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

README.md

@@ -33,14 +33,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - 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: 50
-- num_epochs: 10
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 15
 
 ### Training results
 

adapter_config.json

@@ -15,19 +15,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "value",
-    "query"
+    "query",
+    "value"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001cf383a862914efd3d62ebe9ad07339ad3221d231e460b42707baae201a492
-size 2366064
+oid sha256:69e1fe80cb82359c3d976db9d3da38e2eb725a67418a6426d211d84f6da3522a
+size 4725384

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8509d620da8786a234d7d7c0c84723470640f12ebc7756dda4d55aadf89c38e
+oid sha256:0ca8e4a2408b57e196ba7a46dfd30b33797ef66c307d93c83122e9dd5f256fb1
 size 5240