Upload files.

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mesolitica/roberta-base-bahasa-cased",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d48a8505f1775591638cc4e624e79542cf5ff85f702b4e65d3d27e5141c517
+size 442630808

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65f784b2c3fdc3d56a5818754a01447737d0d794743c5f9e0a05a41abb5d9f0
+size 885332026

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f106bfcbd686e8b855232ab7c41b4be450bb3de5f98229d5fe27ba5803d0b583
+size 14244

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6df9dfd412ce829d568e7cf6a0b84757b2de22ed4d0b9a396c29b9de8077b1c
+size 1000

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/trainer_state.json

@@ -0,0 +1,612 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 5361,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05595970900951315,
+      "grad_norm": 0.3892979919910431,
+      "learning_rate": 4.9067338183174786e-05,
+      "loss": 0.999,
+      "step": 100
+    },
+    {
+      "epoch": 0.1119194180190263,
+      "grad_norm": 0.46390068531036377,
+      "learning_rate": 4.813467636634956e-05,
+      "loss": 0.069,
+      "step": 200
+    },
+    {
+      "epoch": 0.1119194180190263,
+      "eval_loss": 0.0693167895078659,
+      "eval_runtime": 65.2632,
+      "eval_samples_per_second": 109.526,
+      "eval_steps_per_second": 13.698,
+      "step": 200
+    },
+    {
+      "epoch": 0.16787912702853947,
+      "grad_norm": 0.4610772430896759,
+      "learning_rate": 4.7202014549524345e-05,
+      "loss": 0.0704,
+      "step": 300
+    },
+    {
+      "epoch": 0.2238388360380526,
+      "grad_norm": 0.3780522644519806,
+      "learning_rate": 4.626935273269912e-05,
+      "loss": 0.0709,
+      "step": 400
+    },
+    {
+      "epoch": 0.2238388360380526,
+      "eval_loss": 0.06821341067552567,
+      "eval_runtime": 66.0174,
+      "eval_samples_per_second": 108.274,
+      "eval_steps_per_second": 13.542,
+      "step": 400
+    },
+    {
+      "epoch": 0.27979854504756574,
+      "grad_norm": 0.3591707646846771,
+      "learning_rate": 4.5336690915873905e-05,
+      "loss": 0.0696,
+      "step": 500
+    },
+    {
+      "epoch": 0.33575825405707893,
+      "grad_norm": 0.3536950945854187,
+      "learning_rate": 4.440402909904869e-05,
+      "loss": 0.0719,
+      "step": 600
+    },
+    {
+      "epoch": 0.33575825405707893,
+      "eval_loss": 0.06779901683330536,
+      "eval_runtime": 65.7656,
+      "eval_samples_per_second": 108.689,
+      "eval_steps_per_second": 13.594,
+      "step": 600
+    },
+    {
+      "epoch": 0.39171796306659207,
+      "grad_norm": 0.3251872956752777,
+      "learning_rate": 4.347136728222347e-05,
+      "loss": 0.0702,
+      "step": 700
+    },
+    {
+      "epoch": 0.4476776720761052,
+      "grad_norm": 0.5228525400161743,
+      "learning_rate": 4.253870546539825e-05,
+      "loss": 0.0701,
+      "step": 800
+    },
+    {
+      "epoch": 0.4476776720761052,
+      "eval_loss": 0.06743032485246658,
+      "eval_runtime": 65.2227,
+      "eval_samples_per_second": 109.594,
+      "eval_steps_per_second": 13.707,
+      "step": 800
+    },
+    {
+      "epoch": 0.5036373810856184,
+      "grad_norm": 0.42002952098846436,
+      "learning_rate": 4.160604364857303e-05,
+      "loss": 0.0669,
+      "step": 900
+    },
+    {
+      "epoch": 0.5595970900951315,
+      "grad_norm": 0.29522764682769775,
+      "learning_rate": 4.067338183174781e-05,
+      "loss": 0.0683,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5595970900951315,
+      "eval_loss": 0.0664479210972786,
+      "eval_runtime": 65.5976,
+      "eval_samples_per_second": 108.967,
+      "eval_steps_per_second": 13.629,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6155567991046447,
+      "grad_norm": 0.3274015784263611,
+      "learning_rate": 3.974072001492259e-05,
+      "loss": 0.0721,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6715165081141579,
+      "grad_norm": 0.38934898376464844,
+      "learning_rate": 3.880805819809737e-05,
+      "loss": 0.0697,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6715165081141579,
+      "eval_loss": 0.06659408658742905,
+      "eval_runtime": 65.335,
+      "eval_samples_per_second": 109.405,
+      "eval_steps_per_second": 13.683,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7274762171236709,
