File size: 2,550 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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
architecture:
backbone_dtype: int4
force_embedding_gradients: false
gradient_checkpointing: true
intermediate_dropout: 0.0
pretrained: true
pretrained_weights: ''
augmentation:
random_parent_probability: 0.0
skip_parent_probability: 0.0
token_mask_probability: 0.0
dataset:
add_eos_token_to_answer: true
add_eos_token_to_prompt: true
add_eos_token_to_system: true
answer_column: output
chatbot_author: H2O.ai
chatbot_name: h2oGPT
data_sample: 0.01
data_sample_choice:
- Train
- Validation
limit_chained_samples: false
mask_prompt_labels: true
parent_id_column: None
personalize: false
prompt_column:
- instruction
system_column: None
text_answer_separator: <|answer|>
text_prompt_start: <|prompt|>
text_system_start: <|system|>
train_dataframe: examples/data_oasst2/train_full.csv
validation_dataframe: None
validation_size: 0.01
validation_strategy: automatic
environment:
compile_model: false
find_unused_parameters: false
gpus:
- '0'
huggingface_branch: main
mixed_precision: true
number_of_workers: 8
seed: -1
trust_remote_code: true
experiment_name: example_oasst2
llm_backbone: h2oai/h2o-danube2-1.8b-base
logging:
logger: None
neptune_project: test_org/test_project
output_directory: examples/output_oasst2
prediction:
batch_size_inference: 0
do_sample: false
max_length_inference: 256
max_time: 0.0
metric: Perplexity
metric_gpt_model: gpt-3.5-turbo-0301
metric_gpt_template: general
min_length_inference: 1
num_beams: 1
num_history: 4
repetition_penalty: 1.2
stop_tokens: ''
temperature: 0.3
top_k: 0
top_p: 1.0
problem_type: text_causal_language_modeling
tokenizer:
add_prompt_answer_tokens: false
max_length: 512
max_length_answer: 256
max_length_prompt: 256
padding_quantile: 1.0
use_fast: true
training:
batch_size: 2
differential_learning_rate: 1.0e-05
differential_learning_rate_layers: []
drop_last_batch: true
epochs: 1
evaluate_before_training: false
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: ''
loss_function: TokenAveragedCrossEntropy
optimizer: AdamW
save_best_checkpoint: false
schedule: Cosine
train_validation_data: false
warmup_epochs: 0.0
weight_decay: 0.0
|