adlsdztony commited on
Commit
8f2babd
·
verified ·
1 Parent(s): e67379c

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,25 +1,27 @@
1
  {
2
- "_name_or_path": "distilbert/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
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "distilbert",
14
- "n_heads": 12,
15
- "n_layers": 6,
16
  "pad_token_id": 0,
 
17
  "problem_type": "single_label_classification",
18
- "qa_dropout": 0.1,
19
- "seq_classif_dropout": 0.2,
20
- "sinusoidal_pos_embds": false,
21
- "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.49.0",
 
 
24
  "vocab_size": 30522
25
  }
 
1
  {
2
+ "_name_or_path": "google-bert/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
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
 
 
 
 
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.49.0",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
  "vocab_size": 30522
27
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2a9f1f27f7eba8a65523120a9ac9709dbefb46394404ce8b781c6c7cfe584e9
3
- size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9103fd78731f8275697568112b439488df0ea4c8e14beb087db78ea33ab82b
3
+ size 437958648
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
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 sha256:96d2b4550ba46734b460bd8fc8947f5fd10e2f5f6b73fcfeca2d73dfede9cc5b
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d500455c95f0f7246aab9c0186abeeddd8735b2b6b5ee9c775718fc48df05d4f
3
  size 5304