Hugging Face's logo

fledor
/
xnli_mbert_base_multilingual

Safetensors
bert
Model card Files
xet
Community
fledor commited on
Commit
7871b22
·
verified ·
1 Parent(s): 671e921

Upload xnli_mbert_base_multilingual model

Browse files
Files changed (8) hide show
  1. README.md +41 -0
  2. config.json +41 -0
  3. model.safetensors +3 -0
  4. model_metadata.json +10 -0
  5. special_tokens_map.json +7 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +56 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # XNLI Base Model
2
+
3
+ This model was trained on the XNLI dataset using random data selection.
4
+
5
+ ## Training Parameters
6
+
7
+ - **Dataset**: XNLI
8
+ - **Mode**: Base
9
+ - **Selection Method**: Random
10
+ - **Train Size**: 2400 examples
11
+ - **Epochs**: 8
12
+ - **Batch Size**: 16
13
+ - **Effective Batch Size**: 64 (batch_size * gradient_accumulation_steps)
14
+ - **Learning Rate**: 1e-05
15
+ - **Patience**: 6
16
+ - **Max Length**: 256
17
+ - **Gradient Accumulation Steps**: 4
18
+ - **Warmup Ratio**: 0.1
19
+ - **Weight Decay**: 0.01
20
+ - **Optimizer**: AdamW
21
+ - **Scheduler**: cosine_with_warmup
22
+ - **Random Seed**: 42
23
+
24
+ ## Performance
25
+
26
+ - **Overall Accuracy**: 65.47%
27
+ - **Overall Loss**: 0.0141
28
+
29
+ ### Language-Specific Performance
30
+ - **English (EN)**: 72.22%
31
+ - **German (DE)**: 67.60%
32
+ - **Arabic (AR)**: 63.21%
33
+ - **Spanish (ES)**: 68.72%
34
+ - **Hindi (HI)**: 62.04%
35
+ - **Swahili (SW)**: 59.00%
36
+
37
+ ## Model Information
38
+
39
+ - **Base Model**: bert-base-multilingual-cased
40
+ - **Task**: Natural Language Inference
41
+ - **Languages**: 6 languages (EN, DE, AR, ES, HI, SW)
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "pooler_fc_size": 768,
30
+ "pooler_num_attention_heads": 12,
31
+ "pooler_num_fc_layers": 3,
32
+ "pooler_size_per_head": 128,
33
+ "pooler_type": "first_token_transform",
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.50.0",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 119547
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b8bf79973816da320b45d578c0615cf166f273c18261c59869da79a3c16ec1
3
+ size 711446532
model_metadata.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "xnli-bert-base-multilingual-cased-base-random",
3
+ "description": "XNLI Multilingual Base Model - EN: 70.9%, AR: 62.7%, DE: 67.25%, ES: 67.2%",
4
+ "huggingface_url": null,
5
+ "local_path": "xnli_bert-base-multilingual-cased_bs8_ep12_lr1e-05_ts2400_p6_best",
6
+ "mode": "base",
7
+ "dataset": "xnli",
8
+ "task": "multilingual",
9
+ "source": "local"
10
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
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
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff