flan-t5-large-mawpnli-calcx-nli-pt

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

• Loss: 0.1217
• Rouge1: 95.7098
• Rouge2: 89.9271
• Rougel: 95.5836
• Rougelsum: 95.5842
• Gen Len: 10.9151

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
0.2279	1.0	819	0.1290	95.075	87.8764	94.7902	94.8057	10.7978
0.0612	2.0	1638	0.1012	95.6219	89.6809	95.4399	95.4521	10.9029
0.0418	3.0	2457	0.0972	95.7709	90.1703	95.613	95.637	10.9328
0.0272	4.0	3276	0.1174	95.7478	90.1332	95.5931	95.6069	10.9395
0.0215	5.0	4095	0.1217	95.7098	89.9271	95.5836	95.5842	10.9151

Framework versions

• Transformers 4.35.2
• Pytorch 1.12.1+cu113
• Datasets 2.15.0
• Tokenizers 0.15.0