Training in progress, epoch 0

config.json

@@ -1,47 +1,58 @@
 {
-  "_name_or_path": "ai4bharat/indic-bert",
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
   "architectures": [
     "MBartForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "attention_probs_dropout_prob": 0,
   "bos_token_id": 0,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "down_scale_factor": 1,
+  "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "embedding_size": 128,
-  "encoder_attention_heads": 12,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
-  "gap_size": 0,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
   "init_std": 0.02,
-  "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
   "is_encoder_decoder": true,
-  "max_position_embeddings": 512,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 200,
+  "max_position_embeddings": 1024,
   "model_type": "mbart",
-  "net_structure_type": 0,
-  "num_hidden_groups": 1,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
+  "output_past": true,
   "pad_token_id": 1,
-  "scale_embedding": false,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 200000
+  "vocab_size": 250055
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:089119de54d5bcd2751c2006150497822b0ecb2a3829b22a717e111e102c8de3
-size 1563554845
+oid sha256:a664d1fbaf8692686d55a9abfff0de15c1d1be809230f4ff69c62bfa62367a9f
+size 2444698141

special_tokens_map.json

@@ -1,15 +1,63 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[CLS]",
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "af_ZA",
+    "az_AZ",
+    "bn_IN",
+    "fa_IR",
+    "he_IL",
+    "hr_HR",
+    "id_ID",
+    "ka_GE",
+    "km_KH",
+    "mk_MK",
+    "ml_IN",
+    "mn_MN",
+    "mr_IN",
+    "pl_PL",
+    "ps_AF",
+    "pt_XX",
+    "sv_SE",
+    "sw_KE",
+    "ta_IN",
+    "te_IN",
+    "th_TH",
+    "tl_XX",
+    "uk_UA",
+    "ur_PK",
+    "xh_ZA",
+    "gl_ES",
+    "sl_SI"
+  ],
+  "bos_token": "</s>",
+  "cls_token": "<s>",
+  "eos_token": "<CLS>",
+  "mask_token": "<mask>",
   "pad_token": "<pad>",
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b45f21ae03d20a3d2fdd0dc2169843e4b0b41a7b375ce6886d705d7cde76b1
-size 15285781
+oid sha256:e1d4485f24d88d0e8f390de6f5f30f1964698389669dd3b255ca28726400d566
+size 17110207

tokenizer_config.json

@@ -1,23 +1,76 @@
 {
-  "bos_token": "[CLS]",
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "af_ZA",
+    "az_AZ",
+    "bn_IN",
+    "fa_IR",
+    "he_IL",
+    "hr_HR",
+    "id_ID",
+    "ka_GE",
+    "km_KH",
+    "mk_MK",
+    "ml_IN",
+    "mn_MN",
+    "mr_IN",
+    "pl_PL",
+    "ps_AF",
+    "pt_XX",
+    "sv_SE",
+    "sw_KE",
+    "ta_IN",
+    "te_IN",
+    "th_TH",
+    "tl_XX",
+    "uk_UA",
+    "ur_PK",
+    "xh_ZA",
+    "gl_ES",
+    "sl_SI"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[CLS]",
-  "keep_accents": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "__type": "AddedToken",
-    "content": "[MASK]",
+    "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "AlbertTokenizer",
+  "src_lang": "en_XX",
+  "tgt_lang": "mr_IN",
+  "tokenizer_class": "MBart50Tokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2a6be4ad3a5c1599c59eaa7b3a6b997826d01a17612aff760d592079c4961a5
+oid sha256:5c0b1da1d65b7e347abee72cef40777894bf3b4de2c1ed750ab336f0f49555d6
 size 4091