Upload fine-tuned BanglaBERT for NER

.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

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "RemBertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 312,
+  "classifier_dropout_prob": 0.1,
+  "embedding_dropout_prob": 0,
+  "embedding_size": 256,
+  "eos_token_id": 313,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 1152,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "input_embedding_size": 256,
+  "intermediate_size": 4608,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "rembert",
+  "num_attention_heads": 18,
+  "num_hidden_layers": 32,
+  "output_embedding_size": 1664,
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250300
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f59d4ff7e9d9d7d33bc95f18d53ab25d349562954ea4aea0f47d2fbb2c72cd
+size 2298474388

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb3ef6a41a7f6df267fb3c634a0f6f3372a40b27feed38eac79bc26295e1e66
+size 4597262165

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7831349db6e854a291635f934ea3d557d042d385d3adddcde485acdb306680d3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef708965ff84334d3df334d5a400db0733214aecc7b8e5ef203457907c319bc8
+size 1064

sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79a1cc6d8e132de5e342cd7a33af66041e99257b73612d6c01a2772914d76c3
+size 16709915

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "312": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "313": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "314": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "RemBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1525,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 6.152276992797852,
+      "learning_rate": 1.3455737704918036e-05,
+      "loss": 0.2563,
+      "step": 500
+    },
+    {
+      "epoch": 3.278688524590164,
+      "grad_norm": 1.6254922151565552,
+      "learning_rate": 6.8983606557377056e-06,
+      "loss": 0.081,
+      "step": 1000
+    },
+    {
+      "epoch": 4.918032786885246,
+      "grad_norm": 0.03872436285018921,
+      "learning_rate": 3.409836065573771e-07,
+      "loss": 0.0242,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1525,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4774349102423040.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f53660b22fac363b142ef5e36b20b15fbd36a63dec8c569eb08bd7acd3a1920
+size 5304