Training procedure
The following bitsandbytes
quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.4.0
This model was trained with this parameters:
max_seq_length = 2048
training_arguments_mistral = {
'num_train_epochs':10,
'per_device_train_batch_size':2,
'gradient_accumulation_steps':2,
'gradient_checkpointing':True,
'optim':'adamw_torch',
'lr_scheduler_type':'constant_with_warmup',
'logging_steps':10,
'evaluation_strategy':'epoch',
'save_strategy':"epoch",
'load_best_model_at_end':True,
'learning_rate':4e-4,
'save_total_limit':3,
'fp16':True,
'tf32': True,
'max_steps':8000,
'max_grad_norm':0.3,
'warmup_ratio':0.03,
'disable_tqdm':False,
'weight_decay':0.001,
'hub_model_id':'Weni/WeniGPT-Mistral-7B-instructBase-4bit',
'push_to_hub':True,
'hub_strategy':'every_save',
'hub_token':token,
'hub_private_repo':True,
- Downloads last month
- 3