Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +81 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-PERSON",
|
16 |
+
"2": "I-PERSON",
|
17 |
+
"3": "L-PERSON",
|
18 |
+
"4": "U-PERSON",
|
19 |
+
"5": "B-NORP",
|
20 |
+
"6": "I-NORP",
|
21 |
+
"7": "L-NORP",
|
22 |
+
"8": "U-NORP",
|
23 |
+
"9": "B-DATE",
|
24 |
+
"10": "I-DATE",
|
25 |
+
"11": "L-DATE",
|
26 |
+
"12": "U-DATE",
|
27 |
+
"13": "B-USERID",
|
28 |
+
"14": "I-USERID",
|
29 |
+
"15": "L-USERID",
|
30 |
+
"16": "U-USERID",
|
31 |
+
"17": "B-ORG",
|
32 |
+
"18": "I-ORG",
|
33 |
+
"19": "L-ORG",
|
34 |
+
"20": "U-ORG",
|
35 |
+
"21": "B-LOCATION",
|
36 |
+
"22": "I-LOCATION",
|
37 |
+
"23": "L-LOCATION",
|
38 |
+
"24": "U-LOCATION"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"label2id": {
|
43 |
+
"B-DATE": 9,
|
44 |
+
"B-LOCATION": 21,
|
45 |
+
"B-NORP": 5,
|
46 |
+
"B-ORG": 17,
|
47 |
+
"B-PERSON": 1,
|
48 |
+
"B-USERID": 13,
|
49 |
+
"I-DATE": 10,
|
50 |
+
"I-LOCATION": 22,
|
51 |
+
"I-NORP": 6,
|
52 |
+
"I-ORG": 18,
|
53 |
+
"I-PERSON": 2,
|
54 |
+
"I-USERID": 14,
|
55 |
+
"L-DATE": 11,
|
56 |
+
"L-LOCATION": 23,
|
57 |
+
"L-NORP": 7,
|
58 |
+
"L-ORG": 19,
|
59 |
+
"L-PERSON": 3,
|
60 |
+
"L-USERID": 15,
|
61 |
+
"O": 0,
|
62 |
+
"U-DATE": 12,
|
63 |
+
"U-LOCATION": 24,
|
64 |
+
"U-NORP": 8,
|
65 |
+
"U-ORG": 20,
|
66 |
+
"U-PERSON": 4,
|
67 |
+
"U-USERID": 16
|
68 |
+
},
|
69 |
+
"layer_norm_eps": 1e-05,
|
70 |
+
"max_position_embeddings": 514,
|
71 |
+
"model_type": "roberta",
|
72 |
+
"num_attention_heads": 12,
|
73 |
+
"num_hidden_layers": 12,
|
74 |
+
"pad_token_id": 1,
|
75 |
+
"position_embedding_type": "absolute",
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.26.1",
|
78 |
+
"type_vocab_size": 1,
|
79 |
+
"use_cache": true,
|
80 |
+
"vocab_size": 50265
|
81 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb7e89446de2f87ef7072b3c41a4565596ffd0f49bd9183383a4f2e682ba326f
|
3 |
+
size 496369773
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"errors": "replace",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"model_max_length": 512,
|
9 |
+
"name_or_path": "roberta-base",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"tokenizer_class": "RobertaTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43c97c84be7b09a25e9f840616a51ad116358faf681cc33edfba5ddefbf749f3
|
3 |
+
size 3451
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|