Initial models

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "init_mem_cpu_alloc_delta": 2323701760,
+    "init_mem_cpu_peaked_delta": 43028480,
+    "init_mem_gpu_alloc_delta": 44382720,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1256140800,
+    "train_mem_cpu_peaked_delta": 8110080,
+    "train_mem_gpu_alloc_delta": 136292352,
+    "train_mem_gpu_peaked_delta": 22428033024,
+    "train_runtime": 3251.9473,
+    "train_samples": 130488,
+    "train_samples_per_second": 2.229
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Wikidepia/indobert-lite-squad",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0.dev0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa56d4096d9c817ace439adcd30ee72745a6ea2559a9aa2cd580bf7d300b2aa
+size 44393497

special_tokens_map.json

@@ -0,0 +1 @@
+{"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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "use_fast": true, "special_tokens_map_file": "indobert-lite-base-p2/special_tokens_map.json", "name_or_path": "Wikidepia/indobert-lite-squad", "do_basic_tokenize": true, "never_split": null}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "init_mem_cpu_alloc_delta": 2323701760,
+    "init_mem_cpu_peaked_delta": 43028480,
+    "init_mem_gpu_alloc_delta": 44382720,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 1256140800,
+    "train_mem_cpu_peaked_delta": 8110080,
+    "train_mem_gpu_alloc_delta": 136292352,
+    "train_mem_gpu_peaked_delta": 22428033024,
+    "train_runtime": 3251.9473,
+    "train_samples": 130488,
+    "train_samples_per_second": 2.229
+}

trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 7250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.793103448275862e-05,
+      "loss": 1.3311,
+      "step": 500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.586206896551724e-05,
+      "loss": 1.3174,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.3793103448275862e-05,
+      "loss": 1.2975,
+      "step": 1500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1724137931034484e-05,
+      "loss": 1.2811,
+      "step": 2000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9655172413793102e-05,
+      "loss": 1.2528,
+      "step": 2500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7586206896551724e-05,
+      "loss": 1.2374,
+      "step": 3000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5517241379310346e-05,
+      "loss": 1.2414,
+      "step": 3500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.3448275862068966e-05,
+      "loss": 0.9927,
+      "step": 4000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.1379310344827586e-05,
+      "loss": 0.9257,
+      "step": 4500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 9.310344827586207e-06,
+      "loss": 0.9237,
+      "step": 5000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.241379310344828e-06,
+      "loss": 0.9171,
+      "step": 5500
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.172413793103449e-06,
+      "loss": 0.9109,
+      "step": 6000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.103448275862069e-06,
+      "loss": 0.8931,
+      "step": 6500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0344827586206896e-06,
+      "loss": 0.878,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "step": 7250,
+      "total_flos": 8894687420252160.0,
+      "train_runtime": 3251.9473,
+      "train_samples_per_second": 2.229
+    }
+  ],
+  "max_steps": 7250,
+  "num_train_epochs": 2,
+  "total_flos": 8894687420252160.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c75f5e62b7fd0e2f79c067f162b20c4653b0f3b38fa862d245a95d9d2eeb97
+size 2287