+      "grad_norm": 0.34380605816841125,
+      "learning_rate": 3.787539638127216e-05,
+      "loss": 0.0675,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7834359261331841,
+      "grad_norm": 0.4435211718082428,
+      "learning_rate": 3.6942734564446934e-05,
+      "loss": 0.069,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7834359261331841,
+      "eval_loss": 0.06618547439575195,
+      "eval_runtime": 65.6162,
+      "eval_samples_per_second": 108.937,
+      "eval_steps_per_second": 13.625,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8393956351426972,
+      "grad_norm": 0.3766339123249054,
+      "learning_rate": 3.601007274762172e-05,
+      "loss": 0.069,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8953553441522104,
+      "grad_norm": 0.37429243326187134,
+      "learning_rate": 3.5077410930796494e-05,
+      "loss": 0.0671,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8953553441522104,
+      "eval_loss": 0.06602194160223007,
+      "eval_runtime": 65.8243,
+      "eval_samples_per_second": 108.592,
+      "eval_steps_per_second": 13.582,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9513150531617236,
+      "grad_norm": 0.3283040225505829,
+      "learning_rate": 3.414474911397128e-05,
+      "loss": 0.0695,
+      "step": 1700
+    },
+    {
+      "epoch": 1.0072747621712368,
+      "grad_norm": 0.3410968780517578,
+      "learning_rate": 3.3212087297146054e-05,
+      "loss": 0.0638,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0072747621712368,
+      "eval_loss": 0.06569492071866989,
+      "eval_runtime": 65.2116,
+      "eval_samples_per_second": 109.612,
+      "eval_steps_per_second": 13.709,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0632344711807498,
+      "grad_norm": 0.3739614486694336,
+      "learning_rate": 3.227942548032084e-05,
+      "loss": 0.0401,
+      "step": 1900
+    },
+    {
+      "epoch": 1.119194180190263,
+      "grad_norm": 0.3098587393760681,
+      "learning_rate": 3.1346763663495614e-05,
+      "loss": 0.0379,
+      "step": 2000
+    },
+    {
+      "epoch": 1.119194180190263,
+      "eval_loss": 0.06665665656328201,
+      "eval_runtime": 65.3418,
+      "eval_samples_per_second": 109.394,
+      "eval_steps_per_second": 13.682,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1751538891997761,
+      "grad_norm": 0.38271355628967285,
+      "learning_rate": 3.04141018466704e-05,
+      "loss": 0.0406,
+      "step": 2100
+    },
+    {
+      "epoch": 1.2311135982092893,
+      "grad_norm": 0.3953482508659363,
+      "learning_rate": 2.948144002984518e-05,
+      "loss": 0.0412,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2311135982092893,
+      "eval_loss": 0.06673873960971832,
+      "eval_runtime": 65.5404,
+      "eval_samples_per_second": 109.063,
+      "eval_steps_per_second": 13.64,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2870733072188025,
+      "grad_norm": 0.2780703604221344,
+      "learning_rate": 2.854877821301996e-05,
+      "loss": 0.0411,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3430330162283157,
+      "grad_norm": 0.3112993836402893,
+      "learning_rate": 2.761611639619474e-05,
+      "loss": 0.042,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3430330162283157,
+      "eval_loss": 0.06677699089050293,
+      "eval_runtime": 65.4909,
+      "eval_samples_per_second": 109.145,
+      "eval_steps_per_second": 13.651,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3989927252378287,
+      "grad_norm": 0.34681084752082825,
+      "learning_rate": 2.668345457936952e-05,
+      "loss": 0.0412,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4549524342473419,
+      "grad_norm": 0.4000672996044159,
+      "learning_rate": 2.57507927625443e-05,
+      "loss": 0.0402,
+      "step": 2600
+    },
+    {
+      "epoch": 1.4549524342473419,
+      "eval_loss": 0.0668577179312706,
+      "eval_runtime": 65.4051,
+      "eval_samples_per_second": 109.288,
+      "eval_steps_per_second": 13.669,
+      "step": 2600
+    },
+    {
+      "epoch": 1.510912143256855,
+      "grad_norm": 0.3226698338985443,
+      "learning_rate": 2.4818130945719083e-05,
+      "loss": 0.0382,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5668718522663683,
+      "grad_norm": 0.36106088757514954,
+      "learning_rate": 2.3885469128893863e-05,
