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>
122 lines
5.8 KiB
YAML
122 lines
5.8 KiB
YAML
name: &name "Wav2vec_large_Pretrain"
|
|
# For more details on the model parameters, see nemo/collections/asr/models/wav2vec/wav2vec_config.py
|
|
# These parameters are based off the FairSeq implementation.
|
|
# See here: https://github.com/pytorch/fairseq/blob/master/examples/wav2vec/config/pretraining/wav2vec2_large_librivox.yaml
|
|
model:
|
|
transformer_encoder:
|
|
dropout: 0.0 # Dropout probability for the transformer
|
|
conv: # Config for convolutional model that generates positional embeddings required for attention layer
|
|
conv_pos: 128 # Number of filters for convolutional positional embeddings
|
|
conv_pos_groups: 16 # Number of groups for convolutional positional embeddings
|
|
encoder:
|
|
encoder_layers: 24 # Number of encoder layers in transformer model
|
|
encoder_layerdrop: 0.0 # Probability of dropping transformer layers
|
|
embedding_dim: 1024 # Encoder embedding dim
|
|
ffn_embedding_dim: 4096 # Encoder embedding dim for feed forward
|
|
num_attention_heads: 16 # Number of encoder attention heads
|
|
dropout: 0.0 # Dropout probability for transformer encoder
|
|
activation_fn: gelu # Activation for transformer
|
|
layer_norm_first: True # Apply layer norm first within the transformer
|
|
loss:
|
|
prob_ppl_weight: 0.1 # Weight applied to quantized prob perplexity loss
|
|
feature_loss_weight: 0 # Weight applied to feature L2 Norm
|
|
quantizer:
|
|
quantize_targets: True # Quantize targets
|
|
quantize_input: False # Quantize inputs
|
|
same_quantizer: False # Use the same quantizer for inputs and targets (If both enabled)
|
|
latent_vars: 320 # Number of latent variables in each group of the codebook
|
|
latent_groups: 2 # Number of groups within the codebook
|
|
latent_dim: 0 # If greater than 0, use the dim for latest variables else inferred by final dim / latent groups
|
|
latent_temp: [2, 0.1, 0.999995] # Quantize temperature (start, stop, decay factor)
|
|
conv_feature_encoder: # Config for feature extractor taking raw audio waveform and converting to features
|
|
extractor_mode: layer_norm # Mode for feature extractor. [default, layer_norm]
|
|
conv_bias: True # Include bias in convolution feature extractor model
|
|
masking:
|
|
mask_prob: 0.65 # Probability of replacing token with mask
|
|
mask_type: static # Used to select configuration to compute mask lengths [static, uniform, normal, poisson]
|
|
mask_other: 0 # Secondary mask used for complex distributions (see help in compute_mask_indices)
|
|
mask_length: 10 # Length of mask when masking time steps
|
|
no_mask_overlap: False # Whether to allow masks to overlap
|
|
mask_min_space: 1 # Minimum space beetween spans (if no overlap is enabled)
|
|
mask_channel_prob: 0 # Probability of replacing a feature with 0
|
|
mask_channel_type: static # Used to select configuration to compute mask channel lengths [static, uniform, normal, poisson]
|
|
mask_channel_other: 0 # Secondary mask argument (used for more complex distributions (see help in compute_mask_indices)
|
|
mask_channel_length: 10 # Length of masks for features (channels)
|
|
no_mask_channel_overlap: False # Whether to allow channel masks to overlap
|
|
mask_channel_min_space: 1 # Minimum space between spans (if no overlap is enabled)
|
|
dropout_input: 0.0 # Dropout applied to input raw features
|
|
dropout_features: 0.0 # Dropout applied to the features generator by convolutions
|
|
final_dim: 768 # Project final representations and targets to this dimension
|
|
n_negatives: 100 # Number of negatives to sample from the same audio sample
|
|
cross_sample_negatives: 0 # Number of negatives to sample from any sample in the batch
|
|
codebook_negatives: 0 # Number of negative examples in codebook
|
|
negatives_from_everywhere: False # Sample negatives from everywhere, not just masked states
|
|
logit_temp: 0.1 # Temperature to divide logits by
|
|
target_glu: False # Adds project and applies GLU to targets
|
|
feature_grad_mult: 1.0 # Multiply extracted feature gradients
|
|
|
|
train_ds:
|
|
manifest_filepath: ???
|
|
sample_rate: 16000
|
|
batch_size: 32
|
|
shuffle: True
|
|
num_workers: 4
|
|
labels: [ ] # No vocab needed for pre-training
|
|
validation_ds:
|
|
manifest_filepath: ???
|
|
sample_rate: 16000
|
|
batch_size: 32
|
|
shuffle: False
|
|
num_workers: 1
|
|
labels: [ ]
|
|
test_ds:
|
|
manifest_filepath: null
|
|
sample_rate: 16000
|
|
batch_size: 32
|
|
shuffle: False
|
|
num_workers: 4
|
|
labels: [ ]
|
|
optim:
|
|
name: adamw
|
|
lr: 0.0005
|
|
eps: 1e-06
|
|
# optimizer arguments
|
|
betas: [ 0.9, 0.98 ]
|
|
weight_decay: 0.01
|
|
|
|
# scheduler setup
|
|
sched:
|
|
name: PolynomialDecayAnnealing
|
|
min_lr: 0.000
|
|
# Scheduler params
|
|
warmup_steps: null
|
|
warmup_ratio: 0.1
|
|
trainer:
|
|
gpus: 0 # number of gpus
|
|
num_nodes: 1
|
|
max_epochs: 100
|
|
max_steps: null # computed at runtime if not set
|
|
val_check_interval: 0.5 # Set to 0.25 to check 4 times per epoch, or an int for number of iterations
|
|
accelerator: ddp
|
|
accumulate_grad_batches: 1
|
|
gradient_clip_val: 0.0
|
|
precision: 32 # Should be set to 16 for O1 and O2 to enable the AMP.
|
|
log_every_n_steps: 10 # Interval of logging.
|
|
resume_from_checkpoint: null # The path to a checkpoint file to continue the training, restores the whole state including the epoch, step, LR schedulers, apex, etc.
|
|
num_sanity_val_steps: 0 # number of steps to perform validation steps for sanity check the validation process before starting the training, setting to 0 disables it
|
|
check_val_every_n_epoch: 1 # number of evaluations on validation every n epochs
|
|
sync_batchnorm: true
|
|
|
|
checkpoint_callback: false # Provided by exp_manager
|
|
logger: false # Provided by exp_manager
|
|
exp_manager:
|
|
exp_dir: null
|
|
name: *name
|
|
create_tensorboard_logger: true
|
|
create_checkpoint_callback: true
|
|
create_wandb_logger: false
|
|
wandb_logger_kwargs:
|
|
name: null
|
|
project: null
|
|
resume_if_exists: false
|
|
resume_ignore_no_checkpoint: false |