flan-t5-small-asap_t3_f4_prompt_adherence

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: 0.0608
• Rouge1: 82.8313
• Rouge2: 78.4206
• Rougel: 82.8099
• Rougelsum: 82.8613
• Gen Len: 12.0348

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	259	0.0835	79.9299	74.5797	79.9059	79.9231	12.0014
0.4025	2.0	518	0.0650	82.5527	78.0538	82.5428	82.5779	12.0362
0.4025	3.0	777	0.0691	81.7292	76.9481	81.6638	81.7225	12.0348
0.0755	4.0	1036	0.0603	82.7227	78.3165	82.7288	82.7698	12.0435
0.0755	5.0	1295	0.0608	82.8313	78.4206	82.8099	82.8613	12.0348

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2