gemma-2-2B-hermes-function-calling-adapter

README.md

@@ -1,7 +1,6 @@
 ---
-base_model: unsloth/gemma-2-2b-it-bnb-4bit
+base_model: bitshrine/gemma-2-2B-it-hermes-json-mode
 library_name: peft
-license: gemma
 tags:
 - trl
 - sft
@@ -17,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gemma-2-2B-hermes-function-calling-adapter
 
-This model is a fine-tuned version of [unsloth/gemma-2-2b-it-bnb-4bit](https://huggingface.co/unsloth/gemma-2-2b-it-bnb-4bit) on an unknown dataset.
+This model is a fine-tuned version of [bitshrine/gemma-2-2B-it-hermes-json-mode](https://huggingface.co/bitshrine/gemma-2-2B-it-hermes-json-mode) on an unknown dataset.
 
 ## Model description
 
@@ -45,16 +44,12 @@ 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: 5
-- training_steps: 180
+- training_steps: 1262
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
-- PEFT 0.12.0
+- PEFT 0.13.0
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/gemma-2-2b-it-bnb-4bit",
+  "base_model_name_or_path": "bitshrine/gemma-2-2B-it-hermes-json-mode",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,25 +10,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
-    "up_proj",
     "q_proj",
-    "v_proj",
     "o_proj",
-    "gate_proj"
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0645cbf3b72d27961ca56f1f50a32f8200bff47811d71479462b782ef78b91a5
-size 2442466784
+oid sha256:7b7c3d46e3836f421b55996ce3b41f737cfbd441019c6b68b113c76428d99d43
+size 2525534008

runs/Sep26_06-47-30_d62f90f8f9d3/events.out.tfevents.1727333276.d62f90f8f9d3.422.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d94a36551c13286f558617477ca54ad6609d98f879139f0dcd48d75152641a
+size 111229

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6497e601cf2fb129e59a2d7925e04e03dddce9487aee92d124a426fcc8f6d0
-size 5496
+oid sha256:f8c78a30101788d8ccdc3c26c408302563baeec811ff389eb4fcb635898afc66
+size 5560