flan-t5-small-instructiongen

Instead of generating questions from text, generate instructions for LLMs!

This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3401
• Rouge1: 52.201
• Rouge2: 35.6154
• Rougel: 50.2334
• Rougelsum: 50.338
• Gen Len: 14.0450

Intended uses & limitations

This is just a small model/example. There is likely to be even better performance with larger models (ex pszemraj/bart-base-instructiongen) generalizes better)

Additionally, this was trained on a dataset of only instructions+outputs, with the inputs filtered out. This means that text of 1) cookies and cream 2) chocolate chip 3) mint chip 4) oreo will not get you "Rank the following ice cream flavors: oreo, mint chip, chocolate chip, cookies and cream".

Training and evaluation data

See the linked dataset pszemraj/fleece2instructions - it is a filtered/formatted version of tatsu-lab/alpaca to generate instructions for arbitrary text.

• Some of the API examples are intentionally weird to demonstrate the generalizability of the model.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 8e-05
• train_batch_size: 8
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.02
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.6161	1.0	181	1.3714	51.1003	34.5701	49.1277	49.2466	13.8357
1.539	2.0	362	1.3401	52.201	35.6154	50.2334	50.338	14.0450