AriaStarkh commited on
Commit
e3c1eb1
1 Parent(s): a4ec346

Training in progress, step 42

Browse files
config.json CHANGED
@@ -1,13 +1,15 @@
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",
@@ -61,6 +63,7 @@
61
  "49": "LABEL_49"
62
  },
63
  "initializer_range": 0.02,
 
64
  "label2id": {
65
  "LABEL_0": 0,
66
  "LABEL_1": 1,
@@ -113,17 +116,19 @@
113
  "LABEL_8": 8,
114
  "LABEL_9": 9
115
  },
 
116
  "max_position_embeddings": 512,
117
- "model_type": "distilbert",
118
- "n_heads": 12,
119
- "n_layers": 6,
120
  "pad_token_id": 0,
 
 
121
  "problem_type": "single_label_classification",
122
- "qa_dropout": 0.1,
123
- "seq_classif_dropout": 0.2,
124
- "sinusoidal_pos_embds": false,
125
- "tie_weights_": true,
126
  "torch_dtype": "float32",
127
  "transformers_version": "4.46.3",
 
 
128
  "vocab_size": 30522
129
  }
 
1
  {
2
+ "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
 
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "cell": {},
8
+ "classifier_dropout": null,
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
  "id2label": {
14
  "0": "LABEL_0",
15
  "1": "LABEL_1",
 
63
  "49": "LABEL_49"
64
  },
65
  "initializer_range": 0.02,
66
+ "intermediate_size": 1200,
67
  "label2id": {
68
  "LABEL_0": 0,
69
  "LABEL_1": 1,
 
116
  "LABEL_8": 8,
117
  "LABEL_9": 9
118
  },
119
+ "layer_norm_eps": 1e-12,
120
  "max_position_embeddings": 512,
121
+ "model_type": "bert",
122
+ "num_attention_heads": 12,
123
+ "num_hidden_layers": 4,
124
  "pad_token_id": 0,
125
+ "position_embedding_type": "absolute",
126
+ "pre_trained": "",
127
  "problem_type": "single_label_classification",
128
+ "structure": [],
 
 
 
129
  "torch_dtype": "float32",
130
  "transformers_version": "4.46.3",
131
+ "type_vocab_size": 2,
132
+ "use_cache": true,
133
  "vocab_size": 30522
134
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edc1bef311fcea51df2bd17d35e3b41be09787ac31461aea85df42c94ee6e644
3
- size 267980224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d3d32b5679e2c458d1b2b346d314d96fffee4dbb0a796a68e9df71dcbfcb91
3
+ size 57471904
runs/Dec16_15-03-02_c53344d78de6/events.out.tfevents.1734361421.c53344d78de6.295.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624883e7651f321b93c7eecb7813b2bf5abe176b01b3a6dbea31625d25b3121f
3
+ size 7382
runs/Dec16_15-11-25_c53344d78de6/events.out.tfevents.1734361900.c53344d78de6.295.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d45a8ad16370350a189cc659e912ad56f030bc44a87a6e26dc004ca71582c1
3
+ size 7501
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": {
10
  "strategy": "BatchLongest",
11
  "direction": "Right",
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": {
5
  "strategy": "BatchLongest",
6
  "direction": "Right",
tokenizer_config.json CHANGED
@@ -41,15 +41,17 @@
41
  "special": true
42
  }
43
  },
44
- "clean_up_tokenization_spaces": false,
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
  }
 
41
  "special": true
42
  }
43
  },
44
+ "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
  "pad_token": "[PAD]",
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:b4be3aded3a9d8dd6d9c5c92cebcc6334ba062055e82284a7c71bbdb7ac5ffd2
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f774ec1f0aaafd84737fa2ba92eac8ceb73f0a4b26b803de336210995e4cfa37
3
  size 5240