Added IndoLEM

IndoLEM/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "indolem/indobert-base-uncased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "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": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31923
+}

IndoLEM/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e108a042cfad43ec459fc55ac20f22f3d2f466d5e4d07470392eefdf82c40e
+size 879868645

IndoLEM/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84eea664a1f8167bb38f130c48a8c4c7c13c78a568f1213d56d516050dc4c79a
+size 439947057

IndoLEM/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0602e2a6a5cf5cbe7d3d739fb45e623ba4f48cf0ba6de8583e8e33895b84d8ce
+size 14503

IndoLEM/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0d744449ee6c1a9cd7e89246bac9e67ce6e92b4068c224fdbd1eaf0415945f
+size 623

IndoLEM/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

IndoLEM/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "indolem/indobert-base-uncased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/0d67a06ab0513afc9134e37589e146c1ca823a21a00c36d3fc0c1646a69ce972.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

IndoLEM/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "global_step": 3160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.208860759493671e-05,
+      "loss": 1.608,
+      "step": 500
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 3.4177215189873416e-05,
+      "loss": 0.6735,
+      "step": 1000
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 2.626582278481013e-05,
+      "loss": 0.4976,
+      "step": 1500
+    },
+    {
+      "epoch": 12.66,
+      "learning_rate": 1.8354430379746836e-05,
+      "loss": 0.3982,
+      "step": 2000
+    },
+    {
+      "epoch": 15.82,
+      "learning_rate": 1.0443037974683544e-05,
+      "loss": 0.3188,
+      "step": 2500
+    },
+    {
+      "epoch": 18.99,
+      "learning_rate": 2.531645569620253e-06,
+      "loss": 0.2669,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3160,
+  "num_train_epochs": 20,
+  "total_flos": 1.321116402057216e+16,
+  "trial_name": null,
+  "trial_params": null
+}

IndoLEM/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5584f0851de67667f4deccd9eaea50f20678806e6eb52f65355079b4844f0e5e
+size 3311