mpalaval commited on
Commit
cebce78
·
1 Parent(s): 4bbcccf

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +16 -15
  2. pytorch_model.bin +2 -2
  3. tokenizer_config.json +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,13 +1,14 @@
1
  {
2
- "_name_or_path": "distilbert-base-cased",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForTokenClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "O",
13
  "1": "B-MethodName",
@@ -26,6 +27,7 @@
26
  "14": "I-DatasetName"
27
  },
28
  "initializer_range": 0.02,
 
29
  "label2id": {
30
  "B-DatasetName": 13,
31
  "B-HyperparameterName": 3,
@@ -43,17 +45,16 @@
43
  "I-TaskName": 12,
44
  "O": 0
45
  },
 
46
  "max_position_embeddings": 512,
47
- "model_type": "distilbert",
48
- "n_heads": 12,
49
- "n_layers": 6,
50
- "output_past": true,
51
  "pad_token_id": 0,
52
- "qa_dropout": 0.1,
53
- "seq_classif_dropout": 0.2,
54
- "sinusoidal_pos_embds": false,
55
- "tie_weights_": true,
56
  "torch_dtype": "float32",
57
  "transformers_version": "4.34.1",
 
 
58
  "vocab_size": 28996
59
  }
 
1
  {
2
+ "_name_or_path": "bert-base-cased",
 
3
  "architectures": [
4
+ "BertForTokenClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "id2label": {
13
  "0": "O",
14
  "1": "B-MethodName",
 
27
  "14": "I-DatasetName"
28
  },
29
  "initializer_range": 0.02,
30
+ "intermediate_size": 3072,
31
  "label2id": {
32
  "B-DatasetName": 13,
33
  "B-HyperparameterName": 3,
 
45
  "I-TaskName": 12,
46
  "O": 0
47
  },
48
+ "layer_norm_eps": 1e-12,
49
  "max_position_embeddings": 512,
50
+ "model_type": "bert",
51
+ "num_attention_heads": 12,
52
+ "num_hidden_layers": 12,
 
53
  "pad_token_id": 0,
54
+ "position_embedding_type": "absolute",
 
 
 
55
  "torch_dtype": "float32",
56
  "transformers_version": "4.34.1",
57
+ "type_vocab_size": 2,
58
+ "use_cache": true,
59
  "vocab_size": 28996
60
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b34dca0f6066ebec5d061a5556ffa31bdd48b65470cf233b517e5b006c798dc3
3
- size 260845154
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951741da17e413bcb8f15b64b519ad6c753ec7b240388a7e8505072d60f81ca8
3
+ size 430993062
tokenizer_config.json CHANGED
@@ -50,6 +50,6 @@
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9c27f54821fb88d8b61ced1fed4609aac22158152272bb2e173ccf3ecb2ca79
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21dcd4a623c92b683b3250a7c1dd2b2f7e5bd1ff79793904df1f7f0562b0ea4d
3
  size 4600