File size: 1,822 Bytes
07423df |
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 77 |
architecture:
backbone_dtype: float16
force_embedding_gradients: false
gradient_checkpointing: false
intermediate_dropout: 0.0
config_item_that_is_not_used: 0
augmentation:
token_mask_probability: 0.0
dataset:
add_eos_token_to_answer: true
add_eos_token_to_prompt: true
answer_column: output
data_sample: 0.1
data_sample_choice:
- Train
- Validation
mask_prompt_labels: false
prompt_column:
- instruction
text_answer_separator: \n
text_prompt_start: ''
train_dataframe: data/user/train/train.csv
validation_dataframe: None
validation_size: 0.01
validation_strategy: automatic
environment:
compile_model: false
find_unused_parameters: false
gpus:
- '0'
mixed_precision: true
number_of_workers: 8
seed: -1
experiment_name: test
llm_backbone: EleutherAI/pythia-12b-deduped
logging:
logger: None
neptune_project: ''
number_of_texts: 10
output_directory: output/user/test/
prediction:
batch_size_inference: 0
do_sample: false
max_length_inference: 256
max_time: 0.0
metric: GPT3.5
min_length_inference: 2
num_beams: 2
repetition_penalty: 1.2
stop_tokens: ""
temperature: 0.3
problem_type: text_causal_language_modeling
tokenizer:
max_length: 144
max_length_answer: 256
max_length_prompt: 256
padding_quantile: 1.0
training:
batch_size: 3
epochs: 0
evaluate_before_training: true
evaluation_epochs: 1.0
grad_accumulation: 1
gradient_clip: 0.0
learning_rate: 0.0001
lora: true
lora_alpha: 16
lora_dropout: 0.05
lora_r: 4
lora_target_modules: ''
optimizer: AdamW
save_best_checkpoint: false
schedule: Cosine
train_validation_data: false
warmup_epochs: 0.0
weight_decay: 0.0
|