raulangelj commited on
Commit
ad06d89
1 Parent(s): 0eff98d

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +15 -25
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -4
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,35 +1,25 @@
1
  {
2
- "_name_or_path": "nlptown/bert-base-multilingual-uncased-sentiment",
3
- "_num_labels": 5,
4
  "architectures": [
5
- "BertForSequenceClassification"
6
  ],
7
- "attention_probs_dropout_prob": 0.1,
8
- "classifier_dropout": null,
9
- "directionality": "bidi",
10
- "finetuning_task": "sentiment-analysis",
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
  "initializer_range": 0.02,
15
- "intermediate_size": 3072,
16
- "layer_norm_eps": 1e-12,
17
  "max_position_embeddings": 512,
18
- "model_type": "bert",
19
- "num_attention_heads": 12,
20
- "num_hidden_layers": 12,
21
- "output_past": true,
22
  "pad_token_id": 0,
23
- "pooler_fc_size": 768,
24
- "pooler_num_attention_heads": 12,
25
- "pooler_num_fc_layers": 3,
26
- "pooler_size_per_head": 128,
27
- "pooler_type": "first_token_transform",
28
- "position_embedding_type": "absolute",
29
  "problem_type": "single_label_classification",
 
 
 
 
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.28.0",
32
- "type_vocab_size": 2,
33
- "use_cache": true,
34
- "vocab_size": 105879
35
  }
 
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
  "initializer_range": 0.02,
 
 
12
  "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
 
16
  "pad_token_id": 0,
 
 
 
 
 
 
17
  "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.28.0",
24
+ "vocab_size": 30522
 
 
25
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a6387261f0e04fa0399e21ab43e090524d3b4276e719d4246f6173cadfcb9e8
3
- size 669504629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4dc1fd339f0ca825857960dceb49c33b0f13ecd9f917dd3a37c5db58e1785dc
3
+ size 267855533
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,16 +1,13 @@
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
  "do_lower_case": true,
6
  "mask_token": "[MASK]",
7
- "max_len": 512,
8
  "model_max_length": 512,
9
- "never_split": null,
10
  "pad_token": "[PAD]",
11
  "sep_token": "[SEP]",
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
- "tokenizer_class": "BertTokenizer",
15
  "unk_token": "[UNK]"
16
  }
 
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
 
4
  "do_lower_case": true,
5
  "mask_token": "[MASK]",
 
6
  "model_max_length": 512,
 
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
  "unk_token": "[UNK]"
13
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad421ca584bbdf6529a50a402927d244f78cb22d2856e82772b2e9c2953f30ac
3
  size 3643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c13917a547adbfc7b7a797d55ee7da8d226ee71489972b1e5277168d6f55bec
3
  size 3643
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff