first commit

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "akahana/indonesia-roberta-small",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "SEDIH",
+    "1": "MARAH",
+    "2": "CINTA",
+    "3": "TAKUT",
+    "4": "BAHAGIA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "SEDIH": 0,
+    "MARAH": 1,
+    "CINTA": 2,
+    "TAKUT": 3,
+    "BAHAGIA": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 128,
+  "model_type": "roberta",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 1.1938421075994319
+mcc = 0.4171890558712776

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "./output/cache", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 1, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 120, "model_name": "akahana/indonesia-roberta-small", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 200, "optimizer": "AdamW", "output_dir": "./output", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": false, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": "./output/logs", "thread_count": null, "tokenizer_name": "akahana/indonesia-roberta-small", "tokenizer_type": null, "train_batch_size": 64, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 672, "weight_decay": 0.0, "model_class": "ClassificationModel", "labels_list": [0, 1, 2, 3, 4], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094abc62a56b9caea7f34559d0628bc49438e3d0d28bec47863d90e0fc4729a5
+size 89864557

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "akahana/indonesia-roberta-small", "do_lower_case": false, "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe78300b433f1ff5e93347f1a841555f9f285407c39763e9fd60043de36bb205
+size 3183

training_progress_scores.csv

@@ -0,0 +1,21 @@
+global_step,train_loss,mcc,eval_loss
+56,1.703125,-0.0019305380904196326,1.5958140980113635
+112,1.4873046875,0.005282590717631199,1.5764781605113636
+168,1.2998046875,0.11676109113057202,1.5544766512784092
+224,1.3544921875,0.14158701565344484,1.523138982599432
+280,1.173828125,0.20613957603262087,1.4820700905539772
+336,0.99462890625,0.280371305204426,1.375296297940341
+392,0.85400390625,0.31748112574302373,1.3328968394886365
+448,0.80224609375,0.3923794544700449,1.268456476384943
+504,0.87890625,0.4171646523395207,1.231695556640625
+560,0.43359375,0.4397805793731963,1.2022810502485795
+616,1.3134765625,0.4171890558712776,1.1938421075994319
+672,0.599609375,0.40775564601370196,1.2256167325106535
+728,0.2271728515625,0.42256508023959105,1.195064197887074
+784,1.126953125,0.4138079889042665,1.2281960227272728
+840,0.52783203125,0.4501827655037085,1.2430343627929688
+896,0.1387939453125,0.42081066882996965,1.2674077814275568
+952,0.1405029296875,0.42361303087220126,1.3108964399857954
+1008,1.3798828125,0.43090089141849447,1.3714685613458806
+1064,0.132080078125,0.39719076936342657,1.367802013050426
+1120,0.12353515625,0.42008997375928464,1.4051096135919745