anyuanay commited on
Commit
8f171b3
1 Parent(s): 118c0fe

End of training

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: distilbert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - wnut_17
8
+ model-index:
9
+ - name: tmp_trainer
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # tmp_trainer
17
+
18
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3.0
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.33.2
52
+ - Pytorch 2.0.1+cu118
53
+ - Datasets 2.14.5
54
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "O",
13
+ "1": "B-corporation",
14
+ "2": "I-corporation",
15
+ "3": "B-creative-work",
16
+ "4": "I-creative-work",
17
+ "5": "B-group",
18
+ "6": "I-group",
19
+ "7": "B-location",
20
+ "8": "I-location",
21
+ "9": "B-person",
22
+ "10": "I-person",
23
+ "11": "B-product",
24
+ "12": "I-product"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "label2id": {
28
+ "B-corporation": 1,
29
+ "B-creative-work": 3,
30
+ "B-group": 5,
31
+ "B-location": 7,
32
+ "B-person": 9,
33
+ "B-product": 11,
34
+ "I-corporation": 2,
35
+ "I-creative-work": 4,
36
+ "I-group": 6,
37
+ "I-location": 8,
38
+ "I-person": 10,
39
+ "I-product": 12,
40
+ "O": 0
41
+ },
42
+ "max_position_embeddings": 512,
43
+ "model_type": "distilbert",
44
+ "n_heads": 12,
45
+ "n_layers": 6,
46
+ "pad_token_id": 0,
47
+ "qa_dropout": 0.1,
48
+ "seq_classif_dropout": 0.2,
49
+ "sinusoidal_pos_embds": false,
50
+ "tie_weights_": true,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.33.2",
53
+ "vocab_size": 30522
54
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5d77a1a190c935f63238f12b9c744e6d65bb902d9b9722bf77923bf0b2075c
3
+ size 265526309
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce77629635a7a6a2df8b69e27ef3ba8ee785dad4df29c1e4eb487e9aefbd77b0
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff