Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,47 @@
+{
+ "_name_or_path": "ai4bharat/indic-bert",
+ "activation_dropout": 0.0,
+ "activation_function": "gelu",
+ "architectures": [
+ "MBartForConditionalGeneration"
+ ],
+ "attention_dropout": 0.0,
+ "attention_probs_dropout_prob": 0,
+ "bos_token_id": 0,
+ "classifier_dropout": 0.0,
+ "d_model": 768,
+ "decoder_attention_heads": 16,
+ "decoder_ffn_dim": 4096,
+ "decoder_layerdrop": 0.0,
+ "decoder_layers": 12,
+ "down_scale_factor": 1,
+ "dropout": 0.1,
+ "embedding_size": 128,
+ "encoder_attention_heads": 12,
+ "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,
+ "init_std": 0.02,
+ "initializer_range": 0.02,
+ "inner_group_num": 1,
+ "intermediate_size": 3072,
+ "is_encoder_decoder": true,
+ "max_position_embeddings": 512,
+ "model_type": "mbart",
+ "net_structure_type": 0,
+ "num_hidden_groups": 1,
+ "num_hidden_layers": 12,
+ "num_memory_blocks": 0,
+ "pad_token_id": 1,
+ "scale_embedding": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.30.2",
+ "type_vocab_size": 2,
+ "use_cache": true,
+ "vocab_size": 200000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c458b65d4b203a60888392b397283bcf6a246871db82e033a35bb474a34e262
+size 1563554845

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+ "bos_token": "[CLS]",
+ "cls_token": "[CLS]",
+ "eos_token": "[CLS]",
+ "mask_token": {
+ "content": "[MASK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<pad>",
+ "sep_token": "[SEP]",
+ "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a1173c2b6e144a02c001e289a05b5dbefddf247c50d4dcf42633158b2968fcb
+size 5646064

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b45f21ae03d20a3d2fdd0dc2169843e4b0b41a7b375ce6886d705d7cde76b1
+size 15285781

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+ "bos_token": "[CLS]",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "[CLS]",
+ "do_lower_case": true,
+ "eos_token": "[CLS]",
+ "keep_accents": true,
+ "mask_token": {
+ "__type": "AddedToken",
+ "content": "[MASK]",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "model_max_length": 512,
+ "pad_token": "<pad>",
+ "remove_space": true,
+ "sep_token": "[SEP]",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "AlbertTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a605526a38ba14fcd2ec632948a14b709d4a6a91f055744a9cb3a4f239954e
+size 4091