Hugging Face's logo

bjbjbj
/
classifier-chapter4

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
bjbjbj commited on
Commit
63da15c
·
verified ·
1 Parent(s): b23b589

Training in progress, step 500

Browse files
Files changed (3) hide show
  1. config.json +15 -17
  2. model.safetensors +2 -2
  3. training_args.bin +2 -2
config.json CHANGED
@@ -1,14 +1,13 @@
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",
@@ -16,24 +15,23 @@
16
  "3": "LABEL_3"
17
  },
18
  "initializer_range": 0.02,
19
- "intermediate_size": 3072,
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
23
  "LABEL_2": 2,
24
  "LABEL_3": 3
25
  },
26
- "layer_norm_eps": 1e-12,
27
  "max_position_embeddings": 512,
28
- "model_type": "bert",
29
- "num_attention_heads": 12,
30
- "num_hidden_layers": 12,
31
  "pad_token_id": 0,
32
- "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
 
 
 
 
34
  "torch_dtype": "float32",
35
- "transformers_version": "4.46.3",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
  "vocab_size": 30522
39
  }
 
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
  "id2label": {
12
  "0": "LABEL_0",
13
  "1": "LABEL_1",
 
15
  "3": "LABEL_3"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "LABEL_0": 0,
20
  "LABEL_1": 1,
21
  "LABEL_2": 2,
22
  "LABEL_3": 3
23
  },
 
24
  "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
  "pad_token_id": 0,
 
29
  "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
  "torch_dtype": "float32",
35
+ "transformers_version": "4.45.2",
 
 
36
  "vocab_size": 30522
37
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f4296c56cc36a7dcc10aa3c1a1c3e538a5d32536d0c20ec99e38666d76061a0
3
- size 437964800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:215e3ddd3d566bc1d02d91bf67f96fc1edf80f7e5b3b065d80934356002d9491
3
+ size 267838720
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc4ec6d6526b6cd8320d3514e4a314b486dc8464cd1231a5c6bda852a7d7de3c
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84dc8b371743f0deff3d0bf344a8e5e67d76ae4854cc8a128a8f23e74cdd63e5
3
+ size 5176