Training in progress, step 50

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 1,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "down_proj",
     "up_proj",
     "gate_proj",
+    "down_proj",
+    "o_proj",
     "q_proj",
-    "o_proj"
+    "v_proj",
+    "k_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:d3bc62b69a8927df542246779b2a8fa4b7c5b0391da7f77f1c6221acbf6d6669
+oid sha256:28fb7adfaea6654679bea867fad576d037fb74adce5ad1ffd474f781a781a07d
 size 2332095256

runs/Apr04_01-02-45_b562675953c9/events.out.tfevents.1712192575.b562675953c9.2296.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d20d658bd8fd8a6278c80b1e2bb543bceafc352770ed53326fd2e8e39d2b1022
+size 5411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77f2ec9f610235f340d725f469163605db795121bdc046515491f4dc8dac2d5
+oid sha256:f25f22e5af78cfd4cb3a350fdbf786ce0ae235cbee7ecd9ec95b99be916d80f3
 size 4984