Training in progress, step 2500

adapter_config.json

@@ -25,13 +25,13 @@
   "revision": null,
   "target_modules": [
     "query_key_value",
+    "down_proj",
+    "k_proj",
     "o_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj",
     "q_proj",
-    "down_proj",
-    "v_proj"
+    "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b456bcac2f48bbf22e325bdf48cf1a1110c344b413885a7c69d8aaedf9476da
+oid sha256:47feebcdb604aa8140889d5be160c347f07305566fd0a219036cb87ac58d58b0
 size 360740440

toilaluan/7a6f2833-62b5-4c10-813b-08b22ac32093/adapter_config.json

@@ -1 +1 @@
-{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layer_replication": null, "layers_pattern": null, "layers_to_transform": null, "loftq_config": {}, "lora_alpha": 256, "lora_dropout": 0.0, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "r": 128, "rank_pattern": {}, "revision": null, "target_modules": ["up_proj", "query_key_value", "q_proj", "k_proj", "gate_proj", "down_proj", "v_proj", "o_proj"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}
+{"alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layer_replication": null, "layers_pattern": null, "layers_to_transform": null, "loftq_config": {}, "lora_alpha": 256, "lora_dropout": 0.0, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "peft_type": "LORA", "r": 128, "rank_pattern": {}, "revision": null, "target_modules": ["v_proj", "q_proj", "gate_proj", "o_proj", "k_proj", "up_proj", "down_proj", "query_key_value"], "task_type": "CAUSAL_LM", "use_dora": false, "use_rslora": false}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6495d6cc1fca03f97e27c7320f6aabbc12bc716e6507db383b27f8822091b0a
-size 5752
+oid sha256:f8d20c4bf9877d35554600ab548bd0f527c55f2e8f71f8ee163111ea7ebb3b4a
+size 5816