Training in progress, step 500

adapter_config.json

@@ -10,25 +10,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "v_proj",
-    "gate_proj",
-    "k_proj",
+    "q_proj",
     "down_proj",
+    "gate_proj",
     "o_proj",
-    "q_proj"
+    "k_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17eef3f5e8108962efa13a19f757e4845b398c4071904cbddb278b96fa2cf0a
-size 159967880
+oid sha256:9165442c89c6006655902527d60332d5be2c2323ce83c5b64a430c958df66d29
+size 1279323952

runs/Mar30_23-17-12_ae9751f0a8f7/events.out.tfevents.1711840632.ae9751f0a8f7.1547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74679991d7116aa30b33b3f27d2904e083aaa3a0c3bf0be6ec753c6aa23bab50
+size 5059

runs/Mar30_23-17-37_ae9751f0a8f7/events.out.tfevents.1711840657.ae9751f0a8f7.1547.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e116e50410d50463d20eddb303c7c7b5637f03ef150e23ad2721e5328a3883ef
+size 6110

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481cea894ad7167de34231c24c932a7b7dfa677078e02a52999d91edab25e726
+oid sha256:eedc7a704f25868b49e1e9fecb18824968eef7c34af0ab11e756658cd9c76e67
 size 4920