32fa5cfaf3
* fix gpu init after removing debug print in mpu Signed-off-by: ericharper <complex451@gmail.com> * add fused_adam Signed-off-by: ericharper <complex451@gmail.com> * check ds is not none before logging len Signed-off-by: ericharper <complex451@gmail.com> * set fp16 arg to true and fix enum conflict Signed-off-by: ericharper <complex451@gmail.com> * make fp16 arg configurable Signed-off-by: ericharper <complex451@gmail.com> * add grad clip from megatron Signed-off-by: ericharper <complex451@gmail.com> * Linear warmup with cosine annealing and constant holding (#2846) * Testing cosine schedule Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Style fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * More fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * update config for constant steps in schedule Signed-off-by: ericharper <complex451@gmail.com> * temporarily import enum from megatron Signed-off-by: ericharper <complex451@gmail.com> * add grad clip for fp32 Signed-off-by: ericharper <complex451@gmail.com> * update check for _del_model_without_trainer Signed-off-by: ericharper <complex451@gmail.com> * updating restore for model parallel Signed-off-by: ericharper <complex451@gmail.com> * add predict script Signed-off-by: ericharper <complex451@gmail.com> * update test iters Signed-off-by: ericharper <complex451@gmail.com> * add barrier Signed-off-by: ericharper <complex451@gmail.com> * return if clip_val is 0 or None Signed-off-by: ericharper <complex451@gmail.com> * when using amp clip grads after they are unscaled Signed-off-by: ericharper <complex451@gmail.com> * make native amp scaler hyperparams configurable Signed-off-by: ericharper <complex451@gmail.com> * (1) nvfuser, (2) amp-casting decoration (#2894) * (1) nvfuser, (2) amp-casting decoration Signed-off-by: Sangkug Lym <slym@nvidia.com> * support bf16 Signed-off-by: Sangkug Lym <slym@nvidia.com> * update package info Signed-off-by: ericharper <complex451@gmail.com> * add set device to constructor Signed-off-by: ericharper <complex451@gmail.com> * set_device in constructor Signed-off-by: ericharper <complex451@gmail.com> * [BigNLP] Remove megatron-lm dependency. (#2910) * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * update megatron_init Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * update process batch Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * add megatron clip_grad Signed-off-by: ericharper <complex451@gmail.com> * trying to resolve circular import error Signed-off-by: ericharper <complex451@gmail.com> * rename file Signed-off-by: ericharper <complex451@gmail.com> * remove non-gpt models and datasets from __init__ files Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set_device in constructor Signed-off-by: ericharper <complex451@gmail.com> * clean config Signed-off-by: ericharper <complex451@gmail.com> * update MegatronDataset Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * rename fp16 and bf16 flags to fused_softmax_input_in_fp16/bf16 Signed-off-by: ericharper <complex451@gmail.com> * rename to fused_fp16 Signed-off-by: ericharper <complex451@gmail.com> * add fused_fp16 arg to LayerNorm calls Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix import Signed-off-by: ericharper <complex451@gmail.com> * update arg Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * Adding complete method to MegatronGPTModel (#2935) Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * make ffn_hidden_size mandatory Signed-off-by: ericharper <complex451@gmail.com> * Manually migrating timing of step into branch (#2937) * 1. Manually migrating timing of step into branch. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated file name and content. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated to latest code. Signed-off-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> * remove unused imports Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * check fused_fp16 and fused_bf16 are not both True Signed-off-by: ericharper <complex451@gmail.com> * update predict script for model parallel .nemo Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@users.noreply.github.com> Co-authored-by: Micha Livne <michalivne@users.noreply.github.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> * NVfuser (#2943) * activation checkpoint recompute Signed-off-by: Sangkug Lym <slym@nvidia.com> * selective nvfuser setup * Megatron gpt bfloat support (#2926) * Save/restore fix Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Another merge Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Bf16 args in init Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Set precision Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove debug stuff Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * add bf16 casting decorator Signed-off-by: Sangkug Lym <slym@nvidia.com> * Bfloat layernorm propagation Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * activation checkpoint recompute Signed-off-by: Sangkug Lym <slym@nvidia.com> * selective nvfuser setup * More arg removal Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove BERTDataset Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * update to latest apex and patch transformer autocast Signed-off-by: ericharper <complex451@gmail.com> Co-authored-by: Sangkug Lym <slym@nvidia.com> Co-authored-by: