anujsahani01 commited on
Commit
ff4582e
1 Parent(s): 291badc

Training in progress, epoch 0

Browse files
config.json CHANGED
@@ -1,47 +1,58 @@
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
  }
 
1
  {
2
+ "_name_or_path": "facebook/mbart-large-50",
3
+ "_num_labels": 3,
4
  "activation_dropout": 0.0,
5
  "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
  "architectures": [
9
  "MBartForConditionalGeneration"
10
  ],
11
  "attention_dropout": 0.0,
 
12
  "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
  "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
  "decoder_attention_heads": 16,
17
  "decoder_ffn_dim": 4096,
18
  "decoder_layerdrop": 0.0,
19
  "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
  "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
  "encoder_ffn_dim": 4096,
25
  "encoder_layerdrop": 0.0,
26
  "encoder_layers": 12,
27
  "eos_token_id": 2,
28
  "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
  "init_std": 0.02,
 
 
 
36
  "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_length": 200,
43
+ "max_position_embeddings": 1024,
44
  "model_type": "mbart",
45
+ "normalize_before": true,
46
+ "normalize_embedding": true,
47
+ "num_beams": 5,
48
  "num_hidden_layers": 12,
49
+ "output_past": true,
50
  "pad_token_id": 1,
51
+ "scale_embedding": true,
52
+ "static_position_embeddings": false,
53
+ "tokenizer_class": "MBart50Tokenizer",
54
  "torch_dtype": "float32",
55
  "transformers_version": "4.30.2",
 
56
  "use_cache": true,
57
+ "vocab_size": 250055
58
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:089119de54d5bcd2751c2006150497822b0ecb2a3829b22a717e111e102c8de3
3
- size 1563554845
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a664d1fbaf8692686d55a9abfff0de15c1d1be809230f4ff69c62bfa62367a9f
3
+ size 2444698141
special_tokens_map.json CHANGED
@@ -1,15 +1,63 @@
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
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "</s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "<CLS>",
59
+ "mask_token": "<mask>",
60
  "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
  "unk_token": "<unk>"
63
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05b45f21ae03d20a3d2fdd0dc2169843e4b0b41a7b375ce6886d705d7cde76b1
3
- size 15285781
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d4485f24d88d0e8f390de6f5f30f1964698389669dd3b255ca28726400d566
3
+ size 17110207
tokenizer_config.json CHANGED
@@ -1,23 +1,76 @@
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
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
  "clean_up_tokenization_spaces": true,
58
+ "cls_token": "<s>",
59
+ "eos_token": "</s>",
 
 
60
  "mask_token": {
61
  "__type": "AddedToken",
62
+ "content": "<mask>",
63
  "lstrip": true,
64
+ "normalized": true,
65
  "rstrip": false,
66
  "single_word": false
67
  },
68
  "model_max_length": 512,
69
  "pad_token": "<pad>",
70
+ "sep_token": "</s>",
 
71
  "sp_model_kwargs": {},
72
+ "src_lang": "en_XX",
73
+ "tgt_lang": "mr_IN",
74
+ "tokenizer_class": "MBart50Tokenizer",
75
  "unk_token": "<unk>"
76
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2a6be4ad3a5c1599c59eaa7b3a6b997826d01a17612aff760d592079c4961a5
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0b1da1d65b7e347abee72cef40777894bf3b4de2c1ed750ab336f0f49555d6
3
  size 4091