Training in progress, epoch 0

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
     "gate_proj",
-    "q_proj",
-    "up_proj",
     "k_proj",
-    "down_proj"
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41af480f822821d62b566653ae2ac4002bbc1a0c533be97ac38324facc251e4e
-size 83946192
+oid sha256:b9e51b5439beb3f8ad12537bad8d6dab8332dca1b4a87b12af0edcfbed021755
+size 1342239008

runs/Jun05_10-55-49_b2cca46f1a89/events.out.tfevents.1717584962.b2cca46f1a89.10515.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7ebfca14863dd6b5ed1d67d28fec0fea96199f17bbf50e1129bfb3d606b7c6
+size 10510

runs/Jun05_11-06-17_b2cca46f1a89/events.out.tfevents.1717585587.b2cca46f1a89.13778.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95122a034862e364dc7bcb04e6fcf9a5a9d597ce2a319e96051b96a86ac04870
+size 7191

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faeef946f3367d3c5fcdd2914cd4137f346c5c846eb1b45239f8f66ebd5b8b11
+oid sha256:03e91d98eea3deac6afbec1e22b2ff70cb19922f9c752cd3eed3742304297bac
 size 5112