Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,17 +10,19 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d04cea186508d6d49d4a5086e424c6673abbd98ac8b4f9b493af98af82f774
-size 27280152
+oid sha256:1748b3900389f77098b45a45c5cee2468c3acad99544aaac9c134f57263347ba
+size 268470272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e78d437b4ccae46f8c45770eb9e8bc793b52eb6b6af87852cddc789d639e165d
+oid sha256:6024542ff315d35eed80b2aa4af021a13d0e93f6c5ecacdd80e1d5017af88d6b
 size 4856