KemiOm/poetry-meter-best

KemiOm/poetry-meter-best is a LoRA-adapted google/flan-t5-large model for line-level meter/stress prediction in English poetry. Given a single poetic line, the model predicts its stress pattern (meter representation) as a compact symbolic sequence.

Task

• Input: one poetic line
• Output: stress pattern string (e.g., -+-+-+-+-+) Example:
• Input: Tired Nature's sweet restorer, balmy Sleep!
• Output: +-+-+-+-+-+ This is a meter-only labeling model, not a full poetry generator.

Training Data Format

The meter-only dataset uses line-level supervision:

• input: poetic line text
• target: stress/meter pattern string The model is trained to map each line directly to its metrical stress pattern.

Model Details

• Developer: KemiOm
• Base model: google/flan-t5-large
• Method: LoRA fine-tuning
• Library: Hugging Face Transformers + PEFT
• Language: English
• Domain: formal/historical poetry (including eighteenth-century material)

Best Checkpoint and Training Setup

Best meter-only performance in your results appears in: results/round3/meter_only_lora_r3_lr1e4_flan-t5-large_lora_20260415_160740/zero_shot_meter_only_line_only.json Associated run configuration (sft_runs/round3/meter_only_lr1e4/run_params.json):

• epochs: 5.0
• learning rate: 1e-4
• weight decay: 0.01
• warmup ratio: 0.1
• per-device train batch size: 8
• gradient accumulation steps: 1
• per-device eval batch size: 4
• max input length: 256
• max target length: 64
• LoRA rank (r): 16
• LoRA alpha: 32
• LoRA dropout: 0.05
• LoRA target modules: q,v
• seed: 42
• precision flags: bf16=true, fp16 enabled

Intended Uses

• Automatic meter annotation for poetic corpora
• Meter diagnostics for generated verse
• Preprocessing/evaluation component in constrained poetry pipelines
• Educational tooling for stress-pattern analysis

Limitations

• Stress ambiguity in English can produce multiple plausible scansions.
• Archaic spellings and punctuation can affect tokenization and stress assignment.
• Performance may drop on modern slang, non-poetic text, or out-of-domain genres.
• Meter labels reflect dataset conventions and annotation assumptions.

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
model_id = "KemiOm/poetry-meter-best"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
line = "Tired Nature's sweet restorer, balmy Sleep!"
inputs = tokenizer(line, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=24, do_sample=False)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
# expected format: "+-+-+-+-+-+" (example)