End of training

README.md

@@ -9,11 +9,6 @@ base_model: jingyeom/freeze_KoSoLAR-10.7B-v0.2_1.4_dedup
 model-index:
 - name: lora_freeze_KoSoLAR-10.7B-v0.2_1.4_dedup_SFT-DPO
   results: []
-datasets:
-- jondurbin/truthy-dpo-v0.1
-- Intel/orca_dpo_pairs
-- HuggingFaceH4/ultrafeedback_binarized
-- argilla/distilabel-math-preference-dpo
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -37,9 +32,26 @@ More information needed
 
 ## Training procedure
 
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 6
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 48
+- total_eval_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
 ### Training results
 
-:)
+
 
 ### Framework versions
 

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47708157ea8d4c0b5f6cb4c541d5ea5ea9f0aade2dcb40813a32b033084505f3
+oid sha256:f443f560587757126ccacc9aaa78713e63f5acc9d61d64e5edc5c029e7054420
 size 10249120