tm21cy commited on
Commit
8dffd63
·
verified ·
1 Parent(s): da56919

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,13 +1,14 @@
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",
@@ -17,6 +18,7 @@
17
  "5": "LABEL_5"
18
  },
19
  "initializer_range": 0.02,
 
20
  "label2id": {
21
  "LABEL_0": 0,
22
  "LABEL_1": 1,
@@ -25,17 +27,17 @@
25
  "LABEL_4": 4,
26
  "LABEL_5": 5
27
  },
 
28
  "max_position_embeddings": 512,
29
- "model_type": "distilbert",
30
- "n_heads": 12,
31
- "n_layers": 6,
32
  "pad_token_id": 0,
 
33
  "problem_type": "single_label_classification",
34
- "qa_dropout": 0.1,
35
- "seq_classif_dropout": 0.2,
36
- "sinusoidal_pos_embds": false,
37
- "tie_weights_": true,
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.38.2",
 
 
40
  "vocab_size": 30522
41
  }
 
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",
 
18
  "5": "LABEL_5"
19
  },
20
  "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
  "label2id": {
23
  "LABEL_0": 0,
24
  "LABEL_1": 1,
 
27
  "LABEL_4": 4,
28
  "LABEL_5": 5
29
  },
30
+ "layer_norm_eps": 1e-12,
31
  "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
  "pad_token_id": 0,
36
+ "position_embedding_type": "absolute",
37
  "problem_type": "single_label_classification",
 
 
 
 
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
  "vocab_size": 30522
43
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:073c1e26e14668b8a18d967fe5d849526dc7de38821ac70fc81aba043cb86ea2
3
- size 267844872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3087a824feb655c2fdd27a770fa8858d4c077d4d247ce72ff8fee1e1b8ee1212
3
+ size 437970952
runs/Mar11_01-42-39_9d545d9a060f/events.out.tfevents.1710121381.9d545d9a060f.2401.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883176f0403422691d081e48cab45ac6c341d1cec7cb64944d2ae594af7eb1a3
3
+ size 5359
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b0680a9e25567f96abd9c0b9000512aa6602fa50094a20eeb01badc235dfa98
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d83b8b036697ed6c287b7f276abaad23827cc3a7926faacf8cdb06d5955ae1
3
  size 4920