End of training

README.md

@@ -34,13 +34,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2.5e-05
-- train_batch_size: 2
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1
-- training_steps: 10
+- training_steps: 20
 
 ### Training results
 

adapter_config.json

@@ -8,8 +8,11 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 64,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 32,
@@ -17,13 +20,13 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "lm_head",
-    "gate_proj",
     "q_proj",
-    "v_proj",
-    "k_proj",
     "o_proj",
-    "down_proj"
+    "down_proj",
+    "lm_head",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2827c58ca97279a85f4b491135e010b80617aa4a6f145e799934310648244670
-size 324496576
+oid sha256:15f1abdc7691ab2edb87bd4d320af9a75d1757f3ac105a67897cad6e207173fb
+size 848784976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17380de975de1419c11fd42b79873d8fe578e5085cd6e365fd0ff3f1d6e6def2
+oid sha256:de51cf1115f66f380d849a6cf778b3ce30587cc467af26dfe3b1a49a9e63e000
 size 4664