60 lines
1.4 KiB
YAML
60 lines
1.4 KiB
YAML
# EBFT Strided Mode: For unstructured text data (raw code, prose)
|
|
# Uses strided block-parallel generation — no vLLM needed.
|
|
#
|
|
# Run: CUDA_VISIBLE_DEVICES=0 axolotl train examples/ebft/llama-1b-ebft-strided.yaml
|
|
|
|
base_model: meta-llama/Llama-3.2-1B
|
|
rl: ebft
|
|
|
|
ebft:
|
|
mode: strided # strided block-parallel generation
|
|
stride: 8 # tokens between anchor points
|
|
context_length: 8 # context window per block
|
|
generate_max_len: 8 # tokens to generate per block
|
|
n_samples_per_prompt: 4 # rollouts per document
|
|
temperature: 0.6
|
|
top_p: 1.0
|
|
feature_layers: [0.25, 0.5, 0.75]
|
|
embed_method: last_token
|
|
use_whitening: true
|
|
alignment_coef: 1.0
|
|
diversity_coef: 1.0
|
|
rl_coef: 1.0
|
|
ce_coef: 0.0
|
|
advantage_estimator: rloo
|
|
|
|
datasets:
|
|
- path: sjelassi/swallow_code_20m
|
|
type: ebft_pretrain.transform
|
|
split: train[:100]
|
|
|
|
sequence_len: 256
|
|
micro_batch_size: 1
|
|
gradient_accumulation_steps: 2
|
|
num_epochs: 1
|
|
max_steps: 5
|
|
|
|
learning_rate: 1.0e-6
|
|
optimizer: adamw_torch_fused
|
|
lr_scheduler: cosine
|
|
warmup_steps: 2
|
|
|
|
adapter: lora
|
|
lora_r: 16
|
|
lora_alpha: 32
|
|
lora_dropout: 0.05
|
|
lora_target_linear: true
|
|
|
|
bf16: auto
|
|
gradient_checkpointing: true
|
|
|
|
special_tokens:
|
|
pad_token: "<|end_of_text|>"
|
|
|
|
val_set_size: 0.0
|
|
output_dir: ./outputs/ebft-strided-validation
|
|
|
|
wandb_project: ebft
|
|
logging_steps: 1
|
|
save_steps: 100
|