End of training

README.md

@@ -45,7 +45,7 @@ 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: 50
+- training_steps: 20
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
     "v_proj",
+    "q_proj",
     "gate_proj",
-    "q_proj"
+    "up_proj",
+    "down_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:f5db0128caa279a5fceb4e093d92f718c2c79e698e2ac3e77bba24f0ec225961
+oid sha256:1c7212f79277b371dea8626d0d6d5b0a2306b472960fb6188d905a079b3e4dfa
 size 562079784

runs/Apr09_06-05-47_e5f56592dd38/events.out.tfevents.1712642750.e5f56592dd38.14749.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0b6f407aa132bd5dc7140a4ac29ee86cd881fad4b2e590761926262b58c046
+size 5890

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9929dcbcc452f8c2591f3811707f3ca7a8934a00bf26e2f1ece8d6e7212f0715
+oid sha256:bc7ed9bd36fcf6cc6381976b198ae6f07d1565353aa8a02b41ce900a7fd85ee1
 size 4984