Training in progress, step 300

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "k_proj",
     "v_proj",
     "down_proj",
     "q_proj",
-    "k_proj",
-    "gate_proj",
     "o_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 sha256:346fd04c5bacc5ffb04ac0bd5cf6bb4b91d42f6687f341f9beb9f43ca596d200
+oid sha256:8446e2bd6ce37d1b25a8e38e5839dba299680b5a122dc5cef7a8530b51d7cb86
 size 1342238560

runs/Sep25_17-53-25_m3h100/events.out.tfevents.1758787022.m3h100.2160898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374da6e08d9133383264d71c07a0f475a44b182bcb8c979c2820e1af64c644fc
+size 12261

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 8192,
+    "max_length": 16384,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b51d972c8d84512b8bb83aca7c14a003112ff1a6cd6ac4d35437cdad98fee381
+oid sha256:bd1e3e0028dee5d8a3bd413255a745f2891aa2e1bc47a1844ab479f6300488c4
 size 6456