Jlonge4/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: 10
-- training_steps: 120
+- training_steps: 90
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,10 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "v_proj",
     "q_proj",
     "k_proj",
-    "o_proj"
+    "down_proj",
+    "o_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 sha256:44b055d4c5bfae7434431cc9d526bf9a70e2c5354bbd0277bb73b5a5d0b09e02
-size 25174424
+oid sha256:829a69443f3fe71f177eca09c70cd908bdc61650ed37d02134420fd4d2376eb0
+size 71320216

runs/Jun13_00-15-48_0f9589b2456f/events.out.tfevents.1718237749.0f9589b2456f.2185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4a4a49ee91ae5ab84528651430a7fbcb7d04f5265eed016e77c385c00854e1
+size 30330

runs/Jun13_00-17-14_0f9589b2456f/events.out.tfevents.1718237835.0f9589b2456f.2185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6edaffedf260c7585848b5dae276500e786aecbd63909a5737911b70c02227
+size 5556

runs/Jun13_00-18-46_0f9589b2456f/events.out.tfevents.1718237927.0f9589b2456f.3804.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a69e762cdf082b3e7f229b0aa6d52a0f32cb88ac98a9b99b5119520af291469
+size 24119

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5acfaa5d04b3b800b9e24bac08c0fd9dc978e1cb0a7ea621dc0d1eeb4310ba
-size 5112
+oid sha256:096c362b551bd9a6cdb1228a054ff3151a229b79b087fdcc91f945ce13fb1030
+size 5048