File size: 1,610 Bytes
cc25039 54d2ac1 cc25039 |
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 73 74 75 76 |
#Mistral-7b
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
- path: tilemachos/Demo-Dataset #Path to json dataset file in huggingface
#for type,conversation arguments read axolotl readme and pick what is suited for your project, I wanted a chatbot and put sharegpt and chatml
type: sharegpt
conversation: chatml
dataset_prepared_path: tilemachos/Demo-Dataset #Path to json dataset file in huggingface
val_set_size: 0.05
output_dir: ./out
#using lora for lower cost
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
sequence_len: 512
sample_packing: false
pad_to_sequence_len: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
#only 2 epochs because of small dataset
gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
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: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
#default deepspeed, can use more aggresive if needed like zero2, zero3
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
|