Ransaka commited on
Commit
cc3dca9
1 Parent(s): 3105733

Model save

Browse files
Files changed (5) hide show
  1. README.md +46 -0
  2. config.json +24 -0
  3. generation_config.json +5 -0
  4. pytorch_model.bin +3 -0
  5. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: sinhala-bert-small
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # sinhala-bert-small
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
+
16
+ ## Model description
17
+
18
+ More information needed
19
+
20
+ ## Intended uses & limitations
21
+
22
+ More information needed
23
+
24
+ ## Training and evaluation data
25
+
26
+ More information needed
27
+
28
+ ## Training procedure
29
+
30
+ ### Training hyperparameters
31
+
32
+ The following hyperparameters were used during training:
33
+ - learning_rate: 5e-05
34
+ - train_batch_size: 128
35
+ - eval_batch_size: 8
36
+ - seed: 42
37
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
38
+ - lr_scheduler_type: linear
39
+ - num_epochs: 10
40
+
41
+ ### Framework versions
42
+
43
+ - Transformers 4.33.3
44
+ - Pytorch 2.0.0
45
+ - Datasets 2.14.5
46
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 384,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 1024,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 6,
16
+ "num_hidden_layers": 6,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.33.3",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.33.3"
5
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5455187f70a3740a28e2a3d0f77148bb4047601f6b29f9b9cf7cfdf831bc024f
3
+ size 83840693
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ae24cd76f255186d60f2ce7b9ae862eaf39cf68de52696792919c4697b02cd
3
+ size 4091