Training in progress, step 1000

adapter_config.json

@@ -10,8 +10,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.01,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj"
+    "v_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 sha256:8257738dbde976916dd6233c071737a7ca5eeb450c317c6e636d9d46ad981986
+oid sha256:e165143012593ad10391f0b7ff070e70e381d88b894f4eeb18d39c457e1d50d5
 size 9457520

runs/Sep05_00-46-20_9a76d9e283dc/events.out.tfevents.1725497183.9a76d9e283dc.168362.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee066d680601f939ccfad856ef3cb1f4e94cfbc240c418a2725a473452ca60c0
-size 15838
+oid sha256:668fafe8b3896c951fecc339ba1e0d4197afe2c97f74a4a5675eb0fd25a9c6c8
+size 19568

runs/Sep05_01-50-20_9a76d9e283dc/events.out.tfevents.1725501064.9a76d9e283dc.186568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac8241e4a3ffbfcd241cc2ed7cd052013febcfb671833ade0b8d3168fdbef23
+size 4184

runs/Sep05_01-53-39_9a76d9e283dc/events.out.tfevents.1725501229.9a76d9e283dc.187417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12257dc3f570dc0bcf912ddd1e71f705a8003286731682feedec56fb57b61f6e
+size 12250

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56cc3d597093c73b517f138d872a237644420044ff30c450a6b1b74741b62930
+oid sha256:541364ddcc6dcf266f4cdc472b56050ddf0c8c4ab4cd192a9910606549c86c26
 size 5304