|
base_model: /media/renfroe/llms/SmolLM-360M/ |
|
|
|
model_type: LlamaForCausalLM |
|
tokenizer_type: GPT2Tokenizer |
|
seed: 122887 |
|
load_in_8bit: false |
|
load_in_4bit: false |
|
strict: false |
|
|
|
max_steps: 0 |
|
resume_from_checkpoint: |
|
datasets: |
|
- path: /home/renfroe/Desktop/sqa_tiny-llama_dataset/Dynamic_Optimization_Methods_with_Applications_sqa_answers_only.json |
|
type: |
|
field_instruction: question |
|
field_output: answer |
|
format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" |
|
no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" |
|
- path: /home/renfroe/Dev/tinyllama-models/dataset/open_hermes_top_tech.json |
|
type: sharegpt |
|
- path: /home/renfroe/Desktop/sqa_tiny-llama_dataset/hermes_prior_knowledge_question_expansion_with_answers.json |
|
type: |
|
field_instruction: question |
|
field_output: answer |
|
format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" |
|
no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" |
|
- path: /home/renfroe/Desktop/sqa_tiny-llama_dataset/hermes_prior_knowledge_question_expansion_with_answers.json |
|
type: |
|
field_instruction: question |
|
field_output: answer |
|
format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" |
|
no_input_format: "<|im_start|>user\n{instruction}<|im_end|>\n<|im_start|>assistant\n" |
|
- path: /home/renfroe/Desktop/sqa_tiny-llama_dataset/or-farm_sharegpt.json |
|
type: sharegpt |
|
|
|
|
|
|
|
dataset_prepared_path: |
|
val_set_size: 0.2 |
|
output_dir: ./SmolLM-Ora |
|
auto_resume_from_checkpoints: false |
|
|
|
sequence_len: 2048 |
|
sample_packing: true |
|
chat_template: chatml |
|
|
|
wandb_project: SmolLM-Ora |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 1 |
|
micro_batch_size: 10 |
|
num_epochs: 4 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: linear |
|
weight_decay: 0.0000001 |
|
learning_rate: 0.0001 |
|
lr_scheduler_kwargs: |
|
|
|
|
|
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 |
|
|
|
eval_sample_packing: False |
|
|
|
warmup_steps: 50 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
saves_per_epoch: 4 |
|
debug: |
|
deepspeed: |
|
|
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
bos_token: "<|endoftext|>" |
|
eos_token: "<|endoftext|>" |
|
pad_token: "<|endoftext|>" |