File size: 1,366 Bytes
ba226f7 cc88121 ba226f7 |
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 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
base_model: mistralai/Mistral-7B-v0.1
base_model_config: 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: openaccess-ai-collective/oo-gpt4-filtered
type: alpaca_w_system.load_open_orca_chatml
data_files:
- 1M-GPT4-Augmented-filtered-gt10.parquet
dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: ./mistral-oo
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
wandb_project: mistral-oo-7b
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 6
num_epochs: 4
optimizer: adamw_torch
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: 0.05
eval_table_size:
eval_table_max_new_tokens:
save_steps:
debug:
deepspeed: deepspeed/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "<|im_end|>"
unk_token: "<unk>"
tokens:
- "<|im_start|>"
- "<|im_end|>"
|