End of training

README.md

@@ -1,20 +1,20 @@
 ---
-base_model: meta-llama/Meta-Llama-3.1-70B
+base_model: mistralai/Mistral-Large-Instruct-2407
 library_name: peft
-license: llama3.1
+license: other
 tags:
 - generated_from_trainer
 model-index:
-- name: Meta-Llama-3.1-70B-tac08
+- name: Mistral-Large-Instruct-2407-tac08
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Meta-Llama-3.1-70B-tac08
+# Mistral-Large-Instruct-2407-tac08
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-70B](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407) on the None dataset.
 
 ## Model description
 
@@ -33,12 +33,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
+- learning_rate: 0.0004
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.12.0
-- Transformers 4.44.0
+- Transformers 4.44.2
 - Pytorch 2.4.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1