Training in progress, step 200

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 16,
   "lora_dropout": 0.15,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "down_proj",
     "gate_proj",
     "o_proj",
-    "q_proj",
-    "k_proj",
     "up_proj",
     "v_proj",
-    "down_proj"
+    "q_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:db5cce6156c4621517be68ed6604412d1e180059ddcba2665cbdb58955f9bb05
-size 180385008
+oid sha256:7140be330dda6372b6231f1c967402a64cbc852cb4999f9baf8ceb68d4fd23ab
+size 22573704

config.json

@@ -21,6 +21,21 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": 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,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 32.0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5bfb8f9ee0d17252ff4577fc9c15127560771b7e188338420238d872618fd3b
+oid sha256:559463d95a91aa4519eb17ce5aba32cad078cdd9196a6b9560209fa7cf008a3b
 size 6776