Training in progress, step 70

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b6957a46a62b70d44ccad820f0f31fb2584518fa20852e5c5834fb7d3b63d3
-size 80014016
+oid sha256:efac92be3814df93068378ab72cf5f8b4176e7fd3c8cedb41aa2d7b007a315de
+size 159967880

config.json

@@ -20,10 +20,10 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
     "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:c1a5e882ae94a52ef640dccf5bce9f5f80fa18103f4e60fb6949adaf0f8b1ac4
+oid sha256:c0f37fc92047a1ad1856ddf01f66d971410463753ad6f5d2d0f836d1b570a304
 size 5816