Model save

README.md

@@ -37,10 +37,10 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
+- gradient_accumulation_steps: 8
 - total_train_batch_size: 8
 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
-    "down_proj",
     "q_proj",
+    "o_proj",
+    "down_proj",
     "gate_proj",
-    "k_proj",
-    "o_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee58a3cccd886ceb7b3576f2f782dadbca62f93bc4d417854a1dfae6a6087a22
+oid sha256:a2442ad96c03f092800407cb601911c574a99977300b907dc85a26b5f575d171
 size 239536272

trainer_state.json

@@ -11,7 +11,7 @@
   "log_history": [
     {
       "epoch": 0.2807017543859649,
-      "grad_norm": 0.45554453134536743,
+      "grad_norm": 0.47223395109176636,
       "learning_rate": 9.425837320574164e-05,
       "loss": 0.9903,
       "step": 20
@@ -43,8 +43,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3581716173422592.0,
-  "train_batch_size": 2,
+  "total_flos": 2320839556472832.0,
+  "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d05c90144bcf8f52756fa34eb395f16b255214cc39ff08e3d533b3c8e3cf2775
+oid sha256:762ae01d66bb0952e06e030d2e899f178b284f3cef975065f45977cdae82f9c3
 size 5841