jaggernaut007
commited on
End of training
Browse files- README.md +100 -0
- config.json +36 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: ml6team/keyphrase-extraction-distilbert-inspec
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: keyphrase-extraction-distilbert-inspec-finetuned-ner
|
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 |
+
# keyphrase-extraction-distilbert-inspec-finetuned-ner
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [ml6team/keyphrase-extraction-distilbert-inspec](https://huggingface.co/ml6team/keyphrase-extraction-distilbert-inspec) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.9452
|
24 |
+
- Precision: 0.7673
|
25 |
+
- Recall: 0.8288
|
26 |
+
- F1: 0.7969
|
27 |
+
- Accuracy: 0.7700
|
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-06
|
47 |
+
- train_batch_size: 64
|
48 |
+
- eval_batch_size: 4
|
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 |
+
- mixed_precision_training: Native AMP
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
58 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
59 |
+
| No log | 0.29 | 5 | 1.4270 | 0.1544 | 0.1644 | 0.1593 | 0.1605 |
|
60 |
+
| No log | 0.59 | 10 | 1.3944 | 0.1593 | 0.1700 | 0.1645 | 0.1652 |
|
61 |
+
| No log | 0.88 | 15 | 1.3639 | 0.1637 | 0.1750 | 0.1692 | 0.1703 |
|
62 |
+
| No log | 1.18 | 20 | 1.3352 | 0.1735 | 0.1859 | 0.1795 | 0.1794 |
|
63 |
+
| No log | 1.47 | 25 | 1.3078 | 0.1892 | 0.2030 | 0.1959 | 0.1953 |
|
64 |
+
| No log | 1.76 | 30 | 1.2818 | 0.2112 | 0.2270 | 0.2188 | 0.2176 |
|
65 |
+
| No log | 2.06 | 35 | 1.2571 | 0.3059 | 0.3294 | 0.3172 | 0.3118 |
|
66 |
+
| No log | 2.35 | 40 | 1.2337 | 0.5455 | 0.5880 | 0.5660 | 0.5508 |
|
67 |
+
| No log | 2.65 | 45 | 1.2114 | 0.6594 | 0.7109 | 0.6842 | 0.6647 |
|
68 |
+
| No log | 2.94 | 50 | 1.1902 | 0.6924 | 0.7468 | 0.7186 | 0.6969 |
|
69 |
+
| No log | 3.24 | 55 | 1.1700 | 0.7094 | 0.7655 | 0.7364 | 0.7143 |
|
70 |
+
| No log | 3.53 | 60 | 1.1508 | 0.7192 | 0.7760 | 0.7465 | 0.7236 |
|
71 |
+
| No log | 3.82 | 65 | 1.1326 | 0.7248 | 0.7823 | 0.7524 | 0.7293 |
|
72 |
+
| No log | 4.12 | 70 | 1.1153 | 0.7290 | 0.7872 | 0.7570 | 0.7337 |
|
73 |
+
| No log | 4.41 | 75 | 1.0990 | 0.7332 | 0.7920 | 0.7615 | 0.7375 |
|
74 |
+
| No log | 4.71 | 80 | 1.0834 | 0.7366 | 0.7956 | 0.7650 | 0.7407 |
|
75 |
+
| No log | 5.0 | 85 | 1.0687 | 0.7393 | 0.7986 | 0.7678 | 0.7433 |
|
76 |
+
| No log | 5.29 | 90 | 1.0549 | 0.7429 | 0.8024 | 0.7715 | 0.7467 |
|
77 |
+
| No log | 5.59 | 95 | 1.0418 | 0.7445 | 0.8042 | 0.7732 | 0.7485 |
|
78 |
+
| No log | 5.88 | 100 | 1.0295 | 0.7473 | 0.8072 | 0.7761 | 0.7510 |
|
79 |
+
| No log | 6.18 | 105 | 1.0179 | 0.7493 | 0.8093 | 0.7781 | 0.7529 |
|
80 |
+
| No log | 6.47 | 110 | 1.0072 | 0.7522 | 0.8125 | 0.7812 | 0.7558 |
|
81 |
+
| No log | 6.76 | 115 | 0.9973 | 0.7548 | 0.8153 | 0.7839 | 0.7581 |
|
82 |
+
| No log | 7.06 | 120 | 0.9882 | 0.7569 | 0.8176 | 0.7861 | 0.7603 |
|
83 |
+
| No log | 7.35 | 125 | 0.9799 | 0.7587 | 0.8196 | 0.7880 | 0.7619 |
|
84 |
+
| No log | 7.65 | 130 | 0.9725 | 0.7607 | 0.8217 | 0.7900 | 0.7638 |
|
85 |
+
| No log | 7.94 | 135 | 0.9658 | 0.7626 | 0.8237 | 0.7919 | 0.7653 |
|
86 |
+
| No log | 8.24 | 140 | 0.9600 | 0.7644 | 0.8257 | 0.7938 | 0.7671 |
|
87 |
+
| No log | 8.53 | 145 | 0.9550 | 0.7650 | 0.8263 | 0.7945 | 0.7678 |
|
88 |
+
| No log | 8.82 | 150 | 0.9509 | 0.7659 | 0.8273 | 0.7954 | 0.7687 |
|
89 |
+
| No log | 9.12 | 155 | 0.9476 | 0.7667 | 0.8281 | 0.7962 | 0.7694 |
|
90 |
+
| No log | 9.41 | 160 | 0.9452 | 0.7673 | 0.8288 | 0.7969 | 0.7700 |
|
91 |
+
| No log | 9.71 | 165 | 0.9436 | 0.7674 | 0.8290 | 0.7970 | 0.7702 |
|
92 |
+
| No log | 10.0 | 170 | 0.9429 | 0.7674 | 0.8290 | 0.7970 | 0.7702 |
|
93 |
+
|
94 |
+
|
95 |
+
### Framework versions
|
96 |
+
|
97 |
+
- Transformers 4.39.3
|
98 |
+
- Pytorch 2.2.2+cu121
|
99 |
+
- Datasets 2.19.0
|
100 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ml6team/keyphrase-extraction-distilbert-inspec",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0,
|
20 |
+
"LABEL_1": 1,
|
21 |
+
"LABEL_2": 2,
|
22 |
+
"LABEL_3": 3
|
23 |
+
},
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "distilbert",
|
26 |
+
"n_heads": 12,
|
27 |
+
"n_layers": 6,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"qa_dropout": 0.1,
|
30 |
+
"seq_classif_dropout": 0.2,
|
31 |
+
"sinusoidal_pos_embds": false,
|
32 |
+
"tie_weights_": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.39.3",
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf03cedad3153013db1d6f4d0428bbc80f9b05e85d451e128b9f89942d8eb027
|
3 |
+
size 265476168
|
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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "[PAD]",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"100": {
|
13 |
+
"content": "[UNK]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"101": {
|
21 |
+
"content": "[CLS]",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"102": {
|
29 |
+
"content": "[SEP]",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"103": {
|
37 |
+
"content": "[MASK]",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "[SEP]",
|
56 |
+
"stride": 0,
|
57 |
+
"strip_accents": null,
|
58 |
+
"tokenize_chinese_chars": true,
|
59 |
+
"tokenizer_class": "DistilBertTokenizer",
|
60 |
+
"truncation_side": "right",
|
61 |
+
"truncation_strategy": "longest_first",
|
62 |
+
"unk_token": "[UNK]"
|
63 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f59397aa9b945e0651006d9726dd5c0411c67dfea6e517e258fe122f92e5a8e4
|
3 |
+
size 4984
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|