minor changes and add an example config for s3

README.md

@@ -75,6 +75,7 @@ You can find more examples in the [`/examples`](/examples) directory:
 | `mamba` | Train an example Mamba model |
 | `moe` | Train an example Mixture-of-Experts (MoE) model |
 | `mup` | Use spectral µTransfer to scale up your model |
+| `examples/config_tiny_llama_with_s3_upload.yaml` | For automatically uploading checkpoints to S3 |
 
 We're working on adding more examples soon! Feel free to add a PR to add your own example. 🚀
 

examples/config_tiny_llama_with_s3_upload.yaml

@@ -0,0 +1,115 @@
+checkpoints:
+  checkpoint_interval: 10
+  checkpoints_path: checkpoints
+  checkpoints_path_is_shared_file_system: false
+  resume_checkpoint_path: s3://phuc-experiments/temp/config_tiny_llama_with_s3_upload
+  save_initial_state: false
+data_stages:
+- data:
+    dataset:
+      dataset_overwrite_cache: false
+      dataset_processing_num_proc_per_process: 1
+      hf_dataset_config_name: null
+      hf_dataset_or_datasets: stas/openwebtext-10k
+      hf_dataset_splits: train
+      text_column_name: text
+    num_loading_workers: 1
+    seed: 42
+  name: Stable Training Stage
+  start_training_step: 1
+- data:
+    dataset:
+      dataset_overwrite_cache: false
+      dataset_processing_num_proc_per_process: 1
+      hf_dataset_config_name: null
+      hf_dataset_or_datasets: stas/openwebtext-10k
+      hf_dataset_splits: train
+      text_column_name: text
+    num_loading_workers: 1
+    seed: 42
+  name: Annealing Phase
+  start_training_step: 10
+general:
+  benchmark_csv_path: null
+  consumed_train_samples: null
+  ignore_sanity_checks: true
+  project: debug
+  run: tiny_llama_%date_%jobid
+  seed: 42
+  step: null
+lighteval: null
+logging:
+  iteration_step_info_interval: 1
+  log_level: info
+  log_level_replica: info
+model:
+  ddp_bucket_cap_mb: 25
+  dtype: bfloat16
+  init_method:
+    std: 0.025
+  make_vocab_size_divisible_by: 1
+  model_config:
+    bos_token_id: 1
+    eos_token_id: 2
+    hidden_act: silu
+    hidden_size: 16
+    initializer_range: 0.02
+    intermediate_size: 64
+    is_llama_config: true
+    max_position_embeddings: 256
+    num_attention_heads: 4
+    num_hidden_layers: 2
+    num_key_value_heads: 4
+    pad_token_id: null
+    pretraining_tp: 1
+    rms_norm_eps: 1.0e-05
+    rope_scaling: null
+    tie_word_embeddings: true
+    use_cache: true
+    vocab_size: 256
+optimizer:
+  accumulate_grad_in_fp32: true
+  clip_grad: 1.0
+  learning_rate_scheduler:
+    learning_rate: 0.0003
+    lr_decay_starting_step: null
+    lr_decay_steps: 13
+    lr_decay_style: cosine
+    lr_warmup_steps: 2
+    lr_warmup_style: linear
+    min_decay_lr: 1.0e-05
+  optimizer_factory:
+    adam_beta1: 0.9
+    adam_beta2: 0.95
+    adam_eps: 1.0e-08
+    name: adamW
+    torch_adam_is_fused: true
+  weight_decay: 0.01
+  zero_stage: 0
+parallelism:
+  dp: 1
+  expert_parallel_size: 1
+  pp: 1
+  pp_engine: 1f1b
+  tp: 1
+  tp_linear_async_communication: true
+  tp_mode: REDUCE_SCATTER
+profiler: null
+tokenizer:
+  tokenizer_max_length: null
+  tokenizer_name_or_path: robot-test/dummy-tokenizer-wordlevel
+  tokenizer_revision: null
+tokens:
+  batch_accumulation_per_replica: 1
+  limit_test_batches: 0
+  limit_val_batches: 0
+  micro_batch_size: 2
+  sequence_length: 256
+  train_steps: 30
+  val_check_interval: -1
+s3_upload:
+  remove_after_upload: true
+  s5cmd_concurrency: 5
+  s5cmd_numworkers: 16
+  s5cmd_path: /fsx/nouamane/miniconda/envs/2-1-cu121/bin/s5cmd
+  upload_s3_path: s3://phuc-experiments/temp/config_tiny_llama_with_s3_upload

src/nanotron/helpers.py

@@ -53,7 +53,6 @@ def _vocab_size_with_padding(orig_vocab_size: int, pg_size: int, make_vocab_size
     multiple = make_vocab_size_divisible_by * pg_size
     after = int(ceil(orig_vocab_size / multiple) * multiple)
     if after != orig_vocab_size:
-        print("i'm in")
         log_rank(
             f"[Vocab Size Padding] Padded vocab (size: {orig_vocab_size}) with {after - orig_vocab_size} dummy tokens (new size: {after})",
             logger=logger,
@@ -147,10 +146,8 @@ def lr_lambda(current_step: int, initial_lr: float):
                     / lr_decay_steps
                 )
             elif lr_scheduler_args.lr_decay_style == "1-sqrt":
-                lmbda = (
-                    lr_scheduler_args.min_decay_lr
-                    + (initial_lr - lr_scheduler_args.min_decay_lr)
-                    * (1 - math.sqrt((current_step - lr_decay_starting_step) / lr_decay_steps))
+                lmbda = lr_scheduler_args.min_decay_lr + (initial_lr - lr_scheduler_args.min_decay_lr) * (
+                    1 - math.sqrt((current_step - lr_decay_starting_step) / lr_decay_steps)
                 )
             else:
                 raise ValueError(f"Unknown decay style {lr_scheduler_args.lr_decay_style}")
@@ -693,7 +690,7 @@ def is_resume_from_training():
     else:
         next_stage = next((s for s in config.data_stages if s.start_training_step > stage.start_training_step), None)
         total_train_steps = next_stage.start_training_step
-    
+
     if metadata.last_train_step > stage.start_training_step:
         # NOTE: if the last_train_step is larger than the start_training_step of the current stage,
         # it means that the training has already passed this stage

src/nanotron/utils.py

@@ -3,7 +3,6 @@
 import os
 import random
 import socket
-import re
 from contextlib import ExitStack, contextmanager
 from typing import ContextManager, List, Optional