ijazulhaq commited on
Commit
c16e82b
1 Parent(s): 82c057c

Model save

Browse files
Files changed (7) hide show
  1. README.md +49 -0
  2. config.json +1 -1
  3. pytorch_model.bin +2 -2
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +1 -1
  6. training_args.bin +2 -2
  7. vocab.txt +0 -0
README.md CHANGED
@@ -1,3 +1,52 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ base_model: ijazulhaq/bert-base-pashto
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: pold
8
+ results: []
9
  ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # pold
15
+
16
+ This model is a fine-tuned version of [ijazulhaq/bert-base-pashto](https://huggingface.co/ijazulhaq/bert-base-pashto) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 6e-05
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 3
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.33.0
50
+ - Pytorch 2.0.0
51
+ - Datasets 2.1.0
52
+ - Tokenizers 0.13.3
config.json CHANGED
@@ -19,7 +19,7 @@
19
  "position_embedding_type": "absolute",
20
  "problem_type": "single_label_classification",
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.27.4",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
  "vocab_size": 30000
 
19
  "position_embedding_type": "absolute",
20
  "problem_type": "single_label_classification",
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.33.0",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
  "vocab_size": 30000
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cd370a7eb73a6a78e9e37dcad7f98cd4c6aeea0708587382827f81718beff24
3
- size 436404341
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d7d81883964395f198f514ee71d78a63cbccadf5c586fcea8db8be2e55a3741
3
+ size 436399921
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "cls_token": "[CLS]",
3
  "do_basic_tokenize": true,
4
  "do_lower_case": true,
@@ -7,7 +8,6 @@
7
  "never_split": null,
8
  "pad_token": "[PAD]",
9
  "sep_token": "[SEP]",
10
- "special_tokens_map_file": null,
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
  "tokenizer_class": "BertTokenizer",
 
1
  {
2
+ "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
  "do_basic_tokenize": true,
5
  "do_lower_case": true,
 
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
 
11
  "strip_accents": null,
12
  "tokenize_chinese_chars": true,
13
  "tokenizer_class": "BertTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:496d8a5fbb29b73fca47a6ad64a47afedfdcb39fee49bbee56a6547924a11dc1
3
- size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b973753eea5a879301cd3ae5c84dbaba9345183e99a88aea8d08d7fe5df2db83
3
+ size 4027
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff