HoGeeny commited on 29 days ago

Commit

a8713b6

verified ·

1 Parent(s): de3ff39

Upload folder using huggingface_hub

Browse files

Files changed (29) hide show

.DS_Store +0 -0
checkpoint-2407/config.json +25 -0
checkpoint-2407/optimizer.pt +3 -0
checkpoint-2407/pytorch_model.bin +3 -0
checkpoint-2407/rng_state.pth +3 -0
checkpoint-2407/scheduler.pt +3 -0
checkpoint-2407/special_tokens_map.json +7 -0
checkpoint-2407/tokenizer.json +0 -0
checkpoint-2407/tokenizer_config.json +15 -0
checkpoint-2407/trainer_state.json +168 -0
checkpoint-2407/training_args.bin +3 -0
checkpoint-2407/vocab.txt +0 -0
checkpoint-4814/config.json +25 -0
checkpoint-4814/optimizer.pt +3 -0
checkpoint-4814/pytorch_model.bin +3 -0
checkpoint-4814/rng_state.pth +3 -0
checkpoint-4814/scheduler.pt +3 -0
checkpoint-4814/special_tokens_map.json +7 -0
checkpoint-4814/tokenizer.json +0 -0
checkpoint-4814/tokenizer_config.json +15 -0
checkpoint-4814/trainer_state.json +320 -0
checkpoint-4814/training_args.bin +3 -0
checkpoint-4814/vocab.txt +0 -0
config.json +25 -0
pytorch_model.bin +3 -0
special_tokens_map.json +7 -0
tokenizer.json +0 -0
tokenizer_config.json +15 -0
vocab.txt +0 -0

.DS_Store ADDED Viewed

Binary file (6.15 kB). View file

checkpoint-2407/config.json ADDED Viewed

	@@ -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": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-2407/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:28cc4b4bf91b8c21be8df539c02ad71dcdb078ef7c50edee5c6fcb6759a7acca
+size 880343482

checkpoint-2407/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1e017bdb389df1ef31137ac9beb95058294e857c5c0989f8b8ab1c5f2475e832
+size 440185770

checkpoint-2407/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e7011a5d7974c88627516f93e01bcd0705a920b7c7e21c91a0493e06c9fad2
+size 14244

checkpoint-2407/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:df03d5e331a4b213739a24965821ef0e005768a3770fbfe9feea2229d68807a1
+size 1064

checkpoint-2407/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-2407/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-2407/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-2407/trainer_state.json ADDED Viewed

	@@ -0,0 +1,168 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 2407,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9376817615288744e-05,
+      "loss": 2.8963,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.8753635230577484e-05,
+      "loss": 1.646,
+      "step": 200
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.8130452845866227e-05,
+      "loss": 1.4321,
+      "step": 300
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.7507270461154963e-05,
+      "loss": 1.3382,
+      "step": 400
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6884088076443707e-05,
+      "loss": 1.2173,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.6260905691732446e-05,
+      "loss": 1.1811,
+      "step": 600
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.563772330702119e-05,
+      "loss": 1.119,
+      "step": 700
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.501454092230993e-05,
+      "loss": 1.0973,
+      "step": 800
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4391358537598673e-05,
+      "loss": 1.0982,
+      "step": 900
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.3768176152887412e-05,
+      "loss": 1.038,
+      "step": 1000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.3144993768176152e-05,
+      "loss": 1.0198,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.2521811383464895e-05,
+      "loss": 1.031,
+      "step": 1200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1898628998753635e-05,
+      "loss": 0.967,
+      "step": 1300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.1275446614042378e-05,
+      "loss": 0.9116,
+      "step": 1400
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.0652264229331118e-05,
+      "loss": 0.9465,
+      "step": 1500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.002908184461986e-05,
+      "loss": 0.9462,
+      "step": 1600
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.9405899459908598e-05,
+      "loss": 0.9105,
+      "step": 1700
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.878271707519734e-05,
+      "loss": 0.8996,
+      "step": 1800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.8159534690486084e-05,
+      "loss": 0.9045,
+      "step": 1900
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7536352305774824e-05,
+      "loss": 0.8361,
+      "step": 2000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6913169921063567e-05,
+      "loss": 0.8606,
+      "step": 2100
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6289987536352307e-05,
+      "loss": 0.8729,
+      "step": 2200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5666805151641047e-05,
+      "loss": 0.8304,
+      "step": 2300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5043622766929788e-05,
+      "loss": 0.8128,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9848228693008423,
+      "eval_runtime": 308.4998,
+      "eval_samples_per_second": 41.65,
+      "eval_steps_per_second": 2.606,
+      "step": 2407
+    }
+  ],
+  "max_steps": 4814,
+  "num_train_epochs": 2,
+  "total_flos": 7544355933049344.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2407/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:23ab0df96f27e1a4a517c0106e06c9dbf62bb6be148d4adcaf96492b96e03cfe
+size 3960

checkpoint-2407/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-4814/config.json ADDED Viewed

