Training in progress, step 500
Browse files- .gitignore +1 -0
- README.md +92 -0
- config.json +46 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- runs/Jul24_22-36-21_raul-MS-7B98/events.out.tfevents.1690256261.raul-MS-7B98.22661.0 +3 -0
- runs/Jul24_22-36-21_raul-MS-7B98/events.out.tfevents.1690256520.raul-MS-7B98.22661.1 +3 -0
- runs/Jul24_22-48-15_raul-MS-7B98/events.out.tfevents.1690256899.raul-MS-7B98.23786.0 +3 -0
- runs/Jul24_22-48-15_raul-MS-7B98/events.out.tfevents.1690257525.raul-MS-7B98.23786.1 +3 -0
- runs/Jul25_22-02-19_raul-MS-7B98/events.out.tfevents.1690340543.raul-MS-7B98.22135.0 +3 -0
- runs/Jul25_22-02-19_raul-MS-7B98/events.out.tfevents.1690341501.raul-MS-7B98.22135.1 +3 -0
- runs/Jul25_22-19-07_raul-MS-7B98/events.out.tfevents.1690341551.raul-MS-7B98.22548.0 +3 -0
- runs/Jul25_22-33-31_raul-MS-7B98/events.out.tfevents.1690342416.raul-MS-7B98.5700.0 +3 -0
- runs/Jul25_22-33-31_raul-MS-7B98/events.out.tfevents.1690343291.raul-MS-7B98.5700.1 +3 -0
- runs/Jul25_22-56-04_raul-MS-7B98/events.out.tfevents.1690343798.raul-MS-7B98.15660.0 +3 -0
- runs/Jul25_22-56-04_raul-MS-7B98/events.out.tfevents.1690344692.raul-MS-7B98.15660.1 +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
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- conll2003
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
+
model-index:
|
14 |
+
- name: distilbert-base-uncased-finetuned-ner
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: conll2003
|
21 |
+
type: conll2003
|
22 |
+
config: conll2003
|
23 |
+
split: validation
|
24 |
+
args: conll2003
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.9231874447391689
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.9344445687437074
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.9287818980374716
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.9830651182741036
|
38 |
+
---
|
39 |
+
|
40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
41 |
+
should probably proofread and complete it, then remove this comment. -->
|
42 |
+
|
43 |
+
# distilbert-base-uncased-finetuned-ner
|
44 |
+
|
45 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
|
46 |
+
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0620
|
48 |
+
- Precision: 0.9232
|
49 |
+
- Recall: 0.9344
|
50 |
+
- F1: 0.9288
|
51 |
+
- Accuracy: 0.9831
|
52 |
+
|
53 |
+
## Model description
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Intended uses & limitations
|
58 |
+
|
59 |
+
More information needed
|
60 |
+
|
61 |
+
## Training and evaluation data
|
62 |
+
|
63 |
+
More information needed
|
64 |
+
|
65 |
+
## Training procedure
|
66 |
+
|
67 |
+
### Training hyperparameters
|
68 |
+
|
69 |
+
The following hyperparameters were used during training:
|
70 |
+
- learning_rate: 2e-05
|
71 |
+
- train_batch_size: 16
|
72 |
+
- eval_batch_size: 16
|
73 |
+
- seed: 42
|
74 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
+
- lr_scheduler_type: linear
|
76 |
+
- num_epochs: 3
|
77 |
+
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| 0.2477 | 1.0 | 878 | 0.0697 | 0.9049 | 0.9218 | 0.9133 | 0.9801 |
|
83 |
+
| 0.0507 | 2.0 | 1756 | 0.0614 | 0.9241 | 0.9287 | 0.9264 | 0.9824 |
|
84 |
+
| 0.0316 | 3.0 | 2634 | 0.0620 | 0.9232 | 0.9344 | 0.9288 | 0.9831 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.32.0.dev0
|
90 |
+
- Pytorch 2.0.1+cu117
|
91 |
+
- Datasets 2.13.1
|
92 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
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 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8"
|
21 |
+
},
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4,
|
29 |
+
"LABEL_5": 5,
|
30 |
+
"LABEL_6": 6,
|
31 |
+
"LABEL_7": 7,
|
32 |
+
"LABEL_8": 8
|
33 |
+
},
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "distilbert",
|
36 |
+
"n_heads": 12,
|
37 |
+
"n_layers": 6,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"qa_dropout": 0.1,
|
40 |
+
"seq_classif_dropout": 0.2,
|
41 |
+
"sinusoidal_pos_embds": false,
|
42 |
+
"tie_weights_": true,
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.43.3",
|
45 |
+
"vocab_size": 30522
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc13ea804d09f4ddefa62ceef979d6b5426a57d3000fd16f13653881073ae3cc
|
3 |
+
size 265491548
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65c1a7d82a04d6f430c6cec993603c2a09360f033e0c87e5707c60934a77e985
|
3 |
+
size 265514021
|
runs/Jul24_22-36-21_raul-MS-7B98/events.out.tfevents.1690256261.raul-MS-7B98.22661.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d618fe8d964b593cca6e9c0928360a8c5b39a912da3ea48d30170a48b3af34c
|
3 |
+
size 8588
|
runs/Jul24_22-36-21_raul-MS-7B98/events.out.tfevents.1690256520.raul-MS-7B98.22661.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:376b53ac071ef12616e939927b133082d9ebc2ddd2eed8085bafc0179ce5b045
|
3 |
+
size 4338
|
runs/Jul24_22-48-15_raul-MS-7B98/events.out.tfevents.1690256899.raul-MS-7B98.23786.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43eba64d8fdd9ec8ff9fef19af43068a0baf6fb13d2402153f2e200fa8af3ea3
|
3 |
+
size 6577
|
runs/Jul24_22-48-15_raul-MS-7B98/events.out.tfevents.1690257525.raul-MS-7B98.23786.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c736d08fc9d2943f776feb099a9bd2a7cab58f90084a7a77959afb48ab9b34fe
|
3 |
+
size 1032
|
runs/Jul25_22-02-19_raul-MS-7B98/events.out.tfevents.1690340543.raul-MS-7B98.22135.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a462fbc736ce28b143b56f69503c57e7ed53c3f59a76e6c237cd7a6bbf028d46
|
3 |
+
size 4401
|
runs/Jul25_22-02-19_raul-MS-7B98/events.out.tfevents.1690341501.raul-MS-7B98.22135.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20527e095326343d86593164d4b2ec2260df2af7bfaf47c1053daaca1858ebf8
|
3 |
+
size 4401
|
runs/Jul25_22-19-07_raul-MS-7B98/events.out.tfevents.1690341551.raul-MS-7B98.22548.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8397d21308afadc3fcde50aec16121d6497b43aae40dbbab6fdadf0a407f7b01
|
3 |
+
size 8652
|
runs/Jul25_22-33-31_raul-MS-7B98/events.out.tfevents.1690342416.raul-MS-7B98.5700.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:901a7f7f5609ff6eeca84a9a58aa1c631c67bccc4ee48e50cc2176cd7d8162b1
|
3 |
+
size 6954
|
runs/Jul25_22-33-31_raul-MS-7B98/events.out.tfevents.1690343291.raul-MS-7B98.5700.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c22fc5b3b13131bed3c698cd92e139e06b88b549c74100f24d7a616c8dc97710
|
3 |
+
size 560
|
runs/Jul25_22-56-04_raul-MS-7B98/events.out.tfevents.1690343798.raul-MS-7B98.15660.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a569b606e1b45bb9e28dc4969a212ef43dce2cacef23a4e89d2ce00b58b582b1
|
3 |
+
size 6954
|
runs/Jul25_22-56-04_raul-MS-7B98/events.out.tfevents.1690344692.raul-MS-7B98.15660.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63885c9236223255a82069a39ec340cf1566c53d4b35f8379929b9f5b523f259
|
3 |
+
size 560
|
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": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d97d9997ee9bdbf5807ccb789e848884f2d3126382f843aaba2405fa9e8ad5b
|
3 |
+
size 5176
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|