taronklm/Qwen2.5-0.5B-Instruct-chatbot

README.md

@@ -1,60 +1,60 @@
 ---
-library_name: transformers
-license: apache-2.0
 base_model: Qwen/Qwen2.5-0.5B-Instruct
+datasets:
+- generator
+library_name: peft
+license: apache-2.0
 tags:
 - trl
 - sft
 - generated_from_trainer
-datasets:
-- generator
 model-index:
 - name: trained_model
   results: []
 ---
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-# trained_model
-
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the generator dataset.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 1
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.45.1
-- Pytorch 2.5.1+cpu
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# trained_model
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the generator dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.1
+- Pytorch 2.5.1+cpu
+- Datasets 3.0.1
+- Tokenizers 0.20.0

adapter_config.json

@@ -16,14 +16,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "o_proj",
     "q_proj",
-    "v_proj"
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "task_type": "CASUAL_LM",
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49ff0ea53d18b5246a3e8d9ce437725f5e0bfba2e8dbbca724a4c12316da6f8
-size 4338000
+oid sha256:cfbc2159c7fbe53e83476546a5700cb2ddb1714027cc026901ef6ce4d1ee8ff4
+size 8841592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93612e5f080373abe2115f82df55e7a6633a575113ed2345880f59464cec355
+oid sha256:3147a44829aaeded52568334e274104f25be6f4800bb0f2cb2455ee55cb3d918
 size 5368