Model save

README.md

@@ -44,7 +44,8 @@ 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_ratio: 0.05
-- training_steps: 10
+- training_steps: 140
+- mixed_precision_training: Native AMP
 
 ### Framework versions
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "k_proj",
+    "gate_proj",
     "o_proj",
     "v_proj",
-    "q_proj",
-    "gate_proj",
-    "k_proj",
-    "down_proj"
+    "up_proj",
+    "down_proj",
+    "q_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:c130bc7bba51fcf7ba71cf49236239a0e7fc180ba8073c7a8f5d29162b5def1d
+oid sha256:1484cefd504ab7306aa5553ddc4954d0b38af0d72db579a0c056315647289211
 size 156926880

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
-size 17518525
+oid sha256:36827d0e8282c6dfe284c3a59cae2b855cf498397ce22e8fd2559e5a14acb882
+size 17518623

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37fd9e26ec03cda8763231bf0e23468667784d92a977515b44587389b710b87
+oid sha256:a2fa4748920d50ed1222b316e5f2ea21ae716b5ea4d6d2f7c6670ea47be2ecda
 size 4539