Training in progress, step 17

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50401c254e094a02377c05b9358742ad906d53e0301f751e9aebdedf5e68dbf5
-size 159967880
+oid sha256:e8534fd9a68b7a1bfb5fb89d4d010560507de1f510342768d6a7578a8f904cf1
+size 80014016

config.json

@@ -18,18 +18,18 @@
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
+    "_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,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
     "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:bfdefd9888f9a4bcecadde37d55e0db76b9eaebcc2e042269e815b5ad6b55b14
+oid sha256:e13e29972eaa0d73db3ed321653e99f4a4456856084eeedfd6f141b06c8d9635
 size 5816