End of training

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 100
+- training_steps: 50
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "dense",
     "query_key_value",
+    "dense_h_to_4h",
     "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94ba646413bc990801422ee41a083ff379ec85c64726d76878bcababed133e06
+oid sha256:44a46837099ef13a597163b0c7f96840dc196370408feb89129621de1435a7ae
 size 522227376

runs/Apr16_07-28-47_909516a6a7df/events.out.tfevents.1713252540.909516a6a7df.377.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b89ca52b1945cf5215f7f6f42ddcb96277337c70b5095451bd16a748899cd52
+size 6602

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573cb37190230b0004a95a7c3ec7bcfb5818acb85272e543cec69c1bc6ee2861
+oid sha256:853fe1f57fcbde2b0dc10e3eb234fd7e78be685240fb09c4333ee36cf70d65da
 size 4920