Upload 9 files

config.json

@@ -0,0 +1,185 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "indobenchmark/indobert-base-p1",
+    "_num_labels": 5,
+    "add_cross_attention": true,
+    "architectures": [
+      "BertModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2",
+      "3": "LABEL_3",
+      "4": "LABEL_4"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2,
+      "LABEL_3": 3,
+      "LABEL_4": 4
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.2.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50000,
+    "xla_device": null
+  },
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "indobenchmark/indobert-base-p1",
+    "_num_labels": 5,
+    "add_cross_attention": false,
+    "architectures": [
+      "BertModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2",
+      "3": "LABEL_3",
+      "4": "LABEL_4"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2,
+      "LABEL_3": 3,
+      "LABEL_4": 4
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.2.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50000,
+    "xla_device": null
+  },
+  "eos_token_id": 3,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 80,
+  "min_length": 3,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 8,
+  "pad_token_id": 0,
+  "vocab_size": 50000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b23940db6d680ceb775a453beec3fa2d36578950efa1d3bd891f3f73c3653f0a
+size 2213989099

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9faaa85f6b070ba172aeb043e21210ef0858ed204230a0686060043de01710b1
+size 1109433529

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270fefd369092a06397feb399766ee1f6488339bfc213573fcfc63cb832a2528
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/.cache/huggingface/transformers/b515a756d9ddf12a7a391ea596c488ac805f0576790934e590ce250a3e4ff056.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "indobenchmark/indobert-base-p1"}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 62.5,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.25,
+      "learning_rate": 4.647887323943662e-05,
+      "loss": 6.5392,
+      "step": 50
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 4.144869215291751e-05,
+      "loss": 4.3144,
+      "step": 100
+    },
+    {
+      "epoch": 18.75,
+      "learning_rate": 3.641851106639839e-05,
+      "loss": 3.1382,
+      "step": 150
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 3.1388329979879276e-05,
+      "loss": 2.4028,
+      "step": 200
+    },
+    {
+      "epoch": 31.25,
+      "learning_rate": 2.6358148893360163e-05,
+      "loss": 1.856,
+      "step": 250
+    },
+    {
+      "epoch": 37.5,
+      "learning_rate": 2.1327967806841047e-05,
+      "loss": 1.4456,
+      "step": 300
+    },
+    {
+      "epoch": 43.75,
+      "learning_rate": 1.6297786720321935e-05,
+      "loss": 1.1454,
+      "step": 350
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 1.1267605633802817e-05,
+      "loss": 0.935,
+      "step": 400
+    },
+    {
+      "epoch": 56.25,
+      "learning_rate": 6.237424547283703e-06,
+      "loss": 0.7969,
+      "step": 450
+    },
+    {
+      "epoch": 62.5,
+      "learning_rate": 1.2072434607645876e-06,
+      "loss": 0.721,
+      "step": 500
+    }
+  ],
+  "max_steps": 512,
+  "num_train_epochs": 64,
+  "total_flos": 14782480903421952,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634ff2b9e1ec912f965993898403d46551a77af1813c61d7c3d7559215212f95
+size 2107