Model save

README.md

@@ -0,0 +1,52 @@
+---
+license: cc-by-sa-4.0
+base_model: klue/bert-base
+tags:
+- generated_from_trainer
+model-index:
+- name: train_dataset
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_dataset
+
+This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.1.0
+- Datasets 4.3.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6347126753710872,
+    "train_runtime": 558.4324,
+    "train_samples": 7978,
+    "train_samples_per_second": 42.859,
+    "train_steps_per_second": 5.361
+}

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": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1604825c45695256388b0560ceffe19d5be5badfb2abd27a4658b202ac1399b0
+size 440136504

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6347126753710872,
+    "train_runtime": 558.4324,
+    "train_samples": 7978,
+    "train_samples_per_second": 42.859,
+    "train_steps_per_second": 5.361
+}

train_results.txt

@@ -0,0 +1,6 @@
+epoch = 3.0
+train_loss = 0.6347126753710872
+train_runtime = 558.4324
+train_samples = 7978
+train_samples_per_second = 42.859
+train_steps_per_second = 5.361

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2994,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 24.274106979370117,
+      "learning_rate": 4.1649966599866405e-05,
+      "loss": 1.675,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.8456525802612305,
+      "learning_rate": 3.32999331997328e-05,
+      "loss": 1.0539,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 20.231595993041992,
+      "learning_rate": 2.49498997995992e-05,
+      "loss": 0.4262,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 17.46414566040039,
+      "learning_rate": 1.65998663994656e-05,
+      "loss": 0.3978,
+      "step": 2000
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 1.7042111158370972,
+      "learning_rate": 8.249832999331998e-06,
+      "loss": 0.1168,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "step": 2994,
+      "total_flos": 4689746024374080.0,
+      "train_loss": 0.6347126753710872,
+      "train_runtime": 558.4324,
+      "train_samples_per_second": 42.859,
+      "train_steps_per_second": 5.361
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2994,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 4689746024374080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c06bf8823cfefb7f2b31d574eae67090a50467c9bcb4ff70e45f8724f88a0de
+size 4920