Training in progress, step 200

adapter_config.json

@@ -15,12 +15,12 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2eefccf167dbae0d807624ff6337a8d8da54af76a7f86b86e27b71c8a821b24
-size 16794456
+oid sha256:c5387250aff8e09528606187407f7ae47d3af6cbd293032f839175999c02585d
+size 33571752

angle.config

@@ -1,11 +1,11 @@
 {
   "model_name_or_path": "NousResearch/Llama-2-7b-hf",
-  "max_length": 80,
+  "max_length": 60,
   "model_kwargs": {},
   "pooling_strategy": "cls",
   "lora_config_kwargs": {
     "task_type": "CAUSAL_LM",
-    "r": 16,
+    "r": 32,
     "lora_alpha": 32,
     "lora_dropout": 0.05,
     "bias": "none"

runs/Apr07_14-16-18_instance-20240226-074643/events.out.tfevents.1712499390.instance-20240226-074643.1153283.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10beeabab2721c90911a6cdad88595a2c8fb5240fc8881db90ee51877e90b0e
+size 5249

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4034d28a72178cef93c49b447c913fe1c82499164dfa0446e80ce1c426dea364
+oid sha256:7951b6ffc96969c7e663b89ec7c987693999c7bf7fceaf2b0453ed6d0c2b9b2c
 size 5048