JunYK/bert-b.m.c-STT-Summariz-classification-v3

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: bert-base-multilingual-cased
+license: cc-by-sa-4.0
+base_model: klue/bert-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
+This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on an unknown dataset.
 
 ## Model description
 
@@ -33,14 +33,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 15
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 10
 
 ### Training results
 
@@ -50,5 +50,5 @@ The following hyperparameters were used during training:
 
 - PEFT 0.14.0
 - Transformers 4.48.3
-- Pytorch 2.5.1+cu124
-- Tokenizers 0.21.0
+- Pytorch 2.6.0+cu124
+- Tokenizers 0.21.1

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "BertForSequenceClassification",
     "parent_library": "transformers.models.bert.modeling_bert"
   },
-  "base_model_name_or_path": "bert-base-multilingual-cased",
+  "base_model_name_or_path": "klue/bert-base",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -15,19 +15,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "value",
+    "query"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e1fe80cb82359c3d976db9d3da38e2eb725a67418a6426d211d84f6da3522a
-size 4725384
+oid sha256:33df96da1162d01331904fcea80a98d4f1a9791df2e4fc6dd9b9827eac3d4f1a
+size 1186328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca8e4a2408b57e196ba7a46dfd30b33797ef66c307d93c83122e9dd5f256fb1
+oid sha256:da95ffa226d6aa2bd6d2647d73488b8b326b19382c7992280b238c62807f6582
 size 5240