Training in progress, step 5

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "k_proj",
     "q_proj",
     "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
     "v_proj",
-    "o_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:ab74057ae08d664fd9f25479207452cf9dbadb9cd5372a66eca63fb466be9044
-size 1673329784
+oid sha256:441588529cac2091ff21c25f74f48537a1c7119c02be8dbb537ea7e1712d1de5
+size 1095799992

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -7,16 +7,16 @@
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
   "eos_token_id": 128009,
-  "head_dim": 128,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 3072,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 8192,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 24,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4337447c878f7e1befdda3e0a761f7f4365657454ac7b81f7463c396a94f7b
+oid sha256:007964e66e6bbad65bb8156dc024422fa0150e23e56ad2f9dc4f93f87e9c3460
 size 6648