Training in progress, step 500

README.md

@@ -5,8 +5,6 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-- ipex
-- GPU Max 1100
 base_model: google/gemma-2b
 datasets:
 - generator
@@ -36,10 +34,6 @@ More information needed
 
 More information needed
 
-## Training Hardware
-
-This model was trained using Intel(R) Data Center GPU Max 1100
-
 ## Training procedure
 
 ### Training hyperparameters

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "down_proj",
-    "o_proj",
-    "k_proj",
     "q_proj",
     "up_proj",
-    "gate_proj",
-    "v_proj"
+    "k_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ea7af5d7fd4c011f8a2802794d00518c27a6ec259b0546fcc48bf1e9b46eb3
+oid sha256:24429dd8bff3af0e92dbcb30dcf0193ff9af1d61cb4463da96e1a534f41857ac
 size 156926880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48bc734926e958c820e14b3918d8edac20c3d49097f85fedbfb3b48b101d0bbb
+oid sha256:b634a18d51cacfbd1b62bdb9139a2391ed2c881d11bf868f93ff2e14b12e33ee
 size 4539