HugoVoxx/Gemma-2-2b-it-ag

README.md

@@ -27,14 +27,14 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/hugovoxx-fpt-university/Fine-tune%20Gemma-2-2b-it%20on%20AlphaGeometry%20Dataset/runs/z1bghq7x)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/hugovoxx-fpt-university/Fine-tune%20Gemma-2-2b-it%20on%20AlphaGeometry%20Dataset/runs/8lpwdqxj)
 
 This model was trained with SFT.
 
 ### Framework versions
 
 - TRL: 0.12.0
-- Transformers: 4.46.1
+- Transformers: 4.46.2
 - Pytorch: 2.4.0
 - Datasets: 3.1.0
 - Tokenizers: 0.20.0

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "o_proj",
-    "v_proj",
-    "up_proj",
+    "gate_proj",
+    "k_proj",
     "q_proj",
-    "gate_proj"
+    "up_proj",
+    "o_proj",
+    "v_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:ace8410a30faa2f6d79e67fdbfebbb25e9f281452ef4b228f549a28828982849
+oid sha256:828b2f4a9f9248f70a7f24c0db1ba92387398ff2472917fc1b42497f8286f1f9
 size 664584480

special_tokens_map.json

@@ -17,13 +17,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<eos>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ce83119bb404f7f0a6e621b76759d476357dcd01241a90f9ca136ae2b3c11c
+oid sha256:9afc4612a55c9c4b6223058eb59ae051813e1a51cb3f95b0f29ad864d50e4781
 size 34362972

tokenizer_config.json

@@ -2004,7 +2004,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "<eos>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:596413e096e180e4d997c1384160426f0264bcbb06d1845112850d4504f35f5c
+oid sha256:5832e276812db679395e1cdc57431215e3be0e358d384f67cebebe545fe2745a
 size 5496