End of training

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch 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
-- num_epochs: 10
+- training_steps: 2000
 
 ### Training results
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "down_proj",
+    "gate_proj",
+    "v_proj",
     "k_proj",
+    "o_proj",
     "q_proj",
-    "v_proj",
-    "gate_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 sha256:4ec97c93ae698dc7737723793ea20a3a45f4363c227dc8c398e2096ebd34aa61
+oid sha256:2a6c85c2beb20a99847126f4fb4ac1d8514500dad79874cc0e2fed01faac7131
 size 47584968

runs/Jan27_18-02-58_ws-l4-010/events.out.tfevents.1737986579.ws-l4-010.3206440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028d4e0fd091091f4f55e8da5a5985530b4a414815b122edb38c0c0f9861e5a0
+size 10500

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac7606ef00e1540e26f8371d6c43be79f9666224c21baf53fcc5fb038333517
-size 5368
+oid sha256:360f9f46d1eb83ca9bde79e49e638ef333dc2f34c32ba78168d1f72bbfba5076
+size 5432