Training in progress, step 5

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-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": [
+    "k_proj",
+    "v_proj",
     "up_proj",
-    "gate_proj",
     "down_proj",
+    "gate_proj",
     "o_proj",
-    "q_proj",
-    "v_proj",
-    "k_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 sha256:14307fe730856cbaf0dfbb7be4fa93c6514b3842c68373379813bf5e25ed5e41
+oid sha256:fb29d3b53bd465aa7f34d857b9a8d7a67d143a4aa96b687c1e4abc4def144af6
 size 1073255280

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],

tokenizer_config.json

@@ -2067,5 +2067,6 @@
   ],
   "model_max_length": 131072,
   "pad_token": " ",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d3e370b9d6615dabd5613d8b90bf717c2681f461b1cf7375bd2aafe0509e79c
+oid sha256:78b4872ed3ffc7b568bfd68235d51d9bfe0fb0927dd4dd03d89ae03c49e01b2a
 size 6648