End of training

README.md

@@ -41,6 +41,11 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
 
 ### Framework versions
 

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "lm_head",
+    "gate_proj",
     "k_proj",
     "q_proj",
-    "gate_proj",
-    "up_proj",
+    "lm_head",
     "o_proj",
     "v_proj",
+    "up_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:091d01db986b82b92baec6e38e1e57fcecacb667928926185a1d2a60ab9799c8
+oid sha256:5a006b07568e179a86e4b40b4cb84fc5e6e8113c97350a1d40dbe76180c53f67
 size 694431312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22aa1809070ec5ae84dd334a6296b3604ca00810b74ceef5aaef78ce9a9a5d30
+oid sha256:5318028c0a68bbc6499df23837ecfc810922c90fd4962caa2bdba56df140162e
 size 4728