Training in progress, step 400

adapter_config.json

@@ -1,6 +1,9 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama"
+  },
   "base_model_name_or_path": "yentinglin/Taiwan-LLM-7B-v2.0-chat",
   "bias": "none",
   "fan_in_fan_out": false,
@@ -9,16 +12,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "lora_alpha": 16,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.01,
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "v_proj",
-    "q_proj",
-    "k_proj"
+    "lm_head",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": null
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f1f1067be6a33ea97f6a1cd5a370d45ab866eeb2b33810c3599f18f8c865671
-size 12608280
+oid sha256:d5c2b5e1172984e988d98087ac3b71e0795347ee587f3137f7f348948e47ba9e
+size 40613816

runs/Nov27_12-31-53_468235be79bd/events.out.tfevents.1701088314.468235be79bd.1211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b37dd01d6b4177c45678548e051d33088c2c171114413fcd050663c6890cbd1
+size 4740

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e3eea9f301140ceb1c97d07434a9e95649fd3ccf5b7d5fd1b94fca0bd29264
+oid sha256:4e65d3cd186ea61914e778c104bfd57c5efa6047ab6f91167a8debdbdfb05a72
 size 4664