Training in progress, step 3

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "up_proj",
+    "gate_proj",
     "down_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "up_proj",
-    "gate_proj"
+    "v_proj",
+    "k_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:c20df4091a0f5cef9076924e5f7382f28e24ffaaaa8a8c0e8f2c1ac5f5c3229d
+oid sha256:697c571eaf2d2eb687bd716a7282b89321fa4dbe8049cbd6a020a5dac5386953
 size 83945296

config.json

@@ -23,10 +23,10 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e0ff56a10a0a978cf0b90dc8eeaf45a0cb3310da90b24ea610a7d7d0412b81
+oid sha256:429ae8aef14404f5795ffd6129e80e08400dd13727e9bdee786ac606e17fd5bf
 size 6776