Training in progress, step 1000

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "gate_proj",
-    "down_proj",
     "v_proj",
-    "q_proj",
     "k_proj",
     "o_proj",
-    "up_proj"
+    "q_proj",
+    "down_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:ee28fd5fdffe0bc7b8802facb057bf8d6fc1ab96f5ac9e460c935b6ae1f4d568
+oid sha256:e1896dfcaef3c21617a051a60da62a4d0691b3e7f8050634b21d00451b589ccf
 size 72936

config.json

@@ -20,21 +20,6 @@
   "num_hidden_layers": 1,
   "num_key_value_heads": 1,
   "pad_token_id": 0,
-  "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-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0c2acb3ed420619aa9d125228b4a4e6ed4eea82f7d854301e0aa99db91fde2
+oid sha256:a8c1e10b9487de179bb268d26f81c07d34a90b05414faba1c0b1ca4b8e55fe81
 size 6776