Training in progress, step 200

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3b7d456a86dd9fd5a172ebf6a78ecd1111bcbb4d2579ae55b15f0e1040ca2c
+oid sha256:4d755b7615b98c7ec31ca2db112bc7f4d67fcda01adaaecece146334a8d6ed38
 size 628216

config.json

@@ -19,21 +19,6 @@
   "num_key_value_heads": 2,
   "pad_token_id": 1,
   "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"
-  },
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665fd011d4315910644e66be2cee861c6f04e6fd22ea4fc944d74d59761f726d
+oid sha256:fd94430b6ad628499d22ee003a356e4077e4c8b400df27132e019ce7f53bace7
 size 6776