joshnielsen876 commited on
Commit
c42d7dc
1 Parent(s): db9ff0f

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +14 -16
  2. pytorch_model.bin +2 -2
  3. tokenizer_config.json +2 -2
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,36 +1,34 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
 
3
  "architectures": [
4
- "BertForSequenceClassification"
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": "Impersonal",
14
  "1": "Past",
15
  "2": "Present"
16
  },
17
  "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
  "label2id": {
20
  "Impersonal": 0,
21
  "Past": 1,
22
  "Present": 2
23
  },
24
- "layer_norm_eps": 1e-12,
25
  "max_position_embeddings": 512,
26
- "model_type": "bert",
27
- "num_attention_heads": 12,
28
- "num_hidden_layers": 12,
29
  "pad_token_id": 0,
30
- "position_embedding_type": "absolute",
 
 
 
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.26.1",
33
- "type_vocab_size": 2,
34
- "use_cache": true,
35
  "vocab_size": 30522
36
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "Impersonal",
13
  "1": "Past",
14
  "2": "Present"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "Impersonal": 0,
19
  "Past": 1,
20
  "Present": 2
21
  },
 
22
  "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
  "pad_token_id": 0,
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.26.1",
 
 
33
  "vocab_size": 30522
34
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0886c276bd94432837584a273f83ef75362a8c044d4442c46eada06c022f92ca
3
- size 438010997
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763664d2c37072d92717a012836b1c1e94a0d177399a40b25258b8baccceb259
3
+ size 267858605
tokenizer_config.json CHANGED
@@ -3,12 +3,12 @@
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
  "model_max_length": 512,
6
- "name_or_path": "bert-base-uncased",
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
10
  "strip_accents": null,
11
  "tokenize_chinese_chars": true,
12
- "tokenizer_class": "BertTokenizer",
13
  "unk_token": "[UNK]"
14
  }
 
3
  "do_lower_case": true,
4
  "mask_token": "[MASK]",
5
  "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-uncased",
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "special_tokens_map_file": null,
10
  "strip_accents": null,
11
  "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
  "unk_token": "[UNK]"
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1872d0854a67e865e361662d999041ce947fad6d3752759daece27a62363fca0
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06549722f6c25510500ef3a9c1310b29def1573dedfa0eea4b0f37f573fc443d
3
  size 3515