qa_bm25_small_sample2

This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.1438
• Rouge1: 0.1048
• Rouge2: 0.0088
• Rougel: 0.0949
• Rougelsum: 0.0949
• Gen Len: 19.0

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	108	12.1686	0.014	0.0	0.0134	0.0132	6.0357
No log	2.0	216	10.8608	0.0122	0.0	0.0113	0.0113	6.0
No log	3.0	324	8.0196	0.044	0.008	0.041	0.0407	9.1429
No log	4.0	432	5.8188	0.1099	0.0119	0.0988	0.0983	19.0
13.9065	5.0	540	4.6813	0.1254	0.0138	0.1104	0.1103	19.0
13.9065	6.0	648	4.3367	0.1229	0.0158	0.1094	0.1097	19.0
13.9065	7.0	756	4.2485	0.1172	0.0145	0.1033	0.1037	19.0
13.9065	8.0	864	4.1780	0.1048	0.0088	0.0949	0.0949	19.0
13.9065	9.0	972	4.1546	0.1048	0.0088	0.0949	0.0949	19.0
6.0382	10.0	1080	4.1438	0.1048	0.0088	0.0949	0.0949	19.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3