flan-t5-small.yaml

# @package _global_

# to execute this experiment run:
# python train.py experiment=flan-t5-small

defaults:
  - override /data: commit_chronicle
  - override /model: flan-t5-small
  - override /callbacks: default
  - override /trainer: gpu
  - override /logger: tensorboard

# all parameters below will be merged with parameters from default configurations set above
# this allows you to overwrite only specified parameters

tags: ["commit_chronicle", "flan-t5-small"]

seed: 12345

trainer:
  min_epochs: 10
  max_epochs: 20
#  gradient_clip_val: 1

model:
  net:
    encoder_context_max_len: 512
    decoder_context_max_len: 512
    encoder_vocab_size:
      _target_: builtins.len
      _args_:
        - ${data.diff_tokenizer}
    decoder_vocab_size:
      _target_: builtins.len
      _args_:
        - ${data.msg_tokenizer}

data:
  batch_size: 16
  diff_max_len: ${model.net.encoder_context_max_len}
  msg_max_len: ${model.net.decoder_context_max_len}
  diff_tokenizer:
    name_or_path: Salesforce/codet5-small
  msg_tokenizer:
    name_or_path: Salesforce/codet5-small
  # This value is the output obtained from running
  # from  models.components.seq2seq_wrapper Seq2SeqWrapper
  # decoder_start_token_id = Seq2SeqWrapper.get_decoder_start_token_id('Salesforce/codet5-small')
  decoder_start_token_id: 0