| base_model: state-spaces/mamba-2.8b | |
| model_type: MambaLMHeadModel | |
| tokenizer_type: AutoTokenizer | |
| tokenizer_config: EleutherAI/gpt-neox-20b | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| datasets: | |
| - path: mhenrichsen/alpaca_2k_test | |
| type: alpaca | |
| dataset_prepared_path: | |
| val_set_size: 0.0 | |
| output_dir: ./out | |
| sequence_len: 2048 | |
| sample_packing: false | |
| pad_to_sequence_len: false | |
| wandb_project: | |
| wandb_entity: | |
| wandb_watch: | |
| wandb_name: | |
| wandb_log_model: | |
| gradient_accumulation_steps: 4 | |
| micro_batch_size: 1 | |
| num_epochs: 2 | |
| optimizer: paged_adamw_8bit | |
| lr_scheduler: cosine | |
| learning_rate: 5e-5 | |
| train_on_inputs: false | |
| group_by_length: true | |
| bf16: auto | |
| fp16: | |
| tf32: true | |
| gradient_checkpointing: false | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: | |
| warmup_steps: 10 | |
| evals_per_epoch: 4 | |
| eval_table_size: | |
| eval_table_max_new_tokens: 128 | |
| saves_per_epoch: 1 | |
| debug: | |
| deepspeed: | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| special_tokens: | |
| tokens: | |
| save_safetensors: False | |