End of training

README.md

@@ -2,12 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
 base_model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ
 model-index:
 - name: mistral-finetuned-samsum
   results: []
-pipeline_tag: text-generation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,38 +30,17 @@ More information needed
 
 More information needed
 
-
 ## Training procedure
 
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: gptq
-- bits: 4
-- tokenizer: None
-- dataset: None
-- group_size: 128
-- damp_percent: 0.1
-- desc_act: True
-- sym: True
-- true_sequential: True
-- use_cuda_fp16: False
-- model_seqlen: None
-- block_name_to_quantize: None
-- module_name_preceding_first_block: None
-- batch_size: 1
-- pad_token_id: None
-- use_exllama: False
-- max_input_length: None
-- exllama_config: {'version': <ExllamaVersion.ONE: 1>}
-- cache_block_outputs: True
-
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 6
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 24
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - training_steps: 250
@@ -72,8 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.7.0
-- Transformers 4.36.0.dev0
+- PEFT 0.7.1
+- Transformers 4.37.0.dev0
 - Pytorch 2.1.0+cu118
-- Datasets 2.15.0
+- Datasets 2.16.0
 - Tokenizers 0.15.0