End of training

README.md

@@ -36,15 +36,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 1
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 12
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "up_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
-    "v_proj",
+    "k_proj",
     "lm_head",
-    "down_proj",
+    "up_proj",
     "o_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4faa57709045749f488536465f66628637c510a081d5dfbac2ccccf66f8283a0
+oid sha256:34728f77dffeb8a26342bfb9c0b92052a63a29325f68eaad807d0c3739a643d3
 size 2132797264

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e22c9d953c4820f48d03df7155320cec2f5955ba726b11b289bfa63d39d7de
+oid sha256:70eba4de60d858599509cd1997fea636aa21a11d5c5752dc9379fd27dfe7bfcf
 size 4603