ericharper <complex451@gmail.com> * don't set jit for bf16 Signed-off-by: ericharper <complex451@gmail.com> * replace apex.mpu Signed-off-by: ericharper <complex451@gmail.com> * fix grad clip Signed-off-by: ericharper <complex451@gmail.com> * NVFuser fixes (#2951) * Fuser fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove dummy handler Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove PTL plugin based logic for fusion Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * remove duplicated file Signed-off-by: ericharper <complex451@gmail.com> * typo (#2960) Signed-off-by: ericharper <complex451@gmail.com> * [BigNLP] Script to convert GPT checkpoint to .nemo (#2958) * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * update megatron_init Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * update process batch Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * add megatron clip_grad Signed-off-by: ericharper <complex451@gmail.com> * trying to resolve circular import error Signed-off-by: ericharper <complex451@gmail.com> * rename file Signed-off-by: ericharper <complex451@gmail.com> * remove non-gpt models and datasets from __init__ files Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set_device in constructor Signed-off-by: ericharper <complex451@gmail.com> * clean config Signed-off-by: ericharper <complex451@gmail.com> * update MegatronDataset Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * rename fp16 and bf16 flags to fused_softmax_input_in_fp16/bf16 Signed-off-by: ericharper <complex451@gmail.com> * rename to fused_fp16 Signed-off-by: ericharper <complex451@gmail.com> * add fused_fp16 arg to LayerNorm calls Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix import Signed-off-by: ericharper <complex451@gmail.com> * update arg Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * Adding complete method to MegatronGPTModel (#2935) Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * make ffn_hidden_size mandatory Signed-off-by: ericharper <complex451@gmail.com> * Manually migrating timing of step into branch (#2937) * 1. Manually migrating timing of step into branch. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated file name and content. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated to latest code. Signed-off-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> * remove unused imports Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * check fused_fp16 and fused_bf16 are not both True Signed-off-by: ericharper <complex451@gmail.com> * update predict script for model parallel .nemo Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> * add script to convert .ckpt to .nemo Signed-off-by: ericharper <complex451@gmail.com> * in progress Signed-off-by: ericharper <complex451@gmail.com> * update Signed-off-by: ericharper <complex451@gmail.com> * convert mp checkpoints to nemo Signed-off-by: ericharper <complex451@gmail.com> * update help Signed-off-by: ericharper <complex451@gmail.com> * add safeguard for model parallel save_to Signed-off-by: ericharper <complex451@gmail.com> * adjust NLPModel save_to to be safer for model parallel Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@users.noreply.github.com> Co-authored-by: Micha Livne <michalivne@users.noreply.github.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * [BigNLP] Update GPT evaluation to work with tensor model parallel (#2959) * in progress Signed-off-by: ericharper <complex451@gmail.com> * update args Signed-off-by: ericharper <complex451@gmail.com> * add request dataset Signed-off-by: ericharper <complex451@gmail.com> * tokenize request Signed-off-by: ericharper <complex451@gmail.com> * in progress Signed-off-by: ericharper <complex451@gmail.com> * able to run Signed-off-by: ericharper <complex451@gmail.com> * reduce logits Signed-off-by: ericharper <complex451@gmail.com> * capture response Signed-off-by: ericharper <complex451@gmail.com> * squeeze and unsqueeze Signed-off-by: ericharper <complex451@gmail.com> * handle non model parallel case Signed-off-by: ericharper <complex451@gmail.com> * clean imports Signed-off-by: ericharper <complex451@gmail.com> * add file Signed-off-by: ericharper <complex451@gmail.com> * convert logits to log_probs Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * rename logits to log_probs Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * add megatron gpt pretraining Signed-off-by: ericharper <complex451@gmail.com> * add megatron gpt pretraining Signed-off-by: ericharper <complex451@gmail.com> * add megatron gpt pretraining Signed-off-by: ericharper <complex451@gmail.com> * updating to work with latest megatron Signed-off-by: ericharper <complex451@gmail.com> * updating to work with latest megatron Signed-off-by: ericharper <complex451@gmail.com> * update _del_model Signed-off-by: ericharper <complex451@gmail.com> * adding gpt model Signed-off-by: ericharper <complex451@gmail.com> * adding gpt model Signed-off-by: ericharper <complex451@gmail.com> * adding gpt model Signed-off-by: ericharper <complex451@gmail.com> * instantiate GPTmodel Signed-off-by: ericharper <complex451@gmail.com> * adding build dataset Signed-off-by: ericharper <complex451@gmail.com> * build megatron dataset in .setup Signed-off-by: ericharper <complex451@gmail.com> * setup dataloader Signed-off-by: ericharper <complex451@gmail.com> * add vocab_file and merge_file to megatron init Signed-off-by: ericharper <complex451@gmail.com> * add forward Signed-off-by: ericharper <complex451@gmail.com> * add train loss Signed-off-by: ericharper <complex451@gmail.com> * add optimizer Signed-off-by: ericharper <complex451@gmail.com> * add exp_manager Signed-off-by: ericharper <complex451@gmail.com> * multi-gpu is working Signed-off-by: ericharper <complex451@gmail.com> * adding val loop Signed-off-by: ericharper <complex451@gmail.com> * style Signed-off-by: ericharper <complex451@gmail.com> * adding val loop Signed-off-by: ericharper <complex451@gmail.com> * fix ranks Signed-off-by: ericharper <complex451@gmail.com> * fix model parallel checkpoint saving Signed-off-by: ericharper <complex451@gmail.com> * fix _del_model Signed-off-by: ericharper <complex451@gmail.com> * added megatron batch sampler Signed-off-by: ericharper <complex451@gmail.com> * try to fix num steps Signed-off-by: ericharper <complex451@gmail.com> * add wandb to config Signed-off-by: ericharper <complex451@gmail.com> * log lr Signed-off-by: ericharper <complex451@gmail.com> * add warmup ratio to config Signed-off-by: ericharper <complex451@gmail.com> * update configs Signed-off-by: ericharper <complex451@gmail.com> * update configs Signed-off-by: ericharper <complex451@gmail.com> * add cpu init to args Signed-off-by: ericharper <complex451@gmail.com> * update config Signed-off-by: ericharper <complex451@gmail.com> * update config Signed-off-by: ericharper <complex451@gmail.com> * Initial megatron dataset port Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Fix merge conflicts Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * License fixes and megatron model porting Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Style fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * More fixes to import from nemo rather than megatron Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Fix circular imports Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Style fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Revert config file Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Restructure further to avoid circular imports Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * add Makefile Signed-off-by: ericharper <complex451@gmail.com> * Add megatron modules Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * add license Signed-off-by: ericharper <complex451@gmail.com> * Port from latest megatron Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * update cfg Signed-off-by: ericharper <complex451@gmail.com> * update config Signed-off-by: ericharper <complex451@gmail.com> * add _del_model_without_trainer Signed-off-by: ericharper <complex451@gmail.com> * add data preprocessing script Signed-off-by: ericharper <complex451@gmail.com> * update config Signed-off-by: ericharper <complex451@gmail.com> * use apex mpu Signed-off-by: ericharper <complex451@gmail.com> * replace print_rank_0 with nemo utils logging Signed-off-by: ericharper <complex451@gmail.com> * use apex mpu Signed-off-by: ericharper <complex451@gmail.com> * use apex mpu Signed-off-by: ericharper <complex451@gmail.com> * add use_cpu_initialization Signed-off-by: ericharper <complex451@gmail.com> * fixing autoresume in progress Signed-off-by: ericharper <complex451@gmail.com> * properly removing last checkpoint Signed-off-by: ericharper <complex451@gmail.com> * log consumed samples Signed-off-by: ericharper <complex451@gmail.com> * fix mp autoresume Signed-off-by: ericharper <complex451@gmail.com> * add NLPSaveRestoreConnector Signed-off-by: ericharper <complex451@gmail.com> * Megatron GPT training with NeMo tokenizers (#2818) * Update files from megatron repo Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove non NLP data related files from megatron Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Merge megatron and nemo tokenizers Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove get_tokenizer() calls from gpt model Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Update tokenizer yaml config Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * add todo Signed-off-by: ericharper <complex451@gmail.com> * update config Signed-off-by: ericharper <complex451@gmail.com> * make init_method_std configurable Signed-off-by: ericharper <complex451@gmail.com> * make gpu init work by setting random seed earlier Signed-off-by: ericharper <complex451@gmail.com> * fix gpu init after removing debug print in mpu Signed-off-by: ericharper <complex451@gmail.com> * add fused_adam Signed-off-by: ericharper <complex451@gmail.com> * check ds is not none before logging len Signed-off-by: ericharper <complex451@gmail.com> * set fp16 arg to true and fix enum conflict Signed-off-by: ericharper <complex451@gmail.com> * make fp16 arg configurable Signed-off-by: ericharper <complex451@gmail.com> * add grad clip from megatron Signed-off-by: ericharper <complex451@gmail.com> * Linear warmup with cosine annealing and constant holding (#2846) * Testing cosine schedule Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Style fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * More fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * update config for constant steps in schedule Signed-off-by: ericharper <complex451@gmail.com> * temporarily import