Bajiyo/my-finetuned-transliteration-model

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: ai4bharat/IndicBART
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+This model is a fine-tuned version of [ai4bharat/IndicBART](https://huggingface.co/ai4bharat/IndicBART) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0863
+- Wer: 0.4892
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Wer    |
+|:-------------:|:------:|:-----:|:---------------:|:------:|
+| 1.4597        | 0.4504 | 4000  | 0.3822          | 0.6293 |
+| 0.3574        | 0.9008 | 8000  | 0.2432          | 0.5683 |
+| 0.252         | 1.3512 | 12000 | 0.1656          | 0.5286 |
+| 0.1921        | 1.8016 | 16000 | 0.1277          | 0.5102 |
+| 0.1583        | 2.2520 | 20000 | 0.1074          | 0.5010 |
+| 0.1383        | 2.7024 | 24000 | 0.0967          | 0.4937 |
+| 0.1266        | 3.1528 | 28000 | 0.0896          | 0.4904 |
+| 0.1199        | 3.6032 | 32000 | 0.0863          | 0.4892 |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.1.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.1

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "</s>": 64001,
+  "<2as>": 64002,
+  "<2bn>": 64003,
+  "<2en>": 64004,
+  "<2gu>": 64005,
+  "<2hi>": 64006,
+  "<2kn>": 64007,
+  "<2ml>": 64008,
+  "<2mr>": 64009,
+  "<2or>": 64010,
+  "<2pa>": 64011,
+  "<2ta>": 64012,
+  "<2te>": 64013,
+  "<s>": 64000
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "ai4bharat/IndicBART",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 64000,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 64001,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "tokenizer_class": "AlbertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 64014
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 64000,
+  "eos_token_id": 64001,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41e325222bc6de83f0c0cf3ba53f584582800148fc4905ebd3fa649b60539ae
+size 976355336

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<s>",
+    "</s>",
+    "<2as>",
+    "<2bn>",
+    "<2en>",
+    "<2gu>",
+    "<2hi>",
+    "<2kn>",
+    "<2ml>",
+    "<2mr>",
+    "<2or>",
+    "<2pa>",
+    "<2ta>",
+    "<2te>"
+  ],
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "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 sha256:9d924c4e4e0d7a073e8289c20e29cd27657629064f2571fb18ab82008cf79a72
+size 1898704

tokenizer_config.json

@@ -0,0 +1,187 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64002": {
+      "content": "<2as>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64003": {
+      "content": "<2bn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64004": {
+      "content": "<2en>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64005": {
+      "content": "<2gu>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64006": {
+      "content": "<2hi>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64007": {
+      "content": "<2kn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64008": {
+      "content": "<2ml>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64009": {
+      "content": "<2mr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64010": {
+      "content": "<2or>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64011": {
+      "content": "<2pa>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64012": {
+      "content": "<2ta>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64013": {
+      "content": "<2te>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>",
+    "</s>",
+    "<2as>",
+    "<2bn>",
+    "<2en>",
+    "<2gu>",
+    "<2hi>",
+    "<2kn>",
+    "<2ml>",
+    "<2mr>",
+    "<2or>",
+    "<2pa>",
+    "<2ta>",
+    "<2te>"
+  ],
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ef9919bc8d6ff2cf9467910d4e290b6dadad183709d3c8dcb2451e242f65f2
+size 5304