Training in progress, step 97

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: MobileLLM-R1-140M-lora
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 

adapter_config.json

@@ -13,25 +13,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_bias": false,
-  "lora_dropout": 0.01,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "o_proj",
     "gate_proj",
+    "k_proj",
     "up_proj",
-    "o_proj",
+    "v_proj",
     "q_proj",
-    "k_proj",
-    "v_proj"
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e30cd7c77b640eaf9081c4a9f4490ac23be1be3ce4a8623e6b2d86d9b73c7da
-size 22515416
+oid sha256:de89b092bb987a94afe6efbd753ce3c2cfb82695814782363cdd78fd90cd524d
+size 45002544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c649b3c201ab69d276c4c1413ea59d2af1f63e00776d565c80b88eddda3c52
+oid sha256:44b8d4f04459c24bb3be19c474b505c4d3a5b33956e09bbea9b8e841aae9cb30
 size 6161