enum from megatron Signed-off-by: ericharper <complex451@gmail.com> * add grad clip for fp32 Signed-off-by: ericharper <complex451@gmail.com> * update check for _del_model_without_trainer Signed-off-by: ericharper <complex451@gmail.com> * updating restore for model parallel Signed-off-by: ericharper <complex451@gmail.com> * add predict script Signed-off-by: ericharper <complex451@gmail.com> * update test iters Signed-off-by: ericharper <complex451@gmail.com> * add barrier Signed-off-by: ericharper <complex451@gmail.com> * return if clip_val is 0 or None Signed-off-by: ericharper <complex451@gmail.com> * when using amp clip grads after they are unscaled Signed-off-by: ericharper <complex451@gmail.com> * make native amp scaler hyperparams configurable Signed-off-by: ericharper <complex451@gmail.com> * (1) nvfuser, (2) amp-casting decoration (#2894) * (1) nvfuser, (2) amp-casting decoration Signed-off-by: Sangkug Lym <slym@nvidia.com> * support bf16 Signed-off-by: Sangkug Lym <slym@nvidia.com> * update package info Signed-off-by: ericharper <complex451@gmail.com> * add set device to constructor Signed-off-by: ericharper <complex451@gmail.com> * set_device in constructor Signed-off-by: ericharper <complex451@gmail.com> * [BigNLP] Remove megatron-lm dependency. (#2910) * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * update megatron_init Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * update process batch Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * add megatron clip_grad Signed-off-by: ericharper <complex451@gmail.com> * trying to resolve circular import error Signed-off-by: ericharper <complex451@gmail.com> * rename file Signed-off-by: ericharper <complex451@gmail.com> * remove non-gpt models and datasets from __init__ files Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set_device in constructor Signed-off-by: ericharper <complex451@gmail.com> * clean config Signed-off-by: ericharper <complex451@gmail.com> * update MegatronDataset Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * rename fp16 and bf16 flags to fused_softmax_input_in_fp16/bf16 Signed-off-by: ericharper <complex451@gmail.com> * rename to fused_fp16 Signed-off-by: ericharper <complex451@gmail.com> * add fused_fp16 arg to LayerNorm calls Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix import Signed-off-by: ericharper <complex451@gmail.com> * update arg Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * Adding complete method to MegatronGPTModel (#2935) Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * make ffn_hidden_size mandatory Signed-off-by: ericharper <complex451@gmail.com> * Manually migrating timing of step into branch (#2937) * 1. Manually migrating timing of step into branch. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated file name and content. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated to latest code. Signed-off-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> * remove unused imports Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * check fused_fp16 and fused_bf16 are not both True Signed-off-by: ericharper <complex451@gmail.com> * update predict script for model parallel .nemo Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@users.noreply.github.com> Co-authored-by: Micha Livne <michalivne@users.noreply.github.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> * NVfuser (#2943) * activation checkpoint recompute Signed-off-by: Sangkug Lym <slym@nvidia.com> * selective nvfuser setup * Megatron gpt bfloat support (#2926) * Save/restore fix Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Another merge Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Bf16 args in init Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Set precision Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove debug stuff Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * add bf16 casting decorator Signed-off-by: Sangkug Lym <slym@nvidia.com> * Bfloat layernorm propagation Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * activation checkpoint recompute Signed-off-by: Sangkug Lym <slym@nvidia.com> * selective nvfuser setup * More arg removal Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove BERTDataset Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * update to latest apex and patch transformer autocast Signed-off-by: ericharper <complex451@gmail.com> Co-authored-by: Sangkug Lym <slym@nvidia.com> Co-authored-by: ericharper <complex451@gmail.com> * don't set jit for bf16 Signed-off-by: ericharper <complex451@gmail.com> * replace apex.mpu Signed-off-by: ericharper <complex451@gmail.com> * fix grad clip Signed-off-by: ericharper <complex451@gmail.com> * NVFuser fixes (#2951) * Fuser fixes Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove dummy handler Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove PTL plugin based logic for fusion Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * remove duplicated file Signed-off-by: ericharper <complex451@gmail.com> * typo (#2960) Signed-off-by: ericharper <complex451@gmail.com> * [BigNLP] Script to convert GPT checkpoint to .nemo (#2958) * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * remove args in progress Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * add load_fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * update