End of training

README.md

@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 5
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 5
-- total_train_batch_size: 25
+- total_train_batch_size: 40
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 2
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -9,22 +9,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 48,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 24,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
-    "v_proj",
     "fc2",
+    "v_proj",
+    "fc1",
     "dense",
-    "fc1"
+    "k_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:c0fade696f7e6c5a9fd76d2cc286d6d6c866e69a2faf22d564dfef3668607846
-size 94422368
+oid sha256:e6910b73307db3e18e69c9fc52ccb46fee74eec46ef6a9409e584289eb1ecf72
+size 141608544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3b04c7ff4be11a413c35196223e8160fd827c79c063f7d65f69ebc3eb8e0fd2
+oid sha256:d329e05ba9f6a3a402c5e375c7e64b8807ce19c8c419f1336ff9f9eaefe2f52b
 size 4664