Delete xtuner_config.py

xtuner_config.py

@@ -1,189 +0,0 @@
-SYSTEM = 'xtuner.utils.SYSTEM_TEMPLATE.alpaca'
-accumulative_counts = 16
-alpaca_en = dict(
-    dataset=dict(
-        data_files='/petrobr/parceirosbr/radiar/llama_test/ultracabrita3.json',
-        path='json',
-        type='datasets.load_dataset'),
-    dataset_map_fn='xtuner.dataset.map_fns.ultracabrita_map_fn',
-    max_length=4096,
-    pack_to_max_length=True,
-    remove_unused_columns=True,
-    shuffle_before_pack=True,
-    template_map_fn=dict(
-        template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat',
-        type='xtuner.dataset.map_fns.template_map_fn_factory'),
-    tokenizer=dict(
-        padding_side='right',
-        pretrained_model_name_or_path=
-        '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d',
-        trust_remote_code=True,
-        type='transformers.AutoTokenizer.from_pretrained'),
-    type='xtuner.dataset.process_hf_dataset',
-    use_varlen_attn=False)
-alpaca_en_path = '/petrobr/parceirosbr/radiar/llama_test/ultracabrita3.json'
-batch_size = 2
-betas = (
-    0.9,
-    0.999,
-)
-custom_hooks = [
-    dict(
-        tokenizer=dict(
-            padding_side='right',
-            pretrained_model_name_or_path=
-            '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d',
-            trust_remote_code=True,
-            type='transformers.AutoTokenizer.from_pretrained'),
-        type='xtuner.engine.hooks.DatasetInfoHook'),
-    dict(
-        evaluation_inputs=[
-            'O que é um bode?',
-            'Qual a capital da França?',
-            'Você pode me explicar o Teorema de Pitágoras com um exemplo, por favor?',
-            'Olá, tudo bem? Estou procurando livros de ficção científica para ler, você teria sugestões para mim?',
-        ],
-        every_n_iters=500,
-        prompt_template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat',
-        system='xtuner.utils.SYSTEM_TEMPLATE.alpaca',
-        tokenizer=dict(
-            padding_side='right',
-            pretrained_model_name_or_path=
-            '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d',
-            trust_remote_code=True,
-            type='transformers.AutoTokenizer.from_pretrained'),
-        type='xtuner.engine.hooks.EvaluateChatHook'),
-]
-dataloader_num_workers = 0
-default_hooks = dict(
-    checkpoint=dict(
-        by_epoch=False,
-        interval=500,
-        max_keep_ckpts=2,
-        type='mmengine.hooks.CheckpointHook'),
-    logger=dict(
-        interval=10,
-        log_metric_by_epoch=False,
-        type='mmengine.hooks.LoggerHook'),
-    param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'),
-    sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'),
-    timer=dict(type='mmengine.hooks.IterTimerHook'))
-env_cfg = dict(
-    cudnn_benchmark=False,
-    dist_cfg=dict(backend='nccl'),
-    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
-evaluation_freq = 500
-evaluation_inputs = [
-    'O que é um bode?',
-    'Qual a capital da França?',
-    'Você pode me explicar o Teorema de Pitágoras com um exemplo, por favor?',
-    'Olá, tudo bem? Estou procurando livros de ficção científica para ler, você teria sugestões para mim?',
-]
-launcher = 'pytorch'
-load_from = None
-log_level = 'INFO'
-log_processor = dict(by_epoch=False)
-lr = 2e-05
-max_epochs = 1
-max_length = 4096
-max_norm = 1
-model = dict(
-    llm=dict(
-        pretrained_model_name_or_path=
-        '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d',
-        trust_remote_code=True,
-        type='transformers.AutoModelForCausalLM.from_pretrained'),
-    type='xtuner.model.SupervisedFinetune',
-    use_varlen_attn=False)
-optim_type = 'torch.optim.AdamW'
-optim_wrapper = dict(
-    optimizer=dict(
-        betas=(
-            0.9,
-            0.999,
-        ),
-        lr=2e-05,
-        type='torch.optim.AdamW',
-        weight_decay=0),
-    type='DeepSpeedOptimWrapper')
-pack_to_max_length = True
-param_scheduler = [
-    dict(
-        begin=0,
-        by_epoch=True,
-        convert_to_iter_based=True,
-        end=0.03,
-        start_factor=1e-05,
-        type='mmengine.optim.LinearLR'),
-    dict(
-        begin=0.03,
-        by_epoch=True,
-        convert_to_iter_based=True,
-        end=1,
-        eta_min=0.0,
-        type='mmengine.optim.CosineAnnealingLR'),
-]
-pretrained_model_name_or_path = '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d'
-prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.internlm2_chat'
-randomness = dict(deterministic=False, seed=None)
-resume = False
-runner_type = 'FlexibleRunner'
-save_steps = 500
-save_total_limit = 2
-strategy = dict(
-    config=dict(
-        bf16=dict(enabled=False),
-        fp16=dict(enabled=True, initial_scale_power=16),
-        gradient_accumulation_steps='auto',
-        gradient_clipping='auto',
-        train_micro_batch_size_per_gpu='auto',
-        zero_allow_untested_optimizer=True,
-        zero_force_ds_cpu_optimizer=False,
-        zero_optimization=dict(overlap_comm=True, stage=2)),
-    exclude_frozen_parameters=True,
-    gradient_accumulation_steps=16,
-    gradient_clipping=1,
-    sequence_parallel_size=1,
-    train_micro_batch_size_per_gpu=2,
-    type='xtuner.engine.DeepSpeedStrategy')
-tokenizer = dict(
-    padding_side='right',
-    pretrained_model_name_or_path=
-    '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d',
-    trust_remote_code=True,
-    type='transformers.AutoTokenizer.from_pretrained')
-train_cfg = dict(max_epochs=1, type='xtuner.engine.runner.TrainLoop')
-train_dataloader = dict(
-    batch_size=2,
-    collate_fn=dict(
-        type='xtuner.dataset.collate_fns.default_collate_fn',
-        use_varlen_attn=False),
-    dataset=dict(
-        dataset=dict(
-            data_files=
-            '/petrobr/parceirosbr/radiar/llama_test/ultracabrita3.json',
-            path='json',
-            type='datasets.load_dataset'),
-        dataset_map_fn='xtuner.dataset.map_fns.ultracabrita_map_fn',
-        max_length=4096,
-        pack_to_max_length=True,
-        remove_unused_columns=True,
-        shuffle_before_pack=True,
-        template_map_fn=dict(
-            template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat',
-            type='xtuner.dataset.map_fns.template_map_fn_factory'),
-        tokenizer=dict(
-            padding_side='right',
-            pretrained_model_name_or_path=
-            '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--internlm--internlm2-chat-1_8b/snapshots/ecccbb5c87079ad84e5788baa55dd6e21a9c614d',
-            trust_remote_code=True,
-            type='transformers.AutoTokenizer.from_pretrained'),
-        type='xtuner.dataset.process_hf_dataset',
-        use_varlen_attn=False),
-    num_workers=0,
-    sampler=dict(shuffle=True, type='mmengine.dataset.DefaultSampler'))
-use_varlen_attn = False
-visualizer = None
-warmup_ratio = 0.03
-weight_decay = 0
-work_dir = './work_dirs/internlm2_chat_1_8b_full_ultracabrita'