	@@ -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": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-4814/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ab064b4314772fc702ce0b5ed82b52eb4609b99f0b248398cdb6455eddcd9e65
+size 880343482

checkpoint-4814/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce23687fbfd20d93745bc1d242191517d6a0214ad902005296ee0c1b625499f
+size 440185770

checkpoint-4814/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c4026e51f44c825a2a9c2d0d94b5734c73f03514c53faa94e57f86859e899539
+size 14244

checkpoint-4814/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d98caffa46a7d0af041bb244ed2bd6abdcdff7037940191c831e28ef9afdb7
+size 1064

checkpoint-4814/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-4814/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-4814/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-4814/trainer_state.json ADDED Viewed

	@@ -0,0 +1,320 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 4814,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.9376817615288744e-05,
+      "loss": 2.8963,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.8753635230577484e-05,
+      "loss": 1.646,
+      "step": 200
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.8130452845866227e-05,
+      "loss": 1.4321,
+      "step": 300
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.7507270461154963e-05,
+      "loss": 1.3382,
+      "step": 400
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.6884088076443707e-05,
+      "loss": 1.2173,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.6260905691732446e-05,
+      "loss": 1.1811,
+      "step": 600
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.563772330702119e-05,
+      "loss": 1.119,
+      "step": 700
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.501454092230993e-05,
+      "loss": 1.0973,
+      "step": 800
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.4391358537598673e-05,
+      "loss": 1.0982,
+      "step": 900
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.3768176152887412e-05,
+      "loss": 1.038,
+      "step": 1000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.3144993768176152e-05,
+      "loss": 1.0198,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.2521811383464895e-05,
+      "loss": 1.031,
+      "step": 1200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1898628998753635e-05,
+      "loss": 0.967,
+      "step": 1300
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.1275446614042378e-05,
+      "loss": 0.9116,
+      "step": 1400
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2.0652264229331118e-05,
+      "loss": 0.9465,
+      "step": 1500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2.002908184461986e-05,
+      "loss": 0.9462,
+      "step": 1600
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.9405899459908598e-05,
+      "loss": 0.9105,
+      "step": 1700
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.878271707519734e-05,
+      "loss": 0.8996,
+      "step": 1800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.8159534690486084e-05,
+      "loss": 0.9045,
+      "step": 1900
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7536352305774824e-05,
+      "loss": 0.8361,
+      "step": 2000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6913169921063567e-05,
+      "loss": 0.8606,
+      "step": 2100
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6289987536352307e-05,
+      "loss": 0.8729,
+      "step": 2200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5666805151641047e-05,
+      "loss": 0.8304,
+      "step": 2300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5043622766929788e-05,
+      "loss": 0.8128,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9848228693008423,
+      "eval_runtime": 308.4998,
+      "eval_samples_per_second": 41.65,
+      "eval_steps_per_second": 2.606,
+      "step": 2407
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.442044038221853e-05,
+      "loss": 0.5303,
+      "step": 2500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.3797257997507271e-05,
+      "loss": 0.5619,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.3174075612796013e-05,
+      "loss": 0.5283,
+      "step": 2700
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.2550893228084752e-05,
+      "loss": 0.5348,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.1927710843373494e-05,
+      "loss": 0.5228,
+      "step": 2900
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.1304528458662235e-05,
+      "loss": 0.5565,
+      "step": 3000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.0681346073950977e-05,
+      "loss": 0.5732,
+      "step": 3100
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.0058163689239718e-05,
+      "loss": 0.5185,
+      "step": 3200
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 9.43498130452846e-06,
+      "loss": 0.5319,
+      "step": 3300
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 8.8117989198172e-06,
+      "loss": 0.5103,
+      "step": 3400
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 8.188616535105941e-06,
+      "loss": 0.5141,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 7.565434150394683e-06,
+      "loss": 0.5069,
+      "step": 3600
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.942251765683423e-06,
+      "loss": 0.5288,
+      "step": 3700
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 6.319069380972165e-06,
+      "loss": 0.532,
+      "step": 3800
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 5.695886996260906e-06,
+      "loss": 0.4958,
+      "step": 3900
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 5.072704611549647e-06,
+      "loss": 0.5133,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.4495222268383876e-06,
+      "loss": 0.5331,
+      "step": 4100
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.82633984212713e-06,
+      "loss": 0.4632,
+      "step": 4200
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.2031574574158706e-06,
+      "loss": 0.533,
+      "step": 4300
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2.5799750727046116e-06,
+      "loss": 0.546,
+      "step": 4400
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.9567926879933527e-06,
+      "loss": 0.5343,
+      "step": 4500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.333610303282094e-06,
+      "loss": 0.4874,
+      "step": 4600
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.10427918570835e-07,
+      "loss": 0.4871,
+      "step": 4700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 8.724553385957623e-08,
+      "loss": 0.4841,
+      "step": 4800
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0827125310897827,
+      "eval_runtime": 308.6856,
+      "eval_samples_per_second": 41.625,
+      "eval_steps_per_second": 2.605,
+      "step": 4814
+    }
+  ],
+  "max_steps": 4814,
+  "num_train_epochs": 2,
+  "total_flos": 1.5088711866098688e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4814/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:23ab0df96f27e1a4a517c0106e06c9dbf62bb6be148d4adcaf96492b96e03cfe
+size 3960

checkpoint-4814/vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

config.json ADDED Viewed

	@@ -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": "4.28.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce23687fbfd20d93745bc1d242191517d6a0214ad902005296ee0c1b625499f
+size 440185770

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff