End of training

README.md

@@ -5,8 +5,8 @@ model_name: SOC_Query_Generation_Base_Llama_3B
 tags:
 - generated_from_trainer
 - trl
-- sft
 - unsloth
+- sft
 licence: license
 ---
 
@@ -36,7 +36,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.21.0
-- Transformers: 4.55.0
+- Transformers: 4.55.4
 - Pytorch: 2.7.0
 - Datasets: 3.6.0
 - Tokenizers: 0.21.4

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "up_proj",
-    "down_proj",
     "v_proj",
+    "q_proj",
     "o_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a78aa4966aed68a01b6e118d9be6af2e46e7b09fbc0f01a3464a62537ba645
+oid sha256:b09748d6cb8d92a607d88520f5b285646ea19a527350593a8db49fb9dde3733d
 size 194563400

runs/Aug25_23-08-40_95a4ebb9f4e6/events.out.tfevents.1756163324.95a4ebb9f4e6.14443.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe28f2959e4aa7b066dca35a1cf8bc0a6af9ee4ed15dc2db25d79d1f299abed
+size 7208

runs/Aug25_23-10-19_95a4ebb9f4e6/events.out.tfevents.1756163423.95a4ebb9f4e6.15833.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e41a0995d92b844108b4a997ba2677e0a93122413d5363e9c099d802c0c144b
+size 27221

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b5ac3eb18e7aa01f0b881a93e3aea65416ae2b625af2c90964540ec6af9c6e
-size 6225
+oid sha256:4d85f2157f0ea57b363540af326fbe73e45d78293ad26e9e41a02f852e09468e
+size 6289