question-context-bm25-to10-p-v2

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: 10.6274
• Rouge1: 0.0198
• Rouge2: 0.0064
• Rougel: 0.0196
• Rougelsum: 0.0189
• Gen Len: 5.4

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	43	13.6281	0.0052	0.0	0.0052	0.0052	4.2667
No log	2.0	86	11.8718	0.0068	0.0016	0.0068	0.0066	4.4
No log	3.0	129	11.1016	0.01	0.0033	0.0099	0.0099	4.6667
No log	4.0	172	12.4219	0.0118	0.0033	0.0118	0.0113	4.8667
No log	5.0	215	11.5673	0.0118	0.0033	0.0118	0.0113	4.8667
No log	6.0	258	11.8397	0.0086	0.0017	0.0086	0.0086	4.6
No log	7.0	301	11.1954	0.0118	0.0033	0.0118	0.0113	4.8667
No log	8.0	344	10.6161	0.0198	0.0064	0.0196	0.0189	5.4
No log	9.0	387	10.6286	0.0198	0.0064	0.0196	0.0189	5.4
No log	10.0	430	10.6274	0.0198	0.0064	0.0196	0.0189	5.4

Framework versions

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