Upload folder using huggingface_hub

README.md

@@ -1,3 +1,24 @@
 ---
-license: mit
+library_name: peft
 ---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- _load_in_8bit: False
+- _load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bbdc9efaa2efd8412f463e2350751d6019c48c55c6a29265678c7e6bbfe6d4
+size 156984186

xtuner_config.py

@@ -0,0 +1,211 @@
+SYSTEM = 'xtuner.utils.SYSTEM_TEMPLATE.alpaca'
+accumulative_counts = 16
+alpaca_en = dict(
+    dataset=dict(
+        data_files=
+        '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/datasets--recogna-nlp--ultra-alpaca-ptbr/snapshots/e69900d074177d370a911096fc30bdf407eff666/train.json',
+        path='json',
+        type='datasets.load_dataset'),
+    dataset_map_fn='xtuner.dataset.map_fns.ultracabrita_map_fn',
+    max_length=2048,
+    pack_to_max_length=True,
+    remove_unused_columns=True,
+    shuffle_before_pack=True,
+    template_map_fn=dict(
+        template='xtuner.utils.PROMPT_TEMPLATE.gemma',
+        type='xtuner.dataset.map_fns.template_map_fn_factory'),
+    tokenizer=dict(
+        padding_side='right',
+        pretrained_model_name_or_path=
+        '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/',
+        trust_remote_code=True,
+        type='transformers.AutoTokenizer.from_pretrained'),
+    type='xtuner.dataset.process_hf_dataset',
+    use_varlen_attn=False)
+alpaca_en_path = '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/datasets--recogna-nlp--ultra-alpaca-ptbr/snapshots/e69900d074177d370a911096fc30bdf407eff666/train.json'
+batch_size = 1
+betas = (
+    0.9,
+    0.999,
+)
+custom_hooks = [
+    dict(
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path=
+            '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/',
+            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?',
+            'Resolva a equação de segundo grau x² - x - 30 = 0',
+            'Escreva um código em python para calcular x^y usando divisão e conquista.',
+        ],
+        every_n_iters=500,
+        prompt_template='xtuner.utils.PROMPT_TEMPLATE.gemma',
+        system='xtuner.utils.SYSTEM_TEMPLATE.alpaca',
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path=
+            '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/',
+            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?',
+    'Resolva a equação de segundo grau x² - x - 30 = 0',
+    'Escreva um código em python para calcular x^y usando divisão e conquista.',
+]
+launcher = 'pytorch'
+load_from = None
+log_level = 'INFO'
+log_processor = dict(by_epoch=False)
+lr = 0.0002
+max_epochs = 1
+max_length = 2048
+max_norm = 1
+model = dict(
+    llm=dict(
+        pretrained_model_name_or_path=
+        '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/',
+        quantization_config=dict(
+            bnb_4bit_compute_dtype='torch.float16',
+            bnb_4bit_quant_type='nf4',
+            bnb_4bit_use_double_quant=True,
+            llm_int8_has_fp16_weight=False,
+            llm_int8_threshold=6.0,
+            load_in_4bit=True,
+            load_in_8bit=False,
+            type='transformers.BitsAndBytesConfig'),
+        torch_dtype='torch.float16',
+        trust_remote_code=True,
+        type='transformers.AutoModelForCausalLM.from_pretrained'),
+    lora=dict(
+        bias='none',
+        lora_alpha=16,
+        lora_dropout=0.1,
+        r=64,
+        task_type='CAUSAL_LM',
+        type='peft.LoraConfig'),
+    type='xtuner.model.SupervisedFinetune',
+    use_varlen_attn=False)
+optim_type = 'torch.optim.AdamW'
+optim_wrapper = dict(
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ),
+        lr=0.0002,
+        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/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/'
+prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.gemma'
+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=1,
+    type='xtuner.engine.DeepSpeedStrategy')
+tokenizer = dict(
+    padding_side='right',
+    pretrained_model_name_or_path=
+    '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/',
+    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=1,
+    collate_fn=dict(
+        type='xtuner.dataset.collate_fns.default_collate_fn',
+        use_varlen_attn=False),
+    dataset=dict(
+        dataset=dict(
+            data_files=
+            '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/datasets--recogna-nlp--ultra-alpaca-ptbr/snapshots/e69900d074177d370a911096fc30bdf407eff666/train.json',
+            path='json',
+            type='datasets.load_dataset'),
+        dataset_map_fn='xtuner.dataset.map_fns.ultracabrita_map_fn',
+        max_length=2048,
+        pack_to_max_length=True,
+        remove_unused_columns=True,
+        shuffle_before_pack=True,
+        template_map_fn=dict(
+            template='xtuner.utils.PROMPT_TEMPLATE.gemma',
+            type='xtuner.dataset.map_fns.template_map_fn_factory'),
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path=
+            '/petrobr/parceirosbr/home/rafael.rodrigues/.cache/huggingface/hub/models--google--gemma-2b/snapshots/dd006781ade50f5a5216ef690c2e30e7eedf1676/',
+            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/gemma_2b_qlora_ultraalpaca'