yunfan-y/trump-gemma-qa

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: google/gemma-2-2b-it
+base_model: google/gemma-2-9b-it
 library_name: peft
 license: gemma
 tags:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # result
 
-This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
 
 ## Model description
 
@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 2
+- 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: 50

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-2-2b-it",
+  "base_model_name_or_path": "google/gemma-2-9b-it",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72c481391535e2b4a9472cfd0a8e283c3bfe7d1281909e6cbeb180172d5a9af
-size 2372108040
+oid sha256:52a6775017fe5bcfb14c22c6836a807970e7ac8a1a99903e322addf5085dc823
+size 3705850136

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a961c152e85230507f9e76a3dc50ab12e9c625219bff34217964f4203a09ae5b
+oid sha256:8a3462b34fad9adb08be4d5cc15e07db3691d6254a6365e26a49a667ed66232b
 size 5432