Training in progress, step 13

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
     "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
     "down_proj",
     "gate_proj",
-    "up_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:bd953e470c3c1ecf21d01fb144c0b18aaae089e2ebb4429813f320beff8919c1
+oid sha256:8038c7283dcfc56fc9336a2436e6d62b484dddbf79e63e91b4aafe9720a0aec1
 size 30026872

config.json

@@ -21,21 +21,6 @@
   "num_key_value_heads": 16,
   "pad_token_id": 0,
   "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": 10000.0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5caa0757eb6729afb825a23ed26698d31a8eb8144c4a1783996c35560aff000f
+oid sha256:62337e84daf9e238e7d82f06ecf5f60daec6288fb6d90a1c5aa4e8778cca5a3a
 size 6776