+      "loss": 0.0447,
+      "step": 2800
+    },
+    {
+      "epoch": 1.5668718522663683,
+      "eval_loss": 0.06671204417943954,
+      "eval_runtime": 65.3441,
+      "eval_samples_per_second": 109.39,
+      "eval_steps_per_second": 13.681,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6228315612758815,
+      "grad_norm": 0.4615354537963867,
+      "learning_rate": 2.2952807312068643e-05,
+      "loss": 0.043,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6787912702853944,
+      "grad_norm": 0.35336604714393616,
+      "learning_rate": 2.2020145495243423e-05,
+      "loss": 0.041,
+      "step": 3000
+    },
+    {
+      "epoch": 1.6787912702853944,
+      "eval_loss": 0.06641455739736557,
+      "eval_runtime": 65.5257,
+      "eval_samples_per_second": 109.087,
+      "eval_steps_per_second": 13.643,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7347509792949076,
+      "grad_norm": 0.3950590491294861,
+      "learning_rate": 2.1087483678418206e-05,
+      "loss": 0.0418,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7907106883044208,
+      "grad_norm": 0.31117650866508484,
+      "learning_rate": 2.0154821861592986e-05,
+      "loss": 0.0418,
+      "step": 3200
+    },
+    {
+      "epoch": 1.7907106883044208,
+      "eval_loss": 0.06663373112678528,
+      "eval_runtime": 65.346,
+      "eval_samples_per_second": 109.387,
+      "eval_steps_per_second": 13.681,
+      "step": 3200
+    },
+    {
+      "epoch": 1.846670397313934,
+      "grad_norm": 0.3356647491455078,
+      "learning_rate": 1.9222160044767766e-05,
+      "loss": 0.0411,
+      "step": 3300
+    },
+    {
+      "epoch": 1.9026301063234472,
+      "grad_norm": 0.37761080265045166,
+      "learning_rate": 1.828949822794255e-05,
+      "loss": 0.0412,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9026301063234472,
+      "eval_loss": 0.06634122133255005,
+      "eval_runtime": 65.518,
+      "eval_samples_per_second": 109.1,
+      "eval_steps_per_second": 13.645,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9585898153329602,
+      "grad_norm": 0.3452881872653961,
+      "learning_rate": 1.735683641111733e-05,
+      "loss": 0.0404,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0145495243424736,
+      "grad_norm": 0.26575422286987305,
+      "learning_rate": 1.642417459429211e-05,
+      "loss": 0.0392,
+      "step": 3600
+    },
+    {
+      "epoch": 2.0145495243424736,
+      "eval_loss": 0.066836878657341,
+      "eval_runtime": 65.3703,
+      "eval_samples_per_second": 109.346,
+      "eval_steps_per_second": 13.676,
+      "step": 3600
+    },
+    {
+      "epoch": 2.0705092333519866,
+      "grad_norm": 0.2628268003463745,
+      "learning_rate": 1.5491512777466892e-05,
+      "loss": 0.0237,
+      "step": 3700
+    },
+    {
+      "epoch": 2.1264689423614995,
+      "grad_norm": 0.22387896478176117,
+      "learning_rate": 1.455885096064167e-05,
+      "loss": 0.0237,
+      "step": 3800
+    },
+    {
+      "epoch": 2.1264689423614995,
+      "eval_loss": 0.06771736592054367,
+      "eval_runtime": 65.2177,
+      "eval_samples_per_second": 109.602,
+      "eval_steps_per_second": 13.708,
+      "step": 3800
+    },
+    {
+      "epoch": 2.182428651371013,
+      "grad_norm": 0.2680613696575165,
+      "learning_rate": 1.3626189143816454e-05,
+      "loss": 0.0247,
+      "step": 3900
+    },
+    {
+      "epoch": 2.238388360380526,
+      "grad_norm": 0.20846977829933167,
+      "learning_rate": 1.2693527326991233e-05,
+      "loss": 0.0241,
+      "step": 4000
+    },
+    {
+      "epoch": 2.238388360380526,
+      "eval_loss": 0.06801700592041016,
+      "eval_runtime": 65.2857,
+      "eval_samples_per_second": 109.488,
+      "eval_steps_per_second": 13.694,
+      "step": 4000
+    },
+    {
+      "epoch": 2.2943480693900393,
+      "grad_norm": 0.23785445094108582,
+      "learning_rate": 1.1760865510166013e-05,
+      "loss": 0.0256,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3503077783995523,
+      "grad_norm": 0.33284828066825867,
+      "learning_rate": 1.0828203693340795e-05,
+      "loss": 0.0246,
+      "step": 4200
+    },
+    {
+      "epoch": 2.3503077783995523,
+      "eval_loss": 0.0681551992893219,
+      "eval_runtime": 65.4022,
+      "eval_samples_per_second": 109.293,
