Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "csebuetnlp/banglabert",
+  "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": "0",
+    "1": "1-5_err",
+    "2": "2_err",
+    "3": "begin_err",
+    "4": "del_err",
+    "5": "end_err",
+    "6": "one_word_err",
+    "7": "punc_insert_err"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1-5_err": 1,
+    "2_err": 2,
+    "begin_err": 3,
+    "del_err": 4,
+    "end_err": 5,
+    "one_word_err": 6,
+    "punc_insert_err": 7
+  },
+  "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,
+  "task_specific_params": {
+    "finetuned": true
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97a01ef0c9cf5ab55573541c020f69350a7193a786138e1d42112eb77868c8c
+size 440204333

runs/Mar01_22-47-52_home-3090/1677689285.148785/events.out.tfevents.1677689285.home-3090.22209.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b03254576ab47fb66d727f88f5cf3f5b40ba6fdb8317951f110b13a79269d4
+size 5541

runs/Mar01_22-47-52_home-3090/events.out.tfevents.1677689285.home-3090.22209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a80a8c8028265aa46ba469f70757d4cae10d45af5a1765f82761510cab542cf3
+size 7343

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "csebuetnlp/banglabert",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "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:a2d2ac8a3d8b8a36039aa82b80a4067442d8adce92ed1e64c59c97c14a83c754
+size 3451