pczarnik commited on
Commit
3e5feda
1 Parent(s): 9476a06

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allegro/herbert-base-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-PER",
14
+ "2": "I-PER",
15
+ "3": "B-ORG",
16
+ "4": "I-ORG",
17
+ "5": "B-LOC",
18
+ "6": "I-LOC"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "B-LOC": 5,
24
+ "B-ORG": 3,
25
+ "B-PER": 1,
26
+ "I-LOC": 6,
27
+ "I-ORG": 4,
28
+ "I-PER": 2,
29
+ "O": 0
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "tokenizer_class": "HerbertTokenizerFast",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.29.2",
41
+ "type_vocab_size": 2,
42
+ "use_cache": true,
43
+ "vocab_size": 50000
44
+ }
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:f52957c59fede5f5acd59c1cb07a19320e372c4983859a0480ea0e5621f8ee8e
3
+ size 495502829
runs/May27_11-34-04_7f78f55244aa/1685187355.097302/events.out.tfevents.1685187355.7f78f55244aa.196.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f209cacf50cff1132cdde80703524229a2a8599d32b39ac9976f9e2a8d07e38
3
+ size 5907
runs/May27_11-34-04_7f78f55244aa/1685187660.332167/events.out.tfevents.1685187660.7f78f55244aa.196.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e23cd4ecaef82c55a2671e4033295c35ea7febd93f667069b9bc5810f43a891e
3
+ size 5907
runs/May27_11-34-04_7f78f55244aa/events.out.tfevents.1685187355.7f78f55244aa.196.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8061fe44f0bbd57803c2e6362aea6f7795979bc588f40bac8e7ed45689c9cec0
3
+ size 5071
runs/May27_11-34-04_7f78f55244aa/events.out.tfevents.1685187660.7f78f55244aa.196.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbb8693e8c3eab336cf3f31e9e0f9f29354f1c23847c1064ad1e80d3e2abe54
3
+ size 5543
special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "</s>",
7
+ "unk_token": "<unk>"
8
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "do_lowercase_and_remove_accent": false,
7
+ "id2lang": null,
8
+ "lang2id": null,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "HerbertTokenizer",
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edda4b14374418b756e52a24e04be2d280ca90504291515e3042336b331e372
3
+ size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff