Model save

README.md

@@ -1,6 +1,6 @@
 ---
-license: other
-base_model: huggyllama/llama-7b
+license: apache-2.0
+base_model: kaist-ai/CoT-T5-11B
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama_instr_tune_fact_checking
 
-This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on the None dataset.
+This model is a fine-tuned version of [kaist-ai/CoT-T5-11B](https://huggingface.co/kaist-ai/CoT-T5-11B) on the None dataset.
 
 ## Model description
 
@@ -33,11 +33,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 16
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
@@ -51,5 +51,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.34.1
 - Pytorch 2.1.0+cu118
-- Datasets 2.14.5
+- Datasets 2.14.6
 - Tokenizers 0.14.1