Upload 12 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "csebuetnlp/banglabert",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.11.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7057d50140440a4dfc051f3e9eef2dd075d11f03abc4e3222738c9fe28db8c
+size 880351213

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a667e75aedbdfc8533111cbedad354af201d4ed90237a0013bee390c7ef73967
+size 440202935

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454baa985578fa4e6b76f29aa8cb4a680f2b93746cb63bed29e496eff0dbf19f
+size 14657

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e985eb8bf02ef58974d91bc1d920b2617a41af091b03e6ddbcd3b7548fe4b3
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87b31a4f6d7c6c86fb05a846d47b963003587f8be413dabd8e691bb146ddbc4
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": false, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "csebuetnlp/banglabert", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": 73.85502277098726,
+  "best_model_checkpoint": "outputs/banglabert/checkpoint-348",
+  "epoch": 2.9941081949651847,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 6.0104,
+      "step": 1
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.7060702875399364e-05,
+      "loss": 2.8926,
+      "step": 116
+    },
+    {
+      "epoch": 0.99,
+      "eval_HasAns_exact": 54.036770583533176,
+      "eval_HasAns_f1": 67.53514335825187,
+      "eval_HasAns_total": 1251,
+      "eval_NoAns_exact": 77.61790567545964,
+      "eval_NoAns_f1": 77.61790567545964,
+      "eval_NoAns_total": 1251,
+      "eval_best_exact": 65.78737010391687,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 72.53655649127667,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 65.8273381294964,
+      "eval_f1": 72.5765245168559,
+      "eval_total": 2502,
+      "step": 116
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.8530351437699682e-05,
+      "loss": 1.5349,
+      "step": 232
+    },
+    {
+      "epoch": 1.99,
+      "eval_HasAns_exact": 57.95363709032774,
+      "eval_HasAns_f1": 71.37777157674782,
+      "eval_HasAns_total": 1251,
+      "eval_NoAns_exact": 74.74020783373301,
+      "eval_NoAns_f1": 74.74020783373301,
+      "eval_NoAns_total": 1251,
+      "eval_best_exact": 66.30695443645084,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 73.01902167966134,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 66.34692246203038,
+      "eval_f1": 73.05898970524055,
+      "eval_total": 2502,
+      "step": 232
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.0,
+      "loss": 1.3596,
+      "step": 348
+    },
+    {
+      "epoch": 2.99,
+      "eval_HasAns_exact": 58.113509192645886,
+      "eval_HasAns_f1": 71.8507329920142,
+      "eval_HasAns_total": 1251,
+      "eval_NoAns_exact": 75.85931254996004,
+      "eval_NoAns_f1": 75.85931254996004,
+      "eval_NoAns_total": 1251,
+      "eval_best_exact": 66.94644284572342,
+      "eval_best_exact_thresh": 0.0,
+      "eval_best_f1": 73.81505474540803,
+      "eval_best_f1_thresh": 0.0,
+      "eval_exact": 66.98641087130295,
+      "eval_f1": 73.85502277098726,
+      "eval_total": 2502,
+      "step": 348
+    }
+  ],
+  "max_steps": 348,
+  "num_train_epochs": 3,
+  "total_flos": 7.010369880983654e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7e8f3c56375cecd206552b943c457c34f532825daf728bd8f71525a48fb161
+size 2671