Training in progress, step 300

adapter_config.json

@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "v_proj",
     "up_proj",
     "k_proj",
     "o_proj",
-    "v_proj",
-    "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "q_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c03cf130135167da55ddc0a06753fe3bc068d8b6139fb76450e8db473f37ebca
-size 83946192
+oid sha256:6054d6d72554f5a41170a5e381547806b076cc02063e8c2c6750fe6879f5830d
+size 671150064

runs/Mar11_14-39-12_gpu4-119-5/events.out.tfevents.1710128468.gpu4-119-5.1663745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9d422cc08ee248b90c770d53293d85091e069686ecfe55b070f4c780f6159c
+size 5189

runs/Mar11_14-41-58_gpu4-119-5/events.out.tfevents.1710128620.gpu4-119-5.1665820.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abc405cd4b690efb9cafb48cac9d833b63a78c04e4991b287429632d1e70448
+size 13351

runs/Mar11_15-05-06_gpu4-119-5/events.out.tfevents.1710130009.gpu4-119-5.1682853.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d78cc694c6c77045b96118aff241d02c1d970271b3033cfe6cd117588c80805
+size 20404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c2b1e4527f9236fe9f3f80a8772379fdd465b93f41b64e54d51742438aa58d1
-size 4856
+oid sha256:8fc6095f218a47684050da269b4871ab4eef060635b0f7b0904229aab6c96d89
+size 5048