Training in progress, epoch 1

adapter_config.json

@@ -1,41 +1,19 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
-  "beta1": 0.85,
-  "beta2": 0.85,
-  "bias": "none",
-  "deltaT": 1,
   "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "init_r": 12,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 2,
-  "lora_dropout": 0.01,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "classifier",
-    "score"
+  "feedforward_modules": [
+    "down_proj"
   ],
-  "orth_reg_weight": 0.5,
-  "peft_type": "ADALORA",
-  "r": 64,
-  "rank_pattern": null,
+  "inference_mode": false,
+  "init_ia3_weights": true,
+  "modules_to_save": null,
+  "peft_type": "IA3",
   "revision": null,
   "target_modules": [
     "k_proj",
+    "down_proj",
     "v_proj"
   ],
-  "target_r": 8,
-  "task_type": "SEQ_CLS",
-  "tfinal": 0,
-  "tinit": 0,
-  "total_step": null,
-  "use_dora": false,
-  "use_rslora": false
+  "task_type": "SEQ_CLS"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f72b9534ff016da1d1bad2a15c65babd71ac1a0ae42b739a9170449f0d9c6fb
-size 15788680
+oid sha256:574bef5f8ac04bdc5fe9365214d4096b56e987cd6baf92de18c0fa47d21c25f1
+size 2108904

runs/Sep12_11-37-18_114b16efcfc7/events.out.tfevents.1726141039.114b16efcfc7.522.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fd930f272add741f0ec252bb8d8e64f839e028eaeb3ac8b0a5c006ef7f7bb9
+size 70661

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9f2632314a2d06115948b8c8e9aa1ae2912fface551f05f6e0bd539eadd49db
+oid sha256:d08af6d37c511b43dd4f16895ff524bad7d92d5575f880796ba163d23de30936
 size 5176