End of training

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - 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: linear
-- training_steps: 150
+- training_steps: 200
 
 ### Training results
 

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b6d48849aa38a5c71799d9ccbe72d61138c8b3c776de3062681aac0767b5af
-size 109069176
+oid sha256:e282acaa4e48bfa1666beb6918e615797abaf55a7ce81e6f3166a4a78683b097
+size 54543184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056645f87c6b635dccf97b709155dcfb9b9b7d70db0baae7d3b29fc5eb01e22e
+oid sha256:85b503d34f84e74c77c714e272b6ffe6a75ea0e2826d9a1a0a5a8fbdf97f6614
 size 5624