k4tel commited on
Commit
e36df8d
·
1 Parent(s): 5eb953b

Model save

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md CHANGED
@@ -1,3 +1,47 @@
1
  ---
2
- license: openrail
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: bert-geolocation-prediction
7
+ results: []
8
  ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # bert-geolocation-prediction
14
+
15
+ This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 8
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 3
41
+
42
+ ### Framework versions
43
+
44
+ - Transformers 4.23.1
45
+ - Pytorch 1.11.0+cu102
46
+ - Datasets 2.1.0
47
+ - Tokenizers 0.12.1
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertGeoRegressor"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "directionality": "bidi",
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert-geo-regressor",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "pooler_fc_size": 768,
19
+ "pooler_num_attention_heads": 12,
20
+ "pooler_num_fc_layers": 3,
21
+ "pooler_size_per_head": 128,
22
+ "pooler_type": "first_token_transform",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.23.1",
25
+ "type_vocab_size": 2,
26
+ "vocab_size": 119547
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7624d9e456ab13265c8c0860c51ae9c48300554b0eb3c1bc46875abed2f3a8ee
3
+ size 711543661
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_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "bert-base-multilingual-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab6fdd49d925c2befeaa9bcc47e8b66b1120c29354f0e9fe5dc32701773e737
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff