Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: rinna/japanese-gpt-neox-3.6b
+base_model: cyberagent/open-calm-3b
 library_name: peft
-license: mit
+license: cc-by-sa-4.0
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lora
 
-This model is a fine-tuned version of [rinna/japanese-gpt-neox-3.6b](https://huggingface.co/rinna/japanese-gpt-neox-3.6b) on an unknown dataset.
+This model is a fine-tuned version of [cyberagent/open-calm-3b](https://huggingface.co/cyberagent/open-calm-3b) on an unknown dataset.
 
 ## Model description
 

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "GPTNeoXForCausalLM",
     "parent_library": "transformers.models.gpt_neox.modeling_gpt_neox"
   },
-  "base_model_name_or_path": "rinna/japanese-gpt-neox-3.6b",
+  "base_model_name_or_path": "cyberagent/open-calm-3b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "attention.query_key_value",
     "mlp.dense_h_to_4h",
-    "attention.dense",
     "mlp.dense_4h_to_h",
-    "attention.query_key_value"
+    "attention.dense"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9e660babf44b0418a0c73df182d426f49242f735d41c64ccf480f8d9c97ab1
-size 27837832
+oid sha256:93ab0cfc304c15164f60fdb20badb7c85d6b08ffa5001710fc123cfa9ef9eb98
+size 22500040

runs/Oct27_20-13-22_graz/events.out.tfevents.1730027614.graz.1069581.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d126cf006167cca67f1ec1cc3b404c1f198e72a8cd51795980884605a86c486
+size 5687

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a1898da87ecf03bba600ea114f4642e30b06e4011d1add4b3f2d37c1e366e5
+oid sha256:488612a99aa92971b8aeb6f72cef5f5d053ca687fb6d4c423846a7c5dc0220a1
 size 7151