AbrahamSanders's picture
First model version
46a5452
accelerator: null
accumulate_grad_batches: 4
adam_epsilon: 1.0e-08
amp_backend: native
amp_level: null
auto_lr_find: false
auto_scale_batch_size: false
auto_select_gpus: false
base_modelpath: microsoft/DialoGPT-large
batch_size: 2
benchmark: false
check_val_every_n_epoch: 1
checkpoint_callback: null
checkpoint_save_top_k: 5
checkpoint_save_weights_only: true
datasetpath: ../data/persuasion_for_good
default_root_dir: null
detect_anomaly: false
deterministic: false
devices: null
early_stopping_patience: 12
enable_checkpointing: true
enable_model_summary: true
enable_progress_bar: true
fast_dev_run: false
flush_logs_every_n_steps: null
gpus: 1
gradient_clip_algorithm: null
gradient_clip_val: 1.0
ipus: null
learning_rate: 5.0e-05
limit_predict_batches: 1.0
limit_test_batches: 1.0
limit_train_batches: 1.0
limit_val_batches: 1.0
log_every_n_steps: 5
log_gpu_memory: null
logger: true
max_epochs: 20
max_sequence_length: null
max_steps: -1
max_time: null
min_epochs: null
min_steps: null
move_metrics_to_cpu: false
multiple_trainloader_mode: max_size_cycle
num_nodes: 1
num_processes: 1
num_sanity_val_steps: 2
overfit_batches: 0.0
overwrite_prepared_data: false
plugins: null
precision: 32
prepare_data_per_node: null
process_position: 0
profiler: null
progress_bar_refresh_rate: null
random_state: 42
reload_dataloaders_every_epoch: false
reload_dataloaders_every_n_epochs: 0
replace_sampler_ddp: true
resume_from_checkpoint: null
stochastic_weight_avg: false
strategy: null
sync_batchnorm: false
terminate_on_nan: null
test_split: 0.2
tpu_cores: null
track_grad_norm: -1
val_check_interval: 0.25
val_split: 0.1
warmup_steps: 0
weight_decay: 0.0
weights_save_path: null
weights_summary: top