seriouspark/gemma-2b-it-v0.3-lora-persona1_epoch1

README.md

@@ -5,7 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: google/gemma-7b-it
+base_model: google/gemma-2b-it
 model-index:
 - name: outputs
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) on an unknown dataset.
+This model is a fine-tuned version of [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) on an unknown dataset.
 
 ## Model description
 
@@ -44,13 +44,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 0.1
-- training_steps: 1000
+- training_steps: 16000
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.8.2
 - Transformers 4.39.0
-- Pytorch 2.1.2
-- Datasets 2.19.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "v_proj",
     "gate_proj",
-    "down_proj",
+    "o_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
-    "o_proj",
-    "v_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d7fb3cb96f78b6bf279c3ff078caf4bd6fbdcdaa0ad3b4b030d8ba0ce8edb74
-size 400104600
+oid sha256:5e00cb039c054e7b8b981586a207081e21bcb9453dcd86cf2aa8925343bdf3ab
+size 156965440

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e18dd421112bed671fb07745e80f2721b67f3a2fcf4fdf49c1a938140902da
-size 4856
+oid sha256:6f9e68f7c00431ff948ed595f55879bf54e07b92103602e906af35a43fa83280
+size 4920