megatron_init Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * add fused kernels Signed-off-by: ericharper <complex451@gmail.com> * update process batch Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * remove erroneous import Signed-off-by: ericharper <complex451@gmail.com> * add megatron clip_grad Signed-off-by: ericharper <complex451@gmail.com> * trying to resolve circular import error Signed-off-by: ericharper <complex451@gmail.com> * rename file Signed-off-by: ericharper <complex451@gmail.com> * remove non-gpt models and datasets from __init__ files Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set device in constructorfor gpu init Signed-off-by: ericharper <complex451@gmail.com> * set_device in constructor Signed-off-by: ericharper <complex451@gmail.com> * clean config Signed-off-by: ericharper <complex451@gmail.com> * update MegatronDataset Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * clean up MegatronModule Signed-off-by: ericharper <complex451@gmail.com> * rename fp16 and bf16 flags to fused_softmax_input_in_fp16/bf16 Signed-off-by: ericharper <complex451@gmail.com> * rename to fused_fp16 Signed-off-by: ericharper <complex451@gmail.com> * add fused_fp16 arg to LayerNorm calls Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix arg name Signed-off-by: ericharper <complex451@gmail.com> * fix import Signed-off-by: ericharper <complex451@gmail.com> * update arg Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * skip warmup default to True Signed-off-by: ericharper <complex451@gmail.com> * Adding complete method to MegatronGPTModel (#2935) Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * make ffn_hidden_size mandatory Signed-off-by: ericharper <complex451@gmail.com> * Manually migrating timing of step into branch (#2937) * 1. Manually migrating timing of step into branch. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated file name and content. Signed-off-by: Micha Livne <mlivne@nvidia.com> * 1. Updated to latest code. Signed-off-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> * remove unused imports Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * remove unused import Signed-off-by: ericharper <complex451@gmail.com> * check fused_fp16 and fused_bf16 are not both True Signed-off-by: ericharper <complex451@gmail.com> * update predict script for model parallel .nemo Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> * add script to convert .ckpt to .nemo Signed-off-by: ericharper <complex451@gmail.com> * in progress Signed-off-by: ericharper <complex451@gmail.com> * update Signed-off-by: ericharper <complex451@gmail.com> * convert mp checkpoints to nemo Signed-off-by: ericharper <complex451@gmail.com> * update help Signed-off-by: ericharper <complex451@gmail.com> * add safeguard for model parallel save_to Signed-off-by: ericharper <complex451@gmail.com> * adjust NLPModel save_to to be safer for model parallel Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@users.noreply.github.com> Co-authored-by: Micha Livne <michalivne@users.noreply.github.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * [BigNLP] Update GPT evaluation to work with tensor model parallel (#2959) * in progress Signed-off-by: ericharper <complex451@gmail.com> * update args Signed-off-by: ericharper <complex451@gmail.com> * add request dataset Signed-off-by: ericharper <complex451@gmail.com> * tokenize request Signed-off-by: ericharper <complex451@gmail.com> * in progress Signed-off-by: ericharper <complex451@gmail.com> * able to run Signed-off-by: ericharper <complex451@gmail.com> * reduce logits Signed-off-by: ericharper <complex451@gmail.com> * capture response Signed-off-by: ericharper <complex451@gmail.com> * squeeze and unsqueeze Signed-off-by: ericharper <complex451@gmail.com> * handle non model parallel case Signed-off-by: ericharper <complex451@gmail.com> * clean imports Signed-off-by: ericharper <complex451@gmail.com> * add file Signed-off-by: ericharper <complex451@gmail.com> * convert logits to log_probs Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * rename logits to log_probs Signed-off-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@nvidia.com> * style Signed-off-by: ericharper <complex451@gmail.com> * fix copyright headers Signed-off-by: ericharper <complex451@gmail.com> * fix copyright headers Signed-off-by: ericharper <complex451@gmail.com> * remove old TimingCallback Signed-off-by: ericharper <complex451@gmail.com> * style Signed-off-by: ericharper <complex451@gmail.com> * update jenkins to use latest apex and sandeep's fork Signed-off-by: ericharper <complex451@gmail.com> * update jenkins Signed-off-by: ericharper <complex451@gmail.com> * update jenkins Signed-off-by: ericharper <complex451@gmail.com> * update jenkins Signed-off-by: ericharper <complex451@gmail.com> * update jenkins Signed-off-by: ericharper <complex451@gmail.com> * try 2109 container Signed-off-by: ericharper <complex451@gmail.com> * try cuda container Signed-off-by: ericharper <complex451@gmail.com> * use internal container Signed-off-by: ericharper <complex451@gmail.com> * update checkpoint tests Signed-off-by: ericharper <complex451@gmail.com> * fix scheduler args Signed-off-by: ericharper <complex451@gmail.com> * update eval Signed-off-by: ericharper <complex451@gmail.com> * style Signed-off-by: ericharper <complex451@gmail.com> * update