End of training

README.md

@@ -42,11 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 2
-
-### Training results
-
-
+- num_epochs: 1
 
 ### Framework versions
 

adapter_config.json

@@ -26,12 +26,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "o_proj",
     "down_proj",
-    "k_proj",
     "q_proj",
     "up_proj",
+    "gate_proj",
+    "k_proj",
     "v_proj"
   ],
   "task_type": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2e53d3bee1c0d1caf2758304b9c914f73625ef752ec5e2426548a8006e5140
+oid sha256:d3cecbca8684670158348b7025bea802d1b2bac0105a3b547aafefddc63eca85
 size 42220792

runs/May26_04-19-10_dbe146cfebca/events.out.tfevents.1748233151.dbe146cfebca.116.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75bbb9cc959a839730bb13e03d2263625adadc8dfd7747d75b38c443dca40e26
+size 10596

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3d2b7e2de2c844e85a3cca6a7441b8062c79e6f749c032c706a53162d0a1eb
+oid sha256:db42a48b6eca75c298dc7a139f28b45864b1d9e748af8e38fe9d3b7fdeb70d89
 size 5368