o 3wi8@spddlmZGdddeZGdddeZGdddeZGdd d eZGd d d eZGd d d eZdS))Optimizer2Statec4eZdZ         d fd d ZZS)AdamMbP?g?g+?:0yE>rF NdTc s(tjd|||||||| | | | d dS)a Base Adam optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-3): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. amsgrad (`bool`, defaults to `False`): Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. adamis_pagedNsuper__init__ selfparamslrbetaseps weight_decayamsgrad optim_bitsargs min_8bit_sizepercentile_clipping block_wiser  __class__T/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/bitsandbytes/optim/adam.pyr , z Adam.__init__ rrrrFrNr r TF__name__ __module__ __qualname__r __classcell__r r rr!r rcr)Adam8bitrrrrFrNr r Tc (tjd|||||d|| | | | d dS)a 8-bit Adam optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-3): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. amsgrad (`bool`, defaults to `False`): Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. r r Nrrrr r!rHr"zAdam8bit.__init__r#r$r r rr!r*Gr)r*cr) Adam32bitrrrrFrNr r Tc r+)a 32-bit Adam optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-3): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. amsgrad (`bool`, defaults to `False`): Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. r rr Nrrrr r!rr"zAdam32bit.__init__r#r$r r rr!r-r)r-cr) PagedAdamrrrrFrNr r Tc s(tjd|||||||| | | dd dS)a Paged Adam optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-3): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. amsgrad (`bool`, defaults to `False`): Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. r Tr Nrrrr r!rr"zPagedAdam.__init__r#r$r r rr!r.r)r.cr) PagedAdam8bitrrrrFrNr r Tc (tjd|||||d|| | | dd dS)a 8-bit paged Adam optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-3): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. amsgrad (`bool`, defaults to `False`): Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. r r,Tr Nrrrr r!rr"zPagedAdam8bit.__init__r#r$r r rr!r/r)r/cr)PagedAdam32bitrrrrFrNr r Tc r0)a Paged 32-bit Adam optimizer. Arguments: params (`torch.tensor`): The input parameters to optimize. lr (`float`, defaults to 1e-3): The learning rate. betas (`tuple(float, float)`, defaults to (0.9, 0.999)): The beta values are the decay rates of the first and second-order moment of the optimizer. eps (`float`, defaults to 1e-8): The epsilon value prevents division by zero in the optimizer. weight_decay (`float`, defaults to 0.0): The weight decay value for the optimizer. amsgrad (`bool`, defaults to `False`): Whether to use the [AMSGrad](https://hf.co/papers/1904.09237) variant of Adam that uses the maximum of past squared gradients instead. optim_bits (`int`, defaults to 32): The number of bits of the optimizer state. args (`object`, defaults to `None`): An object with additional arguments. min_8bit_size (`int`, defaults to 4096): The minimum number of elements of the parameter tensors for 8-bit optimization. percentile_clipping (`int`, defaults to 100): Adapts clipping threshold automatically by tracking the last 100 gradient norms and clipping the gradient at a certain percentile to improve stability. block_wise (`bool`, defaults to `True`): Whether to independently quantize each block of tensors to reduce outlier effects and improve stability. is_paged (`bool`, defaults to `False`): Whether the optimizer is a paged optimizer or not. r rTr Nrrrr r!r<r"zPagedAdam32bit.__init__r#r$r r rr!r1;r)r1N)bitsandbytes.optim.optimizerrrr*r-r.r/r1r r r r!s =====