End of training

README.md

@@ -1,11 +1,14 @@
 ---
-base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
-license: llama3.2
+license: llama3
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
-- trl
+- base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
+- lora
 - sft
-- generated_from_trainer
+- transformers
+- trl
+pipeline_tag: text-generation
 model-index:
 - name: Baha_2A
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Baha_2A
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset.
+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.
 
 ## Model description
 
@@ -36,15 +39,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 16
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- training_steps: 1100
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -53,8 +56,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.1.dev0
-- Transformers 4.45.1
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.20.0
+- PEFT 0.18.1.dev0
+- Transformers 4.57.2
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1