oz1115/gemma_2b_it_ko_adapter

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 0.03
+- lr_scheduler_warmup_steps: 3
 - training_steps: 100
 - mixed_precision_training: Native AMP
 
@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.9.0
-- Transformers 4.38.2
+- PEFT 0.12.0
+- Transformers 4.43.4
 - Pytorch 2.3.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "down_proj",
-    "q_proj",
     "k_proj",
+    "v_proj",
+    "q_proj",
     "gate_proj",
-    "v_proj"
+    "down_proj",
+    "o_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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:90882106c502840a0e2fbe1f1fe83cce47769b9856403520435fa95ef5fecbd6
+size 29450584

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6060511074d2fd48bd3d5248318fdcfeb03d03ec0d9d9c4ecfa3befc7016173c
-size 17518595
+oid sha256:36827d0e8282c6dfe284c3a59cae2b855cf498397ce22e8fd2559e5a14acb882
+size 17518623

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674d6f5b7e182e62f6c92f67f5060a24c0de8de28bba1face8b9537d423446cd
-size 4856
+oid sha256:b9a44ffd8187d932a01cde7e407be1557d5f34af8cab478d9bdd8a3a458d30ef
+size 5368