Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +57 -0
- pytorch_model.bin +3 -0
- runs/Aug16_00-02-27_jordy-OMEN/1660600958.875375/events.out.tfevents.1660600958.jordy-OMEN.51415.1 +3 -0
- runs/Aug16_00-02-27_jordy-OMEN/events.out.tfevents.1660600958.jordy-OMEN.51415.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertCRF"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bias_0": null,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"freeze": false,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "I-entity"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"I-entity": 1,
|
22 |
+
"O": 0
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 12,
|
28 |
+
"num_hidden_layers": 12,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler": "last",
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"subword_alignment": "first",
|
33 |
+
"test_args": {
|
34 |
+
"CRF": true,
|
35 |
+
"Y": "ner_tags",
|
36 |
+
"dataset": "conll2003",
|
37 |
+
"lowC": true,
|
38 |
+
"model": "bert-base-cased",
|
39 |
+
"setting": "conll2003",
|
40 |
+
"subword_alignment": "first",
|
41 |
+
"task": "ner",
|
42 |
+
"train_args": {
|
43 |
+
"batch_size": 2,
|
44 |
+
"classifier_lr": 0.001,
|
45 |
+
"epochs": 3,
|
46 |
+
"learning_rate": 2e-05,
|
47 |
+
"warmup_ratio": 0.1,
|
48 |
+
"weight_decay": 0.01
|
49 |
+
}
|
50 |
+
},
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.18.0",
|
53 |
+
"type_vocab_size": 2,
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 28996,
|
56 |
+
"weight_0": 0.01
|
57 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d330f6d4aebf06c4060add26c8b66a092b87a98660e552ba4dff1832d1f654d5
|
3 |
+
size 433319143
|
runs/Aug16_00-02-27_jordy-OMEN/1660600958.875375/events.out.tfevents.1660600958.jordy-OMEN.51415.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff633e56a7653595d18dd34794b5c813ff6049828f6576c2ea70c788255091ba
|
3 |
+
size 4946
|
runs/Aug16_00-02-27_jordy-OMEN/events.out.tfevents.1660600958.jordy-OMEN.51415.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a633c74d28d857b296c86bce2025fb6b56b894c280c9dbf2a9e396049a42c610
|
3 |
+
size 6724
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:299b476ca2a03ec30d115debb3e1a0cd1f8583f1e7a4ec26a0a6c9ca7e24a5a9
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|