71 lines
1.4 KiB
YAML
71 lines
1.4 KiB
YAML
base_model: mistralai/Mistral-7B-v0.1
|
|
model_type: MistralForCausalLM
|
|
tokenizer_type: LlamaTokenizer
|
|
is_mistral_derived_model: true
|
|
|
|
load_in_8bit: false
|
|
load_in_4bit: false
|
|
strict: false
|
|
|
|
datasets:
|
|
- path: /workspace/datasets/dolphin/dolphin201.jsonl
|
|
type: alpaca_w_system.load_open_orca_chatml
|
|
- path: /workspace/datasets/WizardLM_evol_instruct_cleaned.jsonl
|
|
type: sharegpt
|
|
conversation: chatml
|
|
- path: /workspace/datasets/not_samantha_norefusals.jsonl
|
|
type: sharegpt
|
|
conversation: chatml
|
|
dataset_prepared_path: last_run_prepared
|
|
val_set_size: 0
|
|
output_dir: /workspace/dolphin-2.2-mistral-7b
|
|
|
|
sequence_len: 8192
|
|
sample_packing: true
|
|
pad_to_sequence_len: true
|
|
|
|
wandb_project: dolphin
|
|
wandb_entity:
|
|
wandb_watch:
|
|
wandb_run_id:
|
|
wandb_log_model:
|
|
|
|
gradient_accumulation_steps: 4
|
|
micro_batch_size: 5
|
|
num_epochs: 4
|
|
adam_beta2: 0.95
|
|
adam_epsilon: 0.00001
|
|
max_grad_norm: 1.0
|
|
lr_scheduler: cosine
|
|
learning_rate: 0.000006
|
|
|
|
train_on_inputs: false
|
|
group_by_length: false
|
|
bf16: true
|
|
fp16: false
|
|
tf32: false
|
|
|
|
gradient_checkpointing: true
|
|
early_stopping_patience:
|
|
resume_from_checkpoint:
|
|
local_rank:
|
|
logging_steps: 1
|
|
xformers_attention:
|
|
flash_attention: true
|
|
|
|
warmup_steps: 100
|
|
eval_steps:
|
|
eval_table_size:
|
|
eval_table_max_new_tokens:
|
|
eval_sample_packing: false
|
|
save_steps: 0.25
|
|
debug:
|
|
deepspeed: deepspeed/zero2.json
|
|
weight_decay: 0.1
|
|
fsdp:
|
|
fsdp_config:
|
|
special_tokens:
|
|
eos_token: "<|im_end|>"
|
|
tokens:
|
|
- "<|im_start|>"
|
|
- "<|im_end|>" |