Training in progress, epoch 1

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "mHossain/bengali_pos_v1_400000",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ADD",
+    "1": "AFX",
+    "2": "CC",
+    "3": "CD",
+    "4": "DT",
+    "5": "EX",
+    "6": "FW",
+    "7": "HYPH",
+    "8": "IN",
+    "9": "JJ",
+    "10": "JJR",
+    "11": "JJS",
+    "12": "LS",
+    "13": "MD",
+    "14": "NFP",
+    "15": "NN",
+    "16": "NNP",
+    "17": "NNPS",
+    "18": "NNS",
+    "19": "PDT",
+    "20": "POS",
+    "21": "PRP",
+    "22": "PRP$",
+    "23": "RB",
+    "24": "RBR",
+    "25": "RBS",
+    "26": "RP",
+    "27": "SYM",
+    "28": "TO",
+    "29": "UH",
+    "30": "VB",
+    "31": "VBD",
+    "32": "VBG",
+    "33": "VBN",
+    "34": "VBP",
+    "35": "VBZ",
+    "36": "WDT",
+    "37": "WP",
+    "38": "WP$",
+    "39": "WRB",
+    "40": "XX"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADD": 0,
+    "AFX": 1,
+    "CC": 2,
+    "CD": 3,
+    "DT": 4,
+    "EX": 5,
+    "FW": 6,
+    "HYPH": 7,
+    "IN": 8,
+    "JJ": 9,
+    "JJR": 10,
+    "JJS": 11,
+    "LS": 12,
+    "MD": 13,
+    "NFP": 14,
+    "NN": 15,
+    "NNP": 16,
+    "NNPS": 17,
+    "NNS": 18,
+    "PDT": 19,
+    "POS": 20,
+    "PRP": 21,
+    "PRP$": 22,
+    "RB": 23,
+    "RBR": 24,
+    "RBS": 25,
+    "RP": 26,
+    "SYM": 27,
+    "TO": 28,
+    "UH": 29,
+    "VB": 30,
+    "VBD": 31,
+    "VBG": 32,
+    "VBN": 33,
+    "VBP": 34,
+    "VBZ": 35,
+    "WDT": 36,
+    "WP": 37,
+    "WP$": 38,
+    "WRB": 39,
+    "XX": 40
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1500dede9041364a2f0edce1f4a3e6dbb61bd018b4e6c1b5fa25b540f31834e6
+size 440257060

runs/Jan01_10-31-45_8a7ecb591e18/events.out.tfevents.1704105106.8a7ecb591e18.383.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c4617390e535b705780fd6f4e5d102e183ba89e893dafd953e2f77f3bca0a8
+size 13271

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ea07d2c96b9129a50096c28a256d65444199ed78a0412f470c68876c919d37
+size 4600