anujsahani01 commited on
Commit
947c895
1 Parent(s): 8d6deef

Training in progress, epoch 0

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai4bharat/indic-bert",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "MBartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_probs_dropout_prob": 0,
10
+ "bos_token_id": 0,
11
+ "classifier_dropout": 0.0,
12
+ "d_model": 768,
13
+ "decoder_attention_heads": 16,
14
+ "decoder_ffn_dim": 4096,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 12,
17
+ "down_scale_factor": 1,
18
+ "dropout": 0.1,
19
+ "embedding_size": 128,
20
+ "encoder_attention_heads": 12,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 12,
24
+ "eos_token_id": 2,
25
+ "forced_eos_token_id": 2,
26
+ "gap_size": 0,
27
+ "hidden_act": "gelu",
28
+ "hidden_dropout_prob": 0,
29
+ "init_std": 0.02,
30
+ "initializer_range": 0.02,
31
+ "inner_group_num": 1,
32
+ "intermediate_size": 3072,
33
+ "is_encoder_decoder": true,
34
+ "max_position_embeddings": 512,
35
+ "model_type": "mbart",
36
+ "net_structure_type": 0,
37
+ "num_hidden_groups": 1,
38
+ "num_hidden_layers": 12,
39
+ "num_memory_blocks": 0,
40
+ "pad_token_id": 1,
41
+ "scale_embedding": false,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.30.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 200000
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d973821ce7dccb7f2ab3a092f836f0c28a93598af3f62832ebdea3b694044603
3
+ size 1563554845
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[CLS]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1173c2b6e144a02c001e289a05b5dbefddf247c50d4dcf42633158b2968fcb
3
+ size 5646064
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b45f21ae03d20a3d2fdd0dc2169843e4b0b41a7b375ce6886d705d7cde76b1
3
+ size 15285781
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "eos_token": "[CLS]",
7
+ "keep_accents": true,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "model_max_length": 512,
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "sp_model_kwargs": {},
21
+ "tokenizer_class": "AlbertTokenizer",
22
+ "unk_token": "<unk>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6565e866aa49498afbc96947fdfaa6fbd67390e95c559ae4da3a0d6bb8f6421c
3
+ size 4091