Hemg commited on
Commit
aceddeb
·
verified ·
1 Parent(s): 8cdb00b

Training in progress, epoch 0

Browse files
Files changed (4) hide show
  1. config.json +15 -17
  2. model.safetensors +2 -2
  3. tokenizer_config.json +2 -3
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,14 +1,13 @@
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": "admiration",
14
  "1": "amusement",
@@ -40,7 +39,6 @@
40
  "27": "neutral"
41
  },
42
  "initializer_range": 0.02,
43
- "intermediate_size": 3072,
44
  "label2id": {
45
  "admiration": 0,
46
  "amusement": 1,
@@ -71,17 +69,17 @@
71
  "sadness": 25,
72
  "surprise": 26
73
  },
74
- "layer_norm_eps": 1e-12,
75
  "max_position_embeddings": 512,
76
- "model_type": "bert",
77
- "num_attention_heads": 12,
78
- "num_hidden_layers": 12,
79
  "pad_token_id": 0,
80
- "position_embedding_type": "absolute",
81
  "problem_type": "single_label_classification",
 
 
 
 
82
  "torch_dtype": "float32",
83
- "transformers_version": "4.48.0.dev0",
84
- "type_vocab_size": 2,
85
- "use_cache": true,
86
  "vocab_size": 30522
87
  }
 
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": "admiration",
13
  "1": "amusement",
 
39
  "27": "neutral"
40
  },
41
  "initializer_range": 0.02,
 
42
  "label2id": {
43
  "admiration": 0,
44
  "amusement": 1,
 
69
  "sadness": 25,
70
  "surprise": 26
71
  },
 
72
  "max_position_embeddings": 512,
73
+ "model_type": "distilbert",
74
+ "n_heads": 12,
75
+ "n_layers": 6,
76
  "pad_token_id": 0,
 
77
  "problem_type": "single_label_classification",
78
+ "qa_dropout": 0.1,
79
+ "seq_classif_dropout": 0.2,
80
+ "sinusoidal_pos_embds": false,
81
+ "tie_weights_": true,
82
  "torch_dtype": "float32",
83
+ "transformers_version": "4.44.2",
 
 
84
  "vocab_size": 30522
85
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:581d78a90a3087b89387bc54fe90959f3c6e481d5e2c30ca51d8f1fabc5644b5
3
- size 438038624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f261b607022ed954b947910f0ff0f6fa51f83c5a2e4282d60cfb96b976f684a
3
+ size 267912544
tokenizer_config.json CHANGED
@@ -41,16 +41,15 @@
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": false,
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
- "extra_special_tokens": {},
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
  "strip_accents": null,
53
  "tokenize_chinese_chars": true,
54
- "tokenizer_class": "BertTokenizer",
55
  "unk_token": "[UNK]"
56
  }
 
41
  "special": true
42
  }
43
  },
44
+ "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
 
47
  "mask_token": "[MASK]",
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be39b00d16e2bc8bd348979d32c39a1fa7cbce862e8fab77d8ac092032426daa
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c818e211038864cd7efefd05c1584ba4bd8f1966948092bef088ee70cae885
3
+ size 5176