romainlhardy
commited on
Commit
•
c9a695c
1
Parent(s):
9d6945a
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +49 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jun26_08-07-45_9f55c9f93a4f/1656230873.4252105/events.out.tfevents.1656230873.9f55c9f93a4f.80.1 +3 -0
- runs/Jun26_08-07-45_9f55c9f93a4f/events.out.tfevents.1656230873.9f55c9f93a4f.80.0 +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 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-large",
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-PER",
|
16 |
+
"2": "I-PER",
|
17 |
+
"3": "B-ORG",
|
18 |
+
"4": "I-ORG",
|
19 |
+
"5": "B-LOC",
|
20 |
+
"6": "I-LOC",
|
21 |
+
"7": "B-MISC",
|
22 |
+
"8": "I-MISC"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"B-LOC": "5",
|
28 |
+
"B-MISC": "7",
|
29 |
+
"B-ORG": "3",
|
30 |
+
"B-PER": "1",
|
31 |
+
"I-LOC": "6",
|
32 |
+
"I-MISC": "8",
|
33 |
+
"I-ORG": "4",
|
34 |
+
"I-PER": "2",
|
35 |
+
"O": "0"
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "roberta",
|
40 |
+
"num_attention_heads": 16,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.20.1",
|
46 |
+
"type_vocab_size": 1,
|
47 |
+
"use_cache": true,
|
48 |
+
"vocab_size": 50265
|
49 |
+
}
|
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:d4d5fb96d5ea338700a095e4e10d109d697ffdb068563fee53bb6e750a2a5be6
|
3 |
+
size 1417414001
|
runs/Jun26_08-07-45_9f55c9f93a4f/1656230873.4252105/events.out.tfevents.1656230873.9f55c9f93a4f.80.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20a275f8e6e1af27ee222e0a7bee5d1554398daf7b6047b2e527cb3b9d9d5c4c
|
3 |
+
size 5350
|
runs/Jun26_08-07-45_9f55c9f93a4f/events.out.tfevents.1656230873.9f55c9f93a4f.80.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d69cea8a91147053ec03f72de6881bd0f84b733ec9f66cf8359a29ad13ad7da
|
3 |
+
size 4940
|
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-large",
|
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 sha256:007e66a8dc2ff9d67233db82ad127439d9cecab51e86123a3890ba4f2ef31626
|
3 |
+
size 3311
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|