Training in progress, step 200

adapter_config.json

@@ -9,7 +9,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
-    "v_proj",
     "o_proj",
+    "down_proj",
     "up_proj",
+    "gate_proj",
+    "v_proj",
     "q_proj",
-    "gate_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cfa4e388177e6e270cc2aacd8cd144f22082f25dcb138cb7660c5abf9175f1
+oid sha256:e7000c7edb92a9468eac36506437e43ab4cf10184b943a7ab9546ec928db20b8
 size 639691872

angle.config

@@ -1,21 +1,21 @@
 {
   "model_name_or_path": "NousResearch/Llama-2-7b-hf",
-  "max_length": 75,
+  "max_length": 85,
   "model_kwargs": {},
   "pooling_strategy": "cls",
   "lora_config_kwargs": {
     "task_type": "CAUSAL_LM",
     "r": 64,
-    "lora_alpha": 16,
+    "lora_alpha": 32,
     "lora_dropout": 0.1,
     "bias": "none",
     "target_modules": [
       "q_proj",
+      "v_proj",
       "o_proj",
       "up_proj",
-      "v_proj",
-      "gate_proj",
       "k_proj",
+      "gate_proj",
       "down_proj"
     ]
   },

runs/Mar23_02-16-23_instance-20240226-074643/events.out.tfevents.1711160195.instance-20240226-074643.3613579.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66aed1c059cc3413c060e235f33afec6b1de9d59ae6dcfc9d9aafdef03d5e558
+size 5624

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8683f1534b803565058f488cf02c4891f4edbcb2b2895ce55448900b3cb5d972
+oid sha256:03ea38a21f34dfac031cbda7385810d20b697435671e70aa1b4d60b84eabc5f2
 size 5048