EdBerg/outputs

README.md

@@ -44,7 +44,7 @@ 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_steps: 2
-- training_steps: 1000
+- training_steps: 1500
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -56,5 +56,5 @@ The following hyperparameters were used during training:
 - PEFT 0.13.3.dev0
 - Transformers 4.45.2
 - Pytorch 2.4.1+cu121
-- Datasets 3.0.1
+- Datasets 3.0.2
 - Tokenizers 0.20.1

adapter_config.json

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "q_proj",
     "v_proj",
     "o_proj",
-    "up_proj",
-    "q_proj",
     "down_proj",
-    "k_proj"
+    "up_proj",
+    "k_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 sha256:5443a6a21c4eedc437bdc8e5102721d67044aeba2b82b28915837c2b3e9aa7f8
+oid sha256:ea682fa826aecb98b4d78c1c200ba24a0cc3cdbd99fcb74181f154a40e38034d
 size 83945296

runs/Oct23_01-17-46_53be919b54ac/events.out.tfevents.1729646271.53be919b54ac.664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7a74c1678f67f81781ecb09eab3e091ca70e586bde5c1cbe2df04fd3eaf8a9
+size 322159

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3050d70ad27c9524f5c98150d5f0a5538fc3a5ed848dcf4b1aea2b8f14542a25
+oid sha256:f1b3c1e83a7ae2e6f34dd35abbc20fd8874956ba9c26a532625c5e8bf6c68a27
 size 5432