End of training

README.md

@@ -350,4 +350,23 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
+- PEFT 0.6.2
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
 - PEFT 0.6.2

adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0ee2ee379b85e0ed78c63e679f47657ed3e94bcfbbf56248630f73ffe7e07e
+oid sha256:eb05cf8e488844569978fc86490caa6eec712591941924aeae1f4f7295572eb9
 size 67155338

runs/Nov23_17-03-34_70e1776c12d2/events.out.tfevents.1700759014.70e1776c12d2.66554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377ed893cb6838b7c39a0003c8dd08691296a850d7bf9bbd172d23d8acaf11bf
+size 35939