jenkins to use ptl 1.5 rc Signed-off-by: ericharper <complex451@gmail.com> * add import guard to jenkins Signed-off-by: ericharper <complex451@gmail.com> * add import guard to jenkins Signed-off-by: ericharper <complex451@gmail.com> * remove deterministic Signed-off-by: ericharper <complex451@gmail.com> * install numba .53 Signed-off-by: ericharper <complex451@gmail.com> * allow for more variance Signed-off-by: ericharper <complex451@gmail.com> * update trainer config dataclass Signed-off-by: ericharper <complex451@gmail.com> * test_get_optimizer on gpu Signed-off-by: ericharper <complex451@gmail.com> * revert comment Signed-off-by: ericharper <complex451@gmail.com> * change trainer config default to 32 Signed-off-by: ericharper <complex451@gmail.com> * [BigNLP] Remove fused kernel code instead use Apex (#2984) * remove fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * remove fused_kernels Signed-off-by: ericharper <complex451@gmail.com> * remove fused layer norm and fused softmax and use apex instead Signed-off-by: ericharper <complex451@gmail.com> * update imports Signed-off-by: ericharper <complex451@gmail.com> * remove comment Signed-off-by: ericharper <complex451@gmail.com> * use apex enums Signed-off-by: ericharper <complex451@gmail.com> * use apex enums Signed-off-by: ericharper <complex451@gmail.com> * add tab Signed-off-by: ericharper <complex451@gmail.com> * Timer with sliding window (#3002) Co-authored-by: Micha Livne <michalivne@users.noreply.github.com> * revert tab Signed-off-by: ericharper <complex451@gmail.com> * check for rank zero Signed-off-by: ericharper <complex451@gmail.com> * check for rank zero Signed-off-by: ericharper <complex451@gmail.com> * try explicit log dir Signed-off-by: ericharper <complex451@gmail.com> * add + Signed-off-by: ericharper <complex451@gmail.com> * don't rm Signed-off-by: ericharper <complex451@gmail.com> * make dir if it doesn't exist Signed-off-by: ericharper <complex451@gmail.com> * create mp nemo file in temp directory Signed-off-by: ericharper <complex451@gmail.com> * simplify mp save_to Signed-off-by: ericharper <complex451@gmail.com> * handle mp 1 case Signed-off-by: ericharper <complex451@gmail.com> * style fix Signed-off-by: ericharper <complex451@gmail.com> * remove files Signed-off-by: ericharper <complex451@gmail.com> * fix consumed_samples when resuming Signed-off-by: ericharper <complex451@gmail.com> * fix reinstall.sh Signed-off-by: ericharper <complex451@gmail.com> * update req Signed-off-by: ericharper <complex451@gmail.com> * add more detailed log for dataloaders Signed-off-by: ericharper <complex451@gmail.com> * check if cuda is available before using fused_adam Signed-off-by: ericharper <complex451@gmail.com> * revert comment Signed-off-by: ericharper <complex451@gmail.com> * update eval script to use model.freeze Signed-off-by: ericharper <complex451@gmail.com> * log train loss averaged over gradient accumulation steps Signed-off-by: ericharper <complex451@gmail.com> * check copyright earlier Signed-off-by: ericharper <complex451@gmail.com> * todo Signed-off-by: ericharper <complex451@gmail.com> * override SaveRestoreConnector in NLPModel init Signed-off-by: ericharper <complex451@gmail.com> * move to scripts Signed-off-by: ericharper <complex451@gmail.com> * remove star import Signed-off-by: ericharper <complex451@gmail.com> * remove comments Signed-off-by: ericharper <complex451@gmail.com> * remove unused dataset Signed-off-by: ericharper <complex451@gmail.com> * removed barrier Signed-off-by: ericharper <complex451@gmail.com> * check cfg Signed-off-by: ericharper <complex451@gmail.com> * remove logging Signed-off-by: ericharper <complex451@gmail.com> * freeze, unfreeze Signed-off-by: ericharper <complex451@gmail.com> * return None Signed-off-by: ericharper <complex451@gmail.com> * remove unused imports Signed-off-by: ericharper <complex451@gmail.com> * add TODO Signed-off-by: ericharper <complex451@gmail.com> * typecheck Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> * todo Signed-off-by: ericharper <complex451@gmail.com> * add common native plugin Signed-off-by: ericharper <complex451@gmail.com> * restore with trainer Signed-off-by: ericharper <complex451@gmail.com> * style Signed-off-by: ericharper <complex451@gmail.com> * deprecate megatron-lm bert Signed-off-by: ericharper <complex451@gmail.com> * deprecate megatron-lm bert Signed-off-by: ericharper <complex451@gmail.com> * compile helpers ont he fly Signed-off-by: ericharper <complex451@gmail.com> * remove amp_level Signed-off-by: ericharper <complex451@gmail.com> * remove amp_level from configs Signed-off-by: ericharper <complex451@gmail.com> * add missing import Signed-off-by: ericharper <complex451@gmail.com> * typo Signed-off-by: ericharper <complex451@gmail.com> * remove amp_level Signed-off-by: ericharper <complex451@gmail.com> * use fast huggingface tokenizers by default Signed-off-by: ericharper <complex451@gmail.com> * deal with huggingface tokenizer positional args Signed-off-by: ericharper <complex451@gmail.com> * deal with huggingface tokenizer positional args Signed-off-by: ericharper <complex451@gmail.com> * deal with huggingface tokenizer positional args Signed-off-by: ericharper <complex451@gmail.com> * revert use_fast default to False Signed-off-by: ericharper <complex451@gmail.com> * return