Training in progress, step 50

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 8,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj",
+    "q_proj",
     "k_proj",
     "down_proj",
-    "q_proj"
+    "o_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8f9b6142a14042717e90b4ef520862d0fceacc131ca271edc529d0cf2fa0c7
-size 3611357976
+oid sha256:57225fa98e9b2abd49f75b2b3b1c05d28b002c3fcf1e8ea3aa0c17b9b1ddc131
+size 2332095256

runs/Apr05_11-12-07_f35651a1a25c/events.out.tfevents.1712315535.f35651a1a25c.151820.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53eb925ad64dbe7093b9120f64431b6756ff81a03d9d985ad9af3553cdc629d5
+size 5410

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403626742f6efe5f62eac6bcb5e8ca4ed2b74f8fadca2dab1b48be04a27ca074
+oid sha256:e972f7017bedd2b0de8ee58686ae82160df49126b7631543383abc249cdaafe4
 size 4984