| base_model: mistralai/Mistral-7B-v0.1 | |
| # optionally might have model_type or tokenizer_type | |
| model_type: MistralForCausalLM | |
| tokenizer_type: LlamaTokenizer | |
| # Automatically upload checkpoint and final model to HF | |
| hub_model_id: AiAF/UFOs-Pretraining-V1.0 | |
| load_in_8bit: false | |
| load_in_4bit: false | |
| strict: false | |
| pretraining_dataset: | |
| - name: | |
| path: AiAF/pretraining.jsonl | |
| split: "train" | |
| text_column: "text" # column in dataset with the data, usually `text` | |
| type: pretrain | |
| trust_remote_code: true | |
| skip: 0 # number of rows of data to skip over from the beginning | |
| dataset_prepared_path: | |
| val_set_size: 0.05 | |
| output_dir: ./outputs | |
| max_steps: 100000 | |
| sequence_len: 4096 | |
| sample_packing: true | |
| pad_to_sequence_len: true | |
| eval_sample_packing: false | |
| wandb_project: "UFO_LLM_Pretraining" | |
| wandb_entity: | |
| wandb_watch: "all" | |
| wandb_name: "UFO_LLM_Pretraining-V1.0" | |
| wandb_log_model: "false" | |
| gradient_accumulation_steps: 4 | |
| micro_batch_size: 2 | |
| num_epochs: 5 | |
| optimizer: adamw_bnb_8bit | |
| lr_scheduler: cosine | |
| learning_rate: 0.000005 | |
| train_on_inputs: false | |
| group_by_length: false | |
| bf16: auto | |
| fp16: | |
| tf32: false | |
| gradient_checkpointing: true | |
| early_stopping_patience: | |
| resume_from_checkpoint: | |
| local_rank: | |
| logging_steps: 1 | |
| xformers_attention: | |
| flash_attention: true | |
| warmup_steps: 10 | |
| evals_per_epoch: 4 | |
| eval_table_size: | |
| eval_max_new_tokens: 128 | |
| saves_per_epoch: 1 | |
| debug: | |
| deepspeed: deepspeed_configs/zero3.json | |
| weight_decay: 0.0 | |
| fsdp: | |
| fsdp_config: | |
| special_tokens: | |