Training in progress, step 500

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b4a80d18fc6dcaa92e33648fdd85a5f4940cab1a819188105c221daaa4bb89
-size 894624
+oid sha256:93d6fcdc4d8c8d8234562a257ed891bb1c0d6e3c4c004dabc32c95639cb4bea4
+size 1779432

runs/Apr13_17-05-51_5a453ccd3267/events.out.tfevents.1713027953.5a453ccd3267.2298.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cd37f255104813ed52fd196e2a8754d0bc66f2678132ac0f12c91bf8bc471a
-size 11439
+oid sha256:d260e4281b8a4bb594e55064c08325fb37b29b0920c86e461156bb92b2153a25
+size 11793

runs/Apr13_17-05-51_5a453ccd3267/events.out.tfevents.1713031243.5a453ccd3267.2298.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cd20f70da3931bf2e4d3f16a2cab11b7f79014c093a3460b2d48f2b8a9d66a
+size 359

runs/Apr13_18-17-46_5a453ccd3267/events.out.tfevents.1713032268.5a453ccd3267.2298.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bd6bdfc260a45be1a788bbf4da82ee6d6a14126a532eafacac5d91f2f32e24
+size 6336

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c644b433f0c0e785d3bc10f899fc0ad9f7057eaf6e9012c85373f7af903cd9
+oid sha256:d050b43edd7c50f88496e38be705946bbda3ce56e0b456627f1f16fed28b14f5
 size 5112