Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,19 @@
+{
+  "<td-d>": 32504,
+  "<td-du>": 32507,
+  "<td-l>": 32503,
+  "<td-ld>": 32509,
+  "<td-ldu>": 32515,
+  "<td-lu>": 32511,
+  "<td-r>": 32502,
+  "<td-rd>": 32508,
+  "<td-rdu>": 32514,
+  "<td-rl>": 32506,
+  "<td-rld>": 32512,
+  "<td-rldu>": 32516,
+  "<td-rlu>": 32513,
+  "<td-ru>": 32510,
+  "<td-u>": 32505,
+  "<td>": 32501,
+  "<tr>": 32500
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "monologg/kobigbird-bert-base",
+  "architectures": [
+    "BigBirdForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "rescale_embeddings": false,
+  "sep_token_id": 3,
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 32517
+}

last-checkpoint/added_tokens.json

@@ -0,0 +1,19 @@
+{
+  "<td-d>": 32504,
+  "<td-du>": 32507,
+  "<td-l>": 32503,
+  "<td-ld>": 32509,
+  "<td-ldu>": 32515,
+  "<td-lu>": 32511,
+  "<td-r>": 32502,
+  "<td-rd>": 32508,
+  "<td-rdu>": 32514,
+  "<td-rl>": 32506,
+  "<td-rld>": 32512,
+  "<td-rldu>": 32516,
+  "<td-rlu>": 32513,
+  "<td-ru>": 32510,
+  "<td-u>": 32505,
+  "<td>": 32501,
+  "<tr>": 32500
+}

last-checkpoint/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "monologg/kobigbird-bert-base",
+  "architectures": [
+    "BigBirdForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "rescale_embeddings": false,
+  "sep_token_id": 3,
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 32517
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ab356fa18f110500a5c92dc47dd1e4511f4ece5e195bf6f39801135def9e7a
+size 943333453

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1aace261b8e6cad923ee6661d1c7271017bc8d22f018c02ff43351ce6bc4e31
+size 471708325

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc19aba973831004a77f20c88b8e3e066a8a55403bc0ad8b246efb14f309ecd
+size 14567

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:586f9b073107d2287ab918b8e3a6c9ec40a7767baa6b65a691f978a7a7ba2ab5
+size 623

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "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>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "model_max_length": 4096,
+  "name_or_path": "monologg/kobigbird-bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/ec2-user/.cache/huggingface/hub/models--monologg--kobigbird-bert-base/snapshots/ceacda477e20abef2c929adfa4a07c6f811323be/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": 0.008156606851549755,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9918433931484505e-05,
+      "loss": 3.6749,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "eval_exact_match": 25.56077203964528,
+      "eval_f1": 30.48757258245567,
+      "eval_loss": 2.4391441345214844,
+      "eval_runtime": 1683.1549,
+      "eval_samples_per_second": 6.834,
+      "eval_steps_per_second": 6.834,
+      "step": 500
+    }
+  ],
+  "max_steps": 183900,
+  "num_train_epochs": 3,
+  "total_flos": 1103235145728000.0,
+  "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:ce3df7dacb746d38927d7b4b5c96e23b1180109e65ab3c5eda16560beab01da4
+size 3439

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1aace261b8e6cad923ee6661d1c7271017bc8d22f018c02ff43351ce6bc4e31
+size 471708325

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "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>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "mask_token": "[MASK]",
+  "model_max_length": 4096,
+  "name_or_path": "monologg/kobigbird-bert-base",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/home/ec2-user/.cache/huggingface/hub/models--monologg--kobigbird-bert-base/snapshots/ceacda477e20abef2c929adfa4a07c6f811323be/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:ce3df7dacb746d38927d7b4b5c96e23b1180109e65ab3c5eda16560beab01da4
+size 3439