richpsharp commited on
Commit
5e09f9f
·
verified ·
1 Parent(s): e93fd48

Training in progress, epoch 1

Browse files
Files changed (4) hide show
  1. config.json +16 -14
  2. pytorch_model.bin +2 -2
  3. tokenizer_config.json +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,35 +1,37 @@
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": "LABEL_0",
13
  "1": "LABEL_1",
14
  "2": "LABEL_2"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "LABEL_0": 0,
19
  "LABEL_1": 1,
20
  "LABEL_2": 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
  "problem_type": "single_label_classification",
28
- "qa_dropout": 0.1,
29
- "seq_classif_dropout": 0.2,
30
- "sinusoidal_pos_embds": false,
31
- "tie_weights_": true,
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.33.3",
 
 
34
  "vocab_size": 30522
35
  }
 
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": "LABEL_0",
14
  "1": "LABEL_1",
15
  "2": "LABEL_2"
16
  },
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
  "label2id": {
20
  "LABEL_0": 0,
21
  "LABEL_1": 1,
22
  "LABEL_2": 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
  "problem_type": "single_label_classification",
 
 
 
 
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.33.3",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
  "vocab_size": 30522
37
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cf61ebdbb349ea2eb711e379000ae522d5496215949a525be5e730dce05cca7
3
- size 267859050
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e459cc5e8e3dd24f8139b0c4050be327e55d3c1dee7ee635e1c98d012df809
3
+ size 438007022
tokenizer_config.json CHANGED
@@ -8,6 +8,6 @@
8
  "sep_token": "[SEP]",
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
- "tokenizer_class": "DistilBertTokenizer",
12
  "unk_token": "[UNK]"
13
  }
 
8
  "sep_token": "[SEP]",
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
  "unk_token": "[UNK]"
13
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4241f627e7584bc861f83d39d8b0bd4b35c87c20116d5d7ba2e016752288d596
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97edd741441bed0e5381452ab9d4ea5ff04a5c4159952bcf12063a871ca77b0
3
  size 4472