airi commited on
Commit
7a694e5
1 Parent(s): 7a14935

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Jean-Baptiste/roberta-large-ner-english",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "PER",
17
+ "2": "ORG",
18
+ "3": "LOC",
19
+ "4": "MISC"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 4096,
23
+ "label2id": {
24
+ "LOC": 3,
25
+ "MISC": 4,
26
+ "O": 0,
27
+ "ORG": 2,
28
+ "PER": 1
29
+ },
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 514,
32
+ "model_type": "roberta",
33
+ "num_attention_heads": 16,
34
+ "num_hidden_layers": 24,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.19.2",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 50265
42
+ }
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:ca7e5dcd691d2ffc5714c770414c3c156de1a9f0ae6056020c232f8068b8cb44
3
+ size 1417397617
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "trim_offsets": true, "model_max_length": 512, "name_or_path": "Jean-Baptiste/roberta-large-ner-english", "special_tokens_map_file": "/home/airi/.cache/huggingface/transformers/386bbab29d21346a601dce02866bc2e2bc3c232da1d075cec3896bcabfabf227.a11ebb04664c067c8fe5ef8f8068b0f721263414a26058692f7b2e4ba2a1b342", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0acd773bfcbcca5b4a10abde8d6300de032f7c4864cd4c0ae8566d7d8241356
3
+ size 3183
vocab.json ADDED
The diff for this file is too large to render. See raw diff