Training in progress, step 200

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,9 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
     "down_proj",
-    "gate_proj"
+    "up_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f138d4a914741d4c09b97be606b477e4aacca167a7e2e496e5b86b29faf50e7
-size 31469800
+oid sha256:c6a35053aa45fdcee5deb77dd71015e46df182a8545535c67b8bf3129f415fe7
+size 45118424

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3ad0852eefb271603007aea78247e1549ac7c203d03b7476ccb0427c6570e0
-size 17210212
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -2059,6 +2059,6 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8d1652c64d5701d7542543217cc8eb0453db379d2bc34a961ad431eb6ebe7fc
+oid sha256:f519abf615386e0857c941fcb28a9140901798289aceaff057539afc5159bd3d
 size 5560