JunYK/bert-b.m.c-STT-Summariz-classification-v2

README.md

@@ -33,14 +33,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- 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: 50
-- num_epochs: 5
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -15,14 +15,14 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d73113efa6d60e5238d89d41bb361e540ef5cae6356ff17169b3e8e9046fa687
-size 1186328
+oid sha256:001cf383a862914efd3d62ebe9ad07339ad3221d231e460b42707baae201a492
+size 2366064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b4db983a67db22817907c6a5fb8e7294b1e943a1b11fd3824c7e28769c79f3
-size 5304
+oid sha256:e8509d620da8786a234d7d7c0c84723470640f12ebc7756dda4d55aadf89c38e
+size 5240