Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +51 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Jean-Baptiste/camembert-ner",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 6,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "I-PER",
|
16 |
+
"1": "B-ORG",
|
17 |
+
"2": "B-LOC",
|
18 |
+
"3": "B-HumanProd",
|
19 |
+
"4": "O",
|
20 |
+
"5": "I-HumanProd",
|
21 |
+
"6": "B-PER",
|
22 |
+
"7": "I-ORG",
|
23 |
+
"8": "I-LOC"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"B-HumanProd": 3,
|
29 |
+
"B-LOC": 2,
|
30 |
+
"B-ORG": 1,
|
31 |
+
"B-PER": 6,
|
32 |
+
"I-HumanProd": 5,
|
33 |
+
"I-LOC": 8,
|
34 |
+
"I-ORG": 7,
|
35 |
+
"I-PER": 0,
|
36 |
+
"O": 4
|
37 |
+
},
|
38 |
+
"layer_norm_eps": 1e-05,
|
39 |
+
"max_position_embeddings": 514,
|
40 |
+
"model_type": "camembert",
|
41 |
+
"num_attention_heads": 12,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"output_past": true,
|
44 |
+
"pad_token_id": 1,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.25.1",
|
48 |
+
"type_vocab_size": 1,
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 32005
|
51 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97356af1574e6faa49949db4c2dd5bddf986e8ff0f7257c6c09f0033054f2a81
|
3 |
+
size 440226095
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
3 |
+
size 810912
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": "<mask>",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"__type": "AddedToken",
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"model_max_length": 512,
|
18 |
+
"name_or_path": "Jean-Baptiste/camembert-ner",
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"special_tokens_map_file": "C:\\Users\\Sammy/.cache\\huggingface\\hub\\models--Jean-Baptiste--camembert-ner\\snapshots\\9f8b2203b6a2daba1ad279ac2adb822518caa167\\special_tokens_map.json",
|
23 |
+
"tokenizer_class": "CamembertTokenizer",
|
24 |
+
"unk_token": "<unk>"
|
25 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:527472f85a4917004e00f895ac1541d21906127cba0e1c92e00c6e6b2ca7b47d
|
3 |
+
size 3375
|