Model save

README.md

@@ -37,15 +37,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 32
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 64
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1
+- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d414d1358bc04dac1a290726e095ecda7ef7c9e524865152af5274d04998f918
-size 67126232
+oid sha256:64f76e5cdec7ad3f6060b4d82e60bef387d112e1544514bea4192f7b82f585a2
+size 134235048

runs/Feb23_00-28-22_97a16b743b3b/events.out.tfevents.1708648297.97a16b743b3b.143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6cd25ea23e046fc9572094e8fc949cde6af7f299969459341b5dc3860ed895
+size 14713

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f434296bdc60b68b40a76e85a6c4d60049a203206265a6a7bd691d95319e75e9
+oid sha256:8428d6d2abf97eaa6c94c3722a996c1fead522d9ecfe977dceb2231dadb1c6c2
 size 4728