8ba3e7b8f352576ffa81340eb964477731bfbb31a4256bbfb91e808af346
3
+ size 4920
vocab.json ADDED
The diff for this file is too large to render. See raw diff