Training in progress, step 76

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
+    "v_proj",
+    "down_proj",
     "up_proj",
-    "o_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj",
-    "down_proj"
+    "o_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:c254c5bd5ffe120a84387ec439775b555c188405159913301d01dbca39e686fd
+oid sha256:68a70b9578e97825da95f71c12002a2a507b30538469e551e35852631fb894ec
 size 335604696

config.json

@@ -16,8 +16,8 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
     "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
@@ -26,8 +26,8 @@
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81b4e081418b0879743d7d6a5e00ef3eb7cb9d41ea129e8a3100ba68d839601
+oid sha256:fb3c64ff9809eadcadb2ae0ee1221e44827abfb616e8b0e2cb804dbd21cdb2d7
 size 6072