Amitava25 commited on
Commit
39cb733
·
verified ·
1 Parent(s): d29c5ed

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,13 +1,14 @@
1
  {
2
- "_name_or_path": "distilbert/distilbert-base-uncased",
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-ORG",
@@ -40,6 +41,7 @@
40
  "28": "I-LAWYER"
41
  },
42
  "initializer_range": 0.02,
 
43
  "label2id": {
44
  "B-CASE_NUMBER": 19,
45
  "B-COURT": 15,
@@ -71,16 +73,16 @@
71
  "I-WITNESS": 6,
72
  "O": 0
73
  },
 
74
  "max_position_embeddings": 512,
75
- "model_type": "distilbert",
76
- "n_heads": 12,
77
- "n_layers": 6,
78
  "pad_token_id": 0,
79
- "qa_dropout": 0.1,
80
- "seq_classif_dropout": 0.2,
81
- "sinusoidal_pos_embds": false,
82
- "tie_weights_": true,
83
  "torch_dtype": "float32",
84
  "transformers_version": "4.48.3",
 
 
85
  "vocab_size": 30522
86
  }
 
1
  {
2
+ "_name_or_path": "bert-base-uncased",
 
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-ORG",
 
41
  "28": "I-LAWYER"
42
  },
43
  "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
  "label2id": {
46
  "B-CASE_NUMBER": 19,
47
  "B-COURT": 15,
 
73
  "I-WITNESS": 6,
74
  "O": 0
75
  },
76
+ "layer_norm_eps": 1e-12,
77
  "max_position_embeddings": 512,
78
+ "model_type": "bert",
79
+ "num_attention_heads": 12,
80
+ "num_hidden_layers": 12,
81
  "pad_token_id": 0,
82
+ "position_embedding_type": "absolute",
 
 
 
83
  "torch_dtype": "float32",
84
  "transformers_version": "4.48.3",
85
+ "type_vocab_size": 2,
86
+ "use_cache": true,
87
  "vocab_size": 30522
88
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:798eb195be13d2a7116db8a7e7d698ffa483980039f5bcded20977243158fa5c
3
- size 265553068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbcb5918ea251ec0df812d94135603937f9b6a673a5942176faf62e011fe9b75
3
+ size 435679140
runs/Feb24_18-19-59_92734c0b55b6/events.out.tfevents.1740421201.92734c0b55b6.1334.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200dcbdecacbcf47c6375c0a9d527edfd243ceae5857c9251ea2070dc596d25c
3
+ size 7060
tokenizer_config.json CHANGED
@@ -51,6 +51,6 @@
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
- "tokenizer_class": "DistilBertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
 
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4322e5bdd4db85d96357c87e9c15b9e7deb27905aa4cd00c1106cabd4475b2c
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1093ffd5ba32861a7f15a2bd54cfd6b3dc481ea2d0f7cf85ffe86121c3ab5bbd
3
  size 5368