lupobricco
commited on
Commit
•
c6923c5
1
Parent(s):
560ce10
Training in progress, epoch 1
Browse files- README.md +72 -0
- config.json +53 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
base_model: aiknowyou/it-emotion-analyzer
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: it-emotion-analyzer_finetuned_pro_multilbel_emit
|
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 |
+
# it-emotion-analyzer_finetuned_pro_multilbel_emit
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [aiknowyou/it-emotion-analyzer](https://huggingface.co/aiknowyou/it-emotion-analyzer) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3116
|
22 |
+
- F1: 0.5269
|
23 |
+
- Roc Auc: 0.7253
|
24 |
+
- Accuracy: 0.3643
|
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: 10
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|
|
55 |
+
| 0.2723 | 1.0 | 1037 | 0.2654 | 0.3992 | 0.6370 | 0.2801 |
|
56 |
+
| 0.2241 | 2.0 | 2074 | 0.2465 | 0.4387 | 0.6603 | 0.2973 |
|
57 |
+
| 0.1774 | 3.0 | 3111 | 0.2547 | 0.5066 | 0.7051 | 0.3608 |
|
58 |
+
| 0.1435 | 4.0 | 4148 | 0.2627 | 0.4834 | 0.6933 | 0.3333 |
|
59 |
+
| 0.1111 | 5.0 | 5185 | 0.2850 | 0.4992 | 0.7052 | 0.3540 |
|
60 |
+
| 0.0873 | 6.0 | 6222 | 0.3010 | 0.5112 | 0.7177 | 0.3505 |
|
61 |
+
| 0.0699 | 7.0 | 7259 | 0.3116 | 0.5269 | 0.7253 | 0.3643 |
|
62 |
+
| 0.054 | 8.0 | 8296 | 0.3288 | 0.5223 | 0.7246 | 0.3625 |
|
63 |
+
| 0.05 | 9.0 | 9333 | 0.3405 | 0.5149 | 0.7223 | 0.3608 |
|
64 |
+
| 0.0416 | 10.0 | 10370 | 0.3437 | 0.5196 | 0.7268 | 0.3591 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.40.1
|
70 |
+
- Pytorch 2.3.0+cu118
|
71 |
+
- Datasets 2.19.0
|
72 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aiknowyou/it-emotion-analyzer",
|
3 |
+
"_num_labels": 6,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Amore",
|
14 |
+
"1": "Anticipazione",
|
15 |
+
"2": "Disgusto",
|
16 |
+
"3": "Fiducia",
|
17 |
+
"4": "Gioia",
|
18 |
+
"5": "Paura",
|
19 |
+
"6": "Rabbia",
|
20 |
+
"7": "Sorpresa",
|
21 |
+
"8": "Tristezza",
|
22 |
+
"9": "Neutro"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"Amore": 0,
|
28 |
+
"Anticipazione": 1,
|
29 |
+
"Disgusto": 2,
|
30 |
+
"Fiducia": 3,
|
31 |
+
"Gioia": 4,
|
32 |
+
"Neutro": 9,
|
33 |
+
"Paura": 5,
|
34 |
+
"Rabbia": 6,
|
35 |
+
"Sorpresa": 7,
|
36 |
+
"Tristezza": 8
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-12,
|
39 |
+
"max_length": 96,
|
40 |
+
"max_position_embeddings": 512,
|
41 |
+
"model_type": "bert",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"pad_token_id": 0,
|
45 |
+
"padding": "max_length",
|
46 |
+
"position_embedding_type": "absolute",
|
47 |
+
"problem_type": "multi_label_classification",
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.40.1",
|
50 |
+
"type_vocab_size": 2,
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 31102
|
53 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eac171f2e233790b4e217fe05dd8c5f1fb4f045d6bf7501254056ada85aa31f
|
3 |
+
size 439765016
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
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_len": 512,
|
50 |
+
"max_length": 96,
|
51 |
+
"model_max_length": 512,
|
52 |
+
"never_split": null,
|
53 |
+
"pad_to_multiple_of": null,
|
54 |
+
"pad_token": "[PAD]",
|
55 |
+
"pad_token_type_id": 0,
|
56 |
+
"padding_side": "right",
|
57 |
+
"sep_token": "[SEP]",
|
58 |
+
"stride": 0,
|
59 |
+
"strip_accents": null,
|
60 |
+
"tokenize_chinese_chars": true,
|
61 |
+
"tokenizer_class": "BertTokenizer",
|
62 |
+
"truncation_side": "right",
|
63 |
+
"truncation_strategy": "longest_first",
|
64 |
+
"unk_token": "[UNK]"
|
65 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41e5350cdd8758db5dbcaf9ef32ae853e5a0dded5a4f6617a20c15b87555d58a
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|