super training_epoch_end Signed-off-by: ericharper <complex451@gmail.com> * remove optimizer_idx arg from training_step Signed-off-by: ericharper <complex451@gmail.com> * remove unused arg from on_train_epoch_end Signed-off-by: ericharper <complex451@gmail.com> * add restore_from_path to nemo config Signed-off-by: ericharper <complex451@gmail.com> * add comment Signed-off-by: ericharper <complex451@gmail.com> * revert Signed-off-by: ericharper <complex451@gmail.com> * override connector if not subclassing NLPSaveRestoreConnector for model parallel save Signed-off-by: ericharper <complex451@gmail.com> * update test optimizer Signed-off-by: ericharper <complex451@gmail.com> * clean up Signed-off-by: ericharper <complex451@gmail.com> * clean up Signed-off-by: ericharper <complex451@gmail.com> * clean up Signed-off-by: ericharper <complex451@gmail.com> * clean up Signed-off-by: ericharper <complex451@gmail.com> * make data_prefix mandatory in config Signed-off-by: ericharper <complex451@gmail.com> * update installation instructions on readme Signed-off-by: ericharper <complex451@gmail.com> * update dockerfile Signed-off-by: ericharper <complex451@gmail.com> * add todo Signed-off-by: ericharper <complex451@gmail.com> * raise error if trying to use always_save_nemo with model parallel model Signed-off-by: ericharper <complex451@gmail.com> * remove comment Signed-off-by: ericharper <complex451@gmail.com> Co-authored-by: Sandeep Subramanian <sandeep.subramanian.1@umontreal.ca> Co-authored-by: Sangkug Lym <slym@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@users.noreply.github.com> Co-authored-by: Micha Livne <michalivne@users.noreply.github.com> Co-authored-by: Micha Livne <mlivne@nvidia.com> Co-authored-by: Oleksii Kuchaiev <okuchaiev@nvidia.com>
184 lines
6.2 KiB
YAML
184 lines
6.2 KiB
YAML
# The bottleneck architecture supports three learning framework (i.e., losses)
|
|
# via model.model_type:
|
|
# 1) nll - Conditional cross entropy (the usual NMT loss)
|
|
# 2) mim - MIM learning framework. A latent variable model with good
|
|
# reconstruction and compressed latent representation.
|
|
# https://arxiv.org/pdf/2003.02645.pdf
|
|
# 3) vae - VAE learning framework. A latent variable model which learns
|
|
# good probability estimation over observations and
|
|
# a regularized latent representation.
|
|
# https://arxiv.org/pdf/1312.6114.pdf
|
|
# The bottleneck architecture supports three encoder architectures via
|
|
# model.encoder.arch:
|
|
# 1) seq2seq - the usual NMT model without bottleneck
|
|
# 2) bridge - a bottleneck which projects the encoder output to a fixed
|
|
# number of steps using attention bridge (https://arxiv.org/pdf/1703.03130.pdf)
|
|
# 3) perceiver - a bottleneck by projecting inputs to a fixed
|
|
# number of steps using perceiver architecture (https://arxiv.org/pdf/2103.03206.pdf)
|
|
# 4) max_pool / avg_pool - a reduction by halving the number of steps at the end of every hidden block.
|
|
# reduction is using max pooling or average pooling.
|
|
name: AttentionIsAllYouNeedBottleneck
|
|
do_training: True # set to False if only preprocessing data
|
|
do_testing: False # set to True to run evaluation on test data after training
|
|
|
|
model:
|
|
beam_size: 4
|
|
len_pen: 0.6
|
|
multilingual: False
|
|
max_generation_delta: -1
|
|
label_smoothing: 0.1
|
|
shared_tokenizer: True # train tokenizer model across src and tgt train data
|
|
preproc_out_dir: null # path to store data preprocessing outputs
|
|
src_language: 'en'
|
|
tgt_language: 'de'
|
|
model_type: 'nll' # learning (i.e., loss) type: nll (i.e., cross-entropy/auto-encoder), mim, vae (see description above)
|
|
min_logv: -6 # minimal allowed log variance for mim
|
|
latent_size: -1 # dimension of latent (projected from hidden) -1 will take value of hidden size
|
|
non_recon_warmup_batches: 200000 # warm-up steps for mim, and vae losses
|
|
recon_per_token: true # when false reconstruction is computed per sample, not per token
|
|
|
|
train_ds:
|
|
src_file_name: null
|
|
tgt_file_name: null
|
|
use_tarred_dataset: False # if true tar_file_name and meta_file_name will be used (or created automatically)
|
|
# config for preprocessing training data and creating a tarred datset automatically
|
|
tar_file_prefix: parallel # prefix for tar file names
|
|
tar_files: null # if data has already been preprocessed (rest of config ignored)
|
|
metadata_file: null # metadata for tarred dataset
|
|
lines_per_dataset_fragment: 1000000 # Number of lines to consider for bucketing and padding
|
|
num_batches_per_tarfile: 100 # Number of batches (pickle files) within each tarfile
|
|
tar_shuffle_n: 100 # How many samples to look ahead and load to be shuffled
|
|
shard_strategy: scatter # tarred dataset shard distribution strategy
|
|
n_preproc_jobs: -2 # number of processes to use for data preprocessing (-2 means all but 2)
|
|
tokens_in_batch: 512
|
|
clean: true
|
|
max_seq_length: 512
|
|
shuffle: true
|
|
num_samples: -1
|
|
drop_last: false
|
|
pin_memory: false
|
|
num_workers: 8
|
|
concat_sampling_technique: temperature # only used with ConcatTranslationDataset
|
|
concat_sampling_temperature: 5 # only used with ConcatTranslationDataset
|
|
concat_sampling_probabilities: null # only used with ConcatTranslationDataset
|
|
|
|
validation_ds:
|
|
src_file_name: ???
