EdBerg/outputs3

README.md

@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Use 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: 2
-- training_steps: 2000
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -56,5 +56,5 @@ The following hyperparameters were used during training:
 - PEFT 0.13.3.dev0
 - Transformers 4.46.1
 - Pytorch 2.5.0+cu121
-- Datasets 3.0.2
+- Datasets 3.1.0
 - Tokenizers 0.20.1

adapter_config.json

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
     "k_proj",
     "q_proj",
-    "down_proj",
-    "v_proj",
-    "o_proj"
+    "up_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:ffd327f40e03c9f45b0997e8ddf7ced4df8fc8ffccf74cf1035f123d642cea98
+oid sha256:d62b44a9a00a2bcb6d3d228c555126316aa3217d8f35b6fb5b182c84f06731cb
 size 83945296

runs/Oct31_19-16-42_a63a83da7440/events.out.tfevents.1730402205.a63a83da7440.1228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3303b33f92a198b76d5c5e3e2048ac57bad367b6525118392ecbd169bc5ad2
+size 216732

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a640119e763e4c9eb7136f248b18a2c38d07abf5f02c39c9e6b4c12a5e65746
+oid sha256:06f278bcce14b20faeed6c7ede331f59e1e7516f78c166354efb11634e6c8d7b
 size 5496