sasi2400 commited on
Commit
fa6f4e2
1 Parent(s): 74c33c5

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,19 +1,20 @@
1
  {
2
- "_name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
- "hidden_size": 384,
11
  "id2label": {
12
  "0": "Female",
13
  "1": "Male"
14
  },
15
  "initializer_range": 0.02,
16
- "intermediate_size": 1536,
17
  "label2id": {
18
  "Female": 0,
19
  "Male": 1
@@ -24,12 +25,16 @@
24
  "num_attention_heads": 12,
25
  "num_hidden_layers": 12,
26
  "pad_token_id": 0,
 
 
 
 
 
27
  "position_embedding_type": "absolute",
28
  "problem_type": "single_label_classification",
29
- "tokenizer_class": "XLMRobertaTokenizer",
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.26.0",
32
  "type_vocab_size": 2,
33
  "use_cache": true,
34
- "vocab_size": 250037
35
  }
 
1
  {
2
+ "_name_or_path": "bert-base-multilingual-cased",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
+ "directionality": "bidi",
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
  "id2label": {
13
  "0": "Female",
14
  "1": "Male"
15
  },
16
  "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
  "label2id": {
19
  "Female": 0,
20
  "Male": 1
 
25
  "num_attention_heads": 12,
26
  "num_hidden_layers": 12,
27
  "pad_token_id": 0,
28
+ "pooler_fc_size": 768,
29
+ "pooler_num_attention_heads": 12,
30
+ "pooler_num_fc_layers": 3,
31
+ "pooler_size_per_head": 128,
32
+ "pooler_type": "first_token_transform",
33
  "position_embedding_type": "absolute",
34
  "problem_type": "single_label_classification",
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.26.0",
37
  "type_vocab_size": 2,
38
  "use_cache": true,
39
+ "vocab_size": 119547
40
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e443b1989a3ebae25bf763267bf0cac0a4c9b08e006e7bcfa5cad2a3ee5622ef
3
- size 470690933
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a03d159d1ace0f652945036c9f90824e20af0bcca54113edc9b212e2c82825
3
+ size 711492725
runs/Jan25_16-24-58_fee55ac23edd/1674664022.7144568/events.out.tfevents.1674664022.fee55ac23edd.1985.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c42c97236992b4e4cba69ef8d1987cc7ab4e5d23518b6469f3a8a8e84f59a65
3
+ size 5670
runs/Jan25_16-24-58_fee55ac23edd/events.out.tfevents.1674664022.fee55ac23edd.1985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5038365d5f2403f7c1ce8021a4c66dacfb134bb21ce2927d7435dc81521156f8
3
+ size 4723
special_tokens_map.json CHANGED
@@ -1,9 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": "<mask>",
6
- "pad_token": "<pad>",
7
- "sep_token": "</s>",
8
- "unk_token": "<unk>"
9
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
7
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bae0289b9bb66bfbf85d834f6313ebd8e40f484df2bd0351539e74a0e4ddeb4
3
- size 17098081
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7529a33b1945f06664a6266d6d5eff9b5545890202e86fb05702f6f01d4b8f44
3
+ size 2919615
tokenizer_config.json CHANGED
@@ -1,21 +1,14 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
5
- "mask_token": {
6
- "__type": "AddedToken",
7
- "content": "<mask>",
8
- "lstrip": true,
9
- "normalized": true,
10
- "rstrip": false,
11
- "single_word": false
12
- },
13
- "model_max_length": 1000000000000000019884624838656,
14
- "name_or_path": "microsoft/Multilingual-MiniLM-L12-H384",
15
- "pad_token": "<pad>",
16
- "sep_token": "</s>",
17
- "sp_model_kwargs": {},
18
- "special_tokens_map_file": "/root/.cache/huggingface/hub/models--microsoft--Multilingual-MiniLM-L12-H384/snapshots/6e8c1ec6b4ec4e3fc6eb7d2cd834fcd582b61daf/special_tokens_map.json",
19
- "tokenizer_class": "XLMRobertaTokenizer",
20
- "unk_token": "<unk>"
21
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-multilingual-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7159ca1fc46db0dce023cada6f0be9f6a81e740e044dcc3cbffc96ac42114f78
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b306338565241b3acd57495bad6a78ac89e436a5add531f0a2e9ddf4a575745c
3
  size 3515
vocab.txt ADDED
The diff for this file is too large to render. See raw diff