End of training

README.md

@@ -1,6 +1,7 @@
 ---
-base_model: NousResearch/Llama-2-7b-hf
+base_model: ahxt/LiteLlama-460M-1T
 library_name: peft
+license: mit
 tags:
 - trl
 - sft
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # YaHaHamaraLlama
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
+This model is a fine-tuned version of [ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T) on the None dataset.
 
 ## Model description
 
@@ -36,15 +37,14 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
 - train_batch_size: 8
-- eval_batch_size: 6
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 3
-- mixed_precision_training: Native AMP
+- num_epochs: 5
 
 ### Training results
 
@@ -53,7 +53,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.12.0
-- Transformers 4.42.4
+- Transformers 4.43.3
 - Pytorch 2.3.1+cu121
-- Datasets 2.20.0
+- Datasets 2.17.0
 - Tokenizers 0.19.1