|
|
--- |
|
|
library_name: peft |
|
|
language: |
|
|
- pt |
|
|
--- |
|
|
## 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, |
|
|
``` |
