Tatvajsh/Lllama_AHS_V_6.6

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 12
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- training_steps: 100
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -8,22 +8,22 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
-    "o_proj",
     "base_layer",
     "v_proj",
-    "gate_proj",
     "k_proj",
-    "q_proj"
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc2f9dd79a80bdd2004823a89a8c3072392ea27dbeef132c2ab6575f2ecdc8a
-size 50982397
+oid sha256:12cbb47dc64a31a3d90710f226f30cc36a3e2bf0122352db00cfddacc45e6b97
+size 101834237

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405f4f73cce30ce5798ff722205f526d10c9241bca55e2988c724316a269fed6
+oid sha256:d427cc796b3149d6120dd0ace878be96a1543a258c7af094af99dbbb2288101c
 size 4027