|
|
tgt_file_name: ???
|
|
tokens_in_batch: 512
|
|
clean: false
|
|
max_seq_length: 512
|
|
shuffle: false
|
|
num_samples: -1
|
|
drop_last: false
|
|
pin_memory: false
|
|
num_workers: 8
|
|
|
|
test_ds:
|
|
src_file_name: ???
|
|
tgt_file_name: ???
|
|
tokens_in_batch: 512
|
|
clean: false
|
|
max_seq_length: 512
|
|
shuffle: false
|
|
num_samples: -1
|
|
drop_last: false
|
|
pin_memory: false
|
|
num_workers: 8
|
|
|
|
optim:
|
|
name: adam
|
|
lr: 0.001
|
|
betas:
|
|
- 0.9
|
|
- 0.98
|
|
weight_decay: 0.0
|
|
sched:
|
|
name: InverseSquareRootAnnealing
|
|
min_lr: 0.0
|
|
last_epoch: -1
|
|
warmup_ratio: 0.1
|
|
|
|
encoder_tokenizer:
|
|
library: yttm
|
|
tokenizer_model: null
|
|
vocab_size: null # vocab size for training bpe
|
|
bpe_dropout: null
|
|
vocab_file: null
|
|
special_tokens: null
|
|
training_sample_size: null # valid for sentencepiece tokenizer
|
|
|
|
decoder_tokenizer:
|
|
library: yttm
|
|
tokenizer_model: null
|
|
vocab_size: null # vocab size for training bpe
|
|
bpe_dropout: null
|
|
vocab_file: null
|
|
special_tokens: null
|
|
training_sample_size: null # valid for sentencepiece tokenizer
|
|
|
|
encoder:
|
|
library: nemo
|
|
model_name: null
|
|
pretrained: false
|
|
max_sequence_length: 512
|
|
num_token_types: 0
|
|
embedding_dropout: 0.1
|
|
learn_positional_encodings: false
|
|
hidden_size: 512
|
|
num_layers: 6
|
|
inner_size: 2048
|
|
num_attention_heads: 8
|
|
ffn_dropout: 0.1
|
|
attn_score_dropout: 0.1
|
|
attn_layer_dropout: 0.1
|
|
hidden_act: relu
|
|
mask_future: false
|
|
pre_ln: false
|
|
pre_ln_final_layer_norm: true
|
|
arch: seq2seq # avg_pool, max_pool, seq2seq, bridge, perceiver (see description above)
|
|
hidden_steps: 32 # fixed number of hidden steps
|
|
hidden_blocks: 1 # number of repeat blocks (see classes for description)
|
|
hidden_init_method: default # see classes for available values
|
|
|
|
decoder:
|
|
library: nemo
|
|
model_name: null
|
|
pretrained: false
|
|
max_sequence_length: 512
|
|
num_token_types: 0
|
|
embedding_dropout: 0.1
|
|
learn_positional_encodings: false
|
|
hidden_size: 512
|
|
inner_size: 2048
|
|
num_layers: 6
|
|
num_attention_heads: 8
|
|
ffn_dropout: 0.1
|
|
attn_score_dropout: 0.1
|
|
attn_layer_dropout: 0.1
|
|
hidden_act: relu
|
|
pre_ln: false
|
|
pre_ln_final_layer_norm: true
|
|
arch: seq2seq # currently only seq2seq is supported
|
|
|
|
head:
|
|
num_layers: 1
|
|
activation: relu
|
|
log_softmax: true
|
|
dropout: 0.0
|
|
use_transformer_init: true
|
|
|
|
trainer:
|
|
gpus: 4
|
|
num_nodes: 1
|
|
max_epochs: 200
|
|
precision: 16 # Should be set to 16 for O1 and O2, default is 16 as PT ignores it when am_level is O0
|
|
accelerator: ddp
|
|
checkpoint_callback: False
|
|
logger: False
|
|
log_every_n_steps: 50 # Interval of logging.
|
|
check_val_every_n_epoch: 1
|
|
|
|
exp_manager:
|
|
name: AAYNBase
|
|
files_to_copy: [] |