Model Card for pygemma:

pygemma is a language model that is trained to act as Python assistant. It is a finetuned version of google/gemma-2b that was trained using SFTTrainer on publicly available dataset iamtarun/python_code_instructions_18k_alpaca.

Training hyperparameters

The following hyperparameters were used during the training:

• output_dir: peft-lora-pygemma

• overwrite_output_dir: True

• do_train: False

• do_eval: False

• do_predict: False

• evaluation_strategy: no

• prediction_loss_only: False

• per_device_train_batch_size: 2

• per_device_eval_batch_size: None

• per_gpu_train_batch_size: None

• per_gpu_eval_batch_size: None

• gradient_accumulation_steps: 4

• eval_accumulation_steps: None

• eval_delay: 0

• learning_rate: 2e-05

• weight_decay: 0.0

• adam_beta1: 0.9

• adam_beta2: 0.999

• adam_epsilon: 1e-08

• max_grad_norm: 0.3

• num_train_epochs: 3

• max_steps: -1

• lr_scheduler_type: cosine

• lr_scheduler_kwargs: {}

• warmup_ratio: 0.1

• warmup_steps: 0

• log_level: passive

• log_level_replica: warning

• log_on_each_node: True

• logging_dir: peft-lora-pygemma/runs/Mar13_16-30-02_e65672b6422a

• logging_strategy: steps

• logging_first_step: False

• logging_steps: 10

• logging_nan_inf_filter: True

• save_strategy: epoch

• save_steps: 500

• save_total_limit: None

• save_safetensors: True

• save_on_each_node: False

• save_only_model: False

• no_cuda: False

• use_cpu: False

• use_mps_device: False

• seed: 42

• data_seed: None

• jit_mode_eval: False

• use_ipex: False

• bf16: True

• fp16: False

• fp16_opt_level: O1

• half_precision_backend: auto

• bf16_full_eval: False

• fp16_full_eval: False

• tf32: None

• local_rank: 0

• ddp_backend: None

• tpu_num_cores: None

• tpu_metrics_debug: False

• debug: []

• dataloader_drop_last: False

• eval_steps: None

• dataloader_num_workers: 0

• dataloader_prefetch_factor: None

• past_index: -1

• run_name: peft-lora-pygemma

• disable_tqdm: False

• remove_unused_columns: True

• label_names: None

• load_best_model_at_end: False

• metric_for_best_model: None

• greater_is_better: None

• ignore_data_skip: False

• fsdp: []

• fsdp_min_num_params: 0

• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}

• fsdp_transformer_layer_cls_to_wrap: None

• accelerator_config: AcceleratorConfig(split_batches=False, dispatch_batches=None, even_batches=True, use_seedable_sampler=True)

• deepspeed: None

• label_smoothing_factor: 0.0

• optim: adamw_torch_fused

• optim_args: None

• adafactor: False

• group_by_length: False

• length_column_name: length

• report_to: ['tensorboard']

• ddp_find_unused_parameters: None

• ddp_bucket_cap_mb: None

• ddp_broadcast_buffers: None

• dataloader_pin_memory: True

• dataloader_persistent_workers: False

• skip_memory_metrics: True

• use_legacy_prediction_loop: False

• push_to_hub: False

• resume_from_checkpoint: None

• hub_model_id: None

• hub_strategy: every_save

• hub_token: None

• hub_private_repo: False

• hub_always_push: False

• gradient_checkpointing: True

• gradient_checkpointing_kwargs: {'use_reentrant': False}

• include_inputs_for_metrics: False

• fp16_backend: auto

• push_to_hub_model_id: None

• push_to_hub_organization: None

• push_to_hub_token: None

• mp_parameters:

• auto_find_batch_size: False

• full_determinism: False

• torchdynamo: None

• ray_scope: last

• ddp_timeout: 1800

• torch_compile: False

• torch_compile_backend: None

• torch_compile_mode: None

• dispatch_batches: None

• split_batches: None

• include_tokens_per_second: False

• include_num_input_tokens_seen: False

• neftune_noise_alpha: None

• distributed_state: Distributed environment: NO Num processes: 1 Process index: 0 Local process index: 0 Device: cuda

• _n_gpu: 1

• __cached__setup_devices: cuda:0

• deepspeed_plugin: None