sherelyn912
commited on
Commit
•
13ca792
1
Parent(s):
dec6a87
End of training
Browse files- README.md +71 -0
- config.json +95 -0
- model.safetensors +3 -0
- runs/Apr11_07-07-29_ce3b1bc82a18/events.out.tfevents.1712819249.ce3b1bc82a18.581.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: emotional-bert
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# emotional-bert
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 2.5503
|
24 |
+
- Accuracy: 0.4065
|
25 |
+
- F1: 0.3831
|
26 |
+
- Precision: 0.3926
|
27 |
+
- Recall: 0.4065
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 2e-05
|
47 |
+
- train_batch_size: 16
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
58 |
+
| 2.82 | 1.0 | 270 | 2.7828 | 0.1733 | 0.1556 | 0.2256 | 0.1733 |
|
59 |
+
| 1.4083 | 2.0 | 540 | 2.3254 | 0.3230 | 0.3235 | 0.3651 | 0.3230 |
|
60 |
+
| 0.6017 | 3.0 | 810 | 2.1533 | 0.3766 | 0.3669 | 0.3880 | 0.3766 |
|
61 |
+
| 0.2357 | 4.0 | 1080 | 2.2329 | 0.3721 | 0.3620 | 0.3727 | 0.3721 |
|
62 |
+
| 0.0868 | 5.0 | 1350 | 2.3517 | 0.4065 | 0.3878 | 0.3897 | 0.4065 |
|
63 |
+
| 0.0328 | 6.0 | 1620 | 2.5503 | 0.4065 | 0.3831 | 0.3926 | 0.4065 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.39.3
|
69 |
+
- Pytorch 2.2.1+cu121
|
70 |
+
- Datasets 2.18.0
|
71 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/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": "serenity",
|
14 |
+
"1": "joy",
|
15 |
+
"10": "terror",
|
16 |
+
"11": "awe",
|
17 |
+
"12": "distraction",
|
18 |
+
"13": "surprise",
|
19 |
+
"14": "amazement",
|
20 |
+
"15": "disapproval",
|
21 |
+
"16": "pensiveness",
|
22 |
+
"17": "sadness",
|
23 |
+
"18": "grief",
|
24 |
+
"19": "remorse",
|
25 |
+
"2": "ecstasy",
|
26 |
+
"20": "boredom",
|
27 |
+
"21": "disgust",
|
28 |
+
"22": "loathing",
|
29 |
+
"23": "contempt",
|
30 |
+
"24": "annoyance",
|
31 |
+
"25": "anger",
|
32 |
+
"26": "rage",
|
33 |
+
"27": "aggressiveness",
|
34 |
+
"28": "interest",
|
35 |
+
"29": "anticipation",
|
36 |
+
"3": "love",
|
37 |
+
"30": "vigilance",
|
38 |
+
"31": "optimism",
|
39 |
+
"4": "acceptance",
|
40 |
+
"5": "trust",
|
41 |
+
"6": "admiration",
|
42 |
+
"7": "submission",
|
43 |
+
"8": "apprehension",
|
44 |
+
"9": "fear"
|
45 |
+
},
|
46 |
+
"initializer_range": 0.02,
|
47 |
+
"intermediate_size": 3072,
|
48 |
+
"label2id": {
|
49 |
+
"acceptance": 4,
|
50 |
+
"admiration": 6,
|
51 |
+
"aggressiveness": 27,
|
52 |
+
"amazement": 14,
|
53 |
+
"anger": 25,
|
54 |
+
"annoyance": 24,
|
55 |
+
"anticipation": 29,
|
56 |
+
"apprehension": 8,
|
57 |
+
"awe": 11,
|
58 |
+
"boredom": 20,
|
59 |
+
"contempt": 23,
|
60 |
+
"disapproval": 15,
|
61 |
+
"disgust": 21,
|
62 |
+
"distraction": 12,
|
63 |
+
"ecstasy": 2,
|
64 |
+
"fear": 9,
|
65 |
+
"grief": 18,
|
66 |
+
"interest": 28,
|
67 |
+
"joy": 1,
|
68 |
+
"loathing": 22,
|
69 |
+
"love": 3,
|
70 |
+
"optimism": 31,
|
71 |
+
"pensiveness": 16,
|
72 |
+
"rage": 26,
|
73 |
+
"remorse": 19,
|
74 |
+
"sadness": 17,
|
75 |
+
"serenity": 0,
|
76 |
+
"submission": 7,
|
77 |
+
"surprise": 13,
|
78 |
+
"terror": 10,
|
79 |
+
"trust": 5,
|
80 |
+
"vigilance": 30
|
81 |
+
},
|
82 |
+
"layer_norm_eps": 1e-12,
|
83 |
+
"max_position_embeddings": 512,
|
84 |
+
"model_type": "bert",
|
85 |
+
"num_attention_heads": 12,
|
86 |
+
"num_hidden_layers": 12,
|
87 |
+
"pad_token_id": 0,
|
88 |
+
"position_embedding_type": "absolute",
|
89 |
+
"problem_type": "single_label_classification",
|
90 |
+
"torch_dtype": "float32",
|
91 |
+
"transformers_version": "4.39.3",
|
92 |
+
"type_vocab_size": 2,
|
93 |
+
"use_cache": true,
|
94 |
+
"vocab_size": 30522
|
95 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9365fec19e877e771cb16dea631f7c7d56c512c9bc983fc794cc1cded225b252
|
3 |
+
size 438050928
|
runs/Apr11_07-07-29_ce3b1bc82a18/events.out.tfevents.1712819249.ce3b1bc82a18.581.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3706c2f2eebc5ae81731b27f111b65c7cbf5efa8f3aee307a6da6454482d134
|
3 |
+
size 10406
|
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 sha256:55978f8422f119d7d368e2cff1eeea2d5b8273480bc99ed8db930e4c348fb113
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|