File size: 929 Bytes
1feb0fe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
base_model: /workspace/mistral-11b-base
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: Open-Orca/SlimOrca
type: sharegpt
conversation: mistral
dataset_prepared_path:
val_set_size: 0.005
output_dir: ./out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
wandb_project: mistral-11b-noresidual
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 16
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005
train_on_inputs: true
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
flash_attention: true
logging_steps: 1
warmup_steps: 10
eval_steps: 100
save_steps: 100
weight_decay: 0.0
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
|