End of training

README.md

@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1.0
+- num_epochs: 2.0
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -21,18 +21,18 @@
   "revision": null,
   "target_modules": [
     "fc2",
-    "down_proj",
-    "out_proj",
-    "lm_head",
-    "q_proj",
-    "linear_1",
-    "linear_2",
     "v_proj",
+    "up_proj",
+    "linear_2",
+    "q_proj",
     "gate_proj",
+    "lm_head",
+    "out_proj",
+    "o_proj",
     "k_proj",
-    "up_proj",
-    "fc1",
-    "o_proj"
+    "down_proj",
+    "linear_1",
+    "fc1"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb43ff1e725e6a7c6eab86439865cdcaa381ed23bca8c88cf19bc8be366d047
+oid sha256:600084361faa3ba22c1637f04a4d5cdc12a37c7d58d80c31a22020878a1a00dc
 size 1462134480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58c533a0c72e48a31f7794dc84f75446ff92ce2dbe7f3e5e4af67de3a58577bc
+oid sha256:66b6d86eece853179fb99ed67b9a27b0a81320f33de8ff66f7ba939cd37c7d83
 size 6712