Training in progress, step 10000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,6 @@
+---
+mask_token: "[MASK]"
+widget:
+  - text: 대한민국의 수도는 [MASK]입니다.
+---
+![image](https://i.imgur.com/brETMw6.jpg)

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Bingsu/my_mobilebert_untrained",
+  "architectures": [
+    "MobileBertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

last-checkpoint/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Bingsu/my_mobilebert_untrained",
+  "architectures": [
+    "MobileBertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f86b7c1030ebca2a6c99c8f28aa18cf67208a00e08fce91eea733b0bec240d
+size 586826597

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf968dcd05b6ea7291b9aeb7e5ef41b98d5f49af58bdfb3e0c4d109ecd867493
+size 146774203

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61fc86e3bcf87c025896dabb3d26ce5ca4103ec874557dd3084c738eb61ad888
+size 14503

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22a3cb16dddcf5c937c1bec07637df13115b6ed917ca6d1cf2116057954b0ce
+size 559

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3821f79e5d56fda48d85057de6b8b28f1ffc595c942da877ef01bd25d14ff514
+size 733553608

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "Bingsu/my_mobilebert_untrained",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,316 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04297249330703417,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0004000105276443632,
+      "loss": 10.1199,
+      "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00040004211053127486,
+      "loss": 9.997,
+      "step": 400
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.000400094748522194,
+      "loss": 9.9386,
+      "step": 600
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00040016844138622554,
+      "loss": 9.8988,
+      "step": 800
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0004002631888001141,
+      "loss": 9.8579,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0004003789903482477,
+      "loss": 9.8159,
+      "step": 1200
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0004005158455226594,
+      "loss": 9.7867,
+      "step": 1400
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0004006737537230326,
+      "loss": 9.7605,
+      "step": 1600
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0004008527142566991,
+      "loss": 9.7357,
+      "step": 1800
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0004010527263386479,
+      "loss": 9.7138,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00040127378909152016,
+      "loss": 9.6894,
+      "step": 2200
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.000401515901545621,
+      "loss": 9.6634,
+      "step": 2400
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00040177906263891804,
+      "loss": 9.6451,
+      "step": 2600
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00040206327121705167,
+      "loss": 9.6279,
+      "step": 2800
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00040236852603333685,
+      "loss": 9.6038,
+      "step": 3000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0004026948257487631,
+      "loss": 9.5874,
+      "step": 3200
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00040304216893201697,
+      "loss": 9.5729,
+      "step": 3400
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004034105540594666,
+      "loss": 9.547,
+      "step": 3600
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004037999795151858,
+      "loss": 9.5348,
+      "step": 3800
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004042104435909525,
+      "loss": 9.5207,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004046419444862573,
+      "loss": 9.5061,
+      "step": 4200
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004050944803083139,
+      "loss": 9.493,
+      "step": 4400
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004055680490720661,
+      "loss": 9.4782,
+      "step": 4600
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004060626487001964,
+      "loss": 9.4636,
+      "step": 4800
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0004065782770231313,
+      "loss": 9.4546,
+      "step": 5000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.000407114931779062,
+      "loss": 9.4453,
+      "step": 5200
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00040767261061393917,
+      "loss": 9.4174,
+      "step": 5400
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00040825131108149573,
+      "loss": 9.4159,
+      "step": 5600
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00040885103064325357,
+      "loss": 9.3993,
+      "step": 5800
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00040947176666852707,
+      "loss": 9.3953,
+      "step": 6000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00041011351643444917,
+      "loss": 9.3854,
+      "step": 6200
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004107762771259713,
+      "loss": 9.3679,
+      "step": 6400
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004114600458358809,
+      "loss": 9.3595,
+      "step": 6600
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00041216481956481664,
+      "loss": 9.3504,
+      "step": 6800
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00041289059522127414,
+      "loss": 9.3417,
+      "step": 7000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004136373696216229,
+      "loss": 9.3275,
+      "step": 7200
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004144051394901274,
+      "loss": 9.3201,
+      "step": 7400
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004151939014589469,
+      "loss": 9.3123,
+      "step": 7600
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004160036520681667,
+      "loss": 9.3084,
+      "step": 7800
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0004168343877657965,
+      "loss": 9.2954,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00041768179413688954,
+      "loss": 9.2862,
+      "step": 8200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00041855438410810103,
+      "loss": 9.283,
+      "step": 8400
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00041944794797888797,
+      "loss": 9.2711,
+      "step": 8600
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00042036248182962185,
+      "loss": 9.2726,
+      "step": 8800
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004212979816486783,
+      "loss": 9.2621,
+      "step": 9000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00042225444333247354,
+      "loss": 9.2527,
+      "step": 9200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004232318626854678,
+      "loss": 9.2453,
+      "step": 9400
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0004242302354201949,
+      "loss": 9.2314,
+      "step": 9600
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000425249557157276,
+      "loss": 9.2337,
+      "step": 9800
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00042628982342543184,
+      "loss": 9.2276,
+      "step": 10000
+    }
+  ],
+  "max_steps": 1000000,
+  "num_train_epochs": 5,
+  "total_flos": 1.593829982208e+16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c33b030231937c49711cbb55890f65b86f81a68638a6a5c30e4f67ed0b41b6f
+size 3375

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf968dcd05b6ea7291b9aeb7e5ef41b98d5f49af58bdfb3e0c4d109ecd867493
+size 146774203

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "Bingsu/my_mobilebert_untrained",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c33b030231937c49711cbb55890f65b86f81a68638a6a5c30e4f67ed0b41b6f
+size 3375