lekhnathrijal commited on
Commit
c67d3cf
·
verified ·
1 Parent(s): ae3403a

Training in progress, step 100

Browse files
Files changed (4) hide show
  1. config.json +16 -14
  2. model.safetensors +2 -2
  3. tokenizer_config.json +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,13 +1,14 @@
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": "d",
13
  "1": "y",
@@ -45,6 +46,7 @@
45
  "33": "positive_perception"
46
  },
47
  "initializer_range": 0.02,
 
48
  "label2id": {
49
  "accumulated wealth": 6,
50
  "business": 22,
@@ -81,14 +83,13 @@
81
  "unearned wealth": 24,
82
  "y": 1
83
  },
 
84
  "max_position_embeddings": 512,
85
- "model_type": "distilbert",
86
- "n_heads": 12,
87
- "n_layers": 6,
88
  "pad_token_id": 0,
89
- "qa_dropout": 0.1,
90
- "seq_classif_dropout": 0.2,
91
- "sinusoidal_pos_embds": false,
92
  "task_specific_params": {
93
  "classifier_config": {
94
  "multi_class": [
@@ -266,8 +267,9 @@
266
  ]
267
  }
268
  },
269
- "tie_weights_": true,
270
  "torch_dtype": "float32",
271
  "transformers_version": "4.48.1",
 
 
272
  "vocab_size": 30522
273
  }
 
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
  "id2label": {
13
  "0": "d",
14
  "1": "y",
 
46
  "33": "positive_perception"
47
  },
48
  "initializer_range": 0.02,
49
+ "intermediate_size": 3072,
50
  "label2id": {
51
  "accumulated wealth": 6,
52
  "business": 22,
 
83
  "unearned wealth": 24,
84
  "y": 1
85
  },
86
+ "layer_norm_eps": 1e-12,
87
  "max_position_embeddings": 512,
88
+ "model_type": "bert",
89
+ "num_attention_heads": 12,
90
+ "num_hidden_layers": 12,
91
  "pad_token_id": 0,
92
+ "position_embedding_type": "absolute",
 
 
93
  "task_specific_params": {
94
  "classifier_config": {
95
  "multi_class": [
 
267
  ]
268
  }
269
  },
 
270
  "torch_dtype": "float32",
271
  "transformers_version": "4.48.1",
272
+ "type_vocab_size": 2,
273
+ "use_cache": true,
274
  "vocab_size": 30522
275
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72327be2fdb8445a8acfd22e7b8ab3a64e45544baebb6877d7cb554978ff4eeb
3
- size 267931008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7191bce521f38961c8889cabb98d5a80367c3805dc63a77d7e6f8ed2c0f3f3
3
+ size 438057080
tokenizer_config.json CHANGED
@@ -52,6 +52,6 @@
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
- "tokenizer_class": "DistilBertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
 
52
  "sep_token": "[SEP]",
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
  "unk_token": "[UNK]"
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42ad9d5f1af44762dd8d3f776071382a92486d76b1d4b08042662d85e5eb2fb7
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b7906345c5485ac0efbe7f1ff99a75652593b8e03b37ee543f70f50f4ca653
3
  size 5368