tm21cy commited on
Commit
d568275
·
verified ·
1 Parent(s): d2155be

Training in progress, step 4000

Browse files
config.json CHANGED
@@ -1,17 +1,13 @@
1
  {
2
- "_name_or_path": "albert-base-v2",
3
  "architectures": [
4
- "AlbertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0,
7
- "bos_token_id": 2,
8
- "classifier_dropout_prob": 0.1,
9
- "down_scale_factor": 1,
10
- "embedding_size": 128,
11
- "eos_token_id": 3,
12
- "gap_size": 0,
13
- "hidden_act": "gelu_new",
14
- "hidden_dropout_prob": 0,
15
  "hidden_size": 768,
16
  "id2label": {
17
  "0": "LABEL_0",
@@ -22,7 +18,6 @@
22
  "5": "LABEL_5"
23
  },
24
  "initializer_range": 0.02,
25
- "inner_group_num": 1,
26
  "intermediate_size": 3072,
27
  "label2id": {
28
  "LABEL_0": 0,
@@ -34,17 +29,15 @@
34
  },
35
  "layer_norm_eps": 1e-12,
36
  "max_position_embeddings": 512,
37
- "model_type": "albert",
38
- "net_structure_type": 0,
39
  "num_attention_heads": 12,
40
- "num_hidden_groups": 1,
41
  "num_hidden_layers": 12,
42
- "num_memory_blocks": 0,
43
  "pad_token_id": 0,
44
  "position_embedding_type": "absolute",
45
  "problem_type": "single_label_classification",
46
  "torch_dtype": "float32",
47
  "transformers_version": "4.38.2",
48
  "type_vocab_size": 2,
49
- "vocab_size": 30000
 
50
  }
 
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",
 
18
  "5": "LABEL_5"
19
  },
20
  "initializer_range": 0.02,
 
21
  "intermediate_size": 3072,
22
  "label2id": {
23
  "LABEL_0": 0,
 
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 sha256:99be2d9e1c53daba2ac6063be0125fd4fcd9182cb41dff875f908ac7a37c1e8b
3
- size 46756216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed15eaa655c34b52fb3f99fbfc6e51940dff98ab192da4fa24df4cc4d67f5a7f
3
+ size 437970952
runs/Mar11_02-44-10_53107997d4b5/events.out.tfevents.1710125050.53107997d4b5.7340.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b66b8725956719f7a36ea95d226e10e22803000e45c872c0903eeb44d7c6f16
3
- size 7396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1df5af0beae5da695febb0b7761fcd70408057823f2b754e2037b3d07737801
3
+ size 7607
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7341803b24e9f8352aa2346b85e246be75ca1f3bc0be5ae2dd30dab8a232c7e
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0e82a385dc85b5a76f530c7e140bfeced48c2fca249d832ecce6bee5c8d712c
3
  size 4920