Upload model epoch 1 - val_loss: 1.2463

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_bias": false,
   "lora_dropout": 0.25,
   "megatron_config": null,
@@ -25,7 +25,7 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431a544246950808340ecaa9aeae9db124e56225f0bdc5d6f2a847e61f17d285
-size 5988672
+oid sha256:b7bfba51a86156aa328e25c8693736fafc763fc16dff46b3d5f15d99f9d1ed70
+size 23877552