Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,19 @@
+{
+  "<td-d>": 32004,
+  "<td-du>": 32007,
+  "<td-l>": 32003,
+  "<td-ld>": 32009,
+  "<td-ldu>": 32015,
+  "<td-lu>": 32011,
+  "<td-r>": 32002,
+  "<td-rd>": 32008,
+  "<td-rdu>": 32014,
+  "<td-rl>": 32006,
+  "<td-rld>": 32012,
+  "<td-rldu>": 32016,
+  "<td-rlu>": 32013,
+  "<td-ru>": 32010,
+  "<td-u>": 32005,
+  "<td>": 32001,
+  "<tr>": 32000
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "klue/bert-base",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32017
+}

last-checkpoint/added_tokens.json

@@ -0,0 +1,19 @@
+{
+  "<td-d>": 32004,
+  "<td-du>": 32007,
+  "<td-l>": 32003,
+  "<td-ld>": 32009,
+  "<td-ldu>": 32015,
+  "<td-lu>": 32011,
+  "<td-r>": 32002,
+  "<td-rd>": 32008,
+  "<td-rdu>": 32014,
+  "<td-rl>": 32006,
+  "<td-rld>": 32012,
+  "<td-rldu>": 32016,
+  "<td-rlu>": 32013,
+  "<td-ru>": 32010,
+  "<td-u>": 32005,
+  "<td>": 32001,
+  "<tr>": 32000
+}

last-checkpoint/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "klue/bert-base",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32017
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7468bccdd3f376b9728d6b2977c0977c40a3c9c2ddc984e1bd3e480537b380
+size 880446181

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e709852debbe95a6f40303894a5a28d7f8ecbefa9e7ab388289b5a43a8f9c9c
+size 440235825

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f645c23e52a0f83c37f08090ab1bfc030983d8596077e1a318302512fdf0eef6
+size 14503

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357c660ac16aec412f85ea115a8091d7c93f34ee70a5b0adafa9a5eaa92162c3
+size 623

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<tr>",
+    "<td>",
+    "<td-r>",
+    "<td-l>",
+    "<td-d>",
+    "<td-u>",
+    "<td-rl>",
+    "<td-du>",
+    "<td-rd>",
+    "<td-ld>",
+    "<td-ru>",
+    "<td-lu>",
+    "<td-rld>",
+    "<td-rlu>",
+    "<td-rdu>",
+    "<td-ldu>",
+    "<td-rldu>"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "klue/bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/ec2-user/.cache/huggingface/hub/models--klue--bert-base/snapshots/812449f1a6bc736e693db7aa0e513e5e90795a62/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05207248489897938,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.947927515101021e-05,
+      "loss": 2.2374,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "eval_exact_match": 49.46965745087811,
+      "eval_f1": 54.705922468625346,
+      "eval_loss": 1.399248480796814,
+      "eval_runtime": 152.8082,
+      "eval_samples_per_second": 92.96,
+      "eval_steps_per_second": 11.622,
+      "step": 500
+    }
+  ],
+  "max_steps": 28806,
+  "num_train_epochs": 3,
+  "total_flos": 1045187026944000.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776fa4ef8f6f1f166b75d3366d3aaca8741a284e685b817922477a28bd89701c
+size 3439

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e709852debbe95a6f40303894a5a28d7f8ecbefa9e7ab388289b5a43a8f9c9c
+size 440235825

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<tr>",
+    "<td>",
+    "<td-r>",
+    "<td-l>",
+    "<td-d>",
+    "<td-u>",
+    "<td-rl>",
+    "<td-du>",
+    "<td-rd>",
+    "<td-ld>",
+    "<td-ru>",
+    "<td-lu>",
+    "<td-rld>",
+    "<td-rlu>",
+    "<td-rdu>",
+    "<td-ldu>",
+    "<td-rldu>"
+  ],
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "klue/bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/ec2-user/.cache/huggingface/hub/models--klue--bert-base/snapshots/812449f1a6bc736e693db7aa0e513e5e90795a62/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776fa4ef8f6f1f166b75d3366d3aaca8741a284e685b817922477a28bd89701c
+size 3439