Training in progress, step 100

adapter_config.json

@@ -1,10 +1,7 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": {
-    "base_model_class": "LlamaForCausalLM",
-    "parent_library": "transformers.models.llama.modeling_llama"
-  },
-  "base_model_name_or_path": "./models/meta-llama_Meta-Llama-3-8B-Instruct",
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -13,20 +10,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.0,
+  "lora_alpha": 16,
+  "lora_dropout": 0.5,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
-    "q_proj"
+    "q_proj",
+    "output_proj"
   ],
-  "task_type": null,
+  "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288c6fd1ceb50d058739422cd41bf9c271e7233a82542e5db69e46e1b5285b90
-size 13648432
+oid sha256:f77b0e83a3e89e2fa666c4dd2b976f461084b328830a247d8d899e9ff1c4b76a
+size 75523312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19232f7ea9a5555e8cb8a2e3b952769356fcc572236123d18a9e1daafe956411
-size 5112
+oid sha256:a429c70c954071280d23e965d09cde309a6ec534e182ae527d0515fa1e120bbb
+size 5368