Model save

README.md

@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
+    "o_proj",
     "up_proj",
     "down_proj",
-    "o_proj",
+    "v_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

runs/Sep11_09-09-19_m3h110/events.out.tfevents.1757545790.m3h110.2694286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3580dc31fcbdcf96850b885727804e511a706df064d9e04f70996d8e236b5c4c
+size 5752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48715564d8294ad94f4c1d121a1672238f39ea1a2f24db9adb0ef5f6c68fbd7d
+oid sha256:6cdf75a28e65bfd01c6bce7c429edd86da74d8a5338b22408c22d8e424fd134b
 size 6520