Training in progress, epoch 1

adapter_config.json

@@ -12,23 +12,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 4,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "Linear(in_features=1152, out_features=262144, bias=False)",
-    "embed_tokens"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "down_proj",
-    "up_proj"
+    "up_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 sha256:6d31e10e52ebc45fa4d8e020b5cea906b6268e90b149e7220ac307b71e8e79f2
-size 1228108352
+oid sha256:dcd1cccfbf5279ff9a411c76bd0ee0888e8ae208ce5fdaded93a05c0192663d6
+size 10083840

runs/Mar22_18-42-24_HAL/events.out.tfevents.1742687007.HAL.20278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b45fef8bde7871800805844b3c8e51f3880f5afd8953ade1073c0d3eb062252
+size 6142

runs/Mar22_18-45-17_HAL/events.out.tfevents.1742687136.HAL.20505.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17c0bc7b6675328e875e681fe73ca8d73e7f2b1992a59d4428dc11fdb314ef4
+size 74833

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2049d239a16c106c8f2493f742f5b6933d63e39c1eb3cb48306735ab8d39df78
+oid sha256:2316c9c5bed85c71cafbea4297ff56db1fb92000dec9f793733ce869506d0e92
 size 5624