End of training

README.md

@@ -1,6 +1,7 @@
 ---
-license: llama3
 base_model: minionai/llama3-8b-all-cove-reas-data-062024
+library_name: peft
+license: llama3
 tags:
 - trl
 - reward-trainer
@@ -52,7 +53,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.12.0
 - Transformers 4.44.0
 - Pytorch 2.3.1+cu121
 - Datasets 2.20.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "minionai/llama3-8b-all-cove-reas-data-062024",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ab7120fa85007425a4f76ad73db485befa5bea1c83af0cccfc1f844ca46542
+size 6841016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807fa6ba147fae5a5f6cd5e86aec68943815e2d346d8eaf07ebf737049f75da6
-size 6328
+oid sha256:a9f019e9a1fff66b9db22f52bbd4243d061e0d31231f2dc41a8d5d36018dc720
+size 6200