Training in progress, epoch 1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "gate_proj",
     "o_proj",
-    "k_proj",
     "v_proj",
-    "q_proj",
+    "k_proj",
     "up_proj",
-    "gate_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1a37908715f711b675de58a39e0536f3cc907843b9855f40b9687d9111edb7
+oid sha256:53dbc0d22a6fc41d62165609704627c4b3384e4b7f82b0a8cb240acbd13a720f
 size 335604696

config.json

@@ -23,10 +23,10 @@
   "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,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e84162329319bca12637f836a9e338df4a22ed057fecf0854bc35bc5ee1487
+oid sha256:6b91dfeccafffd9d26c96c50a1fa51704439f5c1848fd9340408361d34913f59
 size 6776