memeorygreen/kobart_naver

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: mit
+base_model: gogamza/kobart-base-v2
+tags:
+- generated_from_trainer
+model-index:
+- name: kobart_naver
+  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. -->
+
+# kobart_naver
+
+This model is a fine-tuned version of [gogamza/kobart-base-v2](https://huggingface.co/gogamza/kobart-base-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3548
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3833        | 1.0   | 1000 | 0.3548          |
+
+
+### Framework versions
+
+- Transformers 5.10.2
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,57 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "author": "Heewon Jeon(madjakarta@gmail.com)",
+  "bos_token_id": 1,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.1,
+  "d_model": 768,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "init_std": 0.02,
+  "is_decoder": false,
+  "is_encoder_decoder": true,
+  "kobart_version": 2.0,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 1026,
+  "model_type": "bart",
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "pad_token_id": 3,
+  "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tie_word_embeddings": true,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "transformers_version": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f0022716f4b25cfeef44d618abaa6bd07fd9d6c7757d5ec0c3da3b06e45e8d
+size 497838600

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919a410a1ba7c8e4acd92e318c404ce9bfb2448d3a07ab5dd91c267a3ba66632
+size 5201