Training in progress, step 17

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj",
     "q_proj",
     "v_proj",
-    "gate_proj"
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "gate_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 sha256:2d04a055050780e0a0386a1ff2dd9b34fbbeba343ae537ac79c62c785dd8e5ab
+oid sha256:b5b6ed55416d7b5cad7b52930ea576702340b17e2bf44c82e069378d2917ad36
 size 80014016

config.json

@@ -17,21 +17,6 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
-  "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,
-    "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": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13e29972eaa0d73db3ed321653e99f4a4456856084eeedfd6f141b06c8d9635
+oid sha256:96a7d178d4e154493b8526da16d1c1dc3242ab0de42a519fbad8d1c011a626f2
 size 5816