archit11/qwen-finetuned-model

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - 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: cosine
 - lr_scheduler_warmup_steps: 5
-- training_steps: 100
+- training_steps: 10
 
 ### Training results
 

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
     "k_proj",
+    "o_proj",
+    "q_proj",
     "up_proj",
     "gate_proj",
-    "q_proj",
-    "o_proj"
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:113f7f20f0b993c919ae8a61ec3e773db07d9d89ff9975dc10eaf9c34b6cdb8a
+oid sha256:1bc491db94f764048319b43792374193828563de0f398a3fac3e3cb139479745
 size 132187888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d7f1e3bb06001f8ffc3d9f477719c8070000d9417e5f15ae7c05e840df7c60
+oid sha256:1f78fc16015178e3fa541e1a7c13f408478916040b6a9b28b0b2311a8881eecc
 size 5304