[tests] remove and rename tests

tests/test_qwen3_0.6B.sh

@@ -1,133 +0,0 @@
-#!/bin/bash
-
-# for rerun the task
-pkill -9 sglang
-sleep 3
-ray stop --force
-pkill -9 ray
-pkill -9 python
-sleep 3
-pkill -9 ray
-pkill -9 python
-
-set -ex
-
-# will prevent ray from buffering stdout/stderr
-export PYTHONBUFFERED=16
-
-SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" &>/dev/null && pwd)"
-source "${SCRIPT_DIR}/../scripts/models/qwen3-0.6B.sh"
-
-CKPT_ARGS=(
-   --hf-checkpoint /root/Qwen3-0.6B
-   --ref-load /root/Qwen3-0.6B_torch_dist
-)
-
-ROLLOUT_ARGS=(
-   --prompt-data /root/dapo-math-17k/dapo-math-17k.jsonl
-   --input-key prompt
-   --label-key label
-   --apply-chat-template
-   --rollout-shuffle
-   --rm-type deepscaler
-   --num-rollout 3000
-   --rollout-batch-size 32
-   --n-samples-per-prompt 8
-   --rollout-max-response-len 8192
-   --rollout-temperature 0.8
-
-   --over-sampling-batch-size 64
-   --dynamic-sampling-filter-path slime.rollout.filter_hub.dynamic_sampling_filters.check_reward_nonzero_std
-   #--partial-rollout
-
-   --global-batch-size 256
-   #--balance-data
-)
-
-EVAL_ARGS=(
-   --eval-interval 20
-   --eval-prompt-data aime /root/aime-2024/aime-2024.jsonl
-   --n-samples-per-eval-prompt 1
-   --eval-max-response-len 16384
-   --eval-temperature 0
-)
-
-PERF_ARGS=(
-   --tensor-model-parallel-size 1
-   --sequence-parallel
-   --pipeline-model-parallel-size 1
-   --context-parallel-size 1
-   --expert-model-parallel-size 1
-   --expert-tensor-parallel-size 1
-
-   # --micro-batch-size 1
-   --use-dynamic-batch-size
-   --max-tokens-per-gpu 9216
-)
-
-GRPO_ARGS=(
-   --advantage-estimator grpo
-   --use-kl-loss
-   --kl-loss-coef 0.00
-   --kl-loss-type low_var_kl
-   --entropy-coef 0.00
-   --eps-clip 0.2
-   --eps-clip-high 0.28
-)
-
-OPTIMIZER_ARGS=(
-   --optimizer adam
-   --lr 1e-6
-   --lr-decay-style constant
-   --weight-decay 0.1
-   --adam-beta1 0.9
-   --adam-beta2 0.98
-)
-
-WANDB_ARGS=(
-   #--use-wandb
-   --wandb-project slime-test
-   --wandb-group test-qwen-3-0.6B
-)
-
-SGLANG_ARGS=(
-   --rollout-num-gpus-per-engine 1
-   --sglang-mem-fraction-static 0.7
-)
-
-MISC_ARGS=(
-   # default dropout in megatron is 0.1
-   --attention-dropout 0.0
-   --hidden-dropout 0.0
-   # should be good for model performance
-   --accumulate-allreduce-grads-in-fp32
-   --attention-softmax-in-fp32
-   # need to comment this when using model with MLA
-   --attention-backend flash
-)
-
-# launch the master node of ray in container
-ray start --head --node-ip-address ${MASTER_ADDR} --num-gpus 8 --disable-usage-stats
-
-ray job submit --address="http://127.0.0.1:8265" \
-   --runtime-env-json='{
-     "env_vars": {
-        "PYTHONPATH": "/root/Megatron-LM",
-        "CUDA_DEVICE_MAX_CONNECTIONS": "1"
-     }
-   }' \
-   -- python3 train.py \
-   --actor-num-nodes 1 \
-   --actor-num-gpus-per-node 1 \
-   --colocate \
-   ${MODEL_ARGS[@]} \
-   ${CKPT_ARGS[@]} \
-   ${ROLLOUT_ARGS[@]} \
-   ${OPTIMIZER_ARGS[@]} \
-   ${GRPO_ARGS[@]} \
-   ${DISTRIBUTED_ARGS[@]} \
-   ${WANDB_ARGS[@]} \
-   ${PERF_ARGS[@]} \
-   ${EVAL_ARGS[@]} \
-   ${SGLANG_ARGS[@]} \
-   ${MISC_ARGS[@]}