#!/usr/bin/env bash
set -euo pipefail

ROOT=${ROOT:-/ssd/yi/Tokenizer_Swap}
NPROC=${NPROC:-8}
MODEL=${MODEL:-$ROOT/model_building/generated_models/Qwen3-0.6B-DSV4-tokenizer-remap-v2}
TRAIN=${TRAIN:-$ROOT/dataset_building/generated/dsv4_chat_tokenized_alt_sources_1m_fixed_eval_20260607/train_dsv4_chat_tokenized.jsonl.gz}
EVAL=${EVAL:-$ROOT/dataset_building/generated/dsv4_chat_tokenized_alt_sources_1m_fixed_eval_20260607/validation_dsv4_chat_tokenized.jsonl.gz}
OUT=${OUT:-$ROOT/model_training/checkpoints/dsv4_chat_full_sft_remap_v2_alt1m_5epoch_bsz8_accum16}

mkdir -p "$(dirname "$OUT")"
torchrun --nproc_per_node "$NPROC" "$ROOT/model_training/train_dsv4_tokenized_full_sft.py" \
  --model "$MODEL" \
  --train "$TRAIN" \
  --eval "$EVAL" \
  --out "$OUT" \
  --max-length 2048 \
  --epochs 5 \
  --batch-size 8 \
  --grad-accum 16 \
  --lr 5e-5 \
  --eval-steps 500 \
  --save-steps 500 \
  --num-workers 2