Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Meta-Llama-3-8B-Instruct
+base_model: scb10x/llama-3-typhoon-v1.5-8b-instruct
 library_name: peft
 license: llama3
 tags:
@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results_1
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [scb10x/llama-3-typhoon-v1.5-8b-instruct](https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.3737
-- eval_runtime: 77.6899
-- eval_samples_per_second: 5.779
-- eval_steps_per_second: 0.734
-- epoch: 2.4053
+- eval_loss: 1.1364
+- eval_runtime: 81.6834
+- eval_samples_per_second: 5.497
+- eval_steps_per_second: 0.698
+- epoch: 1.8060
 - step: 270
 
 ## Model description
@@ -43,11 +43,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
+- train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- total_train_batch_size: 12
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 12

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4322968182d4fcf7806309944a97da21f1b0a613b655fffd2b15f65a1d86a3f
+oid sha256:f5914ef2ca54f02f064780a95c9270ed42395d0a738046f4e0aedc10ebdb56a1
 size 125889008