End of training

README.md

@@ -34,14 +34,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-09
+- learning_rate: 1.4e-05
 - train_batch_size: 64
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1.0
-- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_config.json

@@ -21,18 +21,18 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "out_proj",
-    "linear_1",
-    "q_proj",
-    "fc1",
+    "v_proj",
     "k_proj",
-    "up_proj",
+    "out_proj",
+    "o_proj",
+    "fc2",
     "down_proj",
-    "v_proj",
     "linear_2",
     "lm_head",
-    "fc2",
-    "o_proj"
+    "q_proj",
+    "linear_1",
+    "up_proj",
+    "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:a6648d1aef1170daf2db772d66fb1a4540071368ae906a223255a6e7ebcb10c1
-size 358476032
+oid sha256:0788030d8afc74a81eeb792f85a29610ed2e16266efc66fb41afe21b3aaf01d5
+size 358476776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8041d243684f9feb2bc2e33c2a736fb4a708f5f2fedd9ba822ebe0ff974c54
+oid sha256:7902f7472461771e28a30e7dbb795c2c7f636b5f26421f5769f72febb829033d
 size 5304