+      "eval_steps_per_second": 13.669,
+      "step": 4200
+    },
+    {
+      "epoch": 2.4062674874090657,
+      "grad_norm": 0.31610041856765747,
+      "learning_rate": 9.895541876515575e-06,
+      "loss": 0.0255,
+      "step": 4300
+    },
+    {
+      "epoch": 2.4622271964185787,
+      "grad_norm": 0.32548844814300537,
+      "learning_rate": 8.962880059690356e-06,
+      "loss": 0.0245,
+      "step": 4400
+    },
+    {
+      "epoch": 2.4622271964185787,
+      "eval_loss": 0.06827463954687119,
+      "eval_runtime": 65.6158,
+      "eval_samples_per_second": 108.937,
+      "eval_steps_per_second": 13.625,
+      "step": 4400
+    },
+    {
+      "epoch": 2.5181869054280916,
+      "grad_norm": 0.3038158714771271,
+      "learning_rate": 8.030218242865136e-06,
+      "loss": 0.0245,
+      "step": 4500
+    },
+    {
+      "epoch": 2.574146614437605,
+      "grad_norm": 0.2560817301273346,
+      "learning_rate": 7.097556426039919e-06,
+      "loss": 0.0245,
+      "step": 4600
+    },
+    {
+      "epoch": 2.574146614437605,
+      "eval_loss": 0.06810575723648071,
+      "eval_runtime": 65.6936,
+      "eval_samples_per_second": 108.808,
+      "eval_steps_per_second": 13.609,
+      "step": 4600
+    },
+    {
+      "epoch": 2.630106323447118,
+      "grad_norm": 0.2895735800266266,
+      "learning_rate": 6.1648946092146994e-06,
+      "loss": 0.0253,
+      "step": 4700
+    },
+    {
+      "epoch": 2.6860660324566314,
+      "grad_norm": 0.3214573264122009,
+      "learning_rate": 5.23223279238948e-06,
+      "loss": 0.0261,
+      "step": 4800
+    },
+    {
+      "epoch": 2.6860660324566314,
+      "eval_loss": 0.06796491146087646,
+      "eval_runtime": 65.5418,
+      "eval_samples_per_second": 109.06,
+      "eval_steps_per_second": 13.64,
+      "step": 4800
+    },
+    {
+      "epoch": 2.7420257414661444,
+      "grad_norm": 0.21886736154556274,
+      "learning_rate": 4.299570975564261e-06,
+      "loss": 0.0259,
+      "step": 4900
+    },
+    {
+      "epoch": 2.7979854504756574,
+      "grad_norm": 0.2672884166240692,
+      "learning_rate": 3.366909158739041e-06,
+      "loss": 0.0245,
+      "step": 5000
+    },
+    {
+      "epoch": 2.7979854504756574,
+      "eval_loss": 0.06810774654150009,
+      "eval_runtime": 65.4563,
+      "eval_samples_per_second": 109.203,
+      "eval_steps_per_second": 13.658,
+      "step": 5000
+    },
+    {
+      "epoch": 2.853945159485171,
+      "grad_norm": 0.32406413555145264,
+      "learning_rate": 2.4342473419138224e-06,
+      "loss": 0.0257,
+      "step": 5100
+    },
+    {
+      "epoch": 2.9099048684946838,
+      "grad_norm": 0.29316550493240356,
+      "learning_rate": 1.5015855250886029e-06,
+      "loss": 0.0251,
+      "step": 5200
+    },
+    {
+      "epoch": 2.9099048684946838,
+      "eval_loss": 0.06802687793970108,
+      "eval_runtime": 65.7583,
+      "eval_samples_per_second": 108.701,
+      "eval_steps_per_second": 13.595,
+      "step": 5200
+    },
+    {
+      "epoch": 2.965864577504197,
+      "grad_norm": 0.3688699007034302,
+      "learning_rate": 5.689237082633837e-07,
+      "loss": 0.0255,
+      "step": 5300
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5361,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5643471742304256.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/checkpoint-5361/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2fb41f71ec262fcdc41e70d7a669b55340ad52fa1053c6a85e06d8e4d71e85
+size 5240

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mesolitica/roberta-base-bahasa-cased",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d48a8505f1775591638cc4e624e79542cf5ff85f702b4e65d3d27e5141c517
+size 442630808

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

RoBERTa-MalayMLMFineTuned/fine_tuned_roberta_withAdamW/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

logs_RoBERTa-MalayMLMFineTuned/logs_fine_tuned_roberta_withAdamW/events.out.tfevents.1729663037.bda43b643f18.264.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2aaf1f0a5c67b96b38cc4ad02f5016144f960c71c22bc5fe4207c4074f4b88
+size 5113

logs_RoBERTa-MalayMLMFineTuned/logs_fine_tuned_roberta_withAdamW/events.out.tfevents.1729674677.e2bae6e39360.602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6417fc9495a25081668cd6201311c5b6b8814b6d7c2d0d2de5a8e9e71d392f26
+size 23692