Training in progress, step 60

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -12,18 +12,17 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "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": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
     "v_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f5bdfc3dc74318198e2a734ba31c4e853cfcf351a0e8cd38fdc8ef8803b798
-size 18899856
+oid sha256:0eacdde8c13b9c9bf354a850b8b92ae1c2bc2686978b612ecf034bacb26c48ef
+size 6824216

runs/Mar26_16-24-15_DESKTOP-OBIMAP9/events.out.tfevents.1742973857.DESKTOP-OBIMAP9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b61d774f79785d108f3795776b1b6fc1abc4ca0f995e73c2d1d75e537fd8ef
+size 5608

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7f26134a97616e520f62100b5f1edb899d3ae758ef45598c7d107b5a22adda
-size 5624
+oid sha256:429bbba745755918276024acd6af29e9a32c50cdcaec7523e06dd1fe9e111ed5
+size 5368