first commit

README.md

@@ -0,0 +1,23 @@
+---
+language: "id"
+widget:
+- text: "dia orang yang baik ya bunds."
+---
+
+## how to use
+
+```python
+from transformers import pipeline, set_seed
+
+path = "akahana/indonesia-emotion-analysis-roberta-base"
+emotion = pipeline('text-classification', 
+                     model=path,device=0)
+set_seed(42)
+
+kalimat = "dia orang yang baik ya bunds."
+preds = emotion(kalimat)
+preds
+
+[{'label': 'HAPPY', 'score': 0.8790940046310425}]
+
+```

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "flax-community/indonesian-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "SADNESS",
+    "1": "ANGER",
+    "2": "LOVE",
+    "3": "FEAR",
+    "4": "HAPPY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "SADNESS": 0,
+    "ANGER": 1,
+    "LOVE": 2,
+    "FEAR": 3,
+    "HAPPY": 4
+  },
+  "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",
+  "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 = 0.958326495777477
+mcc = 0.6253168804343301

logs/events.out.tfevents.1638825687.84b999b21d57.180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a425742ba1cdc9e1bf25a0a402402459666a0a487d9ef741e8b2fcceff6fe4ff
+size 40

logs/events.out.tfevents.1638825757.84b999b21d57.395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab5c4cd12303374f4f9f669c5892cfdb6119eede0016be2a7b9ce7518dac1bd
+size 40

logs/events.out.tfevents.1638825835.84b999b21d57.589.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6114e3f931cb03bdb90bf5555ff1b0e905d542415391331d51830699e61fc94
+size 40

logs/events.out.tfevents.1638825994.84b999b21d57.659.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e08b5819da9a878db4b40c803e7d18fe65e40552f5404a6ee1e507e9baa2330
+size 5811

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": 2, "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": 0.0001, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": 42, "max_grad_norm": 1.0, "max_seq_length": 256, "model_name": "flax-community/indonesian-roberta-base", "model_type": "roberta", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 10, "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": "flax-community/indonesian-roberta-base", "tokenizer_type": null, "train_batch_size": 16, "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": 133, "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:b1418c12a48de36b26a3d2b059299175cef5073e005396fedb13d6ae9764b225
+size 498683309

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": "flax-community/indonesian-roberta-base", "do_lower_case": false, "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cab09402fae91d47e517626c4d13b73c28151f2c0c27edf88a8beb6d4e50314
+size 3183

training_progress_scores.csv

@@ -0,0 +1,12 @@
+global_step,train_loss,mcc,eval_loss
+221,0.7861328125,0.5322008350854679,1.009612343528054
+442,0.08428955078125,0.6253168804343301,0.958326495777477
+663,3.033203125,0.6177684182141293,1.1226650324734775
+884,0.0022411346435546875,0.6177940443273168,1.6422297109257091
+1105,0.0008072853088378906,0.6185759700126116,1.9670504540205003
+1326,0.0001817941665649414,0.6371818915052692,1.964775475859642
+1547,0.0006866455078125,0.6373244049448687,2.0347287462516266
+1768,9.465217590332031e-05,0.6061004518366452,2.1262989894910294
+1989,0.0006518363952636719,0.6154561216565886,2.2048887759447098
+2000,0.00023237615823745728,0.6154561216565886,2.206093869426034
+2210,0.0003991127014160156,0.62709325229009,2.206396930597045